SlideShare une entreprise Scribd logo
1  sur  35
Télécharger pour lire hors ligne
© 2016 Synopsys, Inc. 1
Applying Deep Learning Vision Technology to
Low-cost, Low-power Embedded Systems:
An Industrial Perspective
Pierre Paulin
Director of R&D
16 January 2016
© 2016 Synopsys, Inc. 2
Agenda
• Embedded Vision application
trends and challenges
• Synopsys Embedded Vision
Processor Overview
• Convolution Neural Networks
– Applications, requirements
– Dedicated CNN engine for EV
– Competitive analysis
• Summary & Final Thoughts
© 2016 Synopsys, Inc. 3
Embedded Vision is Coming Fast
• Embedded Vision is the use of computer
vision in embedded systems to interpret
meaning from images or video
• In cars to improve safety
• Surveillance for detection and tracking
• In industrial automation to improve
quality and control
• Estimated $300B+ market in 2020,
35% CAGR
0
50
100
150
200
250
300
350
2013 2014 2015 2016 2017 2018 2019 2020
BillionsofDollars
Vision Systems Shipments
Sources: ABI Research, Insight Media, Transparency
Market Research, Markets And Markets, Synopsys
Wide Variety of Vision Applications
Cameras
Drones
Home AutomationRetailGaming Infotainment
Augmented RealityMobile SurveillanceADAS
© 2016 Synopsys, Inc. 5
Autonomous Driving Buzz
1/14/2016 – U.S. Proposes Spending $4 Billion to Encourage Driverless Cars
Obama administration aims to remove hurdles to making autonomous cars more widespread
Wall Street Journal
8/17/2016 – Ford's self-driving car 'coming in 2021’ (BBC News)
8/24/2016 – Self-driving taxis roll out in Singapore -
beating Uber to it (The Guardian)
10/20/2016 – Elon Musk: You'll be able to summon your driverless Tesla
from cross-country (CNN Money)
10/25/2016 – Uber's Self-Driving Truck Makes Its First Delivery:
50000 Beers (Wired)
© 2016 Synopsys, Inc. 6
Largest Embedded Vision Application Segment
Advanced Driver Assistance Systems Driven By Safety Concerns
Source: IC Market Drivers, IC Insights, January 2015 & Trends and Opportunities in Driver Assistance and Automated Driving, IHS Automotive Sep 2015
© 2016 Synopsys, Inc. 7
Video Surveillance Markets Growing Rapidly
• Global IP Video Surveillance Market
expected to grow at CAGR of 37.3%
from 2012-20
• Demand driven by
– Growing installations of IP cameras
– Need for surveillance cameras
with better video quality
– Limited ability for real-time human
analysis
http://www.alliedmarketresearch.com/IP-video-surveillance-VSaaS-market
3X Growth Forecast
2013 - 2019
Security (Airports, Govt, Banks, Casinos), Home Surveillance, Retail, Healthcare
© 2016 Synopsys, Inc. 8
Less Efficient EV Options Dedicated Embedded Vision Processors
EV Challenges Require Embedded Vision Processors
Performance
Power
Area
CPUs don’t have math horsepower for fast
2D vision processing
GPUs have high performance but large
areas and higher power
DSPs are designed for low power audio
and speech applications, not 2D video
FPGAs are good for prototyping but are
expensive and performance limited
Higher performance
Lower power
Smaller area
Can include a dedicated deep learning
(CNN) engine
© 2016 Synopsys, Inc. 9
Embedded Vision Applications and
Power, Performance and Area (PPA) Requirements
© 2016 Synopsys, Inc. 10
Vision Pipeline Example
Object detection pipeline
Grayscale
Conversion
Image
Pyramid
Detecting
Areas of
Interest in a
Frame
Non-max
Suppression
Draw Box
© 2016 Synopsys, Inc. 11
Vision Pipeline Example
Video surveillance pipeline
Grayscale &
Image
Pyramid
Face
Detection
Tracking &
Detection
Cascade
Fusion &
Learning
© 2016 Synopsys, Inc. 12
Vision Algorithm Computation
• Object detection
• Background
subtraction
• Feature extraction
• Image
segmentation
• Connected comp.
labeling
• Noise reduction
• Color space
conversion
• Gamma correction
• Image scaling
• Gaussian
pyramid
Simple Data-Level
Parallelism (DLP)
• Good spatial locality
• Good compute intensity
• Small context
More Complex DLP
• Complex data structures
• Irregular compute intensity
• Larger context
Scalar Processing
• General purpose compute
• Thread level parallelism
Pre-processing
Selecting Areas
of Interest
Precise
Processing of
Selected Areas
Decision
Making
• Object recognition
• Tracking
• Feature matching
• Gesture
recognition
• Motion analysis
• Match/no match
• Flag events
CNN
RISC scalar
Multi-core Gen2
EV SIMD processorMulti-core Gen1
EV SIMD processor
Multi-core
CNN Engine
© 2016 Synopsys, Inc. 13
Sample Power, Performance and Area Targets
• Intelligent video surveillance applications
– Face detection & tracking, pose detection, gaze
estimation, gender recognition, age estimation
– People detection & counting for video surveillance
– Driver fatigue detection
– Advanced detection and tracking
– Implementation on
GPP and GP-GPU
– Typical customer
targets for
HD @30 fps
Based on 28 nm process node
<500 mW 1-2 mm2
10-500 GOP/s
1-10 W 50-100 mm2
© 2016 Synopsys, Inc. 14
Sample Power, Performance and Area Targets
• ADAS
– Pedestrian, vehicle, traffic sign, lane detections
– Scene segmentation
– Implementation on
GPP and GP-GPU
– Typical customer
targets for
HD @30 fps
Based on 28 nm process node
100-2000 GOP/s
1-2 W 2-5 mm2
>100 W >100 mm2
© 2016 Synopsys, Inc. 15
DesignWare® ARC EV6 Processor and CNN
- Vision-specific wide SIMD engine
- Optimized CNN engine
- Programming tools
© 2016 Synopsys, Inc. 16
EV6x Processor Objectives
Low power:
Over 1000 GMAC/s/W
in CNN engine
High productivity
Highly Scalable Vector Engine
100 GOP/s
620 GOP/s
Low area High-performance CNN:
Up to 880 MAC/cycle
Scalar
Vector
CNN
Standard Programming model
Accelerator
OpenCL C
Most Integrated Solution
C/C++
Embedded
Vision
Libraries
Preliminary – Subject to Change
© 2016 Synopsys, Inc. 17
EV Processor Solution: EV6x with CNN Engine
Embedded Vision Programming Tools
Vision CPU (1 to 4 cores) CNN Engine
Option
Convolution
ALU Conv. 2D
AGUs CC MEMs
Cluster
Comm. Shared Mem.DMA
Classification
AXI Interconnect
User kernels
Ui
Uk
C/C++
OpenCL C
K1 Kn…
Kernel Lib
OpenCL C compiler, with
whole function vectorization
C/C++
compiler
Lib
Ui
Uj
Uk
Kn
Uk
Um
graph
CNN Graph
Mapping Tools
HAPS®
Rapid
Prototyping
Board
Virtual
Prototype
ALU Conv. 1D
AGUs CC MEMs
Coherency
ARConnect Sync Debug Power Mgmt.
Up to 880 MAC/cycle
Up to 620 GOP/s
at 800 MHz
Core 4
Core 3
32b
Scalar
512b
Vector DSP
Core 2
Core 1
32b
Scalar
512b
Vector DSP
VCCMD$I$ VCCMD$I$
CNN
graph
Cn
CNN graph
node
© 2016 Synopsys, Inc. 18
CNN – Convolution Neural Networks
Deep Learning Approach to Embedded Vision
© 2016 Synopsys, Inc. 19
CNN for a Wide Range of Vision Applications
• Image classification, search similar images
• Object detection, classification & localization
– Any type of object(s), depending on training phase
• Face recognition
• Visual attention
• Facial expression recognition
• Gesture recognition / hand tracking
• Resolution upscaling
• Scene recognition and labelling, semantic segmentation
– Sky, mountain, road, tree, building, …
• Recent advocates
– Nvidia, Microsoft, Google, Baidu, Adobe, Qualcomm, Yahoo …
– Mobileye for autonomous driving car
car
sky
building
building
road
© 2016 Synopsys, Inc. 20
Pedestrian Detection: HoG vs. CNN
© 2016 Synopsys, Inc. 21
Computation Requirements for CNN
Accuracy
Computationalcomplexity
Lenet (1994)
4 layers
AlexNet (2012)
8 layers
100MByte
VGG-19 (2014)
19 layers
270MByte
GoogleNet (2014)
22 layer
20MByte
ResNet (2015)
152 layers!
10MByte
1 GOPs/frame
10 GOPs/frame
© 2016 Synopsys, Inc. 22
Scene Segmentation
Source: Press Release by Toshiba and Denso, 17 Oct. 2016
© 2016 Synopsys, Inc. 23
Super resolution using CNN
Source
Bicubic
Interpolation CNN Reference Source
Bicubic
Interpolation CNN Reference
“Image Super-Resolution Using Deep Convolutional Networks (2016), C. Dong et al.”
© 2016 Synopsys, Inc. 24
Super-Resolution using Convolutional Neural Networks
• CNN’s deliver superior Super-Resolution for single image and video
• CNN’s for Super-Resolution require dedicated compute engine with high compute capacity
• Example “Image Super-Resolution Using Deep Convolutional Networks (2016), C. Dong et al.”
Requires 600 GMAC for one 4K frame
© 2016 Synopsys, Inc. 25
CNN Graph Training and Porting
Image labeling
Graph
explore,
training
GPU farm
Code
vectorization
TrainingPorting
coeff.
Code
Object
detection
executable
CNN
graph
GPP
CNN-optimized
processor
GP-GPU
© 2016 Synopsys, Inc. 26
CNN Computation
• Convolution of multiple
inputs together
– Fixed kernel size
• Optional subsampling
– 1x, 2x, 4x
• Optional max-pooling
• Very regular, repetitive
computation
– Dominated by MAC
– Deterministic
• Non-linear activation
function
– Rectifier, Sigmoid,
Hyperbolic tangent
I0
IM-1
I1
O0
ON-1
M inputs
(XI * YI)
Z kernels (K * K) with
associated weights
N outputs (XO * YO)
Oj = act(Bj+ (Iv x Kw) + …)
Convolution (x)
act
act
Activation (tanh, ReLU)
…
© 2016 Synopsys, Inc. 27
EV6x Second Generation CNN Engine for
Object Detection and Semantic Segmentation
- High performance, low power and area
- Fully programmable
car
car
sky
building
building
© 2016 Synopsys, Inc. 28
High-Performance EV6x CNN Engine
• Dedicated EV6x CNN Engine with
performance equal or better than GP-GPU
• Programmable to support full range of fixed point
CNN graphs
• State-of-the-art power-efficiency
• Real-time, high quality image classification, object
recognition, semantic segmentation
• Supports resolutions up to 4K
• Operates in parallel with Vision CPUs increasing
efficiency and throughput
AXIInterconnect
Vision CPU Core
32 bit
RISC
512-bit
Vector DSP
Cluster
Shared
Memory
DMA
ARConnect
CNN Engine
Convolution
Classification
Preliminary – Subject to Change
ALU
Conv. 2D
AGUs CC MEMs
ALU Conv. 1D
AGUs CC MEMs
© 2016 Synopsys, Inc. 29
AlexNet on ImageNet
Quantization opportunities for recognition tasks
32-bit
floating point
16-bit
fixed point
vs
[Moons WACV2016]
Recognitionaccuracy
Fixed-point word length
• 12 bit good compromise between
CNN recognition performance and
hardware cost
– 8 bit will cause recognition rate loss on
existing graphs
– 12 bit multiplier is almost half the area
of a 16 bit multiplier
12-bit
© 2016 Synopsys, Inc. 30
CNN data precision – Qualcomm data
© 2016 Synopsys, Inc. 31
CNN Competitive Analysis
© 2016 Synopsys, Inc. 32
CNN Performance and Area Efficiency Comparison
Preliminary – Subject to Change
GMAC/s/mm2
10 1000
1
10
100
1000
300X
2X
100
GMAC/s
20X
14X
First gen
vision
processors
GP/GPU
EV6x Embedded
Vision Processor
w/integrated CNN
Circle area proportional
to logic area
© 2016 Synopsys, Inc. 33
CNN Performance and Power Efficiency Comparison
Preliminary – Subject to Change
GMAC/s/W
10 100 1000
10
100
1000
10000
11X
30X
GMAC/s
EV6x Embedded
Vision Processor
w/integrated CNN
First gen
vision
processors
GP/GPU
Circle area proportional
to logic area
© 2016 Synopsys, Inc. 34
Less Efficient EV Options Dedicated Embedded Vision Processors
EV Challenges Require Embedded Vision Processors
Performance
Power
Area
CPUs don’t have math horsepower
for fast 2D vision processing
GPUs have high performance but
large areas and higher power
DSPs are designed for low power
audio and speech applications, not
2D video
FPGAs are good for prototyping but
are expensive and performance
limited
High performance
Lower power
Smaller area
Dedicated deep learning (CNN) engine provides
PPA numbers compatible with surveillance,
ADAS and mobile targets
1000
GMACs/W
100-1000
GOP/s
Few
mm2
Thank You
Contact me at:
pierre.paulin@synopsys.com

Contenu connexe

Tendances

“OpenCV: Past, Present and Future,” a Presentation from OpenCV.org
“OpenCV: Past, Present and Future,” a Presentation from OpenCV.org“OpenCV: Past, Present and Future,” a Presentation from OpenCV.org
“OpenCV: Past, Present and Future,” a Presentation from OpenCV.orgEdge AI and Vision Alliance
 
"The OpenVX Hardware Acceleration API for Embedded Vision Applications and Li...
"The OpenVX Hardware Acceleration API for Embedded Vision Applications and Li..."The OpenVX Hardware Acceleration API for Embedded Vision Applications and Li...
"The OpenVX Hardware Acceleration API for Embedded Vision Applications and Li...Edge AI and Vision Alliance
 
“Deploying PyTorch Models for Real-time Inference On the Edge,” a Presentatio...
“Deploying PyTorch Models for Real-time Inference On the Edge,” a Presentatio...“Deploying PyTorch Models for Real-time Inference On the Edge,” a Presentatio...
“Deploying PyTorch Models for Real-time Inference On the Edge,” a Presentatio...Edge AI and Vision Alliance
 
PL-4089, Accelerating and Evaluating OpenCL Graph Applications, by Shuai Che,...
PL-4089, Accelerating and Evaluating OpenCL Graph Applications, by Shuai Che,...PL-4089, Accelerating and Evaluating OpenCL Graph Applications, by Shuai Che,...
PL-4089, Accelerating and Evaluating OpenCL Graph Applications, by Shuai Che,...AMD Developer Central
 
"How to Test and Validate an Automated Driving System," a Presentation from M...
"How to Test and Validate an Automated Driving System," a Presentation from M..."How to Test and Validate an Automated Driving System," a Presentation from M...
"How to Test and Validate an Automated Driving System," a Presentation from M...Edge AI and Vision Alliance
 
Droidcon2013 triangles gangolells_imagination
Droidcon2013 triangles gangolells_imaginationDroidcon2013 triangles gangolells_imagination
Droidcon2013 triangles gangolells_imaginationDroidcon Berlin
 
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 NVIDIA Taiwan
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002Enrico Busto
 
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...Edge AI and Vision Alliance
 
IS-4082, Real-Time insight in Big Data – Even faster using HSA, by Norbert He...
IS-4082, Real-Time insight in Big Data – Even faster using HSA, by Norbert He...IS-4082, Real-Time insight in Big Data – Even faster using HSA, by Norbert He...
IS-4082, Real-Time insight in Big Data – Even faster using HSA, by Norbert He...AMD Developer Central
 
Keynote (Tony King-Smith) - Silicon? Check. HSA? Check. All done? Wrong! - by...
Keynote (Tony King-Smith) - Silicon? Check. HSA? Check. All done? Wrong! - by...Keynote (Tony King-Smith) - Silicon? Check. HSA? Check. All done? Wrong! - by...
Keynote (Tony King-Smith) - Silicon? Check. HSA? Check. All done? Wrong! - by...AMD Developer Central
 
"Deep Learning on Arm Cortex-M Microcontrollers," a Presentation from Arm
"Deep Learning on Arm Cortex-M Microcontrollers," a Presentation from Arm"Deep Learning on Arm Cortex-M Microcontrollers," a Presentation from Arm
"Deep Learning on Arm Cortex-M Microcontrollers," a Presentation from ArmEdge AI and Vision Alliance
 
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati..."Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...Edge AI and Vision Alliance
 
HC-4019, "Exploiting Coarse-grained Parallelism in B+ Tree Searches on an APU...
HC-4019, "Exploiting Coarse-grained Parallelism in B+ Tree Searches on an APU...HC-4019, "Exploiting Coarse-grained Parallelism in B+ Tree Searches on an APU...
HC-4019, "Exploiting Coarse-grained Parallelism in B+ Tree Searches on an APU...AMD Developer Central
 
HC-4022, Towards an Ecosystem for Heterogeneous Parallel Computing, by Wu Feng
HC-4022, Towards an Ecosystem for Heterogeneous Parallel Computing, by Wu FengHC-4022, Towards an Ecosystem for Heterogeneous Parallel Computing, by Wu Feng
HC-4022, Towards an Ecosystem for Heterogeneous Parallel Computing, by Wu FengAMD Developer Central
 
GS-4152, AMD’s Radeon R9-290X, One Big dGPU, by Michael Mantor
GS-4152, AMD’s Radeon R9-290X, One Big dGPU, by Michael MantorGS-4152, AMD’s Radeon R9-290X, One Big dGPU, by Michael Mantor
GS-4152, AMD’s Radeon R9-290X, One Big dGPU, by Michael MantorAMD Developer Central
 
Optimizing High Performance Computing Applications for Energy
Optimizing High Performance Computing Applications for EnergyOptimizing High Performance Computing Applications for Energy
Optimizing High Performance Computing Applications for EnergyDavid Lecomber
 

Tendances (20)

“OpenCV: Past, Present and Future,” a Presentation from OpenCV.org
“OpenCV: Past, Present and Future,” a Presentation from OpenCV.org“OpenCV: Past, Present and Future,” a Presentation from OpenCV.org
“OpenCV: Past, Present and Future,” a Presentation from OpenCV.org
 
"The OpenVX Hardware Acceleration API for Embedded Vision Applications and Li...
"The OpenVX Hardware Acceleration API for Embedded Vision Applications and Li..."The OpenVX Hardware Acceleration API for Embedded Vision Applications and Li...
"The OpenVX Hardware Acceleration API for Embedded Vision Applications and Li...
 
“Deploying PyTorch Models for Real-time Inference On the Edge,” a Presentatio...
“Deploying PyTorch Models for Real-time Inference On the Edge,” a Presentatio...“Deploying PyTorch Models for Real-time Inference On the Edge,” a Presentatio...
“Deploying PyTorch Models for Real-time Inference On the Edge,” a Presentatio...
 
PL-4089, Accelerating and Evaluating OpenCL Graph Applications, by Shuai Che,...
PL-4089, Accelerating and Evaluating OpenCL Graph Applications, by Shuai Che,...PL-4089, Accelerating and Evaluating OpenCL Graph Applications, by Shuai Che,...
PL-4089, Accelerating and Evaluating OpenCL Graph Applications, by Shuai Che,...
 
"How to Test and Validate an Automated Driving System," a Presentation from M...
"How to Test and Validate an Automated Driving System," a Presentation from M..."How to Test and Validate an Automated Driving System," a Presentation from M...
"How to Test and Validate an Automated Driving System," a Presentation from M...
 
Droidcon2013 triangles gangolells_imagination
Droidcon2013 triangles gangolells_imaginationDroidcon2013 triangles gangolells_imagination
Droidcon2013 triangles gangolells_imagination
 
Deep learning with FPGA
Deep learning with FPGADeep learning with FPGA
Deep learning with FPGA
 
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發 GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
GTC Taiwan 2017 自主駕駛車輛發展平台與技術研發
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002
 
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
“A Survey of CMOS Imagers and Lenses—and the Trade-offs You Should Consider,”...
 
IS-4082, Real-Time insight in Big Data – Even faster using HSA, by Norbert He...
IS-4082, Real-Time insight in Big Data – Even faster using HSA, by Norbert He...IS-4082, Real-Time insight in Big Data – Even faster using HSA, by Norbert He...
IS-4082, Real-Time insight in Big Data – Even faster using HSA, by Norbert He...
 
Keynote (Tony King-Smith) - Silicon? Check. HSA? Check. All done? Wrong! - by...
Keynote (Tony King-Smith) - Silicon? Check. HSA? Check. All done? Wrong! - by...Keynote (Tony King-Smith) - Silicon? Check. HSA? Check. All done? Wrong! - by...
Keynote (Tony King-Smith) - Silicon? Check. HSA? Check. All done? Wrong! - by...
 
"Deep Learning on Arm Cortex-M Microcontrollers," a Presentation from Arm
"Deep Learning on Arm Cortex-M Microcontrollers," a Presentation from Arm"Deep Learning on Arm Cortex-M Microcontrollers," a Presentation from Arm
"Deep Learning on Arm Cortex-M Microcontrollers," a Presentation from Arm
 
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati..."Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
 
HC-4019, "Exploiting Coarse-grained Parallelism in B+ Tree Searches on an APU...
HC-4019, "Exploiting Coarse-grained Parallelism in B+ Tree Searches on an APU...HC-4019, "Exploiting Coarse-grained Parallelism in B+ Tree Searches on an APU...
HC-4019, "Exploiting Coarse-grained Parallelism in B+ Tree Searches on an APU...
 
HC-4022, Towards an Ecosystem for Heterogeneous Parallel Computing, by Wu Feng
HC-4022, Towards an Ecosystem for Heterogeneous Parallel Computing, by Wu FengHC-4022, Towards an Ecosystem for Heterogeneous Parallel Computing, by Wu Feng
HC-4022, Towards an Ecosystem for Heterogeneous Parallel Computing, by Wu Feng
 
GS-4152, AMD’s Radeon R9-290X, One Big dGPU, by Michael Mantor
GS-4152, AMD’s Radeon R9-290X, One Big dGPU, by Michael MantorGS-4152, AMD’s Radeon R9-290X, One Big dGPU, by Michael Mantor
GS-4152, AMD’s Radeon R9-290X, One Big dGPU, by Michael Mantor
 
Optimizing High Performance Computing Applications for Energy
Optimizing High Performance Computing Applications for EnergyOptimizing High Performance Computing Applications for Energy
Optimizing High Performance Computing Applications for Energy
 
Deeplearningusingcloudpakfordata
DeeplearningusingcloudpakfordataDeeplearningusingcloudpakfordata
Deeplearningusingcloudpakfordata
 
DRIVE PX 2
DRIVE PX 2DRIVE PX 2
DRIVE PX 2
 

En vedette

Authoring cycle 2
Authoring cycle 2Authoring cycle 2
Authoring cycle 2erbigelow
 
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016Universitat Politècnica de Catalunya
 
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre..."Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...Edge AI and Vision Alliance
 
Low vision rehabilitation
Low vision rehabilitationLow vision rehabilitation
Low vision rehabilitationHira Dahal
 
"Accelerating Deep Learning Using Altera FPGAs," a Presentation from Intel
"Accelerating Deep Learning Using Altera FPGAs," a Presentation from Intel"Accelerating Deep Learning Using Altera FPGAs," a Presentation from Intel
"Accelerating Deep Learning Using Altera FPGAs," a Presentation from IntelEdge AI and Vision Alliance
 
low vision aids
low vision aidslow vision aids
low vision aidsAstha Jain
 
The Low Vision Examination
The Low Vision ExaminationThe Low Vision Examination
The Low Vision ExaminationHossein Mirzaie
 
(BDT311) Deep Learning: Going Beyond Machine Learning
(BDT311) Deep Learning: Going Beyond Machine Learning(BDT311) Deep Learning: Going Beyond Machine Learning
(BDT311) Deep Learning: Going Beyond Machine LearningAmazon Web Services
 
Passive stereo vision with deep learning
Passive stereo vision with deep learningPassive stereo vision with deep learning
Passive stereo vision with deep learningYu Huang
 
Can We Assess Creativity?
Can We Assess Creativity?Can We Assess Creativity?
Can We Assess Creativity?John Spencer
 

En vedette (14)

Pixel Recursive Super Resolution. Google Brain
 Pixel Recursive Super Resolution.  Google Brain Pixel Recursive Super Resolution.  Google Brain
Pixel Recursive Super Resolution. Google Brain
 
Authoring cycle 2
Authoring cycle 2Authoring cycle 2
Authoring cycle 2
 
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
Deep Learning for Computer Vision (2/4): Object Analytics @ laSalle 2016
 
Low vision assessment
Low vision assessmentLow vision assessment
Low vision assessment
 
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre..."Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
 
Low vision rehabilitation
Low vision rehabilitationLow vision rehabilitation
Low vision rehabilitation
 
"Accelerating Deep Learning Using Altera FPGAs," a Presentation from Intel
"Accelerating Deep Learning Using Altera FPGAs," a Presentation from Intel"Accelerating Deep Learning Using Altera FPGAs," a Presentation from Intel
"Accelerating Deep Learning Using Altera FPGAs," a Presentation from Intel
 
low vision aids
low vision aidslow vision aids
low vision aids
 
The Low Vision Examination
The Low Vision ExaminationThe Low Vision Examination
The Low Vision Examination
 
(BDT311) Deep Learning: Going Beyond Machine Learning
(BDT311) Deep Learning: Going Beyond Machine Learning(BDT311) Deep Learning: Going Beyond Machine Learning
(BDT311) Deep Learning: Going Beyond Machine Learning
 
SYNOPSIS WRITING
SYNOPSIS WRITINGSYNOPSIS WRITING
SYNOPSIS WRITING
 
Passive stereo vision with deep learning
Passive stereo vision with deep learningPassive stereo vision with deep learning
Passive stereo vision with deep learning
 
Format Of Synopsis
Format Of SynopsisFormat Of Synopsis
Format Of Synopsis
 
Can We Assess Creativity?
Can We Assess Creativity?Can We Assess Creativity?
Can We Assess Creativity?
 

Similaire à Applying Deep Learning Vision Technology to low-cost/power Embedded Systems

“Optimized Image Processing for Automotive Image Sensors with Novel Color Fil...
“Optimized Image Processing for Automotive Image Sensors with Novel Color Fil...“Optimized Image Processing for Automotive Image Sensors with Novel Color Fil...
“Optimized Image Processing for Automotive Image Sensors with Novel Color Fil...Edge AI and Vision Alliance
 
IoT Tech Expo 2023_Micha vor dem Berge presentation
IoT Tech Expo 2023_Micha vor dem Berge presentationIoT Tech Expo 2023_Micha vor dem Berge presentation
IoT Tech Expo 2023_Micha vor dem Berge presentationVEDLIoT Project
 
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion SystemsMIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion SystemsMIPI Alliance
 
HC28.22.430-Vision-Neural-Net-GregEfland-Cadence-v02-57
HC28.22.430-Vision-Neural-Net-GregEfland-Cadence-v02-57HC28.22.430-Vision-Neural-Net-GregEfland-Cadence-v02-57
HC28.22.430-Vision-Neural-Net-GregEfland-Cadence-v02-57AAMIR FAROOQUI
 
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...MIPI Alliance
 
“Trends in Neural Network Topologies for Vision at the Edge,” a Presentation ...
“Trends in Neural Network Topologies for Vision at the Edge,” a Presentation ...“Trends in Neural Network Topologies for Vision at the Edge,” a Presentation ...
“Trends in Neural Network Topologies for Vision at the Edge,” a Presentation ...Edge AI and Vision Alliance
 
"Is Vision the New Wireless?," a Presentation from Qualcomm
"Is Vision the New Wireless?," a Presentation from Qualcomm"Is Vision the New Wireless?," a Presentation from Qualcomm
"Is Vision the New Wireless?," a Presentation from QualcommEdge AI and Vision Alliance
 
Image Signal Processor and Vision Processor Market and Technology Trends 2019...
Image Signal Processor and Vision Processor Market and Technology Trends 2019...Image Signal Processor and Vision Processor Market and Technology Trends 2019...
Image Signal Processor and Vision Processor Market and Technology Trends 2019...Yole Developpement
 
MIPI DevCon 2020 | Why an Integrated MIPI C-PHY/D-PHY IP is Essential
MIPI DevCon 2020 | Why an Integrated MIPI C-PHY/D-PHY IP is EssentialMIPI DevCon 2020 | Why an Integrated MIPI C-PHY/D-PHY IP is Essential
MIPI DevCon 2020 | Why an Integrated MIPI C-PHY/D-PHY IP is EssentialMIPI Alliance
 
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...Edge AI and Vision Alliance
 
MIPI DevCon Taipei 2019: Enabling MIPI Camera Applications Including Automoti...
MIPI DevCon Taipei 2019: Enabling MIPI Camera Applications Including Automoti...MIPI DevCon Taipei 2019: Enabling MIPI Camera Applications Including Automoti...
MIPI DevCon Taipei 2019: Enabling MIPI Camera Applications Including Automoti...MIPI Alliance
 
IBM Power Systems Update 2Q17
IBM Power Systems Update 2Q17IBM Power Systems Update 2Q17
IBM Power Systems Update 2Q17David Spurway
 
Neuromophic device for Automotive
Neuromophic device for AutomotiveNeuromophic device for Automotive
Neuromophic device for AutomotiveYoshifumi Sakamoto
 
IoT-based Autonomously Driven Vehicle by using Machine Learning & Image Proce...
IoT-based Autonomously Driven Vehicle by using Machine Learning & Image Proce...IoT-based Autonomously Driven Vehicle by using Machine Learning & Image Proce...
IoT-based Autonomously Driven Vehicle by using Machine Learning & Image Proce...IRJET Journal
 
"Highly Efficient, Scalable Vision and AI Processors IP for the Edge," a Pres...
"Highly Efficient, Scalable Vision and AI Processors IP for the Edge," a Pres..."Highly Efficient, Scalable Vision and AI Processors IP for the Edge," a Pres...
"Highly Efficient, Scalable Vision and AI Processors IP for the Edge," a Pres...Edge AI and Vision Alliance
 
"An Ultra-low-power Multi-core Engine for Inference on Encrypted DNNs," a Pre...
"An Ultra-low-power Multi-core Engine for Inference on Encrypted DNNs," a Pre..."An Ultra-low-power Multi-core Engine for Inference on Encrypted DNNs," a Pre...
"An Ultra-low-power Multi-core Engine for Inference on Encrypted DNNs," a Pre...Edge AI and Vision Alliance
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002Enrico Busto
 
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro...
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro..."Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro...
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro...Edge AI and Vision Alliance
 
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...Edge AI and Vision Alliance
 

Similaire à Applying Deep Learning Vision Technology to low-cost/power Embedded Systems (20)

“Optimized Image Processing for Automotive Image Sensors with Novel Color Fil...
“Optimized Image Processing for Automotive Image Sensors with Novel Color Fil...“Optimized Image Processing for Automotive Image Sensors with Novel Color Fil...
“Optimized Image Processing for Automotive Image Sensors with Novel Color Fil...
 
IoT Tech Expo 2023_Micha vor dem Berge presentation
IoT Tech Expo 2023_Micha vor dem Berge presentationIoT Tech Expo 2023_Micha vor dem Berge presentation
IoT Tech Expo 2023_Micha vor dem Berge presentation
 
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion SystemsMIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
MIPI DevCon 2016: MIPI CSI-2 Application for Vision and Sensor Fusion Systems
 
HC28.22.430-Vision-Neural-Net-GregEfland-Cadence-v02-57
HC28.22.430-Vision-Neural-Net-GregEfland-Cadence-v02-57HC28.22.430-Vision-Neural-Net-GregEfland-Cadence-v02-57
HC28.22.430-Vision-Neural-Net-GregEfland-Cadence-v02-57
 
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
MIPI DevCon 2020 | MIPI DevCon 2020 | How MIPI Interfaces Solve Challenges in...
 
“Trends in Neural Network Topologies for Vision at the Edge,” a Presentation ...
“Trends in Neural Network Topologies for Vision at the Edge,” a Presentation ...“Trends in Neural Network Topologies for Vision at the Edge,” a Presentation ...
“Trends in Neural Network Topologies for Vision at the Edge,” a Presentation ...
 
"Is Vision the New Wireless?," a Presentation from Qualcomm
"Is Vision the New Wireless?," a Presentation from Qualcomm"Is Vision the New Wireless?," a Presentation from Qualcomm
"Is Vision the New Wireless?," a Presentation from Qualcomm
 
Image Signal Processor and Vision Processor Market and Technology Trends 2019...
Image Signal Processor and Vision Processor Market and Technology Trends 2019...Image Signal Processor and Vision Processor Market and Technology Trends 2019...
Image Signal Processor and Vision Processor Market and Technology Trends 2019...
 
MIPI DevCon 2020 | Why an Integrated MIPI C-PHY/D-PHY IP is Essential
MIPI DevCon 2020 | Why an Integrated MIPI C-PHY/D-PHY IP is EssentialMIPI DevCon 2020 | Why an Integrated MIPI C-PHY/D-PHY IP is Essential
MIPI DevCon 2020 | Why an Integrated MIPI C-PHY/D-PHY IP is Essential
 
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
 
MIPI DevCon Taipei 2019: Enabling MIPI Camera Applications Including Automoti...
MIPI DevCon Taipei 2019: Enabling MIPI Camera Applications Including Automoti...MIPI DevCon Taipei 2019: Enabling MIPI Camera Applications Including Automoti...
MIPI DevCon Taipei 2019: Enabling MIPI Camera Applications Including Automoti...
 
IBM Power Systems Update 2Q17
IBM Power Systems Update 2Q17IBM Power Systems Update 2Q17
IBM Power Systems Update 2Q17
 
Neuromophic device for Automotive
Neuromophic device for AutomotiveNeuromophic device for Automotive
Neuromophic device for Automotive
 
Omniverse for the Metaverse
Omniverse for the MetaverseOmniverse for the Metaverse
Omniverse for the Metaverse
 
IoT-based Autonomously Driven Vehicle by using Machine Learning & Image Proce...
IoT-based Autonomously Driven Vehicle by using Machine Learning & Image Proce...IoT-based Autonomously Driven Vehicle by using Machine Learning & Image Proce...
IoT-based Autonomously Driven Vehicle by using Machine Learning & Image Proce...
 
"Highly Efficient, Scalable Vision and AI Processors IP for the Edge," a Pres...
"Highly Efficient, Scalable Vision and AI Processors IP for the Edge," a Pres..."Highly Efficient, Scalable Vision and AI Processors IP for the Edge," a Pres...
"Highly Efficient, Scalable Vision and AI Processors IP for the Edge," a Pres...
 
"An Ultra-low-power Multi-core Engine for Inference on Encrypted DNNs," a Pre...
"An Ultra-low-power Multi-core Engine for Inference on Encrypted DNNs," a Pre..."An Ultra-low-power Multi-core Engine for Inference on Encrypted DNNs," a Pre...
"An Ultra-low-power Multi-core Engine for Inference on Encrypted DNNs," a Pre...
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002
 
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro...
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro..."Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro...
"Computer Vision 2.0: Where We Are and Where We're Going," a Presentation fro...
 
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
 

Plus de Jenny Midwinter

Practical Challenges ML Workflows
Practical Challenges ML WorkflowsPractical Challenges ML Workflows
Practical Challenges ML WorkflowsJenny Midwinter
 
Machine learning applications in clinical brain computer interfacing
Machine learning applications in clinical brain computer interfacingMachine learning applications in clinical brain computer interfacing
Machine learning applications in clinical brain computer interfacingJenny Midwinter
 
Augmented Intelligence Bridging the Gap Between BI and AI
Augmented Intelligence  Bridging the Gap Between BI and AIAugmented Intelligence  Bridging the Gap Between BI and AI
Augmented Intelligence Bridging the Gap Between BI and AIJenny Midwinter
 
Autonomous Learning for Autonomous Systems, by Prof. Plamen Angelov
Autonomous Learning for Autonomous Systems, by Prof. Plamen AngelovAutonomous Learning for Autonomous Systems, by Prof. Plamen Angelov
Autonomous Learning for Autonomous Systems, by Prof. Plamen AngelovJenny Midwinter
 
Ai and analytics for business
Ai and analytics for businessAi and analytics for business
Ai and analytics for businessJenny Midwinter
 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language ProcessingJenny Midwinter
 
Building an NLP DNN in 5 Minutes
Building an NLP DNN in 5 MinutesBuilding an NLP DNN in 5 Minutes
Building an NLP DNN in 5 MinutesJenny Midwinter
 
Machine Learning meets Granular Computing
Machine Learning meets Granular ComputingMachine Learning meets Granular Computing
Machine Learning meets Granular ComputingJenny Midwinter
 
2016 09-19 - stephan jou - machine learning meetup v1
2016 09-19 - stephan jou - machine learning meetup v12016 09-19 - stephan jou - machine learning meetup v1
2016 09-19 - stephan jou - machine learning meetup v1Jenny Midwinter
 
Machine Learning at Amazon
Machine Learning at AmazonMachine Learning at Amazon
Machine Learning at AmazonJenny Midwinter
 
AI and Machine Learning: The many different approaches
AI and Machine Learning: The many different approachesAI and Machine Learning: The many different approaches
AI and Machine Learning: The many different approachesJenny Midwinter
 

Plus de Jenny Midwinter (11)

Practical Challenges ML Workflows
Practical Challenges ML WorkflowsPractical Challenges ML Workflows
Practical Challenges ML Workflows
 
Machine learning applications in clinical brain computer interfacing
Machine learning applications in clinical brain computer interfacingMachine learning applications in clinical brain computer interfacing
Machine learning applications in clinical brain computer interfacing
 
Augmented Intelligence Bridging the Gap Between BI and AI
Augmented Intelligence  Bridging the Gap Between BI and AIAugmented Intelligence  Bridging the Gap Between BI and AI
Augmented Intelligence Bridging the Gap Between BI and AI
 
Autonomous Learning for Autonomous Systems, by Prof. Plamen Angelov
Autonomous Learning for Autonomous Systems, by Prof. Plamen AngelovAutonomous Learning for Autonomous Systems, by Prof. Plamen Angelov
Autonomous Learning for Autonomous Systems, by Prof. Plamen Angelov
 
Ai and analytics for business
Ai and analytics for businessAi and analytics for business
Ai and analytics for business
 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language Processing
 
Building an NLP DNN in 5 Minutes
Building an NLP DNN in 5 MinutesBuilding an NLP DNN in 5 Minutes
Building an NLP DNN in 5 Minutes
 
Machine Learning meets Granular Computing
Machine Learning meets Granular ComputingMachine Learning meets Granular Computing
Machine Learning meets Granular Computing
 
2016 09-19 - stephan jou - machine learning meetup v1
2016 09-19 - stephan jou - machine learning meetup v12016 09-19 - stephan jou - machine learning meetup v1
2016 09-19 - stephan jou - machine learning meetup v1
 
Machine Learning at Amazon
Machine Learning at AmazonMachine Learning at Amazon
Machine Learning at Amazon
 
AI and Machine Learning: The many different approaches
AI and Machine Learning: The many different approachesAI and Machine Learning: The many different approaches
AI and Machine Learning: The many different approaches
 

Dernier

My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesZilliz
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 

Dernier (20)

My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector Databases
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 

Applying Deep Learning Vision Technology to low-cost/power Embedded Systems

  • 1. © 2016 Synopsys, Inc. 1 Applying Deep Learning Vision Technology to Low-cost, Low-power Embedded Systems: An Industrial Perspective Pierre Paulin Director of R&D 16 January 2016
  • 2. © 2016 Synopsys, Inc. 2 Agenda • Embedded Vision application trends and challenges • Synopsys Embedded Vision Processor Overview • Convolution Neural Networks – Applications, requirements – Dedicated CNN engine for EV – Competitive analysis • Summary & Final Thoughts
  • 3. © 2016 Synopsys, Inc. 3 Embedded Vision is Coming Fast • Embedded Vision is the use of computer vision in embedded systems to interpret meaning from images or video • In cars to improve safety • Surveillance for detection and tracking • In industrial automation to improve quality and control • Estimated $300B+ market in 2020, 35% CAGR 0 50 100 150 200 250 300 350 2013 2014 2015 2016 2017 2018 2019 2020 BillionsofDollars Vision Systems Shipments Sources: ABI Research, Insight Media, Transparency Market Research, Markets And Markets, Synopsys
  • 4. Wide Variety of Vision Applications Cameras Drones Home AutomationRetailGaming Infotainment Augmented RealityMobile SurveillanceADAS
  • 5. © 2016 Synopsys, Inc. 5 Autonomous Driving Buzz 1/14/2016 – U.S. Proposes Spending $4 Billion to Encourage Driverless Cars Obama administration aims to remove hurdles to making autonomous cars more widespread Wall Street Journal 8/17/2016 – Ford's self-driving car 'coming in 2021’ (BBC News) 8/24/2016 – Self-driving taxis roll out in Singapore - beating Uber to it (The Guardian) 10/20/2016 – Elon Musk: You'll be able to summon your driverless Tesla from cross-country (CNN Money) 10/25/2016 – Uber's Self-Driving Truck Makes Its First Delivery: 50000 Beers (Wired)
  • 6. © 2016 Synopsys, Inc. 6 Largest Embedded Vision Application Segment Advanced Driver Assistance Systems Driven By Safety Concerns Source: IC Market Drivers, IC Insights, January 2015 & Trends and Opportunities in Driver Assistance and Automated Driving, IHS Automotive Sep 2015
  • 7. © 2016 Synopsys, Inc. 7 Video Surveillance Markets Growing Rapidly • Global IP Video Surveillance Market expected to grow at CAGR of 37.3% from 2012-20 • Demand driven by – Growing installations of IP cameras – Need for surveillance cameras with better video quality – Limited ability for real-time human analysis http://www.alliedmarketresearch.com/IP-video-surveillance-VSaaS-market 3X Growth Forecast 2013 - 2019 Security (Airports, Govt, Banks, Casinos), Home Surveillance, Retail, Healthcare
  • 8. © 2016 Synopsys, Inc. 8 Less Efficient EV Options Dedicated Embedded Vision Processors EV Challenges Require Embedded Vision Processors Performance Power Area CPUs don’t have math horsepower for fast 2D vision processing GPUs have high performance but large areas and higher power DSPs are designed for low power audio and speech applications, not 2D video FPGAs are good for prototyping but are expensive and performance limited Higher performance Lower power Smaller area Can include a dedicated deep learning (CNN) engine
  • 9. © 2016 Synopsys, Inc. 9 Embedded Vision Applications and Power, Performance and Area (PPA) Requirements
  • 10. © 2016 Synopsys, Inc. 10 Vision Pipeline Example Object detection pipeline Grayscale Conversion Image Pyramid Detecting Areas of Interest in a Frame Non-max Suppression Draw Box
  • 11. © 2016 Synopsys, Inc. 11 Vision Pipeline Example Video surveillance pipeline Grayscale & Image Pyramid Face Detection Tracking & Detection Cascade Fusion & Learning
  • 12. © 2016 Synopsys, Inc. 12 Vision Algorithm Computation • Object detection • Background subtraction • Feature extraction • Image segmentation • Connected comp. labeling • Noise reduction • Color space conversion • Gamma correction • Image scaling • Gaussian pyramid Simple Data-Level Parallelism (DLP) • Good spatial locality • Good compute intensity • Small context More Complex DLP • Complex data structures • Irregular compute intensity • Larger context Scalar Processing • General purpose compute • Thread level parallelism Pre-processing Selecting Areas of Interest Precise Processing of Selected Areas Decision Making • Object recognition • Tracking • Feature matching • Gesture recognition • Motion analysis • Match/no match • Flag events CNN RISC scalar Multi-core Gen2 EV SIMD processorMulti-core Gen1 EV SIMD processor Multi-core CNN Engine
  • 13. © 2016 Synopsys, Inc. 13 Sample Power, Performance and Area Targets • Intelligent video surveillance applications – Face detection & tracking, pose detection, gaze estimation, gender recognition, age estimation – People detection & counting for video surveillance – Driver fatigue detection – Advanced detection and tracking – Implementation on GPP and GP-GPU – Typical customer targets for HD @30 fps Based on 28 nm process node <500 mW 1-2 mm2 10-500 GOP/s 1-10 W 50-100 mm2
  • 14. © 2016 Synopsys, Inc. 14 Sample Power, Performance and Area Targets • ADAS – Pedestrian, vehicle, traffic sign, lane detections – Scene segmentation – Implementation on GPP and GP-GPU – Typical customer targets for HD @30 fps Based on 28 nm process node 100-2000 GOP/s 1-2 W 2-5 mm2 >100 W >100 mm2
  • 15. © 2016 Synopsys, Inc. 15 DesignWare® ARC EV6 Processor and CNN - Vision-specific wide SIMD engine - Optimized CNN engine - Programming tools
  • 16. © 2016 Synopsys, Inc. 16 EV6x Processor Objectives Low power: Over 1000 GMAC/s/W in CNN engine High productivity Highly Scalable Vector Engine 100 GOP/s 620 GOP/s Low area High-performance CNN: Up to 880 MAC/cycle Scalar Vector CNN Standard Programming model Accelerator OpenCL C Most Integrated Solution C/C++ Embedded Vision Libraries Preliminary – Subject to Change
  • 17. © 2016 Synopsys, Inc. 17 EV Processor Solution: EV6x with CNN Engine Embedded Vision Programming Tools Vision CPU (1 to 4 cores) CNN Engine Option Convolution ALU Conv. 2D AGUs CC MEMs Cluster Comm. Shared Mem.DMA Classification AXI Interconnect User kernels Ui Uk C/C++ OpenCL C K1 Kn… Kernel Lib OpenCL C compiler, with whole function vectorization C/C++ compiler Lib Ui Uj Uk Kn Uk Um graph CNN Graph Mapping Tools HAPS® Rapid Prototyping Board Virtual Prototype ALU Conv. 1D AGUs CC MEMs Coherency ARConnect Sync Debug Power Mgmt. Up to 880 MAC/cycle Up to 620 GOP/s at 800 MHz Core 4 Core 3 32b Scalar 512b Vector DSP Core 2 Core 1 32b Scalar 512b Vector DSP VCCMD$I$ VCCMD$I$ CNN graph Cn CNN graph node
  • 18. © 2016 Synopsys, Inc. 18 CNN – Convolution Neural Networks Deep Learning Approach to Embedded Vision
  • 19. © 2016 Synopsys, Inc. 19 CNN for a Wide Range of Vision Applications • Image classification, search similar images • Object detection, classification & localization – Any type of object(s), depending on training phase • Face recognition • Visual attention • Facial expression recognition • Gesture recognition / hand tracking • Resolution upscaling • Scene recognition and labelling, semantic segmentation – Sky, mountain, road, tree, building, … • Recent advocates – Nvidia, Microsoft, Google, Baidu, Adobe, Qualcomm, Yahoo … – Mobileye for autonomous driving car car sky building building road
  • 20. © 2016 Synopsys, Inc. 20 Pedestrian Detection: HoG vs. CNN
  • 21. © 2016 Synopsys, Inc. 21 Computation Requirements for CNN Accuracy Computationalcomplexity Lenet (1994) 4 layers AlexNet (2012) 8 layers 100MByte VGG-19 (2014) 19 layers 270MByte GoogleNet (2014) 22 layer 20MByte ResNet (2015) 152 layers! 10MByte 1 GOPs/frame 10 GOPs/frame
  • 22. © 2016 Synopsys, Inc. 22 Scene Segmentation Source: Press Release by Toshiba and Denso, 17 Oct. 2016
  • 23. © 2016 Synopsys, Inc. 23 Super resolution using CNN Source Bicubic Interpolation CNN Reference Source Bicubic Interpolation CNN Reference “Image Super-Resolution Using Deep Convolutional Networks (2016), C. Dong et al.”
  • 24. © 2016 Synopsys, Inc. 24 Super-Resolution using Convolutional Neural Networks • CNN’s deliver superior Super-Resolution for single image and video • CNN’s for Super-Resolution require dedicated compute engine with high compute capacity • Example “Image Super-Resolution Using Deep Convolutional Networks (2016), C. Dong et al.” Requires 600 GMAC for one 4K frame
  • 25. © 2016 Synopsys, Inc. 25 CNN Graph Training and Porting Image labeling Graph explore, training GPU farm Code vectorization TrainingPorting coeff. Code Object detection executable CNN graph GPP CNN-optimized processor GP-GPU
  • 26. © 2016 Synopsys, Inc. 26 CNN Computation • Convolution of multiple inputs together – Fixed kernel size • Optional subsampling – 1x, 2x, 4x • Optional max-pooling • Very regular, repetitive computation – Dominated by MAC – Deterministic • Non-linear activation function – Rectifier, Sigmoid, Hyperbolic tangent I0 IM-1 I1 O0 ON-1 M inputs (XI * YI) Z kernels (K * K) with associated weights N outputs (XO * YO) Oj = act(Bj+ (Iv x Kw) + …) Convolution (x) act act Activation (tanh, ReLU) …
  • 27. © 2016 Synopsys, Inc. 27 EV6x Second Generation CNN Engine for Object Detection and Semantic Segmentation - High performance, low power and area - Fully programmable car car sky building building
  • 28. © 2016 Synopsys, Inc. 28 High-Performance EV6x CNN Engine • Dedicated EV6x CNN Engine with performance equal or better than GP-GPU • Programmable to support full range of fixed point CNN graphs • State-of-the-art power-efficiency • Real-time, high quality image classification, object recognition, semantic segmentation • Supports resolutions up to 4K • Operates in parallel with Vision CPUs increasing efficiency and throughput AXIInterconnect Vision CPU Core 32 bit RISC 512-bit Vector DSP Cluster Shared Memory DMA ARConnect CNN Engine Convolution Classification Preliminary – Subject to Change ALU Conv. 2D AGUs CC MEMs ALU Conv. 1D AGUs CC MEMs
  • 29. © 2016 Synopsys, Inc. 29 AlexNet on ImageNet Quantization opportunities for recognition tasks 32-bit floating point 16-bit fixed point vs [Moons WACV2016] Recognitionaccuracy Fixed-point word length • 12 bit good compromise between CNN recognition performance and hardware cost – 8 bit will cause recognition rate loss on existing graphs – 12 bit multiplier is almost half the area of a 16 bit multiplier 12-bit
  • 30. © 2016 Synopsys, Inc. 30 CNN data precision – Qualcomm data
  • 31. © 2016 Synopsys, Inc. 31 CNN Competitive Analysis
  • 32. © 2016 Synopsys, Inc. 32 CNN Performance and Area Efficiency Comparison Preliminary – Subject to Change GMAC/s/mm2 10 1000 1 10 100 1000 300X 2X 100 GMAC/s 20X 14X First gen vision processors GP/GPU EV6x Embedded Vision Processor w/integrated CNN Circle area proportional to logic area
  • 33. © 2016 Synopsys, Inc. 33 CNN Performance and Power Efficiency Comparison Preliminary – Subject to Change GMAC/s/W 10 100 1000 10 100 1000 10000 11X 30X GMAC/s EV6x Embedded Vision Processor w/integrated CNN First gen vision processors GP/GPU Circle area proportional to logic area
  • 34. © 2016 Synopsys, Inc. 34 Less Efficient EV Options Dedicated Embedded Vision Processors EV Challenges Require Embedded Vision Processors Performance Power Area CPUs don’t have math horsepower for fast 2D vision processing GPUs have high performance but large areas and higher power DSPs are designed for low power audio and speech applications, not 2D video FPGAs are good for prototyping but are expensive and performance limited High performance Lower power Smaller area Dedicated deep learning (CNN) engine provides PPA numbers compatible with surveillance, ADAS and mobile targets 1000 GMACs/W 100-1000 GOP/s Few mm2
  • 35. Thank You Contact me at: pierre.paulin@synopsys.com