2009 IEEE Conference on Computer Vision and Pattern Recognition (2009)
Miami, FL, USA
June 20, 2009 to June 25, 2009
Zhe Lin , Univ. of Maryland, College Park, MD, USA
L.S. Davis , Univ. of Maryland, College Park, MD, USA
Feature misalignment in object detection refers to the phenomenon that features which fire up in some positive detection windows do not fire up in other positive detection windows. Most often it is caused by pose variation and local part deformation. Previous work either totally ignores this issue, or naively performs a local exhaustive search to better position each feature. We propose a learning framework to mitigate this problem, where a boosting algorithm is performed to seed the position of the object part, and a multiple instance boosting algorithm further pursues an aggregated feature for this part, namely multiple instance feature. Unlike most previous boosting based object detectors, where each feature value produces a single classification result, the value of the proposed multiple instance feature is the Noisy-OR integration of a bag of classification results. Our approach is applied to the task of human detection and is tested on two popular benchmarks. The proposed approach brings significant improvement in performance, i.e., smaller number of features used in the cascade and better detection accuracy.
human detection, multiple instance feature, robust part-based object detection, feature misalignment, positive detection windows, pose variation, multiple instance boosting algorithm, boosting based object detectors, noisy-OR integration
Gang Hua, Zhe Lin and L. Davis, "Multiple instance fFeature for robust part-based object detection," 2009 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Miami, FL, USA, 2009, pp. 405-412.