Light “You Only Look Once”: An Improved Lightweight Vehicle-Detection Model for Intelligent Vehicles under Dark Conditions

Abstract

Vehicle detection is crucial for traffic surveillance and assisted driving. To overcome the loss of efficiency, accuracy, and stability in low-light conditions, we propose a lightweight “You Only Look Once” (YOLO) detection model. A polarized self-attention-enhanced aggregation feature pyramid network is used to improve feature extraction and fusion in low-light scenarios, and enhanced “Swift” spatial pyramid pooling is used to reduce model parameters and enhance real-time nighttime detection. To address imbalanced low-light samples, we integrate an anchor mechanism with a focal loss to improve network stability and accuracy. Ablation experiments show the superior accuracy and real-time performance of our Light-YOLO model. Compared with EfficientNetv2-YOLOv5, Light-YOLO boosts mAP@0.5 and mAP@0.5:0.95 by 4.03 and 2.36%, respectively, cuts parameters by 44.37%, and increases recognition speed by 20.42%. Light-YOLO competes effectively with advanced lightweight networks and offers a solution for efficient nighttime vehicle-detection.