EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction

Figure 4

The structure of FU to calculate Z. is the initial input from equation (3). is the sequence length and is the number of pedestrians. is the embedded dimension, which is defined as 32 dimensions. 4 represents the number of attention heads. , , and are convolution operations. and calculate the intimacy between nodes, that is, the weight of adjacent nodes. is a display function, which is used to calculate the feature of adjacent nodes. and represent addition and multiplication of matrices, respectively. BN is normalization. It is better to show in color.