Small, but important: Traffic light proposals for detecting small traffic lights and beyond
This addresses a critical safety issue for self-driving cars and driver assistance systems by improving detection of small traffic lights, though it is an incremental advance in a specific domain.
The paper tackled the problem of detecting small and tiny traffic lights, which are often overlooked in existing systems, by proposing a new detection system with a novel proposal generator and detection head, achieving at least 12.6% improvement on small and tiny traffic lights.
Traffic light detection is a challenging problem in the context of self-driving cars and driver assistance systems. While most existing systems produce good results on large traffic lights, detecting small and tiny ones is often overlooked. A key problem here is the inherent downsampling in CNNs, leading to low-resolution features for detection. To mitigate this problem, we propose a new traffic light detection system, comprising a novel traffic light proposal generator that utilizes findings from general object proposal generation, fine-grained multi-scale features, and attention for efficient processing. Moreover, we design a new detection head for classifying and refining our proposals. We evaluate our system on three challenging, publicly available datasets and compare it against six methods. The results show substantial improvements of at least $12.6\%$ on small and tiny traffic lights, as well as strong results across all sizes of traffic lights.