Abstract

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. Specifi- cally, logistic multiple instance boost (LMIBoost) is advocated to learn the pedestrian appearance model. To efficiently use the histogram fea- ture, we propose the graph embedding based decision stump for the data with non-Gaussian distribution. First the topology structure of the ex- amples 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 pedes- trian detection methods, on two public test sets: INRIA and VOC2006’s person detection subtask [1].