Recognition of pedestrian activity based on dropped-object detection

Abstract

Aiming at recognizing dropped objects and matching their owners, this paper presents a method for analyzing pedestrian activity based on dropped-object detection in video surveillance. The recognition results may be applied to further analyzing human activity and intentions such as determining whether the dropped-objects are intentional hazardous or unconsciously lost articles according to the appearance of dropped-objects. The method consists of dropped-object detection and recognition. The dropped-object detection algorithm uses foreground detection based on bi-directional background modeling, MeanShift tracking, and pixel-based regional information at the drop-off point. It analyzes the relationship between the dropped objects and pedestrians at the pixel level in complex environments with noises and occlusions. Afterwards, an algorithm based on moment invariant and Principal Component Analysis (PCA) is proposed to further recognize the dropped-objects viewed from different directions and locations from video cameras. In addition, in order to solve the limitation of the centralized video processing model for large-scale video streams in real time, the proposed method is designed and accomplished in a distributed model. The experimental results showed that the proposed method can effectively and efficiently recognize the pedestrian activity through the dropped objects in real-time video data.