MOT (Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking)demo阅读
变量:all_wts:3D-3D,3D-2D和2D-2D权重global_id:车辆总数K_all:相机内参angleMapdetectionsQ_dnos:原帧车辆回归框号detectionsT_dnos:下一帧车辆回归框号result_for_kitti_eval:预估结果total_detecions总检测数params_carCuboid(avgCar_Sz,sz_ub,sz_lb):车辆