1. Many slides based on P. FelzenszwalbP. Felzenszwalb General object detection with deformable part-based models

2. Challenge: Generic object detection

3. Histograms of oriented gradients (HOG) Partition image into blocks at multiple scales and compute histogram of gradient orientations in each block N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, CVPR 2005Histograms of Oriented Gradients for Human Detection 10x10 cells 20x20 cells Image credit: N. Snavely

4. Histograms of oriented gradients (HOG) Partition image into blocks at multiple scales and compute histogram of gradient orientations in each block N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, CVPR 2005Histograms of Oriented Gradients for Human Detection Image credit: N. Snavely

5. Pedestrian detection with HOG Train a pedestrian template using a linear support vector machine N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, CVPR 2005Histograms of Oriented Gradients for Human Detection positive training examples negative training examples

6. Pedestrian detection with HOG Train 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 2005Histograms of Oriented Gradients for Human Detection Template HOG feature mapDetector response map

7. Example detections [Dalal and Triggs, CVPR 2005]

8. Are we done? Single rigid template usually not enough to represent a category Many objects (e.g. humans) are articulated, or have parts that can vary in configuration Many object categories look very different from different viewpoints, or from instance to instance Slide by N. Snavely

9. Discriminative part-based models P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan, Object Detection with Discriminatively Trained Part Based Models, PAMI 32(9), 2010Object Detection with Discriminatively Trained Part Based Models Root filter Part filters Deformation weights

10. Discriminative part-based models P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan, Object Detection with Discriminatively Trained Part Based Models, PAMI 32(9), 2010Object Detection with Discriminatively Trained Part Based Models Multiple components

11. Discriminative part-based models P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan, Object Detection with Discriminatively Trained Part Based Models, PAMI 32(9), 2010Object Detection with Discriminatively Trained Part Based Models

12. Object hypothesis Multiscale model: the resolution of part filters is twice the resolution of the root

13. Scoring an object hypothesis The score of a hypothesis is the sum of filter scores minus the sum of deformation costs Filters Subwindow features Deformation weights Displacements

14. Scoring an object hypothesis The score of a hypothesis is the sum of filter scores minus the sum of deformation costs Concatenation of filter and deformation weights Concatenation of subwindow features and displacements Filters Subwindow features Deformation weights Displacements

15. Detection Define the score of each root filter location as the score given the best part placements:

16. 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 score of the “best” displacement Head filter Deformation cost

17. 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 score of the “best” displacement Head filter responsesDistance transform Head filter

18. Detection

19. Matching result

20. Training Training data consists of images with labeled bounding boxes Need to learn the filters and deformation parameters

21. 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

22. Car model Component 1 Component 2

23. Car detections

24. Person model

25. Person detections

26. Cat model

27. Cat detections

28. Bottle model

29. More detections

30. 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 BicyclesPersonBird Proposed approach