Towards Optimal Training of Cascaded Detectors

Cascades of boosted ensembles have become popular in the object detection community following their highly successful introduction in the face detector of Viola and Jones [1]. In this paper, we explore several aspects of this architecture that have not yet received adequate attention: decision points of cascade stages, faster ensemble learning, and stronger weak hypotheses. We present a novel strategy to determine the appropriate balance between false positive and detection rates in the individual stages of the cascade based on a probablistic model of the overall cascade's performance. To improve the training time of individual stages, we explore the use of feature filtering before the application of Adaboost. Finally, we show that the use of stronger weak hypotheses based on CART can significantly improve upon the standard face detection results on the CMU-MIT data set.

[1]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[2]  Paul A. Viola,et al.  Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade , 2001, NIPS.

[3]  Narendra Ahuja,et al.  Detecting Faces in Images: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  James M. Rehg,et al.  Learning a Rare Event Detection Cascade by Direct Feature Selection , 2003, NIPS.

[5]  Harry Shum,et al.  Kullback-Leibler boosting , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  Rainer Lienhart,et al.  Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection , 2003, DAGM-Symposium.

[7]  Rong Xiao,et al.  Boosting chain learning for object detection , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[8]  Shimon Ullman,et al.  Object recognition with informative features and linear classification , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[10]  Peter Auer,et al.  Weak Hypotheses and Boosting for Generic Object Detection and Recognition , 2004, ECCV.

[11]  James M. Rehg,et al.  Automatic cascade training with perturbation bias , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[12]  Yair Weiss,et al.  Learning object detection from a small number of examples: the importance of good features , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[13]  Takeo Kanade,et al.  Object Detection Using the Statistics of Parts , 2004, International Journal of Computer Vision.

[14]  H. Schneiderman.  Feature-centric evaluation for efficient cascaded object detection , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[15]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[16]  Stan Z. Li,et al.  FloatBoost learning and statistical face detection , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  F. Fleuret.  Fast Binary Feature Selection with Conditional Mutual Information , 2004, J. Mach. Learn. Res..

[18]  E. Grossmann,et al.  Towards Interactive Generation of "Ground-truth" in Background Subtraction from Partially Labeled Examples , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[19]  Huitao Luo,et al.  Optimization design of cascaded classifiers , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[20]  Jiri Matas,et al.  WaldBoost - learning for time constrained sequential detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[21]  Paul A. Viola,et al.  Detecting Pedestrians Using Patterns of Motion and Appearance , 2005, International Journal of Computer Vision.

[22]  James M. Rehg,et al.  Linear Asymmetric Classifier for cascade detectors , 2005, ICML.

[23]  Richard J. Cleary.  Handbook of Beta Distribution and Its Applications , 2006 .

[24]  James M. Rehg,et al.  On the Design of Cascades of Boosted Ensembles for Face Detection , 2008, International Journal of Computer Vision.