Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction

02/27/2020
by   Abduallah Mohamed, et al.
0

Better machine understanding of pedestrian behaviors enables faster progress in modeling interactions between agents such as autonomous vehicles and humans. Pedestrian trajectories are not only influenced by the pedestrian itself but also by interaction with surrounding objects. Previous methods modeled these interactions by using a variety of aggregation methods that integrate different learned pedestrians states. We propose the Social Spatio-Temporal Graph Convolutional Neural Network (Social-STGCNN), which substitutes the need of aggregation methods by modeling the interactions as a graph. Our results show an improvement over the state of art by 20 (FDE) and an improvement on the Average Displacement Error (ADE) with 8.5 times less parameters and up to 48 times faster inference speed than previously reported methods. In addition, our model is data efficient, and exceeds previous state of the art on the ADE metric with only 20 We propose a kernel function to embed the social interactions between pedestrians within the adjacency matrix. Through qualitative analysis, we show that our model inherited social behaviors that can be expected between pedestrians trajectories.

READ FULL TEXT

page 4

page 8

page 11

research
04/22/2020

Recursive Social Behavior Graph for Trajectory Prediction

Social interaction is an important topic in human trajectory prediction ...
research
11/18/2020

Res-GCNN: A Lightweight Residual Graph Convolutional Neural Networks for Human Trajectory Forecasting

Autonomous driving vehicles (ADVs) hold great hopes to solve traffic con...
research
07/24/2019

Stochastic trajectory prediction with social graph network

Pedestrian trajectory prediction is a challenging task because of the co...
research
11/23/2020

Attentional-GCNN: Adaptive Pedestrian Trajectory Prediction towards Generic Autonomous Vehicle Use Cases

Autonomous vehicle navigation in shared pedestrian environments requires...
research
05/26/2020

CARPe Posterum: A Convolutional Approach for Real-time Pedestrian Path Prediction

Pedestrian path prediction is an essential topic in computer vision and ...
research
12/08/2021

A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos

Deep learning models have been widely used for anomaly detection in surv...

Please sign up or login with your details

Forgot password? Click here to reset