基于多注意力的改进YOLOv5s小目标检测算法OA北大核心CSTPCD
Improved small target detection algorithm based on multiattention and YOLOv5s for traffic sign recognition
交通标志识别应用中待检测目标多为小目标,因其携带信息少、定位精度要求高、易被环境噪声淹没等特点成为当前交通标志检测的难点.针对小目标交通标志漏检、误检、检测准确率低等问题,本文设计了一种用于小目标检测的STD-YOLOv5s(Small target detection YOLOv5s)模型.首先,通过增加上采样和Prediction输出层数获得了更丰富的位置信息,解决了YOLOv5s模型在处理小目标时信息不足的问题,增强了对图像的全局理解能力;…查看全部>>
Traffic sign detection and recognition facilitates real-time monitoring and interpretation of various traffic signs on the road, such as those indicating speed limits, prohibition of overtaking, and navigation cues. This has substantial applications for autonomous driving and decision-making systems. Consequently, designing accurate and efficient algorithms for the automatic recognition of traffic signs is crucial in the intelligent transportation field. How…查看全部>>
马鸽;李洪伟;严梓维;刘志杰;赵志甲
广州大学机械与电气工程学院,广州 510006广州大学机械与电气工程学院,广州 510006广州市公用事业技师学院,广州 510199北京科技大学智能科学与技术学院,北京100083广州大学机械与电气工程学院,广州 510006
计算机与自动化
小目标检测交通标志识别注意力机制YOLOv5s深度学习
small target detectiontraffic sign recognitionattention mechanismYOLOv5sdeep learning
《工程科学学报》 2024 (9)
1647-1658,12
国家自然科学基金资助项目(NO.62173102,U20A20225)
评论