1 / 51

Advance Computer Vision

Advance Computer Vision. Lectures 03 Roger S. Gaborski. Reference Examples. Recognizing Indoor Scenes Ariadna Quattoni and Antonio Torralba (http:// people.csail.mit.edu / torralba /publications/ indoor.pdf ) Building the gist of a scene: the role of global image features in recognition

siran
Download Presentation

Advance Computer Vision

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. Advance Computer Vision Lectures 03 Roger S. Gaborski Roger S. Gaborski

  2. Reference Examples Recognizing Indoor Scenes AriadnaQuattoni and Antonio Torralba (http://people.csail.mit.edu/torralba/publications/indoor.pdf) Building the gist of a scene: the role of global image features in recognition AudeOliva and Antonio Torralba Objects as Attributes for Scene Classi¯cation Li-Jia Li, Hao Su, Yongwhan Lim, Li Fei-Fei (http://vision.stanford.edu/documents/LiSuLimFeiFei_ECCV2010.pdf) See references for each paper Roger S. Gaborski

  3. Modeling the shape of the scene: a holistic representation of the spatial envelope http://people.csail.mit.edu/torralba/code/spatialenvelope/ • SIFT flow: dense correspondence across difference scenes http://people.csail.mit.edu/celiu/ECCV2008/ Roger S. Gaborski

  4. Paper: VLFeat-An open and portable library of computer vision algorithms • http://vision.ucla.edu/papers/vedaldiF10.pdf • Learning and Recognizing Visual Object Categories • http://www.youtube.com/watch?v=w2C-WffS-AE&feature=bf_prev&list=PL9415E136FBEE3016&lf=results_main • http://www.youtube.com/watch?v=xMNIxKy3MG0 Roger S. Gaborski

  5. HW#3 Assignment • Due 12/15 • Choose a relevant paper • Make a 10-15 minute presentation Roger S. Gaborski

  6. Harris Edge Detection:Not Invariant to Scaling Corner All points will be classified as edges Roger S. Gaborski

  7. Blob Detection Roger S. Gaborski

  8. Recall: Edge detectionDerivative of Gaussian Edge f Derivativeof Gaussian Edge = maximumof derivative Roger S. Gaborski * Is the convolution operator (otherwise polarity flipped) Source: S. Seitz

  9. Edge detection – Second Derivative of Gaussian Edge f Second derivativeof Gaussian (Laplacian) Edge = zero crossingof second derivative Roger S. Gaborski Source: S. Seitz

  10. Scale Issue – Laplacianwide pulse edge Note Value of Response – about -0.05 Roger S. Gaborski

  11. Scale Issue – Laplaciannarrower pulse Roger S. Gaborski

  12. Scale Issue – Laplacian Pulse matches Laplacian – Max Response Note Value of Response for Matched Pulse – about -0.10 Roger S. Gaborski

  13. Blob Detection • The magnitude of Laplacian response is maximum when scale of Laplacian is matched to the blob • Convolve the blob with Laplacians at several different scales and look for the maximum • BUT – Laplacian response decays as scale increases  see next slide Roger S. Gaborski

  14. Note Response Values Increasing scale – sigma  Decreasing Response Values Roger S. Gaborski

  15. Scale selection We want to find the characteristic scale of the blob by convolving it with Laplacians at several scales and looking for the maximum response However, Laplacian response decays as scale increases: original signal(radius=8) increasing σ Roger S. Gaborski

  16. Scale normalization The response of a derivative of Gaussian filter to a perfect step edge decreases as σ increases Roger S. Gaborski

  17. Scale normalization The response of a derivative of Gaussian filter to a perfect step edge decreases as σ increases To keep response the same (scale-invariant), must multiply Gaussian derivative by σ Laplacian is the second Gaussian derivative, so it must be multiplied by σ2 Roger S. Gaborski

  18. Effect of scale normalization Scale-normalized Laplacian response maximum Original signal Unnormalized Laplacian response Roger S. Gaborski

  19. Blob detection in 2D Laplacian of Gaussian: Circularly symmetric operator for blob detection in 2D Roger S. Gaborski

  20. Blob detection in 2D Laplacian of Gaussian: Circularly symmetric operator for blob detection in 2D Scale-normalized: Roger S. Gaborski

  21. Scale selection At what scale does the Laplacian achieve a maximum response to a binary circle of radius r? r Roger S. Gaborski image Laplacian

  22. Scale selection At what scale does the Laplacian achieve a maximum response to a binary circle of radius r? To get maximum response, the zeros of the Laplacian have to be aligned with the circle The Laplacian is given by (up to scale): The maximum response occurs at r circle Roger S. Gaborski image Laplacian

  23. Characteristic scale We define the characteristic scale of a blob as the scale that produces peak of Laplacian response in the blob center characteristic scale T. Lindeberg (1998). "Feature detection with automatic scale selection."International Journal of Computer Vision30 (2): pp 77--116. Roger S. Gaborski

  24. Scale-space blob detector Convolve image with scale-normalized Laplacian at several scales Find maxima of squared Laplacian response in scale-space Roger S. Gaborski

  25. Scale-space blob detector: Example Roger S. Gaborski

  26. Scale-space blob detector: Example Roger S. Gaborski

  27. Scale-space blob detector: Example Roger S. Gaborski

  28. Approximating the Laplacian with a Difference of Gaussians: Efficient implementation (Laplacian) (Difference of Gaussians) Roger S. Gaborski

  29. Scale Space • Start with original image • Create progressively blurred images • Blur with Gaussian function • Progressive increase blur • One octave: doubling of blur • Resize original image to 50% • Repeat creating progressively blurred images • Repeat … Roger S. Gaborski

  30. DoGimplementation David G. Lowe. "Distinctive image features from scale-invariant keypoints.”IJCV 60 (2), pp. 91-110, 2004. Roger S. Gaborski

  31. Gaussian Blurred Images and Difference of Gaussian Images Grouped by octave From Striker Roger S. Gaborski

  32. Scale Invariant Feature Transform • Feature Detector and Feature Descriptor • Detection stages for SIFT features: • Scale-space extrema detection • Keypoint localization • Orientation assignment • Generation of keypoint descriptors. Following slides based on Strider, Univ. Toronto and Lowe Roger S. Gaborski

  33. Keypoints are maxima of Difference of Gaussians (DoG) that occur at multiple scales • Start with Gaussian blurred image: L(x; y; σ ) = G(x; y; σ )* I(x; y) Where: G(x; y; σ ) = 1/(2 pi*σ2) (exp-(x2 +y2 )/σ2 ) Roger S. Gaborski

  34. Difference of Gaussian Filter: G(x; y; kσ ) – G(x; y; σ) • Convolve blurred image with Difference of Gaussian: D(x; y; σ ) = L(x; y; k σ) - L(x; y; σ) Which is simply the difference of Gaussian blurred images at scales σ and k σ Roger S. Gaborski

  35. Blurred Images at Different Scales Computation of DoG REF: Lowe , 2004 Roger S. Gaborski

  36. Scale Space Extrema Detection • Group convolved images by octave Octave  doubling of σ • Keypoints are idenitied as local maxima or minima of the DoG images across scales. • Each pixel in the DoG images is compared to its 8 neighbors at the same scale, plus the 9 corresponding neighbors at neighboring scales. • If the pixel is a local maximum or minimum, it is selected as a candidate keypoint Roger S. Gaborski

  37. Local extrema detection – pixel marked with X compared to 26 neighbors in 3x3x3 space of adjacent DoGimages X is a key point if X is either greater (or less than) than all of the neighbors Roger S. Gaborski

  38. Keypoint Selection • Keypoints with low contrast are deleted • Keypoints on edges are deleted • Each remaining keypoint is assigned an orientation Roger S. Gaborski

  39. Keypoint Orientation • For each remaining keypoint • Compute gradient orientation histogram in the neighborhood of keypoint • Contribution of each neighboring pixel is weighted by the gradient magnitude and a Gaussian window with a σ that is 1.5 the scale of the keypoint • Peaks in histogram correspond to dominate orientations • Separate keypoint for direction corresponding to maximum in histogram and any direction within 80% of the maximum Roger S. Gaborski

  40. 16x16 Pixels Around Keypoint Divide 16x16 pixels into 16 , 4x4 sub windows Calculate gradient magnitude and direction in each sub window Store gradient and magnitude in 8 bin histograms Roger S. Gaborski

  41. Gradients with an angle between 0 and 44 degrees goes in the first bin, etc. The magnitude depends on the gradients magnitude and the gradient’s distance from the key point Roger S. Gaborski

  42. Key Point Vector • Each 4x4 sub window has 8 numbers associate with the sub window (the histogram) • 16 sub windows • 16 * 8 = 128 numbers • Normalize the vector (divide vector by the sqrt of the sum of the elements squared) • The resulting normalized vector is the feature vector associated with each key point Roger S. Gaborski

  43. SIFT Descriptor • Histogram contains 8 bins • Each descriptor has 16 histograms around keypoint • 4 x 4 x 8 = 128 long feature vector for each keypoint • Normalize feature for illumination invariance Roger S. Gaborski

  44. Recognition using SIFT • Compute SIFT features for input image • Match features in SIFT database Roger S. Gaborski

  45. Gaussian Blurred Images and Difference of Gaussian Images Grouped by octave From Striker Roger S. Gaborski

  46. Maxima of DoG across scales Keypoints after removing low contrast points Roger S. Gaborski

  47. Removal of Edge Points Roger S. Gaborski

  48. Arrows indicate Scale and Orientation Roger S. Gaborski

  49. VLFeat.org • MSER • SURF (Speeded Up Robust Features) Roger S. Gaborski

  50. Image Features http://videolectures.net/mcvc08_gousseau_cmlf/ • The Future of Image Search author: Jitendra Malik, UC Berkeley, University of California,   http://videolectures.net/kdd08_malik_fis/ Roger S. Gaborski

More Related