基于视频帧的交通灯识别模型，实现在嵌入式设备上的实时高鲁棒性检测。
Video-based Traffic Light Recognition by Rockchip RV1126 for Autonomous Driving
- 利用多帧视频输入与卷积自注意力机制，提升复杂场景下的识别能力。
- 在Rockchip RV1126上实现超过25 FPS的实时推理，性能优于单帧方法。
- 适用于自动驾驶中的车道级交通灯识别，开源代码和数据集便于复现。
实时交通灯识别是城市环境中自动驾驶安全与导航的基础。现有方法依赖车载摄像头的单帧分析，在遮挡和恶劣光照条件下表现不佳。本文提出一种名为ViTLR的新型视频端到端神经网络，通过处理连续多帧实现鲁棒的交通灯检测与状态分类。该架构采用类Transformer设计，结合卷积自注意力模块，专为Rockchip RV1126嵌入式平台优化。在两个真实世界数据集上的大量实验表明，ViTLR在保持>25 FPS实时性能的同时达到当前最佳效果，相比单帧方法在时间稳定性、目标距离变化及复杂环境条件下表现出更强鲁棒性。我们已将ViTLR成功集成至基于高清地图的本车车道交通灯识别系统中。完整实现（含源码与数据集）已公开，以促进该领域的进一步研究。
原文摘要 · Abstract (English)
Real-time traffic light recognition is fundamental for autonomous driving safety and navigation in urban environments. While existing approaches rely on single-frame analysis from onboard cameras, they struggle with complex scenarios involving occlusions and adverse lighting conditions. We present \textit{ViTLR}, a novel video-based end-to-end neural network that processes multiple consecutive frames to achieve robust traffic light detection and state classification. The architecture leverages a transformer-like design with convolutional self-attention modules, which is optimized specifically for deployment on the Rockchip RV1126 embedded platform. Extensive evaluations on two real-world datasets demonstrate that \textit{ViTLR} achieves state-of-the-art performance while maintaining real-time processing capabilities (>25 FPS) on RV1126's NPU. The system shows superior robustness across temporal stability, varying target distances, and challenging environmental conditions compared to existing single-frame approaches. We have successfully integrated \textit{ViTLR} into an ego-lane traffic light recognition system using HD maps for autonomous driving applications. The complete implementation, including source code and datasets, is made publicly available to facilitate further research in this domain.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。