Download - Background Subtraction
Outline
What is background subtraction?
Project motivation
How is BGS performed and what makes it difficult?
Project goals and results
Concluding remarks
What is background subtraction?
Real-time method for identifying moving foreground objects within a video
Project motivation BGS is an important low-level step in
many computer vision applications: Video surveillance Traffic monitoring FG/BG segmentation
My interest is in using BGS to extract human silhouettes for pose estimation
How “good” are the obtained silhouettes in unconstrained environment?
Images from: Sminchisescu and Telea, “Human Pose Estimation from Silhouettes”, 2002.
How is BGS performed?
Static frame differencing BG model = first frame of video
BGDifferencing
Input Stream
BG Model
Output Masks
Threshold
Adaptive, statistical BG models
BGDifferencing
Mean
Input Stream
BG Model
Output Masks
Threshold
Update BGModel
0 50 100 150 200 2500
0.005
0.01
0.015
0.02
0.025
0.03
Component Value
Pro
babi
lity
0 50 100 150 200 2500
0.005
0.01
0.015
0.02
0.025
0.03
Component Value
Pro
babi
lity
0 50 100 150 200 2500
0.005
0.01
0.015
0.02
0.025
0.03
Component Value
Pro
babi
lity
Variance
Gaussian Pixel Model
Shadow removal
Shadows have little effect on chromaticity, but reduce luminosity
BGDifferencing
Mean
Input Stream
BG Model
Output Masks
Threshold
Update BGModel
Variance
ShadowRemoval
Ghost detection via optical flow
Low optical flow = ghost!
BGDifferencing
Mean
Input Stream
BG Model
Output Masks
Threshold
Update BGModel
Variance
ShadowRemoval
ConnectedComponents
OpticalFlow Test
Project goals
Evaluate a selection of state-of-the-art background subtraction algorithms Considering 10 algorithms in all
Analyze how post-processing influences the performance of these algorithms Shadow removal Optical flow testing Morphological “cleaning” Area thresholding
Conclusions
Many factors which make BGS difficult
Post-processing can significantly improve results
Results not as “clean” as more computationally expensive approaches