more sliding window detection: discriminative part-based models many slides based on p....
TRANSCRIPT
![Page 1: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/1.jpg)
More sliding window detection:Discriminative part-based models
Many slides based on P. Felzenszwalb
![Page 2: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/2.jpg)
Challenge: Generic object detection
![Page 3: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/3.jpg)
Pedestrian detection• Features: Histograms of oriented gradients (HOG)
• Partition image into 8x8 pixel blocks and compute histogram of gradient orientations in each block
• Learn a pedestrian template using a linear support vector machine• At test time, convolve feature map with template
N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, CVPR 2005
TemplateHOG feature map Detector response map
![Page 4: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/4.jpg)
Discriminative part-based models
P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan, Object Detection with Discriminatively Trained Part Based Models, PAMI 32(9),
2010
Root filter
Part filters
Deformation weights
![Page 5: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/5.jpg)
Object hypothesis• Multiscale model: the resolution of part
filters is twice the resolution of the root
![Page 6: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/6.jpg)
Scoring an object hypothesis• The score of a hypothesis is the sum of filter scores
minus the sum of deformation costs
),,,()(),...,( 22
0 10 ii
n
i
n
iiiiiin dydxdydxDpHFppscore
Filters
Subwindow features
Deformation weights
Displacements
![Page 7: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/7.jpg)
Scoring an object hypothesis• The score of a hypothesis is the sum of filter scores
minus the sum of deformation costs
• Recall: pictorial structures
i ji
jiijiin lldlmllE,
1 ),()(),...,(
Matching cost
Deformation cost
),,,()(),...,( 22
0 10 ii
n
i
n
iiiiiin dydxdydxDpHFppscore
Filters
Subwindow features
Deformation weights
Displacements
![Page 8: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/8.jpg)
Scoring an object hypothesis• The score of a hypothesis is the sum of filter scores
minus the sum of deformation costs
)()( zHwzscore
Concatenation of filter and deformation
weights
Concatenation of subwindow features and displacements
),,,()(),...,( 22
0 10 ii
n
i
n
iiiiiin dydxdydxDpHFppscore
Filters
Subwindow features
Deformation weights
Displacements
![Page 9: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/9.jpg)
Detection• Define the score of each root filter location as the
score given the best part placements:
),...,(max)( 0,...,
01
npp
ppscorepscoren
![Page 10: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/10.jpg)
Detection• Define the score of each root filter location as the
score given the best part placements:
• Efficient computation: generalized distance transforms• For each “default” part location, find the best-
scoring displacement
),...,(max)( 0,...,
01
npp
ppscorepscoren
),,,(),(max),( 22
,dydxdydxDdyydxxHFyxR ii
dydxi
Head filterHead filter responsesDistance transform
![Page 11: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/11.jpg)
Detection
![Page 12: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/12.jpg)
Matching result
![Page 13: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/13.jpg)
Training• Training data consists of images with labeled
bounding boxes• Need to learn the filters and deformation parameters
![Page 14: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/14.jpg)
Training• Our classifier has the form
• w are model parameters, z are latent hypotheses
• Latent SVM training:• Initialize w and iterate:
• Fix w and find the best z for each training example (detection)• Fix z and solve for w (standard SVM training)
• Issue: too many negative examples• Do “data mining” to find “hard” negatives
),(max)( zxHwxf z
![Page 15: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/15.jpg)
Car model
Component 1
Component 2
![Page 16: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/16.jpg)
Car detections
![Page 17: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/17.jpg)
Person model
![Page 18: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/18.jpg)
Person detections
![Page 19: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/19.jpg)
Cat model
![Page 20: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/20.jpg)
Cat detections
![Page 21: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/21.jpg)
Bottle model
![Page 22: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/22.jpg)
More detections
![Page 23: More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb](https://reader030.vdocuments.mx/reader030/viewer/2022032723/56649d1e5503460f949f2105/html5/thumbnails/23.jpg)
Quantitative results (PASCAL 2008)
• 7 systems competed in the 2008 challenge• Out of 20 classes, first place in 7 classes and
second place in 8 classes
Bicycles Person Bird
Proposed approach Proposed approach
Proposed approach