1 / 72

Object Segmentation

Object Segmentation. Presented by Sherin Aly. What is a ‘ Good Segmentation ’ ?. http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html. Learning a classification model for segmentation. Xiaofeng Ren and Jitendra Malik. methodology.

dori
Download Presentation

Object Segmentation

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. Object Segmentation Presented by Sherin Aly

  2. What is a ‘Good Segmentation’?

  3. http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.htmlhttp://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html

  4. Learning a classification model for segmentation Xiaofeng Ren and Jitendra Malik

  5. methodology • Two-class classification model • Over segmentation as preprocessing • They use classical Gestalt cues • Contour, texture, brightness and continuation • A linear classifier is used for training

  6. Good Vs Bad segmentation a) Image from Corel Imagebase b) superimposed with a human marked segmentation c) Same image with Bad segmentation

  7. How do we distinguish good segmentations from badsegmentations?

  8. How? • Use “Classical Gestalt cues” • proximity, similarity and good continuation • Instead of Ad-hoc decision about features combination

  9. Gestalt Principles of Grouping In order to interpret what we receive through our senses,we attempt to organize this information into certain groups. http://allpsych.com/psychology101/perception.html

  10. Methodology • Preprocessing • Feature extraction • Feature evaluation • Training • Optimization • Find good segmentaion

  11. Preprocessing • Local • Coherent • Preserve structure • Contour • texture Superpixel map K=200 Reconstruction of human segmentation from Superpixels a contour-based measure is used to quantify this approximation

  12. Tolerance 1,2,and 3 The percentage of human marked boundaries covered by the superpixel maps

  13. Feature Extraction 1. inter-region texture similarity 2. intra-region texture similarity 3. inter-region brightness similarity 4. intra-region brightness similarity 5. inter-region contour energy 6. intra-region contour energy 7. curvilinear continuity

  14. Feature Extraction 1. inter-region texture similarity 2. intra-region texture similarity 3. inter-region brightness similarity 4. intra-region brightness similarity 5. inter-region contour energy 6. intra-region contour energy 7. curvilinear continuity

  15. Feature Extraction 1. inter-region texture similarity 2. intra-region texture similarity 3. inter-region brightness similarity 4. intra-region brightness similarity 5. inter-region contour energy 6. intra-region contour energy 7. curvilinear continuity

  16. Power of Gestalt cues =

  17. Training the classifier • simple logistic regression classifier, Empirical distribution of pairs of features

  18. Precision is the fraction of detections which are true positives. Recall is the fraction of true positives which are detected

  19. Conclusion • There simple linear classifier had promising results on a variety of natural images. • boundary contour is the most informative grouping cue, and it is in essence discriminative.

  20. Pros & Cons • Cons • The larger spatial support that superpixels provide, allowing more global features to be computed than on pixels alone. • The use of superpixels improves the computational efficiency • SuperPixels technique is very applicable • Pros • Might fall in Local Minima

  21. Combining Top-down and Bottom-up Segmentation Eran Borenstein Eitan Sharon Shimon Ullman

  22. Motivation • Bottom-Up segmentation • Rely on continuity principle • Capture image properties “texture, grey level uniformity and contour continuity” • Segmentation based on similarities between image regions • How can we capture prior knowledge of a specific object (class)? • Answer: Top-Down Segmentation • use prior knowledge about an object Credit: Joseph Djugash

  23. Bottom-Up Segmentation Credit: Joseph Djugash Slides from Eitan Sharon, “Segmentation and Boundary Detection Using Multiscale Intensity Measurements”.

  24. Normalized-Cut Measure Credit: Joseph Djugash Slides from Eitan Sharon, “Segmentation and Boundary Detection Using Multiscale Intensity Measurements”.

  25. Top-Down approach Fragments Input Matching Cover Credit: Joseph Djugash

  26. Another step towards the middle Top-Down Bottom-Up Credit: Joseph Djugash

  27. Some Definitions & Constraints • Measure of saliency h(Γi), hiє [0,1) • A configuration vector s contains labels si (1/-1) of all the segments (Si) in the tree • The label si can be different from its parent’s label s i – • Cost function for a given s Defines the weighted edge between Si & Si– Top-down term Bottom-up term

  28. Classification Costs • The terminal segments of the tree determine the final classification • The top-down term is defined as: • The saliency of a segment should restrict its label (based on its parent’s label) • The bottom-up term is defined as:

  29. Confidence Map • Evaluating the confidence of a region: • Causes of Uncertainty of Classification • Bottom-up uncertainty – regions where there is no salient bottom-up segment matching the top-down classification • Top-down uncertainty – regions where the top-down classification is ambiguous (highly variable shape regions) • The type of uncertainty and the confidence values can be used to select appropriate additional processing to improve segmentation

  30. Results • Calculate average distance between a given segmentation contour and a benchmark contour. • Removing from the average all contour points having a confidence measure less than 0.1. • The resulting confidence map efficiently separated regions of high and low consistency. • The combined scheme improved the top-down contour by over 67% on average. • This improvement was even larger in object parts with highly variable shape.

  31. The initial classification map T(x, y) Results (cont.) Buttom up • top-down process may produce a figure-ground approximation that does not follow the image discontinuities. • Salient bottom-up segments can correct these errors and delineate precise region boundaries

  32. Results III (cont.)

  33. Results III (cont.) the top-down completely misses a part of the object . The confidence map may be helpful in identifying such cases,

  34. Results III (cont.) bottom-up segmentation may be insufficient in detecting the figure-ground contour, and the top-down process completes the missing information

  35. Results III (cont.)

  36. Results III (cont.) Salient bottom-up segments can correct these errors and delineate precise region boundaries

  37. Conclusion • Buttom-up and top-down merits • Provide reliable confidence map • It take into account all discontinuities at all scales But: • If the object is assigned a given category, the specific features cannot be adopted for other categories

  38. Constrained Parametric Min-Cuts for Automatic Object Segmentation Joao Carreira Cristian Sminchisescu

  39. Traditional Segmentation: Finding Homogeneous Regions gPb-owt-ucm: P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik. PAMI 2010.

  40. Bottom-up Object Segmentation Conventional Bottom-up Segmentation Proposed approach • Split multiple times • Retain object-like segmentations High redundancy Credit: J. Carreira

  41. Bottom-up Object Segmentation A single multi-region segmentation or a hierarchy Credit: J. Carreira

  42. Proposed Bottom-up Object Segmentation robust set of overlapping figure-ground segmentations Credit: J. Carreira single-shot multi-region segmentation superpixels Segments with object-like regularities

  43. Constrained Parametric Min-Cuts for Automatic Object Segmentation Figure ground segmentation by growing regions around seeds parametric max-flow solver Ranking Credit: J. Carreira

  44. Constrained Parametric Min-Cuts for Automatic Object Segmentation Credit: J. Carreira

  45. Initialization • Foreground • Regular 5x5 grid geometry • Centroids of large N-Cuts regions • Centroids of superpixels closest to grid positions • Background • Full image boundary • Horizontal boundaries • Vertical boundaries • All boundaries excluding the bottom one Performance broadly invariant to different initializations

  46. Generating a segment pool:constrained min-cut object min cut hard constraint hard constraint background Credit: J. Carreira

  47. Generating a Segment Pool:Constrained Parametric Min-Cuts Credit: J. Carreira

  48. Generating a Segment Pool:Constrained Parametric Min-Cuts Credit: J. Carreira

  49. Generating a Segment Pool:Constrained Parametric Min-Cuts Credit: J. Carreira

  50. Generating a Segment Pool:Constrained Parametric Min-Cuts Can solve for all values of object bias in the same time complexity of solving a single min-cut using a parametric max-flow solver Credit: J. Carreira

More Related