A credibility scoring algorithm to match surveillance video targets and UWB tags

Pedestrian positioning by surveillance video offers high accuracy and real-time performance in indoor scenes. However, pedestrian positioning based on surveillance video presents both challenges and promising application prospects. The practical application of existing surveillance video is hindered by the lack of tag information and incomplete video coverage. Although positioning methods with terminal devices provide tag information, simultaneous signal transmission from multiple tags to the base station can lead to collisions and mutual interference, such as with ultrawide-band (UWB) positioning. A positioning method that combines surveillance video and terminal devices is expected to solve this problem. This paper introduces a credibility scoring algorithm for matching surveillance video targets with terminal tags. The algorithm considers four factors: the distance between the obtained positioning points, the weighted average speed, the direction of motion, and the number of positioning points obtained from both the video and the UWB tag. The algorithm matches the surveillance video target with the UWB tag according to the highest score. The experimental results show that the proposed credibility scoring algorithm achieved accurate matching results in both unobstructed scenes (scores for the same tag are generally twice as high as scores for different tags) and obstructed scenes (scores for the same tag are 13% higher than scores for different tags). This approach improves the usability of pedestrian positioning via surveillance videos in indoor scenes, avoids the problem of tag misalignment, and will provide further technical support for pedestrian positioning and management based on surveillance videos.