This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Real-Time Deformable Detector
February 2012 (vol. 34 no. 2)
pp. 225-239
K. Ali, EPFL IC CVLAB, Lausanne, Switzerland
F. Fleuret, Centre du Parc, Idiap Res. Inst., Martigny, Switzerland
D. Hasler, CSEM SA, Neuchdtel, Switzerland
P. Fua, EPFL IC CVLAB, Lausanne, Switzerland
We propose a new learning strategy for object detection. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform based on the signal of interest. We train a detector with a standard AdaBoost procedure by using combinations of pose-indexed features and pose estimators. This allows the learning process to select and combine various estimates of the pose with features able to compensate for variations in pose without the need to label data for training or explore the pose space in testing. We validate our framework on three types of data: hand video sequences, aerial images of cars, and face images. We compare our method to a standard boosting framework, with access to the same ground truth, and show a reduction in the false alarm rate of up to an order of magnitude. Where possible, we compare our method to the state of the art, which requires pose annotations of the training data, and demonstrate comparable performance.

[1] Y. Amit, D. Geman, and B. Jedynak, "Efficient Focusing and Face Detection," Face Recognition: From Theory to Applications, Springer, 1998.
[2] P. Carbonetto, G. Dorkó, C. Schmid, H. Kück, and N. Freitas, "Learning to Recognize Objects with Little Supervision," Int'l J. Computer Vision, vol. 77, nos. 1-3, pp. 219-237, 2008.
[3] O. Chum and A. Zisserman, "An Exemplar Model for Learning Object Classes," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, June 2007.
[4] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2005.
[5] G.y. Dorkó and C. Schmid, "Selection of Scale-Invariant Parts for Object Class Recognition," Proc. IEEE Int'l Conf. Computer Vision, pp. 634-639, 2003.
[6] P. Felzenszwalb, D. Mcallester, and D. Ramanan, "A Discriminatively Trained, Multiscale, Deformable Part Model," Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2008.
[7] R. Fergus, P. Perona, and A. Zisserman, "Object Class Recognition by Unsupervised Scale-Invariant Learning," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 264-271, June 2003.
[8] F. Fleuret and D. Geman, "Stationary Features and Cat Detection," J. Machine Learning Research, vol. 9, pp. 2549-2578, 2008.
[9] 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, pp. 23-37, 1995.
[10] M. Kolsch and M. Turk, "Analysis of Rotational Robustness of Hand Detection with a Viola-Jones Detector," Proc. Int'l Conf. Pattern Recognition, vol. 3, pp. 107-110, Aug. 2004.
[11] A. Kushal, C. Schmid, and J. Ponce, "Flexible Object Models for Category-Level 3D Object Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[12] B. Leibe and B. Schiele, "Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search," Proc. Ann. Pattern Recognition Symp., 2004.
[13] S.Z. 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.
[14] S.Z. Li, L. Zhu, Z. Zhang, A. Blake, H.Z. Zhang, and H. Shum, "Statistical Learning of Multi-View Face Detection," Proc. European Conf. Computer Vision, pp. 67-81, 2002.
[15] J. Liebelt, C. Schmid, and K. Schertler, "Viewpoint-Independent Object Class Detection Using 3D Feature Maps," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[16] A. Mohan, C. Papageorgiou, and T. Poggio, "Example-Based Object Detection in Images by Components," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 4, pp. 349-361, Apr. 2001.
[17] A. Opelt, M. Fussenegger, A. Pinz, and P. Auer, "Weak Hypotheses and Boosting for Generic Object Detection and Recognition," Proc. European Conf. Computer Vision, pp. 71-84, 2004.
[18] M. Ozuysal, V. Lepetit, and P. Fua, "Pose Estimation for Category Specific Multiview Object Localization," Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2009.
[19] C. Papageorgiou and T. Poggio, "A Trainable System for Object Detection," Int'l J. Computer Vision, vol. 38, no. 1, pp. 15-33, 2000.
[20] H.A. Rowley, S. Baluja, and T. Kanade, "Neural Network-Based Face Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 1996.
[21] H.A. Rowley, S. Baluja, and T. Kanade, "Rotation Invariant Neural Network-Based Face Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 38-44, 1998.
[22] P.-F. Ruedi, P. Heim, F. Kaess, E. Grenet, F. Heitger, P.-Y. Burgi, S. Gyger, and P. Nussbaum, "A 128 X 128 Pixel 120-db Dynamic-Range Vision-Sensor Chip for Image Contrast and Orientation Extraction," IEEE J. Solid-State Circuits, vol. 38, no. 12, pp. 2325-2333, Dec. 2003.
[23] S. Savarese and L. Fei-Fei, "3D Generic Object Categorization Localization and Pose Estimation," Proc. IEEE Int'l Conf. Computer Vision, 2007.
[24] H. Schneiderman and T. Kanade, "A Statistical Method for 3D Object Detection Applied to Faces and Cars," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 746-751, 2000.
[25] H. Schneiderman and T. Kanade, "Object Detection Using the Statistics of Parts," Int'l J. Computer Vision, vol. 56, pp. 151-177, 2004.
[26] B. Stenger, A. Thayananthan, P.H.S. Torr, and R. Cipolla, "Filtering Using a Tree-Based Estimator," Proc. IEEE Int'l Conf. Computer Vision, pp. 1063-1070, 2003.
[27] B. Stenger, A. Thayananthan, P.H.S. Torr, and R. Cipolla, "Estimating 3D Hand Pose Using Hierarchical Multi-Label Classification," Image and Vision Computing, vol. 25, no. 12, pp. 1885-1894, 2007.
[28] H. Su, M. Sun, L. Fei-Fei, and S. Savarese, "Learning a Dense Multi-View Representation for Detection Viewpoint Classification and Synthesis of Object Categories," Proc. IEEE Int'l Conf. Computer Vision, 2009.
[29] A. Thomas, V. Ferrari, B. Leibe, T. Tuytelaars, B. Schiele, and L. Van Gool, "Towards Multi-View Object Class Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2006.
[30] A. Torralba, K.P. Murphy, and W.T. Freeman, "Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2004.
[31] P. Viola and M. Jones, "Fast Multi-View Face Detection," technical report, MERL, 2003.
[32] P. Viola and M. Jones, "Robust Real-Time Face Detection," Int'l J. Computer Vision, vol. 57, no. 2, pp. 137-154, 2004.
[33] P. Viola, M. Jones, and D. Snow, "Detecting Pedestrians Using Patterns of Motion and Appearance," Proc. IEEE Int'l Conf. Computer Vision, pp. 734-741, 2003.
[34] P. Yan, S.M. Khan, and M. Shah, "3D Model Based Object Class Detection in an Arbitrary View," Proc. IEEE Int'l Conf. Computer Vision, 2007.
[35] J. Zhang, S.K. Zhou, L. McMillan, and D. Comaniciu, "Joint Real-Time Object Detection and Pose Estimation Using Probabilistic Boosting Network," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.

Index Terms:
real-time systems,object detection,pose estimation,face images,real-time deformable detector,object detection,AdaBoost procedure,pose estimators,video sequences,aerial images,Feature extraction,Image processing,Object detection,Training data,Image edge detection,Machine learning,Learning systems,object detection.,Image processing and computer vision,machine learning
Citation:
K. Ali, F. Fleuret, D. Hasler, P. Fua, "A Real-Time Deformable Detector," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 2, pp. 225-239, Feb. 2012, doi:10.1109/TPAMI.2011.117
Usage of this product signifies your acceptance of the Terms of Use.