电子测量与仪器学报

史朋飞,韩松,倪建军,杨鑫.结合数据增强和改进 YOLOv4 的水下目标检测算法[J].电子测量与仪器学报,2022,36(3):113-121

结合数据增强和改进 YOLOv4 的水下目标检测算法

Underwater object detection algorithm combining dataenhancement and improved YOLOv4

DOI：

英文关键词:deep learning object detection YOLOv4 underwater detection

基金项目:国家自然科学基金（61801169，61873086）、中央高校基本科研业务费(B220202020)项目资助

作者	单位
史朋飞	1.河海大学物联网工程学院
韩松	1.河海大学物联网工程学院
倪建军	1.河海大学物联网工程学院
杨鑫	1.河海大学物联网工程学院

Author	Institution
Shi Pengfei	1.College of Internet of Things Engineering, Hohai University
Han Song	1.College of Internet of Things Engineering, Hohai University
Ni Jianjun	1.College of Internet of Things Engineering, Hohai University
Yang Xin	1.College of Internet of Things Engineering, Hohai University

摘要点击次数: 971

全文下载次数: 2606

中文摘要:

针对水下低质量成像、水下目标形态大小各异、以及水下目标重叠或遮挡导致水下目标检测精度低的问题,提出一种结合数据增强和改进 YOLOv4(you look only once)的水下目标检测算法,在 YOLOv4 的主干特征提取网络 CSPDarknet53 中添加卷积块注意力机制(convolutional block attention module,CBAM),以提高网络模型特征提取能力;在路径聚合网络( path aggregation network,PANet)中添加同层跳接和跨层跳接结构,以增强网络模型多尺度特征融合能力;通过数据增强方法 PredMix(predictionmix)模拟水下生物重叠、遮挡等显示不完全的情形,以增强网络模型鲁棒性。实验结果表明,结合数据增强和改进 YOLOv4 的水下目标检测算法在 URPC2018(underwater robot picking control 2018)数据集上的检测精度提升到了 78. 39%,比 YOLOv4 高出 7. 03%,充分证明所提算法的有效性。

英文摘要:

Aiming at the problem of low underwater object detection accuracy caused by low-quality underwater imaging, different shapes or sizes of underwater objects, and overlapping or occlusion of underwater objects, an underwater object detection algorithm combining data enhancement and improved YOLOv4 is proposed. By adding CBAM ( convolutional block attention module) to the backbone of YOLOv4—CSPDarknet53, the feature extraction ability of network model is improved. In order to enhance the multi-scale feature fusion ability, the same-layer skip connections and cross-layer skip connections are added to PANet (path aggregation network). To enhance the robustness of the network model, the data enhancement method PredMix (prediction mix) is used to simulate the incomplete display of underwater organisms such as overlap or occlusion. The experimental results show that the detection accuracy of the underwater object detection algorithm combining data enhancement and improved YOLOv4 on URPC2018 dataset is improved to 78. 39%, 7. 03% higher than YOLOv4, which fully proves the effectiveness of the proposed algorithm.

查看全文查看/发表评论下载PDF阅读器