Subscribe
Issue No.01 - January (2008 vol.30)
pp: 36-51
ABSTRACT
We present a family of scale-invariant local shape features formed by chains of k connected, roughly straight contour segments (kAS), and their use for object class detection. kAS are able to cleanly encode pure fragments of an object boundary, without including nearby clutter. Moreover, they offer an attractive compromise between information content and repeatability, and encompass a wide variety of local shape structures. We also define a translation and scale invariant descriptor encoding the geometric configuration of the segments within a kAS, making kAS easy to reuse in other frameworks, for example as a replacement or addition to interest points. Software for detecting and describing kAS is released on lear.inrialpes.fr/software. We demonstrate the high performance of kAS within a simple but powerful sliding-window object detection scheme. Through extensive evaluations, involving eight diverse object classes and more than 1400 images, we 1) study the evolution of performance as the degree of feature complexity k varies and determine the best degree; 2) show that kAS substantially outperform interest points for detecting shape-based classes; 3) compare our object detector to the recent, state-of-the-art system by Dalal and Triggs [4].
INDEX TERMS
Local features, shape descriptors, object detection
CITATION
L. Fevrier, V. Ferrari, C. Schmid, "Groups of Adjacent Contour Segments for Object Detection", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.30, no. 1, pp. 36-51, January 2008, doi:10.1109/TPAMI.2007.1144
REFERENCES
[1] A. Berg, T. Berg, and J. Malik, “Shape Matching and Object Recognition Using Low Distortion Correspondence,” Proc. Conf. Computer Vision and Pattern Recognition, 2005.
[2] E. Borenstein, E. Sharon, and S. Ullman, “Combining Top-Down and Bottom-Up Segmentations,” Proc. POCV Workshop Computer Vision and Pattern Recognition, 2004.
[3] G. Csurka, C. Dance, L. Fan, J. Willamowski, and C. Bray, “Visual Categorization with Bags of Keypoints,” Proc. Statistical Learning in Computer Vision, Workshop European Conf. Computer Vision, 2004.
[4] N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” Proc. Conf. Computer Vision and Pattern Recognition, 2005.
[5] G. Dorko and C. Schmid, “Selection of Scale-Invariant Parts for Object Class Recognition,” Proc. Int'l Conf. Computer Vision, 2003.
[6] F. Estrada and A. Jepson, “Perceptual Grouping for Contour Extraction,” Proc. Int'l Conf. Pattern Recognition, 2004.
[7] L. Fei-Fei, R. Fergus, and P. Perona, “Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories,” Proc. Generative-Model-Based Vision Workshop Computer Vision and Pattern Recognition, 2004, Caltech 101 Dataset www.vision.caltech.edu/Image_ Datasets/Caltech101 Caltech101.html.
[8] V. Ferrari, T. Tuytelaars, and L. Van Gool, “Real-Time Affine Region Tracking and Coplanar Grouping,” Proc. Conf. Computer Vision and Pattern Recognition, 2001.
[9] V. Ferrari, T. Tuytelaars, and L. Van Gool, “Object Detection by Contour Segment Networks,” Proc. European Conf. Computer Vision, 2006, Dataset www.vision.ee.ethz.ch~ferrari.
[10] V. Ferrari, F. Jurie, and C. Schmid, “Accurate Object Detection with Deformable Shape Models Learnt from Images,” Proc. Conf. Computer Vision and Pattern Recognition, 2007.
[11] R. Fergus, P. Perona, and A. Zisserman, “Object Class Recognition by Unsupervised Scale-invariant Learning,” Proc. Conf. Computer Vision and Pattern Recognition, 2003.
[12] P. Gros, “Matching and Clustering: Two Steps Toward Automatic Object Modeling in Computer Vision,” Proc. Int'l J. Robotics, vol. 14, no. 6, pp. 633-642, 2005.
[13] D. Jacobs, “Robust and Efficient Detection of Salient Convex Groups,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 1, pp. 23-37, Jan. 1996.
[14] F. Jurie and C. Schmid, “Scale-Invariant Shape Features for Recognition of Object Categories,” Proc. Conf. Computer Vision and Pattern Recognition, 2004, Dataset lear.inrialpes.frdata.
[15] F. Jurie and B. Triggs, “Creating Efficient Codebooks for Visual Recognition,” Proc. Int'l Conf. Computer Vision, 2005.
[16] S. Lazebnik, C. Schmid, and J. Ponce, “Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories,” Proc. Conf. Computer Vision and Pattern Recognition, 2006.
[17] B. Leibe and B. Schiele, “Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search,” Proc. German Pattern Recognition Symp., 2004.
[18] D. Lowe and T. Binford, “Perceptual Organization as a Basis for Visual Recognition,” Proc. Nat'l Conf. Artificial Intelligence, 1983.
[19] D. Lowe, “Three-Dimensional Object Recognition from Single Two-Dimensional Images,” Artificial Intelligence, 1987.
[20] D. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int'l J. Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[21] D. Martin, C. Fowlkes, and J. Malik, “Learning to Detect Natural Image Boundaries Using Local Brightness, Color and Texture Cues,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 5, pp. 530-549, May 2004.
[22] K. Mikolajczyk and C. Schmid, “Indexing Based on Scale Invariant Interest Points,” Proc. Int'l Conf. Computer Vision, 2001.
[23] A. Opelt, A. Pinz, and A. Zisserman, “A Boundary-Fragment-Model for Object Detection,” Proc. European Conf. Computer Vision, 2006.
[24] F. Porikly, “Integral Histogram: A Fast Way to Extract Histograms in Cartesian Spaces,” Proc. Conf. Computer Vision and Pattern Recognition, 2005.
[25] C. Rothwell, J. Mundy, W. Hoffman, and V.-D. Nguyen, “Driving Vision by Topology,” Proc. IEEE Int'l Symp. Computer Vision, 1995.
[26] C. Rothwell, A. Zisserman, D. Forsyth, and J. Mundy, “Planar Object Recognition Using Projective Shape Representation,” Int'l J. Computer Vision, vol. 16, no. 1, pp. 57-99, 1995.
[27] A. Selinger and R. Nelson, “A Cubist Approach to Object Recognition,” Proc. Int'l Conf. Computer Vision, 1998.
[28] A. Shashua and S. Ullman, “Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network,” Proc. Int'l Conf. Computer Vision, 1998.
[29] J. Shotton, A. Blake, and R. Cipolla, “Contour-Based Learning for Object Detection,” Proc. Int'l Conf. Computer Vision, 2005.
[30] T. Tuytelaars and L. Van Gool, “Matching Widely Separated Views Based on Affine Invariant Regions,” Int'l J. Computer Vision, vol. 59, no. 1, pp. 61-85, 2004.
[31] P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” Proc. Conf. Computer Vision and Pattern Recognition, 2001.
[32] M. Zerroug and R. Nevatia, “Volumetric Descriptions from a Single Intensity Image,” Int'l J. Computer Vision, vol. 20, no. 1, pp.11-42, 1996.
[33] PASCAL Challenge 2006 Visual Object Classes, www.pascal-network.org/challenges/VOCvoc2006 .
[34] J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid, “Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study,” Int'l J. Computer Vision, vol. 73, no. 2, pp. 213-238, 2007.