1 / 30

General object detection with deformable part-based models

General object detection with deformable part-based models. Many slides based on P. Felzenszwalb. Challenge: Generic object detection. Histograms of oriented gradients (HOG). Partition image into blocks at multiple scales and compute histogram of gradient orientations in each block.

urbana
Download Presentation

General object detection with deformable part-based models

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

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

  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 10x10 cells 20x20 cells N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, CVPR 2005 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 2005 Image credit: N. Snavely

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

  6. Pedestrian detection with HOG • Train a pedestrian template using a linear support vector machine • At test time, convolve feature map with template HOG feature map Detector response map Template N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, CVPR 2005

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

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

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

  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 Subwindow features Displacements Deformation weights Filters

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

  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 responses Distance 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 Bicycles Person Bird Proposed approach Proposed approach Proposed approach

More Related