Phase Space Reconstruction Network for Lane Intrusion Action Recognition

TL;DR

This paper introduces PSRNet, a novel phase space reconstruction network that effectively recognizes lane intrusion actions in autonomous driving by analyzing motion time series, achieving high accuracy on real-world data.

Contribution

The paper presents a new object-level phase space reconstruction network with a Lyapunov exponent-like classifier for lane intrusion recognition in autonomous driving.

Findings

Achieves 98.0% accuracy on THU-IntrudBehavior dataset.

Outperforms existing action recognition methods by over 30%.

Effectively transforms video into motion time series for classification.

Abstract

In a complex road traffic scene, illegal lane intrusion of pedestrians or cyclists constitutes one of the main safety challenges in autonomous driving application. In this paper, we propose a novel object-level phase space reconstruction network (PSRNet) for motion time series classification, aiming to recognize lane intrusion actions that occur 150m ahead through a monocular camera fixed on moving vehicle. In the PSRNet, the movement of pedestrians and cyclists, specifically viewed as an observable object-level dynamic process, can be reconstructed as trajectories of state vectors in a latent phase space and further characterized by a learnable Lyapunov exponent-like classifier that indicates discrimination in terms of average exponential divergence of state trajectories. Additionally, in order to first transform video inputs into one-dimensional motion time series of each object, a lane width normalization based on visual object tracking-by-detection is presented. Extensive experiments are conducted on the THU-IntrudBehavior dataset collected from real urban roads. The results show that our PSRNet could reach the best accuracy of 98.0%, which remarkably exceeds existing action recognition approaches by more than 30%.