YOLOv11在恶劣天气下检测精度更高，适合边缘部署。
Performance Analysis of YOLOv11 and YOLOv8 for Mixed Traffic Object Detection under Adverse Weather Conditions in Developing Countries
- 对比YOLOv8，采用新架构提升检测精度
- mAP@50达46.6%，误检率降低3.2%并减少22%计算量
- 适合发展中国家复杂交通场景的实时安全应用
在现代车载系统中，恶劣条件下的鲁棒性已成为自动驾驶的关键挑战。本研究对最新YOLO系列迭代——YOLOv11 Nano架构进行了全面评估，并以广泛使用的YOLOv8 Nano为基准，在融合印度驾驶数据集（IDD）与伯克利深度驾驶数据集（BDD100K）的自定义数据集上进行测试。分析了在高熵场景（密集混合交通、雨天、低光照）下检测精度、推理速度与计算效率之间的权衡。结果表明，YOLOv11n实现46.6%的mAP@50，较基线精度提升3.2%，有效减少复杂场景中的误检。同时，模型能耗更低，仅需6.3G FLOPs（相比8.1G减少22%），在Tesla T4 GPU上保持70.9 FPS的实时推理速度，适用于安全关键型边缘部署。
原文摘要 · Abstract (English)
In modern vehicular systems, robust performance under harsh conditions has become a critical problem of autonomous driving. Our study delivers a comprehensive evaluation of the newest iteration of the YOLO series, which is YOLOv11 Nano architecture benchmarked against the widely adopted YOLOv8 Nano as a baseline on a custom fused dataset that combines the Indian Driving Dataset (IDD) [1] and Berkeley Deep Drive Dataset (BDD100K) [2]. We have analyzed the trade-offs among detection accuracy, inference speed, and computational efficiency in high-entropy scenarios involving dense mixed traffic, rain, and low-light conditions. Specifically, YOLOv11n achieves a mean Average Precision (mAP@50) of 46.6%, with a notable 3.2% improvement in Precision over the baseline, effectively reducing false positives in cluttered scenes. Furthermore, the proposed model exhibits enhanced energy efficiency, requiring 22% fewer FLOPs (6.3G vs. 8.1G) while maintaining real-time inference speed of 70.9 FPS on a Tesla T4 GPU, offering an optimal trade-off for safety-critical edge deployment.
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。