Intelligent video analysis: A Pedestrian trajectory extraction method for the whole indoor space without blind areas

Abstract

Pedestrian trajectory extraction is an important part of intelligent monitoring, which is of great significance to many fields such as statistics on pedestrian flow and density, population behavior analysis, abnormal behavior detection, etc. However, it is quite challenging to extract pedestrian trajectory without blind areas in the whole space due to the limited view angle of ordinary cameras. So far, no efficient method has been proposed to deal with this problem. In this paper, we propose a pedestrian trajectory extraction method based on a single fisheye camera, which can realize no blind areas pedestrian trajectory extraction in the whole interior space. First, the fisheye camera with a perspective of 180∘ is adopted in our work which can realize the entire space monitoring without blind areas and avoid object matching among multiple cameras. Then, the deep convolutional neural network, the Kalman Filter algorithm, and the Hungarian algorithm are combined for pedestrian head detection and tracking. In order to calculate the coordinates of the trajectory points according to the obtained head position, we propose a novel pedestrian height estimation method for fisheye cameras. Finally, the pedestrian trajectory points are calculated based on the detected head position and the estimated height. The performance of the proposed pedestrian trajectory extraction method has been evaluated by a variety of experiments. The experimental results show that the trajectories of multiple pedestrians can be extracted simultaneously through the method proposed in this paper, and the average error of the trajectory points is less than 5.07 pixels in the 512×512 images.