The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.10 - Oct. (2012 vol.34)
pp: 2005-2018
Mohammad Javad Saberian , UC San Diego, La Jolla
Nuno Vasconcelos , UC San Diego, La Jolla
ABSTRACT
The problem of automatic and optimal design of embedded object detector cascades is considered. Two main challenges are identified: optimization of the cascade configuration and optimization of individual cascade stages, so as to achieve the best tradeoff between classification accuracy and speed, under a detection rate constraint. Two novel boosting algorithms are proposed to address these problems. The first, RCBoost, formulates boosting as a constrained optimization problem which is solved with a barrier penalty method. The constraint is the target detection rate, which is met at all iterations of the boosting process. This enables the design of embedded cascades of known configuration without extensive cross validation or heuristics. The second, ECBoost, searches over cascade configurations to achieve the optimal tradeoff between classification risk and speed. The two algorithms are combined into an overall boosting procedure, RCECBoost, which optimizes both the cascade configuration and its stages under a detection rate constraint, in a fully automated manner. Extensive experiments in face, car, pedestrian, and panda detection show that the resulting detectors achieve an accuracy versus speed tradeoff superior to those of previous methods.
INDEX TERMS
Computer vision, Detectors, Training, Real-time systems, Algorithm design and analysis, Object detection, Computer architecture, boosting., Computer vision, real-time object detection, embedded detector cascades
CITATION
Mohammad Javad Saberian, Nuno Vasconcelos, "Learning Optimal Embedded Cascades", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.34, no. 10, pp. 2005-2018, Oct. 2012, doi:10.1109/TPAMI.2011.281
REFERENCES
[1] P. Viola and M.J. Jones, "Rapid Object Detection Using a Boosted Cascade of Simple Features," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2001.
[2] P. Viola and M. Jones, "Fast and Robust Classification Using Asymmetric Adaboost and a Detector Cascade," Proc. Advances in Neural Information and Processing System, 2001.
[3] X. Hou, C.-L. Liu, and T. Tan, "Learning Boosted Asymmetric Classifiers for Object Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2006.
[4] S. Li and Z. Zhang, "Floatboost Learning and Statistical Face Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 9, pp. 1112-1123, Sept. 2004.
[5] H. Luo, "Optimization Design of Cascaded Classifiers," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 480-485, 2005.
[6] C. Liu and H.-Y. Shum, "Kullback-Leibler Boosting," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 587-594, 2003.
[7] S.C. Brubaker, J. Wu, J. Sun, M.D. Mullin, and J.M. Rehg, "On the Design of Cascades of Boosted Ensembles for Face Detection," Int'l J. Computer Vision, vol. 77, pp. 65-86, 2008.
[8] R. Xiao, L. Zhu, and H.-J. Zhang, "Boosting Chain Learning for Object Detection," Proc. IEEE Int'l Conf. Computer Vision, pp. 709-715, 2003.
[9] R. Xiao, H. Zhu, H. Sun, and X. Tang, "Dynamic Cascades for Face Detection," Proc. IEEE Int'l Conf. Computer Vision, pp. 1-8, 2007.
[10] J. Sochman and J. Matas, "Waldboost-Learning for Time Constrained Sequential Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 150-156, 2005.
[11] H. Masnadi-Shirazi and N. Vasconcelos, "High Detection-Rate Cascades for Real-Time Object Detection," Proc. IEEE Int'l Conf. Computer Vision, 2007.
[12] M.-T. Pham, V.-D. Hoang, and T.-J. Cham, "Detection with Multi-Exit Asymmetric Boosting," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2008.
[13] L. Bourdev and J. Brandt, "Robust Object Detection via Soft Cascade," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 236-243, 2005,
[14] W. Fan, S.J. Stolfo, J. Zhang, and P.K. Chan, "Adacost: Misclassification Cost-Sensitive Boosting," Proc. Int'l Conf. Machine Learning, 1999.
[15] K.M. Ting, "A Comparative Study of Cost-Sensitive Boosting Algorithms," Proc. Int'l Conf. Machine Learning, pp. 983-990, 2000.
[16] A. Wong, Y. Sun, and Y. Wang, "Parameter Inference of Cost-Sensitive Boosting Algorithms," Proc. Int'l Conf. Machine Learning and Data Mining in Pattern Recognition, 2005.
[17] J. Wu, S.C. Brubaker, M.D. Mullin, and J.M. Rehg, "Fast Asymmetric Learning for Cascade Face Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 3, pp. 369-382, Mar. 2008.
[18] K.-K. Sung and T. Poggio, "Example-Based Learning for View-Based Human Face Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp. 39-51, Jan. 1998.
[19] Y. Freund and R.E. Schapire, "A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting," Proc. European Conf. Computational Learning Theory, 1995.
[20] J. Friedman, T. Hastie, and R. Tibshirani, "Additive Logistic Regression: A Statistical View of Boosting," Annals of Statistics, vol. 28, pp. 337-407, 2000.
[21] L. Mason, J. Baxter, P. Bartlett, and M. Frean, "Boosting Algorithms as Gradient Descent," Proc. Advances in Neural Information Processing Systems, 2000.
[22] J. Nocedal and S. Wright, Numerical Optimization. Springer Verlag, 1999.
[23] R.E. Schapire and Y. Singer, "Improved Boosting Algorithms Using Confidence-Rated Predictions," Machine Learning, vol. 37, pp. 297-336, 1999.
[24] H. Masnadi-Shirazi, V. Mahadevan, and N. Vasconcelos, "On the Design of Robust Classifiers for Computer Vision," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2010.
[25] D. Mease and A. Wyner, "Evidence Contrary to the Statistical View of Boosting," J. Machine Learning Research, vol. 9, pp. 131-156, 2008.
[26] H. Masnadi-Shirazi and N. Vasconcelos, "Cost-Sensitive Boosting," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 2, pp. 294-309, Feb. 2011.
[27] J. Sochman, "Learning for Sequential Classification," PhD dissertation, Czech Technical Univ., 2009.
[28] A. Wald, Sequential Analysis. Dover, 1947.
[29] S. Agarwal, A. Awan, and D. Roth, "Learning to Detect Objects in Images via a Sparse, Part-Based Representation," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 11, pp. 1475-1490, Nov. 2004.
[30] P. Dollár, C. Wojek, B. Schiele, and P. Perona, "Pedestrian Detection: A Benchmark," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009.
[31] S. Maji, A.C. Berg, and J. Malik, "Classification Using Intersection Kernel Support Vector Machines Is Efficient," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2008.
[32] P. Dollár, C. Wojek, B. Schiele, and P. Perona, "Pedestrian Detection: An Evaluation of the State of the Art," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 34, no. 4, pp. 743-761, Apr. 2012.
[33] P. Dollár, S. Belongie, and P. Perona, "The Fastest Pedestrian Detector in the West," Proc. British Machine Vision Conf., 2010.
[34] B. Leibe, A. Leonardis, and B. Schiele, "Robust Object Detection with Interleaved Categorization and Segmentation," Int'l J. Computer Vision, vol. 77, pp. 259-289, 2008.
[35] C. Lampert, M. Blaschko, and T. Hofmann, "Efficient Subwindow Search: A Branch and Bound Framework for Object Localization," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2129-2142, Dec. 2009.
[36] M. Fritz, B. Leibe, B. Caputo, and B. Schiele, "Integrating Representative and Discriminant Models for Object Category Detection," Proc. IEEE Int'l Conf. Computer Vision, vol. 2, pp. 1363-1370, 2005.
[37] R. Fergus, P. Perona, and A. Zisserman, "Object Class Recognition by Unsupervised Scale-Invariant Learning," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 264-271, 2003.
[38] J. Mutch and D. Lowe, "Multiclass Object Recognition with Sparse, Localized Features," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 11-18, 2006.
[39] H. Schneiderman, "Feature-Centric Evaluation for Efficient Cascaded Object Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 29-36, 2004.
[40] B. Wu and R. Nevatia, "Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature Based Classifier," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[41] S. Han and N. Vasconcelos, "Biologically Plausible Detection of Amorphous Objects in the Wild," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition Workshop, 2011.
[42] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan, "Object Detection with Discriminatively Trained Part-Based Models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 32, no. 9, pp. 1627-1645, Sept. 2010.
[43] J. Yang, K. Yu, Y. Gong, and T. Huang, "Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1794-1801, 2009.
[44] S. Lazebnik, C. Schmid, and J. Ponce, "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 2169-2178, 2006.
7 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool