Exploring the Future Potential of AI-Enabled Smartphone Processors
ICIP2013-video stabilization with l1 l2 optimization
1. Video Stabilization with L1-L2
Optimization
Hui Qu, Li Song
Institute of Image Communication and Network
Engineering
Shanghai Jiao Tong University
17 September 2013
2. Outline
Introduction
Benchmark work
Our algorithm
L1-L2 mixed optimization model
Online video stabilization scheme
Experimental results
Conclusion
7. Introduction
Video Stabilization methods
Original camera path estimation
2D camera path——2D linear model
3D camera path——Structure from Motion (SfM)
……
Smooth camera path computation
Filtering
Optimization
……
Synthesizing the stabilized video
Cropping——keep the central part
Inpainting——full frame
……
8. Grundmann et al. 2011
L1 camera path optimization
Integrated into Google ‘s YouTube Editor
Benchmark work
L1 Camera Path Optimization method
Original camera path: 𝐶
Optimal camera path: 𝑃
9. Objective function:
D means derivative operator
𝜔1, 𝜔2, 𝜔3 are empirical weights
2 3
1 2 31 1 1
( ) ( ) ( ) ( )P D P D P D P
Benchmark work
L1 Camera Path Optimization method
constant path
static camera
10. Objective function:
2 3
1 2 31 1 1
( ) ( ) ( ) ( )P D P D P D P
Benchmark work
L1 Camera Path Optimization method
path with constant
velocity
panning or
dolly shot
11. Objective function:
2 3
1 2 31 1 1
( ) ( ) ( ) ( )P D P D P D P
Benchmark work
L1 Camera Path Optimization method
path with constant
acceleration
ease in and out
transition
13. Benchmark work
Problem of L1 Path Method
The method discards information due to cropping
not suitable for videos with important information near the
boundary.
14. Benchmark work
Problem of L1 Path Method
𝜔1, 𝜔2, 𝜔3 are empirically set
hard to be adaptable to different kinds of videos
sequence 1 sequence 2
15. Our algorithm
L1-L2 mixed optimization model
Objective function:
2 3
1 1 1 2
( ) ( ) ( ) ( )P D P D P D P P C
L1 part, ensure smoothness
L2 part, ensure proximity to original path
weight, adjust the degree of smoothness and fidelity
16. Our algorithm
L1-L2 mixed optimization model
Objective function:
2 3
1 1 1 2
( ) ( ) ( ) ( )P D P D P D P P C
17. Our algorithm
L1-L2 mixed optimization model
Objective function:
2 3
1 1 1 2
( ) ( ) ( ) ( )P D P D P D P P C
30. Conclusion
Video stabilization method by mixed L1-
L2 optimization
Stabilize & preserve video content
Adjust the degree of stabilization according
to different demands
Able to handle online stabilization and
unlimited length videos