摘要
为提高DeepSORT目标检测器YOLOv5s算法的检测精度,本文将注意力机制CBAM融入到YOLOv5s网络结构中,改进双向特征融合网络BiFPN,使用EIoU作为边界框损失函数.基于VOC 2007行人数据集的测试结果表明本文算法的精确率、召回率和平均精度相比于原算法分别提高0.3、1.0和0.3个百分点;在MOT17数据集上的测试结果表明本文算法的MOTA、IDF1、MT、IDR分别提升1.8个百分点、2.9个百分点和1、2.7,FN与ML分别降低了4373和11.测试结果验证了改进YOLOv5s作为检测器能够有效提升算法的跟踪精度.
Abstract
The study conducts focus on enhancing the detection accuracy of the YOLOv5s algorithm within the DeepSORT frame-work.The research work encompasses the integration of the attention mechanism called Convolutional Block Attention Module(CBAM)into the network structure of YOLOv5s,the refinement of the bidirectional feature fusion network Bi-directional Fea-ture Pyramid Network(BiFPN),and the adoption of Enhanced Intersection over Union(EIoU)as the bounding box loss func-tion.Test results obtained from the VOC 2007 pedestrian dataset indicates improvements when compared to the original algo-rithm.Specifically,the proposed algorithm exhibits an increase of 0.3 percentage points in precision,1.0 percentage points in re-call,and 0.3 percentage points in average precision.Subsequently,the algorithm is evaluated on the MOT17 dataset,showcas-ing significant enhancements in multiple metrics.The MOTA metric experiences a 1.8 percentage points improvement,while IDF1,MT,and IDR see enhancements of 2.9 percentage points,1,and 2.7,respectively.Moreover,the number of false nega-tives(FN)decreases by 4373,and the number of mostly lost targets(ML)decreases by 11.Overall,these empirical findings substantiate the efficacy of the improved YOLOv5s algorithm as a detector,effectively augmenting tracking precision in various scenarios.
国家科技期刊平台
NSTL
万方数据