A General Framework of Learning Multi-Vehicle Interaction Patterns from Videos
This work addresses the challenge of autonomous vehicle decision-making by providing a method to analyze intricate traffic interactions, though it appears incremental as it builds on existing techniques like Gaussian velocity fields and deep autoencoders.
The paper tackles the problem of understanding multi-vehicle interaction patterns in cluttered driving environments by proposing a general framework that extracts traffic primitives from bird's-eye view videos, enabling semantic analysis of complex scenarios.
Semantic learning and understanding of multi-vehicle interaction patterns in a cluttered driving environment are essential but challenging for autonomous vehicles to make proper decisions. This paper presents a general framework to gain insights into intricate multi-vehicle interaction patterns from bird's-eye view traffic videos. We adopt a Gaussian velocity field to describe the time-varying multi-vehicle interaction behaviors and then use deep autoencoders to learn associated latent representations for each temporal frame. Then, we utilize a hidden semi-Markov model with a hierarchical Dirichlet process as a prior to segment these sequential representations into granular components, also called traffic primitives, corresponding to interaction patterns. Experimental results demonstrate that our proposed framework can extract traffic primitives from videos, thus providing a semantic way to analyze multi-vehicle interaction patterns, even for cluttered driving scenarios that are far messier than human beings can cope with.