CPU环境下多传感器数据融合的机器人3D目标检测方法OA北大核心CSTPCD

Real-time and accurate 3D object detection algorithms can provide target position and shape information,en-suring efficient navigation and effective obstacle avoidance for mobile robots,among other tasks.Existing 3D object de-tection algorithms heavily rely on the computational capabilities of hardware devices.A multi-sensor fusion 3D object de-tection method that can be deployed in mobile robot CPU environments has been proposed to reduce hardware require-ments while ensuring detection accuracy.The method combines 2D object detection and point cloud clustering tech-niques.It utilizes 2D object detection technology to obtain object detection information from images,then performs point cloud segmentation within the detection bounding boxes based on the spatial mapping relationship between cameras and lidars.The segmented point clouds are further clustered and processed for information extraction,achieving 3D object de-tection and localization capabilities.By comparing with the classical multi-sensor 3D target detection algorithm MVX-Net,the algorithm in this paper has better detection accuracy with smaller computational complexity.Furthermore,the method is deployed and analyzed on actual mobile robot CPU devices at the edge terminal,achieving a processing speed of 0.069 seconds per frame,satisfying the 10 Hz laser radar frequency requirement.