Sciweavers

Share
ECCV
2008
Springer

Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection

8 years 9 months ago
Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection
Pedestrian detection in still image should handle the large appearance and stance variations arising from the articulated structure, various clothing of human as well as viewpoints. In this paper, we address this problem from a view which utilizes multiple instances to represent the variations in multiple instance learning (MIL) framework. Specifically, logistic multiple instance boost (LMIBoost) is advocated to learn the pedestrian appearance model. To efficiently use the histogram feature, we propose the graph embedding based decision stump for the data with non-Gaussian distribution. First the topology structure of the examples are carefully designed to keep between-class far and within-class close. Second, K-means algorithm is adopted to fast locate the multiple decision planes for the weak classifier. Experiments show the improved accuracy of the proposed approach in comparison with existing pedestrian detection methods, on two public test sets: INRIA and VOC2006's person det...
Junbiao Pang, Qingming Huang, Shuqiang Jiang
Added 19 Oct 2010
Updated 19 Oct 2010
Type Conference
Year 2008
Where ECCV
Authors Junbiao Pang, Qingming Huang, Shuqiang Jiang
Comments (0)
books