Directional traffic light recognition improves city driving decisions
One Perception, All Maneuvers: Directional Traffic Signal Understanding for Maneuver-Level Signal Intent Prediction
Computer Vision and Pattern Recognition
Summary
Traffic lights tell cars when to stop or go at intersections, but they don’t just show colors—they control specific maneuvers like going straight or turning left. The authors created a system that looks at a single camera view and figures out what each traffic light means for these different driving moves. Their system does better than older methods, especially where there are many traffic lights. This approach gives self-driving cars clearer instructions for safe and smart driving.
What this means in practice
- •For autonomous vehicle engineers: Add direct interpretation of traffic lights for specific maneuvers to improve self-driving car decisions at city intersections.
- •For urban traffic management teams: Use maneuver-aware traffic light data to better understand and simulate traffic flow and safety at complex intersections.
Authors
Ang Zou, Runzhe Zheng, Zhigang li, Zhen Yang, Han Xia, Xuewei Li, Zequn Qin, Xi Li
Abstract
Traffic lights are a key regulatory signal for autonomous driving at urban intersections, yet existing traffic signal perception is still predominantly formulated as instance-level detection or color recognition. Such formulations identify where traffic lights are and what colors they display, but leave a critical semantic gap before downstream planning: which ego maneuver is controlled by each visible signal and what dynamic permission the signal expresses for that maneuver. In this paper, we formulate Directional Traffic Signal Understanding, a decision-oriented task that predicts structured signal states for straight, left-turn, right-turn, and U-turn maneuvers from a front-view image. Each state contains the associated signal color and signal-implied passability. Based on OpenLane-V2, we provide a direction-level benchmark with maneuver-level supervision and metrics for color recognition, passability, full-frame consistency, and safety-critical errors. A direction-aware baseline combines global context, localized traffic-light evidence, and maneuver-specific representations. Experiments show that direction-level modeling improves passability prediction over image-level classifiers and detection-oriented pipelines, particularly at complex multi-signal intersections. The resulting representation provides a direct and interpretable traffic-signal interface for downstream planning together with topology, route, and surrounding-agent information.