基于多头软注意力图卷积网络的行人轨迹预测

Pedestrian trajectory prediction based on multi-head soft attention graph convolutional network

行人间交互作用的复杂性给行人轨迹预测带来了挑战,且现有算法难以捕获行人间有意义的交互信息,不能直观地建模行人间的交互作用。针对以上问题,提出多头软注意力图卷积网络。首先利用多头软注意力(MS ATT)结合内卷网络Involution分别从空间图和时间图输入中提取稀疏空间和稀疏时间邻接矩阵,生成稀疏空间和稀疏时间有向图;然后,利用图卷积网络(GCN)从稀疏空间和稀疏时间有向图中学习交互作用与运动趋势特征;最后,将学习到的轨迹特征输入时间卷积网络(TCN)以预测双高斯分布参数,生成行人预测轨迹。在ETH和UCY数据集上的实验结果表明:相较于空时社交关系池化行人轨迹预测模型(SOPM),所提算法的平均位移误差(ADE)降低了2.78%;相较于稀疏图卷积网络(SGCN),所提算法的最终位移误差(FDE)降低了16.92%。

The complexity of pedestrian interaction is a challenge for pedestrian trajectory prediction,and the existing algorithms are difficult to capture meaningful interaction information between pedestrians,which cannot intuitively model the interaction between pedestrians.To address this problem,a multi-head soft attention graph convolutional network was proposed.Firstly,a Multi-head Soft ATTention(MS ATT)combined with involution network was used to extract sparse spatial adjacency matrix and sparse temporal adjacency matrix from spatial and temporal graph inputs respectively to generate sparse spatial directed graph and sparse temporal directed graph.Then,a Graph Convolutional Network(GCN)was used to learn interaction and motion trend features from sparse spatial and sparse temporal directed graphs.Finally,the learned trajectory features were input into a Temporal Convolutional Network(TCN)to predict double Gaussian distribution parameters,thereby generating the predicted pedestrian trajectories.Experiments on Eidgenossische Technische Hochschule(ETH)and University of CYprus(UCY)datasets show that,compared with Space-time sOcial relationship pooling pedestrian trajectory Prediction Model(SOPM),the proposed algorithm reduces the Average Displacement Error(ADE)by 2.78%,and compared to Sparse Graph Convolution Network(SGCN),the proposed algorithm reduces the Final Displacement Error(FDE)by 16.92%.