Inferring the pose and shape of vehicles in 3D from a movable platform still
remains a challenging task due to the projective sensing principle of cameras,
difficult surface properties e.g. reflections or transparency, and illumination
changes between images. In this paper, we propose to use
提出了一种基于单目视觉的 3D 车辆检测和跟踪的在线框架,并利用 3D 车辆坐标信息和深度匹配对数据进行关联,并设计了一个基于 LSTM 的动作学习模块,以进行更准确的长期运动外推。实验结果表明,该跟踪系统可以提供抗干扰性更强的数据关联和跟踪能力,并且在跟踪 30 米内的行驶车辆方面比基于激光雷达的方法表现更好。