Multi-sensor Spatial and Time Scale Fusion Method for Off-road Environment Personnel Identification

Abstract

Unmanned vehicle can be used as a transport tool for teams and groups to accompany and follow soldiers, reduce the load of team members and identify team members accurately in real time. It is a prerequisite for the realization of control algorithm and one of the core technologies for automatic control of military vehicles. Aiming at the problem of personnel identification under the fusion perception of lidar and camera, especially the problem of multi-sensor space and time synchronization, this paper proposes a solution based on multi-sensor fusion, and designs fusion criteria of space scale, time scale and personnel identification. The experimental results show that a designed personnel identification algorithm based on multi-sensor space and time fusion can accurately identify personnel targets in complex environment, and the intersection ratio of lidar and camera fusion algorithm exceeds 95%.