Future pedestrian trajectory prediction offers great prospects for many practical applications. Most existing methods focus on social interaction among pedestrians but ignore the factors that heterogeneous traffic objects (cars, dogs, bicycles, motorcycles, etc.) have significant influence on the future trajectory of a subject pedestrian. Also, the walking direction intention of a pedestrian may be referred by his/her pose keypoints. Considering this, this work proposes to predict a pedestrian’s future trajectory by jointly using neighboring heterogeneous traffic information and his/her pose keypoints. To fulfill this, an end-to-end pose keypoints-based convolutional encoder-decoder network (PK-CEN) is designed, in which the heterogeneous traffic and pose keypoints are modeled as input. After training, PK-CEN is evaluated on manifold crowded video sequences collected from the public dataset MOT16, MOT17 and MOT20. Experimental results demonstrate that it outperforms state-of-the-art approaches, in terms of prediction errors.

中文翻译：

---

基于姿势关键点的卷积编码器-解码器网络在异构交通中的行人轨迹预测

未来的行人轨迹预测为许多实际应用提供了广阔的前景。现有的大多数方法都集中在行人之间的社交互动上，却忽略了异类交通对象（汽车，狗，自行车，摩托车等）对目标行人的未来轨迹产生重大影响的因素。而且，行人的步行方向意图可以通过他/她的姿势关键点来参考。考虑到这一点，这项工作建议通过联合使用邻近的异构交通信息和他/她的姿势关键点来预测行人的未来轨迹。为此，设计了一种基于端到端姿势关键点的卷积编码器/解码器网络（PK-CEN），其中将异构流量和姿势关键点建模为输入。训练结束后，在从公共数据集MOT16，MOT17和MOT20收集的大量拥挤视频序列上评估PK-CEN。实验结果表明，在预测误差方面，它优于最新方法。