SlideShare une entreprise Scribd logo
1  sur  26
Télécharger pour lire hors ligne
Evaluation of Vision-based Human Activity
Recognition in Dense Trajectory Framework
Hirokatsu Kataoka, Yoshimitsu Aoki†, Kenji Iwata, Yutaka Satoh
National Institute of Advanced Industrial Science and Technology (AIST)
† Keio University
http://www.hirokatsukataoka.net/
Background
Computer vision for human sensing
-  Detection, Tracking, Trajectory Analysis
-  Posture Estimation, Activity Recognition
-  Action recognition is able to extend human sensing applications
Mental state
Body Situation
Attention
Activity Analysis
shakinghands
Look at people
Detection
Gaze Estimation
Action Recognition
Posture Estimation
Face Recognition
Trajectory extraction
Tracking
Activity Recognition
“Activity” is a low-level primitive with semantic meaning
e.g. walking, running, sitting
This image contains a man walking
- The classification (location is given)
Activity recognition
- The classification and localization
Activity detection
Walking
Dense Trajectories (DT) [Wang+, IJCV2013]
•  State-of-the-art space-time recognition approach
–  State-of-the-art: DT + Deep Learning [THUMOS2015]
–  Usable motion analyzer
–  Simply, (i) flow tracker (ii) feature vectorization
Large amount of opt. flows
[THUMOS2015] http://www.thumos.info/results.html
History of keypoint/traj.-based approach
•  Space-time interest points (STIP) – DT
STIP: Space-time interest points	
[Laptev et al., IJCV2005]	
Dense Trajectories	
[Wang et al., CVPR2
[Laptev et al., CVPR2008]	
HOG + HOF on STIP	
Feature Mining for Activity Recognition	
[Gilbert et al., PAMI2011]	
Cuboid
Features	
[Dollar et al., PETS2005]	
STR: Spatio-Temporal Relationship Match	
[Ryoo et al., ICCV2009]	
[Raptis et al., ECCV2010]	
Tracklet Descriptors
STIP & DT: Sampling
•  Space-time interest points (STIP) – DT
STIP: Space-time interest points	
[Laptev et al., IJCV2005]	
Dense Trajectories	
[Wang et al., CVPR2011]	
Action Bank	
[Sadanand et al., CVPR2012]	
[Laptev et al., CVPR2008]	
HOG + HOF on STIP	
Feature Mining for Activity Recognition	
[Gilbert et al., PAMI2011]	
Cuboid
Features	
[Dollar et al., PETS2005]	
STR: Spatio-Temporal Relationship Match	
[Ryoo et al., ICCV2009]	
[Raptis et al., ECCV2010]	
Tracklet Descriptors
Co-occurrence features in DT
•  Extended co-occurrence feature (ECoHOG)
–  Feature
•  CoHOG[Watanabe, PSIVT2009] (pair-count), ECoHOG (edge-magnitude accum.)
•  PCA for codeword
•  DT+Co-occurrence features (62.4%) > DT (59.2%) on MPII cooking
CoHOG
ECoHOG
H. Kataoka+, “Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity Recognition”, in ACCV2014.
Need for more features!
Pose-based approach	
Holistic appraoch
Proposal
•  Feature evaluation for more better performance
–  Evaluation of 13 features at fair settings
–  5 Category
•  Trajectory: traj. feature (originally in DT)
•  Shape: HOG, SIFT
•  Motion: HOF, MBHx, MBHy, MIP
•  Texture: HLAC, LBP, iLBP, LTP
•  Co-occurrence: CoHOG, ECoHOG
–  4 different datasets
•  NTSEL (traffic)
•  INRIA surgery (surgery)
•  MSR daily activity 3d (daily living)
•  UCF50 (sports)
Simple algorithm
•  (i) Flow tracking
–  Pyramidal images & sampling
–  Farneback optical flow & flow tracking
•  (ii) Feature vectorization
–  HOG, HOF, MBH, Trajectory, SIFT, LBP…..
–  Bag-of-words (BoW) representation
Pyramidal images & sampling
•  Scaling and dense sampling
–  Pyramidal images
•  Scales *= 1/√2
–  Sampling at each scale
•  Grid: 5x5 [pxls] (experimentally decided)
•  Corner detection T: threshold, λ: eigen value
Scale invariant
Detailed description
Farneback Optical Flow
•  Dense Optical Flow + ST-patch
–  Farneback Optical Flow is included OpenCV
–  Comparison of KLT tracker and SIFT
–  Local space-time patch around tracked sampling points
Noises
Tracking-error
Trajectory-based feature
•  Trajectory shape
–  Calculating flow between frames
–  Scale normalization
Pt = (Pt+1 − Pt) = (xt+1 − xt, yt+1 − yt)	
[Wang+, IJCV2013]
Shape-based feature
•  HOG, SIFT Edge-orient., mag. from block representation
with overlapping and normalization
Edge-shape from background
Simply divided 4x4 blocks
[Lowe, IJCV2004]
[Dalal+, CVPR2005]
Motion
•  HOF, MBHx, MBHy, MIP
Block optical flow extraction
Quantization
Motion boundary with dense optical flow [Dalal+, ECCV2006]
Trinary (-1, 0, +1) from block flow direction, [Kliper-Gross+, ECCV2012]
[Laptev+, CVPR2008]
Texture
•  HLAC, LBP, iLBP, LTP
Higher-order local auto-correlation
0-, 1st-, 2nd- order pattern
Texture binarization in a 3x3 patch, [Ojala+, TPAMI2002]
[Otsu+, IAIP1988] [Kobayashi+, ICPR2004]
Co-occurrence
•  Extended co-occurrence feature (ECoHOG)
–  Feature
•  CoHOG[Watanabe, PSIVT2009] (pair-count), ECoHOG (edge-magnitude accum.)
•  PCA for codeword
•  DT+Co-occurrence features (62.4%) > DT (59.2%) on MPII cooking
CoHOG ECoHOG
H. Kataoka+, “Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity Recognition”, in ACCV2014.
Experiments
•  Evaluation of 13 features in dense trajectory
framework
–  4 different datasets
•  Traffic scene (NTSEL dataset): 4 classes
•  Surgery (INRIA surgery): 4 classes
•  Daily living (MSR daily action 3D): 12 classes
•  Sports (UCF50): 50 classes
Results on the 4 datasets
•  High-performance features
–  Top three features at each dataset
–  4 different scenes
Results on the 4 datasets
•  High-performance features
–  CoHOG, SIFT, MBH
–  CoHOG is the stable accuracy at all datasets
Detailed performance rate
•  Depending on recognition task!
–  We need to experimentally concatenate several features
–  Feature concatenation on the NTSEL and INRIA surgery
Rate of feature concatenation
•  Baseline, 5 categories and concatenated vector
–  Baseline: DT + BoW model
–  Motion and co-occurrence feature
–  No need to apply all features
Conclusion
•  We evaluated 13 features in the framework of DT
–  For more effective activity recognition
–  4 different scenes at each dataset
–  Detailed evaluation and concatenated vectors
–  Top-N ranked concatenation is needed for activity recognition
Feature extraction
Around trajectories
–  Extraction of 13 features in ST-patch
–  2 (x dir.) x 2 (y dir.) x 3 (t dir.) region
–  Calculating features with bag-of-words(BoW)
ST-patch and xyt block extraction
13 features extractioin
Trajectory feature
•  Trajectory shape
–  フレーム間のフローを算出
–  全体のフローの大きさで正規化
Pt = (Pt+1 − Pt) = (xt+1 − xt, yt+1 − yt)
HOG特徴量
•  Histograms of Oriented Gradients (HOG)
–  物体のおおまかな形状を表現可能
–  局所領域をブロック分割して特徴取得
–  エッジ勾配(下式g(x,y))により量子化ヒストグラム作成
–  勾配毎のエッジ強度(下式m(x,y))を累積
歩行者画像から取得した形状
背景から取得した形状
HOF特徴量
•  Histograms of Optical Flow (HOF)
–  局所領域をブロック毎に分割
–  前後フレーム(tとt+1)のフローをブロックごとに記述
–  フロー方向と強度(長さ)
前後2フレームからフローを算出
動作ベースの特徴ベクトルを取得

Contenu connexe

Tendances

Tendances (20)

Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...Faster R-CNN: Towards real-time object detection with region proposal network...
Faster R-CNN: Towards real-time object detection with region proposal network...
 
IRJET- Behavior Analysis from Videos using Motion based Feature Extraction
IRJET-  	  Behavior Analysis from Videos using Motion based Feature ExtractionIRJET-  	  Behavior Analysis from Videos using Motion based Feature Extraction
IRJET- Behavior Analysis from Videos using Motion based Feature Extraction
 
GAN Evaluation
GAN EvaluationGAN Evaluation
GAN Evaluation
 
Physics informed deep learning for efficient b-mode ultrasound imaging
Physics informed deep learning for efficient b-mode ultrasound imagingPhysics informed deep learning for efficient b-mode ultrasound imaging
Physics informed deep learning for efficient b-mode ultrasound imaging
 
Tatsuya Sueki Master thesis
Tatsuya Sueki Master thesisTatsuya Sueki Master thesis
Tatsuya Sueki Master thesis
 
Variational formulation of unsupervised deep learning for ultrasound image ar...
Variational formulation of unsupervised deep learning for ultrasound image ar...Variational formulation of unsupervised deep learning for ultrasound image ar...
Variational formulation of unsupervised deep learning for ultrasound image ar...
 
[DL輪読会]ClearGrasp
[DL輪読会]ClearGrasp[DL輪読会]ClearGrasp
[DL輪読会]ClearGrasp
 
PR098: MegaDepth: Learning Single-View Depth Prediction from Internet Photos
PR098: MegaDepth: Learning Single-View Depth Prediction from Internet PhotosPR098: MegaDepth: Learning Single-View Depth Prediction from Internet Photos
PR098: MegaDepth: Learning Single-View Depth Prediction from Internet Photos
 
PR-240: Modulating Image Restoration with Continual Levels via Adaptive Featu...
PR-240: Modulating Image Restoration with Continual Levels viaAdaptive Featu...PR-240: Modulating Image Restoration with Continual Levels viaAdaptive Featu...
PR-240: Modulating Image Restoration with Continual Levels via Adaptive Featu...
 
ISM2014
ISM2014ISM2014
ISM2014
 
One-Pass Clustering Superpixels
One-Pass Clustering SuperpixelsOne-Pass Clustering Superpixels
One-Pass Clustering Superpixels
 
Comparison of Matrix Completion Algorithms for Background Initialization in V...
Comparison of Matrix Completion Algorithms for Background Initialization in V...Comparison of Matrix Completion Algorithms for Background Initialization in V...
Comparison of Matrix Completion Algorithms for Background Initialization in V...
 
Deep Learning - a Path from Big Data Indexing to Robotic Applications
Deep Learning - a Path from Big Data Indexing to Robotic ApplicationsDeep Learning - a Path from Big Data Indexing to Robotic Applications
Deep Learning - a Path from Big Data Indexing to Robotic Applications
 
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCEHUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
 
物体検出の歴史(R-CNNからSSD・YOLOまで)
物体検出の歴史(R-CNNからSSD・YOLOまで)物体検出の歴史(R-CNNからSSD・YOLOまで)
物体検出の歴史(R-CNNからSSD・YOLOまで)
 
I0343065072
I0343065072I0343065072
I0343065072
 
Benchmarking of indoor localization and tracking systems (LTSs)
Benchmarking of indoor localization and tracking systems (LTSs)Benchmarking of indoor localization and tracking systems (LTSs)
Benchmarking of indoor localization and tracking systems (LTSs)
 
When Remote Sensing Meets Artificial Intelligence
When Remote Sensing Meets Artificial IntelligenceWhen Remote Sensing Meets Artificial Intelligence
When Remote Sensing Meets Artificial Intelligence
 
Review : Rethinking Pre-training and Self-training
Review : Rethinking Pre-training and Self-trainingReview : Rethinking Pre-training and Self-training
Review : Rethinking Pre-training and Self-training
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ
 

En vedette

En vedette (15)

【CVPR2016_LAP】Dominant Codewords Selection with Topic Model for Action Recogn...
【CVPR2016_LAP】Dominant Codewords Selection with Topic Model for Action Recogn...【CVPR2016_LAP】Dominant Codewords Selection with Topic Model for Action Recogn...
【CVPR2016_LAP】Dominant Codewords Selection with Topic Model for Action Recogn...
 
ILSVRC2015 手法のメモ
ILSVRC2015 手法のメモILSVRC2015 手法のメモ
ILSVRC2015 手法のメモ
 
【慶應大学講演】なぜ、博士課程に進学したか?
【慶應大学講演】なぜ、博士課程に進学したか?【慶應大学講演】なぜ、博士課程に進学したか?
【慶應大学講演】なぜ、博士課程に進学したか?
 
PythonによるCVアルゴリズム実装
PythonによるCVアルゴリズム実装PythonによるCVアルゴリズム実装
PythonによるCVアルゴリズム実装
 
【論文紹介】Fashion Style in 128 Floats: Joint Ranking and Classification using Wea...
【論文紹介】Fashion Style in 128 Floats: Joint Ranking and Classification using Wea...【論文紹介】Fashion Style in 128 Floats: Joint Ranking and Classification using Wea...
【論文紹介】Fashion Style in 128 Floats: Joint Ranking and Classification using Wea...
 
Deep Residual Learning (ILSVRC2015 winner)
Deep Residual Learning (ILSVRC2015 winner)Deep Residual Learning (ILSVRC2015 winner)
Deep Residual Learning (ILSVRC2015 winner)
 
TensorFlowによるCNNアーキテクチャ構築
TensorFlowによるCNNアーキテクチャ構築TensorFlowによるCNNアーキテクチャ構築
TensorFlowによるCNNアーキテクチャ構築
 
ECCV 2016 速報
ECCV 2016 速報ECCV 2016 速報
ECCV 2016 速報
 
CVPR 2016 速報
CVPR 2016 速報CVPR 2016 速報
CVPR 2016 速報
 
【チュートリアル】コンピュータビジョンによる動画認識
【チュートリアル】コンピュータビジョンによる動画認識【チュートリアル】コンピュータビジョンによる動画認識
【チュートリアル】コンピュータビジョンによる動画認識
 
【2016.08】cvpaper.challenge2016
【2016.08】cvpaper.challenge2016【2016.08】cvpaper.challenge2016
【2016.08】cvpaper.challenge2016
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
 
20150930
2015093020150930
20150930
 
Convolutional Neural Networks のトレンド @WBAFLカジュアルトーク#2
Convolutional Neural Networks のトレンド @WBAFLカジュアルトーク#2Convolutional Neural Networks のトレンド @WBAFLカジュアルトーク#2
Convolutional Neural Networks のトレンド @WBAFLカジュアルトーク#2
 
CVPR 2016 まとめ v1
CVPR 2016 まとめ v1CVPR 2016 まとめ v1
CVPR 2016 まとめ v1
 

Similaire à 【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Trajectory Framework

Gait Recognition for Person Identification using Statistics of SURF
Gait Recognition for Person Identification using Statistics of SURFGait Recognition for Person Identification using Statistics of SURF
Gait Recognition for Person Identification using Statistics of SURF
ijtsrd
 
TechnicalBackgroundOverview
TechnicalBackgroundOverviewTechnicalBackgroundOverview
TechnicalBackgroundOverview
Motaz El-Saban
 
MICCAI CLIP 2013 - Endoscopy Navigation System
MICCAI CLIP 2013 - Endoscopy Navigation SystemMICCAI CLIP 2013 - Endoscopy Navigation System
MICCAI CLIP 2013 - Endoscopy Navigation System
Frederic Perez
 
Mobile operator study webinar final am19012011
Mobile operator study webinar final am19012011Mobile operator study webinar final am19012011
Mobile operator study webinar final am19012011
UserZoom
 
An Innovative Moving Object Detection and Tracking System by Using Modified R...
An Innovative Moving Object Detection and Tracking System by Using Modified R...An Innovative Moving Object Detection and Tracking System by Using Modified R...
An Innovative Moving Object Detection and Tracking System by Using Modified R...
sipij
 

Similaire à 【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Trajectory Framework (20)

Human action recognition with kinect using a joint motion descriptor
Human action recognition with kinect using a joint motion descriptorHuman action recognition with kinect using a joint motion descriptor
Human action recognition with kinect using a joint motion descriptor
 
Human Action Recognition Using 3D Joint Information and HOOFD Features
Human Action Recognition Using 3D Joint Information and HOOFD FeaturesHuman Action Recognition Using 3D Joint Information and HOOFD Features
Human Action Recognition Using 3D Joint Information and HOOFD Features
 
ACTIVITY RECOGNITION USING HISTOGRAM OF ORIENTED GRADIENT PATTERN HISTORY
ACTIVITY RECOGNITION USING HISTOGRAM OF ORIENTED GRADIENT PATTERN HISTORYACTIVITY RECOGNITION USING HISTOGRAM OF ORIENTED GRADIENT PATTERN HISTORY
ACTIVITY RECOGNITION USING HISTOGRAM OF ORIENTED GRADIENT PATTERN HISTORY
 
ACTIVITY RECOGNITION USING HISTOGRAM OF ORIENTED GRADIENT PATTERN HISTORY
ACTIVITY RECOGNITION USING HISTOGRAM OF ORIENTED GRADIENT PATTERN HISTORYACTIVITY RECOGNITION USING HISTOGRAM OF ORIENTED GRADIENT PATTERN HISTORY
ACTIVITY RECOGNITION USING HISTOGRAM OF ORIENTED GRADIENT PATTERN HISTORY
 
Embedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour ScienceEmbedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour Science
 
Silhouette analysis based action recognition via exploiting human poses
Silhouette analysis based action recognition via exploiting human posesSilhouette analysis based action recognition via exploiting human poses
Silhouette analysis based action recognition via exploiting human poses
 
Activity recognition using histogram of
Activity recognition using histogram ofActivity recognition using histogram of
Activity recognition using histogram of
 
Fast Feature Pyramids for Object Detection
Fast Feature Pyramids for Object DetectionFast Feature Pyramids for Object Detection
Fast Feature Pyramids for Object Detection
 
On the Development of A Real-Time Multi-Sensor Activity Recognition System
On the Development of A Real-Time Multi-Sensor Activity Recognition SystemOn the Development of A Real-Time Multi-Sensor Activity Recognition System
On the Development of A Real-Time Multi-Sensor Activity Recognition System
 
feature processing and modelling for 6D motion gesture database.....
feature processing and modelling for 6D motion gesture database.....feature processing and modelling for 6D motion gesture database.....
feature processing and modelling for 6D motion gesture database.....
 
Gait Recognition for Person Identification using Statistics of SURF
Gait Recognition for Person Identification using Statistics of SURFGait Recognition for Person Identification using Statistics of SURF
Gait Recognition for Person Identification using Statistics of SURF
 
Symbolic representation and recognition of gait an approach based on lbp of ...
Symbolic representation and recognition of gait  an approach based on lbp of ...Symbolic representation and recognition of gait  an approach based on lbp of ...
Symbolic representation and recognition of gait an approach based on lbp of ...
 
TechnicalBackgroundOverview
TechnicalBackgroundOverviewTechnicalBackgroundOverview
TechnicalBackgroundOverview
 
MICCAI CLIP 2013 - Endoscopy Navigation System
MICCAI CLIP 2013 - Endoscopy Navigation SystemMICCAI CLIP 2013 - Endoscopy Navigation System
MICCAI CLIP 2013 - Endoscopy Navigation System
 
PDR for lab-forming field and its benchmarking
PDR for lab-forming field and its benchmarkingPDR for lab-forming field and its benchmarking
PDR for lab-forming field and its benchmarking
 
Soundarya m.sc
Soundarya m.scSoundarya m.sc
Soundarya m.sc
 
Mobile operator study webinar final am19012011
Mobile operator study webinar final am19012011Mobile operator study webinar final am19012011
Mobile operator study webinar final am19012011
 
An Innovative Moving Object Detection and Tracking System by Using Modified R...
An Innovative Moving Object Detection and Tracking System by Using Modified R...An Innovative Moving Object Detection and Tracking System by Using Modified R...
An Innovative Moving Object Detection and Tracking System by Using Modified R...
 
HUMAN IDENTIFIER WITH MANNERISM USING DEEP LEARNING
HUMAN IDENTIFIER WITH MANNERISM USING DEEP LEARNINGHUMAN IDENTIFIER WITH MANNERISM USING DEEP LEARNING
HUMAN IDENTIFIER WITH MANNERISM USING DEEP LEARNING
 
HOL, GDCT AND LDCT FOR PEDESTRIAN DETECTION
HOL, GDCT AND LDCT FOR PEDESTRIAN DETECTIONHOL, GDCT AND LDCT FOR PEDESTRIAN DETECTION
HOL, GDCT AND LDCT FOR PEDESTRIAN DETECTION
 

Dernier

Pests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdf
PirithiRaju
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
Areesha Ahmad
 
biology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGYbiology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGY
1301aanya
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
Areesha Ahmad
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
PirithiRaju
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Sérgio Sacani
 
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
ssuser79fe74
 
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxSCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
RizalinePalanog2
 

Dernier (20)

Pests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdf
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
 
CELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdfCELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdf
 
Zoology 5th semester notes( Sumit_yadav).pdf
Zoology 5th semester notes( Sumit_yadav).pdfZoology 5th semester notes( Sumit_yadav).pdf
Zoology 5th semester notes( Sumit_yadav).pdf
 
biology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGYbiology HL practice questions IB BIOLOGY
biology HL practice questions IB BIOLOGY
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
 
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
 
GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICESAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
 
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
 
Clean In Place(CIP).pptx .
Clean In Place(CIP).pptx                 .Clean In Place(CIP).pptx                 .
Clean In Place(CIP).pptx .
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
 
Call Girls Alandi Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Alandi Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Alandi Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Alandi Call Me 7737669865 Budget Friendly No Advance Booking
 
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptxSCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
SCIENCE-4-QUARTER4-WEEK-4-PPT-1 (1).pptx
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdf
 

【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Trajectory Framework

  • 1. Evaluation of Vision-based Human Activity Recognition in Dense Trajectory Framework Hirokatsu Kataoka, Yoshimitsu Aoki†, Kenji Iwata, Yutaka Satoh National Institute of Advanced Industrial Science and Technology (AIST) † Keio University http://www.hirokatsukataoka.net/
  • 2. Background Computer vision for human sensing -  Detection, Tracking, Trajectory Analysis -  Posture Estimation, Activity Recognition -  Action recognition is able to extend human sensing applications Mental state Body Situation Attention Activity Analysis shakinghands Look at people Detection Gaze Estimation Action Recognition Posture Estimation Face Recognition Trajectory extraction Tracking
  • 3. Activity Recognition “Activity” is a low-level primitive with semantic meaning e.g. walking, running, sitting This image contains a man walking - The classification (location is given) Activity recognition - The classification and localization Activity detection Walking
  • 4. Dense Trajectories (DT) [Wang+, IJCV2013] •  State-of-the-art space-time recognition approach –  State-of-the-art: DT + Deep Learning [THUMOS2015] –  Usable motion analyzer –  Simply, (i) flow tracker (ii) feature vectorization Large amount of opt. flows [THUMOS2015] http://www.thumos.info/results.html
  • 5. History of keypoint/traj.-based approach •  Space-time interest points (STIP) – DT STIP: Space-time interest points [Laptev et al., IJCV2005] Dense Trajectories [Wang et al., CVPR2 [Laptev et al., CVPR2008] HOG + HOF on STIP Feature Mining for Activity Recognition [Gilbert et al., PAMI2011] Cuboid Features [Dollar et al., PETS2005] STR: Spatio-Temporal Relationship Match [Ryoo et al., ICCV2009] [Raptis et al., ECCV2010] Tracklet Descriptors
  • 6. STIP & DT: Sampling •  Space-time interest points (STIP) – DT STIP: Space-time interest points [Laptev et al., IJCV2005] Dense Trajectories [Wang et al., CVPR2011] Action Bank [Sadanand et al., CVPR2012] [Laptev et al., CVPR2008] HOG + HOF on STIP Feature Mining for Activity Recognition [Gilbert et al., PAMI2011] Cuboid Features [Dollar et al., PETS2005] STR: Spatio-Temporal Relationship Match [Ryoo et al., ICCV2009] [Raptis et al., ECCV2010] Tracklet Descriptors
  • 7. Co-occurrence features in DT •  Extended co-occurrence feature (ECoHOG) –  Feature •  CoHOG[Watanabe, PSIVT2009] (pair-count), ECoHOG (edge-magnitude accum.) •  PCA for codeword •  DT+Co-occurrence features (62.4%) > DT (59.2%) on MPII cooking CoHOG ECoHOG H. Kataoka+, “Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity Recognition”, in ACCV2014. Need for more features! Pose-based approach Holistic appraoch
  • 8. Proposal •  Feature evaluation for more better performance –  Evaluation of 13 features at fair settings –  5 Category •  Trajectory: traj. feature (originally in DT) •  Shape: HOG, SIFT •  Motion: HOF, MBHx, MBHy, MIP •  Texture: HLAC, LBP, iLBP, LTP •  Co-occurrence: CoHOG, ECoHOG –  4 different datasets •  NTSEL (traffic) •  INRIA surgery (surgery) •  MSR daily activity 3d (daily living) •  UCF50 (sports)
  • 9. Simple algorithm •  (i) Flow tracking –  Pyramidal images & sampling –  Farneback optical flow & flow tracking •  (ii) Feature vectorization –  HOG, HOF, MBH, Trajectory, SIFT, LBP….. –  Bag-of-words (BoW) representation
  • 10. Pyramidal images & sampling •  Scaling and dense sampling –  Pyramidal images •  Scales *= 1/√2 –  Sampling at each scale •  Grid: 5x5 [pxls] (experimentally decided) •  Corner detection T: threshold, λ: eigen value Scale invariant Detailed description
  • 11. Farneback Optical Flow •  Dense Optical Flow + ST-patch –  Farneback Optical Flow is included OpenCV –  Comparison of KLT tracker and SIFT –  Local space-time patch around tracked sampling points Noises Tracking-error
  • 12. Trajectory-based feature •  Trajectory shape –  Calculating flow between frames –  Scale normalization Pt = (Pt+1 − Pt) = (xt+1 − xt, yt+1 − yt) [Wang+, IJCV2013]
  • 13. Shape-based feature •  HOG, SIFT Edge-orient., mag. from block representation with overlapping and normalization Edge-shape from background Simply divided 4x4 blocks [Lowe, IJCV2004] [Dalal+, CVPR2005]
  • 14. Motion •  HOF, MBHx, MBHy, MIP Block optical flow extraction Quantization Motion boundary with dense optical flow [Dalal+, ECCV2006] Trinary (-1, 0, +1) from block flow direction, [Kliper-Gross+, ECCV2012] [Laptev+, CVPR2008]
  • 15. Texture •  HLAC, LBP, iLBP, LTP Higher-order local auto-correlation 0-, 1st-, 2nd- order pattern Texture binarization in a 3x3 patch, [Ojala+, TPAMI2002] [Otsu+, IAIP1988] [Kobayashi+, ICPR2004]
  • 16. Co-occurrence •  Extended co-occurrence feature (ECoHOG) –  Feature •  CoHOG[Watanabe, PSIVT2009] (pair-count), ECoHOG (edge-magnitude accum.) •  PCA for codeword •  DT+Co-occurrence features (62.4%) > DT (59.2%) on MPII cooking CoHOG ECoHOG H. Kataoka+, “Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity Recognition”, in ACCV2014.
  • 17. Experiments •  Evaluation of 13 features in dense trajectory framework –  4 different datasets •  Traffic scene (NTSEL dataset): 4 classes •  Surgery (INRIA surgery): 4 classes •  Daily living (MSR daily action 3D): 12 classes •  Sports (UCF50): 50 classes
  • 18. Results on the 4 datasets •  High-performance features –  Top three features at each dataset –  4 different scenes
  • 19. Results on the 4 datasets •  High-performance features –  CoHOG, SIFT, MBH –  CoHOG is the stable accuracy at all datasets
  • 20. Detailed performance rate •  Depending on recognition task! –  We need to experimentally concatenate several features –  Feature concatenation on the NTSEL and INRIA surgery
  • 21. Rate of feature concatenation •  Baseline, 5 categories and concatenated vector –  Baseline: DT + BoW model –  Motion and co-occurrence feature –  No need to apply all features
  • 22. Conclusion •  We evaluated 13 features in the framework of DT –  For more effective activity recognition –  4 different scenes at each dataset –  Detailed evaluation and concatenated vectors –  Top-N ranked concatenation is needed for activity recognition
  • 23. Feature extraction Around trajectories –  Extraction of 13 features in ST-patch –  2 (x dir.) x 2 (y dir.) x 3 (t dir.) region –  Calculating features with bag-of-words(BoW) ST-patch and xyt block extraction 13 features extractioin
  • 24. Trajectory feature •  Trajectory shape –  フレーム間のフローを算出 –  全体のフローの大きさで正規化 Pt = (Pt+1 − Pt) = (xt+1 − xt, yt+1 − yt)
  • 25. HOG特徴量 •  Histograms of Oriented Gradients (HOG) –  物体のおおまかな形状を表現可能 –  局所領域をブロック分割して特徴取得 –  エッジ勾配(下式g(x,y))により量子化ヒストグラム作成 –  勾配毎のエッジ強度(下式m(x,y))を累積 歩行者画像から取得した形状 背景から取得した形状
  • 26. HOF特徴量 •  Histograms of Optical Flow (HOF) –  局所領域をブロック毎に分割 –  前後フレーム(tとt+1)のフローをブロックごとに記述 –  フロー方向と強度(長さ) 前後2フレームからフローを算出 動作ベースの特徴ベクトルを取得