GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowds

2018/12/18 by Tharindu Fernando, Fernando, Tharindu, Simon Denman +5
Computer Science · Social Sciences · #Anomaly Detection Techniques and Applications #Human Mobility and Location-Based Analysis #Video Surveillance and Tracking Methods #cs.CV

paper · pdf · doi:10.48550/arxiv.1812.07667

Appeared in ACCV 2108

arxiv created 2018/12/18 · arxiv updated 2018/12/20

Abstract

This paper presents a novel deep learning framework for human trajectory prediction and detecting social group membership in crowds. We introduce a generative adversarial pipeline which preserves the spatio-temporal structure of the pedestrian's neighbourhood, enabling us to extract relevant attributes describing their social identity. We formulate the group detection task as an unsupervised learning problem, obviating the need for supervised learning of group memberships via hand labeled databases, allowing us to directly employ the proposed framework in different surveillance settings. We evaluate the proposed trajectory prediction and group detection frameworks on multiple public benchmarks, and for both tasks the proposed method demonstrates its capability to better anticipate human sociological behaviour compared to the existing state-of-the-art methods.

Related

• Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting
• Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs
• Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting
• HGCN-GJS: Hierarchical Graph Convolutional Network with Groupwise Joint Sampling for Trajectory Prediction
• Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks