Rapid classification based pedestrian detection in changing scenes

Abstract

How to adapt to changing scenes in pedestrian detection is a difficult problem in visual monitoring. This paper proposed a pedestrian detection method in changing scenes. Response to the requirements of high detection speed and high detection rate of pedestrian detection method in changing scenes, this paper mainly consists of two parts: (1) proposing a general ternary classification framework. It is based on cascade classification framework and each stage is a ternary detection pattern, that is, through comparing stage threshold to exclude current pedestrians or non-pedestrians object and objects which is difficult determine will enter the next layer filtering. Such detection framework is faster than traditional method and is suitable for real time pedestrian detection system. (2) Considering the above mentioned detection framework relies on thresholds, the parameters of cascade classifier which trained in old scene require adaptive adjustment in a new scenario. We design a pedestrian method in changing scenes, using a small amount of data in new scene to assist the old scene classifier, taking cross entropy method to quickly optimizing these parameters combination so that the optimized classifier can be better adapt to pedestrian detection in changing scenes. The new classifier can receive high detection rate and high detection speed. Taking AHHF dataset as an old scene and NICTA dataset as the new scene, experiments show that the proposed method can apply to pedestrian detection in new scene and obtain good results.