GSTA: Pedestrian trajectory prediction based on global spatio-temporal association of graph attention network

Most encoder-decoder structure based predictions models usually predict trajectory according to the position and historical movement of nearby pedestrians. Their input range (receptive field) is small. They often ignore some specific information such as speed direction pedestrians’ or temporal attention. This leads detailed pedestrian interaction that cannot be obtained. Therefore, we propose a novel spatio-temporal graph attention network (GAT) called GSTA. In spatial domain, GSTA obtains complex by (SA) on multi-feature fusion, expands receptive field through feature updating mechanism (FUM). design module (TAM) selection (FSM). TAM used discover internal relationship solve problem averaged. FSM overcomes adverse effect small perceptual reasonably controls flow information. Experimental results 5 commonly datasets show prediction accuracy our proposed model further improved.