基于全局自适应有向图的行人轨迹预测  

Pedestrian Trajectory Prediction Based on Global Adaptive Directed Graph

作　　者：孔玮 刘云[1] 李辉[1] 崔雪红[1] 杨浩冉 KONG Wei;LIU Yun;LI Hui;CUI Xue-hong;YANG Hao-ran(School of Information Science and Technology,Qingdao University of Science and Technology,Qingdao,Shandong 266061,China)

机构地区：[1]青岛科技大学信息科学技术学院,山东青岛266061

出　　处：《电子学报》2022年第8期1905-1916,共12页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61702295);山东省高等学校优秀青年创新团队计划(No.2019KJN047)。

摘　　要：由于行人交互的复杂性和周围环境的多变性,行人轨迹预测仍是一项具有挑战性的任务.然而,基于图结构的方法建模行人之间的交互时,存在着网络感受野小、成对行人间的相互交互对称、固定的图结构不能适应场景变化的问题,导致预测轨迹与真实轨迹偏差较大.为了解决这些问题,本文提出一种基于全局自适应有向图的行人轨迹预测方法(pedestrian trajectory prediction method based on Global Adaptive Directed Graph,GADG).设计全局特征更新(Global Feature Updating,GFU)和全局特征选择(Global Feature Selection,GFS)分别提升空间域和时间域的网络感受范围,以获取全局交互特征.构建有向特征图,定义行人间的不对称交互,提高网络建模的方向性.建立自适应图模型,灵活调整行人间的交互关系,减少冗余连接,增强图模型的自适应能力.在ETH和UCY数据集上的实验结果表明,与最优值相比,平均位移误差降低14%,最终位移误差降低3%.Due to the complexity of pedestrian interaction and the variability of the surrounding environment,pedestrian trajectory prediction is still a challenging task.However,when modeling pedestrian interaction based on graph structure,there are some problems,such as small sensing field of the network,symmetrical interaction between pedestrians,and fixed graph structure that can not adapt to scene changes,which lead to a large deviation of the predicted trajectory from the real trajectory.To solve these problems,a pedestrian trajectory prediction method based on global adaptive directed graph is proposed.Global feature updating(GFU)and global feature selection(GFS)are designed to improve the perception range in spatial and temporal domain respectively and get global interaction features.A directed feature graph is constructed to define the asymmetric interaction between pedestrians and improve the directionality of network modeling.An adaptive graph model is established to flexibly adjust the relationship between pedestrians,reduce redundant connections and enhance the adaptive ability of the graph.The experimental results on ETH and UCY datasets show that comparing with the optimal value,the average displacement error is reduced by 14%and the final displacement error is reduced by 3%.

关 键 词：轨迹预测 自适应图 有向图 感受野 行人轨迹 图卷积 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]