620 likes | 718 Vues
Lecture 2. Mei-Chen Yeh 03/09/2010. Outline. Demos Image representation and feature extraction Global features Local features: SIFT Assignment #2 (due: 03/16). Demos. Augmented Reality http://www.youtube.com/watch?v=P9KPJlA5yds http://www.youtube.com/watch?v=U2uH-jrsSxs Tracking
E N D
Lecture 2 Mei-Chen Yeh 03/09/2010
Outline • Demos • Image representation and feature extraction • Global features • Local features: SIFT • Assignment #2 (due: 03/16)
Demos • Augmented Reality • http://www.youtube.com/watch?v=P9KPJlA5yds • http://www.youtube.com/watch?v=U2uH-jrsSxs • Tracking • Traffic • Counting people • Image search • MyFinder: http://128.111.56.44/myFinder/ • Simplicity: http://wang14.ist.psu.edu/cgi-bin/zwang/regionsearch_show.cgi • Image annotation • ALIPR: http://alipr.com/ • Embedded face detection and recognition • Tiling slide show • Pivot: http://www.technologyreview.com/video/?vid=533
Multimedia Systems: A Multidisciplinary Subject • Signal Processing • Data Mining • Machine Learning • Pattern Recognition • Networking • … and more!
Topics (1) • Image/video processing • Feature extraction • Video syntax analysis • Compression
Topics (2) • Content-based image/video retrieval • Copy detection • Region-based retrieval • Multi-dimensional indexing
Topics (3) • Multimodal system • Audio processing • Multimodality analysis
Topics (4) • Semantic concept detection • Object detection • Object recognition
Topics (5) • Tracking • Motion features • Models • Single-, multiple-object tracking
Topic (6) • Qualify of Service/Experience • QoE Framework • VoIP System Evaluation • Imaging System Evaluation
Resources of the readings • ACM International Conference on Multimedia • The premier annual event on multimedia research, technology, and art • Started since 1993 • >400 attendees • Program: Content, Systems, Applications, HC tracks • Full papers (16%), short papers (28%) • Technical demonstrations, open source software competition, the doctoral symposium, tutorials (6), workshops (11), a brave new topic session, panels (2), Multimedia grand challenge • IEEE Transactions on Multimedia
Multimedia file formats • A list of some formats used in the popular product “Macromedia Director” • These formats differ mainly in how data are compressed. • Features are normally extracted from raw data.
1-bit images • Each pixel is stored as a single bit (0 or 1), so also referred to as binary image. • So-called 1-bitmonochrome image No color
8-bit gray-level images • Each pixel has a gray-value between 0 and 255. (0=>black, 255=>white) • Image resolution refers to the number of pixels in a digital image • A 640 x 480 grayscale image requires ??? kB One byte per pixel 640x480 = 307,200 ~ 300 kB
24-bit color images • Each pixel is represented by three bytes, usually representing RGB. • This format supports 256x256x256 (16,777,216) possible colors. • A 640x480 24-bit color image would require 921.6 kB! Lena: 1997 Lena: 1972
Feature types • Global features • Color • Shape • Texture • Local features • SIFT • SURF • Self-similarity descriptor • Shape context descriptor • … … A fixed-length feature vector … …
Color histogram • A color histogram counts pixels with a given pixel value in Red, Green, and Blue (RGB). • An example of histogram that has 2563 bins, for 24-bit color images:
Color histogram (cont.) • Quantization
Color histogram (cont.) • Problems of such a representation SAME! Case 1 SAME! Case 2 SAME! Case 3
Regional color • Divide the image into regions • Extract a color histogram for each region • Put together those color histograms into a long feature vector
Textures • Many natural and man-made objects are distinguished by their texture. • Man-made textures • Walls, clothes, rugs… • Natural textures • Water, clouds, sand, grass, … What is this?
Examples More: http://www.ux.uis.no/~tranden/brodatz.html
Texture features • Structural • Describe arrangement of texture elements • E.g., “texton model”, “texel model” • Statistical • Characterize texture in terms of statistics • E.g., co-occurrence matrix, Markov random field • Spectral • Analyze in spatial-frequency domain • E.g., Fourier transform, Gabor filter, wavelets
Textual Properties • Coarseness: coarse vs. fine • Contrast: high vs. low • Orientation: directional vs. non-directional • Edge: line-like vs. blob-like • Regularity: regular vs. random • Roughness: rough vs. smooth
Shape • Boundary-based feature • Use only the outer boundary of the shape • E.g. Fourier descriptor, shape context descriptor • Region-based feature • Use the entire shape region • Local descriptors
Properties • Invariant to translation, scale, and rotation
Feature types • Global features • Color • Shape • Texture • Local features • SIFT • SURF • Self-similarity descriptor • Shape context descriptor • … … A fixed-length feature vector … …
David G. Lowe. Distinctive Image Features from Scale-Invariant Key-points, IJCV, 2004
What is SIFT? • Scale Invariant Feature Transform (SIFT) is an approach for detecting and extracting local feature descriptors from an image. • SIFT feature descriptors are reasonably invariant to • scaling • rotation • image noise • changes in illumination • small changes in viewpoint
Types of invariance viewing angle illumination scale rotation
621 128 162.38 155.79 44.30 2.615 7 6 0 0 0 0 0 1 58 63 1 0 7 6 1 8 8 9 0 0 24 42 39 14 0 0 0 0 0 0 7 2 44 7 0 0 23 22 6 69 137 64 0 0 0 0 11 137 55 12 0 0 2 25 137 112 0 0 0 0 3 17 30 6 34 1 0 0 20 51 137 89 137 89 0 0 0 15 115 102 137 47 0 0 4 37 26 43 0 0 0 0 19 45 4 0 0 0 0 0 0 16 137 53 33 2 0 0 0 56 137 51 57 2 0 0 0 3 14 35 0 0 0 0 0 2 0 0 282.47 185.76 27.80 2.009 0 0 0 0 0 0 0 0 1 41 13 1 0 12 4 0 5 17 15 16 17 83 35 16 19 0 0 1 2 13 24 104 0 1 9 0 0 0 0 0 22 127 127 5 0 0 0 1 127 127 75 16 6 0 0 70 55 2 0 1 0 0 25 127 1 1 9 0 0 1 1 2 115 22 49 4 0 0 0 68 127 127 30 4 0 0 0 58 67 127 69 0 0 0 5 20 2 0 0 0 4 65 5 2 85 50 6 0 1 15 2 30 56 93 53 19 0 0 4 41 22 127 86 1 0 2 17 20 ………. Number of keypoints Feature dimension
Densely cover the image (an image with 500x500 pixels => 2000 feature vectors) • Distinctive • Invariant to image scale, rotation, and partially invariant to changing viewpoints and illumination • Perform the best among local descriptors • K. Mikolajczyk and C. Schmid, “A performance evaluation of local descriptors,” PAMI 05.
Simple test (scale and rotate) 214 matches! • Scale to 60% and rotate 30 degree 693 keypoints 349 keypoints
Simple test (illumination) 467 matches! 693 keypoints 633 keypoints
Simple test (different appearance) 25 matches! 693 keypoints 728 keypoints
Simple test (different appearance) 1 match! 693 keypoints 832 keypoints
Simple Test (different appearance with occlusion) 0 match! 693 keypoints 1124 keypoints
About SIFT… • How to generate SIFT feature descriptors? • How to use SIFT features descriptors (for object recognition, image retrieval, etc.) ?
Interest point detector + descriptor SIFT: Overview • Major stages of SIFT computation An image Identify potential interest points (location, scale) Scale-space extrema detection Localize candidate keypoints Reduced sets of (location, scale) Keypoint localization Identify the dominant orientations (location, scale, orientation) Orientation assignment Build a descriptor based on histogram of gradients in local neighborhood Keypoint descriptor feature vectors (128-d)
Step 1: Scale-space extrema detection • How do we detect locations that are invariant to scale change of the image? • Detecting extrema in scale-space • For a given image I(x,y), its linear scale-space representation: • Be efficiently implemented by searching for local peaks in a series of DoG (difference-of-Gaussian) images
Gaussian images DoG images
Step 2: Scale-space extrema detection DoG If X is the largest or the smallest of all of its neighbors, X is called a keypoint. DoG DoG
Why DoG? • An efficient function to compute • A close approximation to the scale-normalized Laplacian of Gaussian • Lindeberg showed that the normalization of the Laplacian with the factor σ2 is required for true scale invariance. (1994) • Mikolajczyk found that the maxima and minima of produce the most stable image features. (2002) • DoG v.s.