Scene Gated Social Graph: Pedestrian Trajectory Prediction Based on Dynamic Social Graphs and Scene Constraints
arXiv:2010.05507
Abstract
Pedestrian trajectory prediction is valuable for understanding human motion behaviors and it is challenging because of the social influence from other pedestrians, the scene constraints and the multimodal possibilities of predicted trajectories. Most existing methods only focus on two of the above three key elements. In order to jointly consider all these elements, we propose a novel trajectory prediction method named Scene Gated Social Graph (SGSG). In the proposed SGSG, dynamic graphs are used to describe the social relationship among pedestrians. The social and scene influences are taken into account through the scene gated social graph features which combine the encoded social graph features and semantic scene features. In addition, a VAE module is incorporated to learn the scene gated social feature and sample latent variables for generating multiple trajectories that are socially and environmentally acceptable. We compare our SGSG against twenty state-of-the-art pedestrian trajectory prediction methods and the results show that the proposed method achieves superior performance on two widely used trajectory prediction benchmarks.
References in corpus (10)
- Social Force Model for Pedestrian Dynamics
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- Toward Multimodal Image-to-Image Translation
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- A simple neural network module for relational reasoning
- Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
- Scene-LSTM: A Model for Human Trajectory Prediction
- Recursive Social Behavior Graph for Trajectory Prediction
- Reciprocal Learning Networks for Human Trajectory Prediction
- Collaborative Motion Prediction via Neural Motion Message Passing