基于YOLO算法的非机动车辆检测模型  

Non-Motor Vehicle Detection Model Based on YOLO Algorithm

作　　者：王树凤[1] 梁庆伟 王宇航 周倩 Wang Shufeng;Liang Qingwei;Wang Yuhang;Zhou Qian(Shandong University of Science and Technology,Qingdao 266590;BYD Auto Co.,Ltd.,Xi’an 710119)

机构地区：[1]山东科技大学,青岛266590 [2]比亚迪汽车有限公司,西安710119

出　　处：《汽车工程师》2024年第8期8-14,共7页Automotive Engineer

基　　金：山东省研究生优质专业学位教学案例库建设项目(SDYAL2023051)。

摘　　要：针对自动驾驶车辆目标检测过程中非机动车因体积小、易被遮挡而导致误检和漏检的问题,为提高非机动车的检测精度,对YOLOv4基础算法进行改进,利用跨阶段连接优化特征提取融合网络,在减少计算量的同时提高检测性能,并嵌入卷积块注意力模块(CBAM),通过通道和空间注意力权值分配来增大有效特征权重、提高检测精度,同时,利用自建的非机动车数据集,在锚框(Anchor)自适应匹配的基础上建立非机动车检测模型。最后,为验证模型的有效性,通过消融实验对比模型性能,结果表明,所提出的检测模型能够有效提高非机动车的检测和识别效果,较好地解决误检和漏检问题。To address the issue of false and missed detection of non-motorized vehicles due to the small size and obstructed vision in autonomous vehicle target detection,this research refines YOLOv4 basic algorithm to bolster the accuracy of non-motorized vehicle detection.The optimized algorithm streamlines the feature extraction process through a cross-stage connection,concurrently diminishing computational overhead and bolstering detection efficiency.Additionally,Convolutional Block Attention Module(CBAM)is embedded to increase effective feature weights and improve detection accuracy through channel and spatial attention weights.A non-motorized vehicle detection model is established based on anchor adaptive matching using a self-built non-motorized vehicle dataset.To verify the effectiveness of the model,the performance of the model is compared through ablation experiments.The results show that the proposed detection model substantially improves the detection and recognition performance of non-motor vehicles,effectively solve the problems of missed and false detections.

关 键 词：非机动车检测 YOLOv4算法 卷积块注意力模块 跨阶段连接 消融实验 

分 类 号：U471.15[机械工程—车辆工程]