Abstract 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.
Towards Optimal Training of Cascaded Detectors
Computer Vision – ECCV 2006 ; 3 ; 325-337
Lecture Notes in Computer Science ; 3951 , 3
2006-01-01
13 pages
Article/Chapter (Book)
Electronic Resource
English
Towards Optimal Training of Cascaded Detectors
British Library Conference Proceedings | 2006
|Long-term Navigation Optimal Operation of Cascaded Reservoirs
HENRY – Federal Waterways Engineering and Research Institute (BAW) | 2014
|Training Object Detectors With Noisy Data
IEEE | 2019
|