1 / 28

Lecture 08

Lecture 08. 27 /12/2011 Shai Avidan. הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת. Today. Hough Transform Generalized Hough Transform Implicit Shape Model Video Google. Hough Transform & Generalized Hough Transform. y. ρ. x. θ. Hough Transform.

alaula
Download Presentation

Lecture 08

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. Lecture 08 27/12/2011 ShaiAvidan הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.

  2. Today • Hough Transform • Generalized Hough Transform • Implicit Shape Model • Video Google

  3. Hough Transform & Generalized Hough Transform

  4. y ρ x θ Hough Transform • Origin: Detection of straight lines in clutter • Basic idea: each candidate point votes for all lines that it is consistent with. • Votes are accumulated in quantized array • Local maxima correspond to candidate lines • Representation of a line • Usual form y = a x + b has a singularity around 90º. • Better parameterization: x cos() + y sin() = K. Grauman, B. Leibe

  5. Examples • Hough transform for a square (left) and a circle (right) K. Grauman, B. Leibe

  6. Hough Transform: Noisy Line ρ • Problem: Finding the true maximum θ Tokens Votes K. Grauman, B. Leibe

  7. Hough Transform: Noisy Input ρ • Problem: Lots of spurious maxima θ Tokens Votes K. Grauman, B. Leibe

  8. Generalized Hough Transform [Ballard81] • Generalization for an arbitrary contour or shape • Choose reference point for the contour (e.g. center) • For each point on the contour remember where it is located w.r.t. to the reference point • Remember radius r and angle relative to the contour tangent • Recognition: whenever you find a contour point, calculate the tangent angle and ‘vote’ for all possible reference points • Instead of reference point, can also vote for transformation  The same idea can be used with local features! K. Grauman, B. Leibe Slide credit: Bernt Schiele

  9. Implicit Shape Model

  10. Gen. Hough Transform with Local Features • For every feature, store possible “occurrences” • For new image, let the matched features vote for possible object positions K. Grauman, B. Leibe

  11. 3D Object Recognition [Lowe99] • Gen. HT for Recognition • Typically only 3 feature matches needed for recognition • Extra matches provide robustness • Affine model can be used for planar objects K. Grauman, B. Leibe Slide credit: David Lowe

  12. View Interpolation • Training • Training views from similar viewpoints are clusteredbased on feature matches. • Matching features between adjacent views are linked. • Recognition • Feature matches may bespread over several training viewpoints.  Use the known links to “transfer votes” to other viewpoints. [Lowe01] K. Grauman, B. Leibe

  13. Recognition Using View Interpolation K. Grauman, B. Leibe

  14. Location Recognition Training K. Grauman, B. Leibe

  15. Applications • Sony Aibo(Evolution Robotics) • SIFT usage • Recognize docking station • Communicate with visual cards • Other uses • Place recognition • Loop closure in SLAM K. Grauman, B. Leibe Slide credit: David Lowe

  16. Video Google

  17. Indexing local features • Each patch / region has a descriptor, which is a point in some high-dimensional feature space (e.g., SIFT) K. Grauman, B. Leibe

  18. Indexing local features • When we see close points in feature space, we have similar descriptors, which indicates similar local content. K. Grauman, B. Leibe Figure credit: A. Zisserman

  19. Indexing local features • We saw in the previous section how to use voting and pose clustering to identify objects using local features Figure credit: David Lowe K. Grauman, B. Leibe

  20. Indexing local features • With potentially thousands of features per image, and hundreds to millions of images to search, how to efficiently find those that are relevant to a new image? • Low-dimensional descriptors : can use standard efficient data structures for nearest neighbor search • High-dimensional descriptors: approximate nearest neighbor search methods more practical • Inverted file indexing schemes K. Grauman, B. Leibe

  21. Indexing local features: inverted file index • For text documents, an efficient way to find all pages on which a word occurs is to use an index… • We want to find all images in which a feature occurs. • To use this idea, we’ll need to map our features to “visual words”. K. Grauman, B. Leibe

  22. Visual words • More recently used for describing scenes and objects for the sake of indexing or classification. Sivic & Zisserman 2003; Csurka, Bray, Dance, & Fan 2004; many others. K. Grauman, B. Leibe

  23. Inverted file index for images comprised of visual words List of image numbers Word number K. Grauman, B. Leibe Image credit: A. Zisserman

  24. Bags of visual words • Summarize entire image based on its distribution (histogram) of word occurrences. • Analogous to bag of words representation commonly used for documents. K. Grauman, B. Leibe Image credit: Fei-Fei Li

  25. Video Google System Query region • Collect all words within query region • Inverted file index to find relevant frames • Compare word counts • Spatial verification Sivic & Zisserman, ICCV 2003 • Demo online at : http://www.robots.ox.ac.uk/~vgg/research/vgoogle/index.html Retrieved frames K. Grauman, B. Leibe

  26. Visual vocabulary formation Issues: • Sampling strategy • Clustering / quantization algorithm • What corpus provides features (universal vocabulary?) • Vocabulary size, number of words K. Grauman, B. Leibe

  27. Sampling strategies Sparse, at interest points Dense, uniformly Randomly • To find specific, textured objects, sparse sampling from interest points often more reliable. • Multiple complementary interest operators offer more image coverage. • For object categorization, dense sampling offers better coverage. • [See Nowak, Jurie & Triggs, ECCV 2006] Multiple interest operators K. Grauman, B. Leibe Image credits: F-F. Li, E. Nowak, J. Sivic

  28. Clustering / quantization methods • k-means (typical choice), agglomerative clustering, mean-shift,… K. Grauman, B. Leibe

More Related