1 / 15

Part 4: combined segmentation and recognition

Part 4: combined segmentation and recognition. Li Fei-Fei. Aim. Given an image and object category, to segment the object. Object Category Model. Segmentation. Cow Image. Segmented Cow. Segmentation should (ideally) be shaped like the object e.g. cow-like

xylia
Download Presentation

Part 4: combined segmentation and recognition

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. Part 4: combined segmentation and recognition Li Fei-Fei

  2. Aim • Given an image and object category, to segment the object Object Category Model Segmentation Cow Image Segmented Cow • Segmentation should (ideally) be • shaped like the object e.g. cow-like • obtained efficiently in an unsupervised manner • able to handle self-occlusion

  3. In this section: brief paper reviews • Jigsaw approach: Borenstein & Ullman, 2001, 2002 • Concurrent recognition and segmentation: Yu and Shi, 2002 • Image parsing: Tu et al. 2003 • Interleaved segmentation: Liebe & Schiele, 2004, 2005 • OBJCUT: Kumar et al. 2005 • LOCUS: Winn and Jojic, 2005

  4. Jigsaw approach: Borenstein and Ullman, 2001, 2002

  5. Object-Specific Figure-Ground Segregation Stella X. Yu and Jianbo Shi, 2002

  6. Object-Specific Figure-Ground Segregation Some segmentation/detection results Yu and Shi, 2002

  7. Image parsing: Tu, Zhu and Yuille 2003

  8. Image parsing: Tu, Zhu and Yuille 2003

  9. Matched Codebook Entries Probabilistic Voting Interest Points Voting Space(continuous) Segmentation Backprojectionof Maxima Refined Hypotheses(uniform sampling) BackprojectedHypotheses Implicit Shape Model - Recognition Liebe and Schiele, 2003, 2005

  10. Cows: Results • Segmentations from interest points Single-frame recognition - No temporal continuity used! Liebe and Schiele, 2003, 2005

  11. OBJCUT:shape prior -- Layered Pictorial Structures (LPS) • Generative model • Composition of parts + spatial layout Layer 2 Spatial Layout (Pairwise Configuration) Layer 1 Parts in Layer 2 can occlude parts in Layer 1 Kumar, et al. 2004, 2005

  12. OBJCUT • Probability of labelling in addition has • Unary potential which depend on distance from Θ (shape parameter) Θ (shape parameter) Unary Potential Φx(mx|Θ) mx m(labels) my Object Category Specific MRF x y D(pixels) Image Plane Kumar, et al. 2004, 2005

  13. OBJCUT: Results Using LPS Model for Cow In the absence of a clear boundary between object and background Image Segmentation

  14. LOCUS model Shared between images Class shape π Class edge sprite μo,σo Deformation field D Position & size T Different for each image Mask m Edge image e Background appearance λ0 Object appearance λ1 Image Winn and Jojic, 2005

  15. Summary • Strength • Explains every pixel of the image • Useful for image editing, layering, etc. • Issues • Invariance issues • (especially) scale, view-point variations

More Related