Improving Part based Object Detection by Unsupervised, Online Boosting

Detection of objects of a given class is important for many applications. However it is difficult to learn a general detector with high detection rate as well as low false alarm rate. Especially, the labor needed for manually labeling a huge training sample set is usually not affordable. We propose an unsupervised, incremental learning approach based on online boosting to improve the performance on special applications of a set of general part detectors, which are learned from a small amount of labeled data and have moderate accuracy. Our oracle for unsupervised learning, which has high precision, is based on a combination of a set of shape based part detectors learned by off-line boosting. Our online boosting algorithm, which is designed for cascade structure detector, is able to adapt the simple features, the base classifiers, the cascade decision strategy, and the complexity of the cascade automatically to the special application. We integrate two noise restraining strategies in both the oracle and the online learner. The system is evaluated on two public video corpora.

[1]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[2]  Theodoros Evgeniou,et al.  A TRAINABLE PEDESTRIAN DETECTION SYSTEM , 1998 .

[3]  Nikunj C. Oza,et al.  Online Ensemble Learning , 2000, AAAI/IAAI.

[4]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Paul A. Viola,et al.  Unsupervised improvement of visual detectors using cotraining , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Maria-Florina Balcan,et al.  Co-Training and Expansion: Towards Bridging Theory and Practice , 2004, NIPS.

[7]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

[8]  Vinod Nair,et al.  An unsupervised, online learning framework for moving object detection , 2004, CVPR 2004.

[9]  Nikunj C. Oza,et al.  AveBoost2: Boosting for Noisy Data , 2004, Multiple Classifier Systems.

[10]  Shihong Lao,et al.  Boosting nested cascade detector for multi-view face detection , 2004, ICPR 2004.

[11]  A. Leonardis,et al.  On-line Conservative Learning for Person Detection , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[12]  Jonathan Brandt,et al.  Robust object detection via soft cascade , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[13]  Mubarak Shah,et al.  Online detection and classification of moving objects using progressively improving detectors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Stuart J. Russell,et al.  Online bagging and boosting , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[15]  Ramakant Nevatia,et al.  Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[16]  Yuan Li,et al.  Vector boosting for rotation invariant multi-view face detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[17]  Stephen Kwek,et al.  A boosting approach to remove class label noise , 2005, Fifth International Conference on Hybrid Intelligent Systems (HIS'05).

[18]  Horst Bischof,et al.  On-line Boosting and Vision , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[19]  C. Oza,et al.  AveBoost 2 : Boosting for Noisy Data , .