计算机科学 ›› 2026, Vol. 53 ›› Issue (6A): 250300090-7.doi: 10.11896/jsjkx.250300090
张首一, 申强, 郭怡然, 王晗瑜
ZHANG Shouyi, SHEN Qiang, GUO Yiran, WANG Hanyu
摘要： 针对传统目标检测算法在雨雾天气条件下识别精度下降的问题,提出了一种基于改进YOLOv8模型的目标检测方法。首先,引入FogEnhanceNet去雾增强模块,在模型输入阶段提升目标区域的对比度和清晰度,以增强特征可辨识度;其次,结合自适应对比度注意力机制,动态调整通道与空间信息权重,优化目标特征在低对比度环境下的表达能力;最后,设计轻量化C2f-Ghost-GF结构,以减少模型参数量,同时利用导向滤波增强雾天图像的边缘特征提取能力。实验结果表明,改进模型在模型参数量不明显增加的情况下目标检测平均精度均值(mAP)提升了11.3%,为复杂天气条件下的目标检测提供了有效的解决方案。
中图分类号:
| [1] WU P C,ZHENG Z W,WANG T T,et al.Haze Traffic Sign Recognition Based on CF-YOLO[J].Computer Engineering and Design,2024,45(7):2203-2211. [2] TANG L,WANG S Q,WANG N T,et al.Foggy Insulator Defect Detection Based on Improved YOLOX Network[J].High Voltage Apparatus,2024,60(3):223-228. [3] LU P D,FAN J,SUN S K.UAV Target Detection Based on Improved Dark Channel Prior Defogging[J].Laser Journal,2024,45(7):102-110. [4] XIAO J J,FAN B Y,YANG Y T.Ship Target Detection in Foggy Environments[J].Journal of Chongqing University of Technology,2024,38(5):212-219. [5] BHARAT SIVA VARMA P,ADIMOOLAM P,MARNA Y L,et al.Enhancing Robust Object Detection in Weather-Impacted Environments using Deep Learning Techniques[C]//IEEE.2024. [6] HA M,KIM C,PARK T.Object Recognition for Autonomous Driving in Adverse Weather Condition Using Polarized Camera[C]//IEEE.2022. [7] QIU Y,LU Y,WANG Y,et al.IDOD-YOLOV7:Image-Deha-zing YOLOV7 for Object Detection in Low-Light Foggy Traffic Environments[J].Sensors,2023,23(3):1347. [8] LUO P,NIE J,XIE J,et al.Localization-aware logit mimicking for object detection in adverse weather conditions[J].Image and Vision Computing,2024,146:105035. [9] KUMAR D,MUHAMMAD N.Object Detection in AdverseWeather for Autonomous Driving through Data Merging and YOLOv8[J].Sensors,2023,23(20):8471. [10] SU H,GAO H,WANG X,et al.Object Detection in Adverse Weather for Autonomous Vehicles Based on Sensor Fusion and Incremental Learning[J].IEEE Transactions on Instrumentation and Measurement,2024,73:1-10. [11] SU H,WANG X,GAO H,et al.Object Detection Method for Autonomous Vehicles in Adverse Weather[C]//IEEE.2023. [12] ZHANG L,ZHAO J,LANG Z,et al.Vehicle detection algorithm for foggy based on improved AOD-Net[J].Transactions of the Institute of Measurement and Control,2024,46(14):2696-2705. [13] SU J,LIANG B,FENG K K,et al.Foggy Target Detection Algorithm Based on Dimension Interaction and Cross-Layer Scale Cascade[J].Microelectronics & Computer,2024,41(1):53-62. [14] JING Z,LI S,ZHANG Q.YOLOv8-STE:Enhancing Object Detection Performance Under Adverse Weather Conditions with Deep Learning[J].Electronics,2024,13(24):5049. [15] LI R S,SHI Y Y,LIU X,et al.Foggy Image Target Detection Based on Double-Head[J].Liquid Crystal and Display,2023,38(12):1717-1727. [16] LAI J A,CHEN Z Q,SUN Z W,et al.Lightweight Foggy Target Detection Method Based on YOLOv5[J].Computer Engineering and Applications,2024,60(6):78-88. [17] LIU Z,YANG X Z,CHEN Y,et al.Foggy Target Detection Algorithm Based on Improved YOLOv8s[J].Electronic Measurement Technology,2024,47(20):186-194. [18] ZHAO S Y,FANG Y J.DCP-YOLOv7:Dark Channel Prior Image-Dehazing YOLOv7 For Vehicle Detection in Foggy Scene[C]//International Conference on Computer Vision and Pattern Analysis.2023. [19] KENK M A,HASSABALLAH M.DAWN:Vehicle Detection in Adverse Weather Nature Dataset[J].arXiv:2208.05402,2020. [20] ZHU P F,WEN L Y,DU D W,et al.Detection and Tracking Meet Drones Challenge[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(11):7380-7399. [21] XIA G S,BAI X,DING J,et al.DOTA:A Large-scale Dataset for Object Detection in Aerial Images[J].arXiv:1711.10398,2018. [22] GHARATAPPEH S,NESHATFAR S,SEKEH S Y,et al.FogGuard:guarding YOLO against fog using perceptual loss[J].arXiv:2403.08939,2024. [23] DING Y,LUO X.SDNIA-YOLO:A Robust Object DetectionModel for Extreme Weather Conditions[J].arXiv:2406.12395,2024. |
|
||
首页