1 / 15

Project 3 Results

Project 3 Results. base pipeline + careful parameter choices. base pipeline. Spatial pyramids and additional features. Example Results. Tala Huhe Betsy Hilliard Hang Su Yun Zhang Seth Goldenberg Paul Sastrasinh Andy Loomis Emanuel Zgraggen. 10/3111.

orobbins
Download Presentation

Project 3 Results

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. Project 3 Results

  2. base pipeline + careful parameter choices base pipeline Spatial pyramids and additional features

  3. Example Results • Tala Huhe • Betsy Hilliard • Hang Su • Yun Zhang • Seth Goldenberg • Paul Sastrasinh • Andy Loomis • Emanuel Zgraggen

  4. 10/3111 Object Category Detection: Sliding Windows (continued) Computer Vision CS 143, Brown James Hays Many Slides from Kristen Grauman

  5. Previously • Category recognition (proj3) • Bag of words over not-so-invariant local features. • Instance recognition • Local invariant features: interest point detection and feature description • Local feature matching, spatial verification • Scalable indexing

  6. Today (continued from Wed.) • Window-based generic object detection • basic pipeline • boosting classifiers • face detection as case study

  7. What other categories are amenable to window-based representation?

  8. Pedestrian detection • Detecting upright, walking humans also possible using sliding window’s appearance/texture; e.g., SVM with Haar wavelets [Papageorgiou & Poggio, IJCV 2000] Space-time rectangle features [Viola, Jones & Snow, ICCV 2003] SVM with HoGs [Dalal & Triggs, CVPR 2005] Kristen Grauman

  9. Window-based detection: strengths • Sliding window detection and global appearance descriptors: • Simple detection protocol to implement • Good feature choices critical • Past successes for certain classes Kristen Grauman

  10. Window-based detection: Limitations • High computational complexity • For example: 250,000 locations x 30 orientations x 4 scales = 30,000,000 evaluations! • If training binary detectors independently, means cost increases linearly with number of classes • With so many windows, false positive rate better be low Kristen Grauman

  11. Limitations (continued) • Not all objects are “box” shaped Kristen Grauman

  12. Limitations (continued) • Non-rigid, deformable objects not captured well with representations assuming a fixed 2d structure; or must assume fixed viewpoint • Objects with less-regular textures not captured well with holistic appearance-based descriptions Kristen Grauman

  13. Limitations (continued) • If considering windows in isolation, context is lost Sliding window Detector’s view Figure credit: Derek Hoiem Kristen Grauman

  14. Limitations (continued) • In practice, often entails large, cropped training set (expensive) • Requiring good match to a global appearance description can lead to sensitivity to partial occlusions Kristen Grauman Image credit: Adam, Rivlin, & Shimshoni

  15. Summary • Basic pipeline for window-based detection • Model/representation/classifier choice • Sliding window and classifier scoring • Viola-Jones face detector • Exemplar of basic paradigm • Plus key ideas: rectangular features, Adaboost for feature selection, cascade, hard negatives. • Pros and cons of window-based detection

More Related