论文信息 - Title-Template for Papers ECOC 2004

Title-Template for Papers ECOC 2004

This paper shows how to improve the real-time object detection in complex robotics applications, by exploring new visual features as AdaBoost weak classifiers. These new features are symmetric Haar filters (enforcing global horizontal and vertical symmetry) and N-connexity control points. Experimental evaluation on a car database show that the latter appear to provide the best results for the vehicle-detection problem.

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

[2] Bruno Steux,et al. YEF (Yet Even Faster) Real-Time Object Detection , 2005, ALaRT.

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

[4] Yoav Freund,et al. A Short Introduction to Boosting , 1999 .

[5] Gunnar Rätsch,et al. An Introduction to Boosting and Leveraging , 2002, Machine Learning Summer School.

[6] 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.

[7] Fabien Moutarde,et al. COMBINING ADABOOST WITH A HILL-CLIMBING EVOLUTIONARY FEATURE SEARCH FOR EFFICIENT TRAINING OF PERFORMANT VISUAL OBJECT DETECTORS , 2006 .

[8] Paul A. Viola,et al. Detecting Pedestrians Using Patterns of Motion and Appearance , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9] Yoav Freund,et al. A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.