This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Keypoint Recognition Using Randomized Trees
September 2006 (vol. 28 no. 9)
pp. 1465-1479
In many 3D object-detection and pose-estimation problems, runtime performance is of critical importance. However, there usually is time to train the system, which we will show to be very useful. Assuming that several registered images of the target object are available, we developed a keypoint-based approach that is effective in this context by formulating wide-baseline matching of keypoints extracted from the input images to those found in the model images as a classification problem. This shifts much of the computational burden to a training phase, without sacrificing recognition performance. As a result, the resulting algorithm is robust, accurate, and fast-enough for frame-rate performance. This reduction in runtime computational complexity is our first contribution. Our second contribution is to show that, in this context, a simple and fast keypoint detector suffices to support detection and tracking even under large perspective and scale variations. While earlier methods require a detector that can be expected to produce very repeatable results, in general, which usually is very time-consuming, we simply find the most repeatable object keypoints for the specific target object during the training phase. We have incorporated these ideas into a real-time system that detects planar, nonplanar, and deformable objects. It then estimates the pose of the rigid ones and the deformations of the others.

[1] Y. Amit, 2D Object Detection and Recognition: Models, Algorithms, and Networks. MIT Press, 2002.
[2] Y. Amit and D. Geman, “Shape Quantization and Recognition with Randomized Trees,” Neural Computation, vol. 9, no. 7, pp. 1545-1588, 1997.
[3] A. Baumberg, “Reliable Feature Matching across Widely Separated Views,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 774-781, 2000.
[4] J. Beis and D.G. Lowe, “Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 1000-1006, 1997.
[5] L. Breiman, J.H. Friedman, R.A. Olshen, and C.J. Stone, Classification and Regression Trees. Chapman and Hall, 1984.
[6] L. Breiman, “Bagging Predictors,” Machine Learning, vol. 24, no. 2, pp. 123-140, 1996.
[7] P. Debevec, “Rendering Synthetic Objects into Real Scenes: Bridging Traditional and Image-Based Graphics with Global Illumination and High Dynamic Range Photography,” Proc. ACM SIGGRAPH Conf., July 1998.
[8] R. Fergus, P. Perona, and A. Zisserman, “A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition,” Proc. Conf. Computer Vision and Pattern Recognition, July 2005.
[9] F. Fleuret and D. Geman, “Coarse-to-Fine Visual Selection,” Int'l J. Computer Vision, vol. 41, no. 1, pp. 85-107, Jan. 2001.
[10] P. Fua, “Model-Based Optimization: An Approach to Fast, Accurate, and Consistent Site Modeling from Imagery,” RADIUS: Image Understanding for Intelligence Imagery, Morgan Kaufmann, 1997.
[11] Y. Ke and R. Sukthankar, “PCA-SIFT: A More Distinctive Representation for Local Image Descriptors,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 111-119, 2000.
[12] V. Lepetit and P. Fua, “Towards Recognizing Feature Points Using Classification Trees,” Technical Report IC/2004/74, EPFL, 2004.
[13] V. Lepetit, J. Pilet, and P. Fua, “Point Matching as a Classification Problem for Fast and Robust Object Pose Estimation,” Proc. Conf. Computer Vision and Pattern Recognition, June 2004.
[14] T. Lindeberg, “Scale-Space Theory: A Basic Tool for Analysing Structures at Different Scales,” J. Applied Statistics, vol. 21, no. 2, pp. 224-270, 1994.
[15] D.G. Lowe, “Object Recognition from Local Scale-Invariant Features,” Proc. Int'l Conf. Computer Vision, pp. 1150-1157, 1999.
[16] D.G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int'l J. Computer Vision, vol. 20, no. 2, pp. 91-110, 2004.
[17] R. Marèe, P. Geurts, J. Piater, and L. Wehenkel, “Random Subwindows for Robust Image Classification,” Proc. Conf. Computer Vision and Pattern Recognition, 2005.
[18] J. Matas, O. Chum, U. Martin, and T. Pajdla, “Robust Wide Baseline Stereo from Maximally Stable Extremal Regions,” Proc. British Machine Vision Conf., pp. 384-393, Sept. 2002.
[19] J. Meltzer, M.-H. Yang, R. Gupta, and S. Soatto, “Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis,” Proc. European Conf. Computer Vision, pp. 215-227, May 2004.
[20] K. Mikolajczyk and C. Schmid, “An Affine Invariant Interest Point Detector,” Proc. European Conf. Computer Vision, pp. 128-142, 2002.
[21] K. Mikolajczyk and C. Schmid, “A Performance Evaluation of Local Descriptors,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 257-263, June 2003.
[22] K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. Van Gool, “A Comparison of Affine Region Detectors,” Int'l J. Computer Vision, 2005.
[23] F. Mindru, T. Moons, and L. Van Gool, “Recognizing Color Patterns Irrespective of Viewpoint and Illumination,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 368-373, 1999.
[24] S.K. Nayar, S.A. Nene, and H. Murase, “Real-Time 100 Object Recognition System,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 12, pp. 1186-1198, Dec. 1996
[25] J. Pilet, V. Lepetit, and P. Fua, “Real-Time NonRigid Surface Detection,” Proc. Conf. Computer Vision and Pattern Recognition, June 2005.
[26] D. Pritchard and W. Heidrich, “Cloth Motion Capture,” Proc. Eurographics, vol. 22, no. 3, pp. 263-271 Sept. 2003.
[27] E. Rosten and T. Drummond, “ Fusing Points and Lines for High Performance Tracking,” Proc. Int'l Conf. Computer Vision, Oct. 2005.
[28] F. Schaffalitzky and A. Zisserman, “MultiView Matching for Unordered Image Sets, or 'How Do I Organize My Holiday Snaps?'” Proc. European Conf. Computer Vision, pp. 414-431, 2002.
[29] C. Schmid and R. Mohr, “Local Grayvalue Invariants for Image Retrieval,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 5, pp. 530-534, May 1997.
[30] T. Tuytelaars and L. Van Gool, “Wide Baseline Stereo Matching Based on Local, Affinely Invariant Regions,” Proc. British Machine Vision Conf., pp. 412-422, 2000.
[31] P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 511-518, 2001.

Index Terms:
Image processing and computer vision, object recognition, tracking, statistical, classifier design and evaluation, edge and feature detection.
Citation:
Vincent Lepetit, Pascal Fua, "Keypoint Recognition Using Randomized Trees," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 9, pp. 1465-1479, Sept. 2006, doi:10.1109/TPAMI.2006.188
Usage of this product signifies your acceptance of the Terms of Use.