Cross-camera pedestrian detection tracking method based on depth learning

Abstract

The invention discloses a cross-camera pedestrian detection tracking method based on depth learning, which comprises the steps of: by training a pedestrian detection network, carrying out pedestrian detection on an input monitoring video sequence; initializing tracking targets by a target box obtained by pedestrian detection, extracting shallow layer features and deep layer features of a region corresponding to a candidate box in the pedestrian detection network, and implementing tracking; when the targets disappear, carrying out pedestrian re-identification which comprises the process of: after target disappearance information is obtained, finding images with the highest matching degrees with the disappearing targets from candidate images obtained by the pedestrian detection network and continuously tracking; and when tracking is ended, outputting motion tracks of the pedestrian targets under multiple cameras. The features extracted by the method can overcome influence of illuminationvariations and viewing angle variations; moreover, for both the tracking and pedestrian re-identification parts, the features are extracted from the pedestrian detection network; pedestrian detection, multi-target tracking and pedestrian re-identification are organically fused; and accurate cross-camera pedestrian detection and tracking in a large-range scene are implemented.

Description

technical field [0001] The invention belongs to the technical fields of computer vision and video analysis, and in particular relates to a method for detecting and tracking pedestrians across cameras based on deep learning. Background technique [0002] With people's emphasis on public safety issues and the rapid increase in the number and coverage of surveillance cameras, intelligent multi-camera surveillance is playing an increasingly important role. Pedestrians, as the subject of monitoring, not only have the commonality of general targets, but also have diversity within the class, which is the difficulty of pedestrian detection and tracking. Cross-camera pedestrian detection and tracking refers to the detection and tracking of pedestrian targets under multiple cameras. When a target leaves the field of view of the current camera, the target can be quickly retrieved in the adjacent camera area for continuous omni-directional tracking, and finally an effective pedestrian ...

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to overcome the problems of target occlusion and cross-camera illumination changes, viewing angle changes, scale changes, etc., and propose a cross-camera pedestrian detection and tracking method based on deep learning

Images