Taillight Detection for Driving Intention Recognition in Multi-Scene Autonomous Driving

Reliable perception of taillight signals is essential for robust driving intention recognition in autonomous vehicles. However, real-world conditions, such as varying illumination and adverse weather, often degrade image quality and obscure visual cues, leading to detection errors and poor generalization in traditional vision-based methods. To address these challenges, this paper proposes the Multi-Scene Preceding Vehicle Intention Recognition Network (MS-PVIRNet), a framework designed for adaptive intention recognition across diverse driving environments. Central to the method is a Global-Local Attention-guided CLAHE module (GLA-CLAHE), which employs an attention fusion mechanism to combine global illumination context and local texture cues, allowing adaptive regression of CLAHE parameters. This strategy significantly improves taillight visibility under complex environmental conditions. MS-PVIRNet adopts a YOLO-based detection architecture, enhanced with multi-scale feature fusion and omni-dimensional dynamic convolution to improve robustness and efficiency in intention recognition. Extensive experiments are conducted on a self-constructed multi-scene driving intention dataset. Results show that MS-PVIRNet outperforms other methods under various lighting and weather conditions, providing a practical solution for intention recognition in real-world autonomous driving scenarios. Furthermore, sensitivity analysis on vehicle distance and relative velocity shows that the proposed method maintains high recognition accuracy within 0–30 meters and 0–25 km/h, validating its effectiveness in dynamic and complex environments.