Asymmetric Totally-corrective Boosting for Real-time Object Detection

Details Asymmetric Totally-corrective Boosting for Real-time Object Detection Asymmetric Totally-corrective Boosting for Real-time Object Detection

2010-09-16

arxiv.org/abs/1009.3078v1

Computer Science

Computer Vision and Pattern Recognition

14 pages, published in Asian Conf. Computer Vision 2010

Scientific paper

Real-time object detection is one of the core problems in computer vision. The cascade boosting framework proposed by Viola and Jones has become the standard for this problem. In this framework, the learning goal for each node is asymmetric, which is required to achieve a high detection rate and a moderate false positive rate. We develop new boosting algorithms to address this asymmetric learning problem. We show that our methods explicitly optimize asymmetric loss objectives in a totally corrective fashion. The methods are totally corrective in the sense that the coefficients of all selected weak classifiers are updated at each iteration. In contract, conventional boosting like AdaBoost is stage-wise in that only the current weak classifier's coefficient is updated. At the heart of the totally corrective boosting is the column generation technique. Experiments on face detection show that our methods outperform the state-of-the-art asymmetric boosting methods.

Affiliated with

Also associated with

No associations

Rating

Asymmetric Totally-corrective Boosting for Real-time Object Detection does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Asymmetric Totally-corrective Boosting for Real-time Object Detection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Asymmetric Totally-corrective Boosting for Real-time Object Detection will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-27072