文档介绍：: .
兵工学报
更为全面的目标信息，跟踪目标未出现漏检，未发生跳变，且跟踪器输出位置状态结果与检测结果误差较小，
能够对所跟踪目标的状态进行准确估计，跟踪轨迹保持连续，有效提高了单车环境感知视野。
关键词：地面无人系统；多车协同感知；激光雷达；目标检测；目标跟踪
中图分类号： 文献标识码：A
DOI:
Method for Multi-Vehicle Cooperative Object Tracking
GONG Shixiong1，WANG Xu1，KONG Guojie1，2，GONG Jianwei1
(1. School of Mechanical Engineering，Beijing Institute of Technology，Beijing 100081，China； Special Vehicle Research
Institute，Beijing 100081，China)
Abstract:Multi-vehicle information fusion technology in ground unmanned systems is an important way to
improve system environment perception. Aiming at the problem of discontinuous and unstable object tracking caused
by vision occlusion and blind spots in single-vehicle sensors，a result-level fusion system model for centralized multi-
vehicle cooperative perception is proposed. The system model uses lidar as the vehicle perception sensor，and uses
D-S evidence theory to fuse the environment grid maps constructed by different vehicles at main control terminal to
obtain a global static environment map，completing the construction of the multi-vehicle cooperative perception
environment model. On the basis of this environment model，a multi-vehicle cooperative object detection and tracking
method is designed. First，the maximum value suppression method is used to resolve the detection object fusion
conflict； then a cascaded dynamic object matching and tracking management method is designed to complete object
prediction and tracking and send the results to each test results of a real-vehicle system composed of two
unmanned vehicles show that when the object is occ