改进YOLOv3-SPP水下目标检测研究

doi:10.3778/j.issn.1002-8331.2204-0264

摘要/Abstract

摘要： 针对水下目标检测任务中图像模糊、背景复杂以及目标小而导致误检和漏检问题，提出一种改进YOLOv3-SPP的水下目标检测算法。利用UWGAN网络对水下原始图像进行恢复，采用Mixup方法增强数据，减少错误标签记忆；以YOLOv3-SPP网络结构为基础，增加网络预测尺度，提高小目标检测性能；引入CIoU边框回归损失，提高定位精度；利用[K]-Means++聚类算法，筛选最佳Anchor box。将改进YOLOv3-SPP算法在处理后的URPC数据集上进行实验，平均检测精度由79.58%提升到88.71%，速度为28.9?FPS。结果表明，改进算法综合检测能力优于其他算法。

关键词: 水下目标, 图像增强, YOLOv3-SPP, UWGAN, CIoU, [K]-Means++

Abstract: To solve the problem of faulty and omitted detection that results from blurred images, complex backgrounds and small targets in underwater target detection tasks, an improved YOLOv3-SPP underwater target detection algorithm is proposed. Firstly, the original underwater image is recovered by UWGAN network, and the Mixup method is employed to strengthen the data and diminish the mislabeled memory. Secondly, the YOLOv3-SPP network structure is used as the basis to increase the network prediction scale to raise the small target detection performance. Then the CIoU border regression loss is introduced to improve the localization accuracy. Finally, the [K]-Means++ clustering algorithm is applied to filter the best Anchor box. The improved YOLOv3-SPP algorithm is experimented on the processed URPC dataset, and the average detection accuracy is improved from 79.58% to 88.71% with a speed of 28.9 FPS. The performance show that the improved algorithm has better comprehensive detection capability than other algorithms.

Key words: underwater target, image enhancement, YOLOv3-SPP, UWGAN, CIoU, [K]-Means++

叶赵兵, 段先华, 赵楚. 改进YOLOv3-SPP水下目标检测研究[J]. 计算机工程与应用, 2023, 59(6): 231-240.

YE Zhaobing, DUAN Xianhua, ZHAO Chu. Research on Underwater Target Detection by Improved YOLOv3-SPP[J]. Computer Engineering and Applications, 2023, 59(6): 231-240.

参考文献

[1] YEH C H，LIN C H，KANG L W，et al.Lightweight deep neural network for joint learning of underwater object detection and color conversion[J].IEEE Transactions on Neural Networks and Learning Systems，2021（99）.
[2] CHEN X，LU Y，WU Z，et al.Reveal of domain effect：how visual restoration contributes to object detection in aquatic scenes[J].arXiv：2003.01913，2020.
[3] CHEN L，LIU Z，TONG L，et al.Underwater object detection using invert multi-class adaboost with deep learning[C]//2020 International Joint Conference on Neural Networks（IJCNN），2020：1-8.
[4] CHEN B，LI R，BAI W，et al.Research on recognition method of optical detection image of underwater robot for submarine cable[C]//2019 IEEE 3rd Advanced Information Management，Communicates，Electronic and Automation Control Conference（IMCEC），2019：1973-1976.
[5] HAO X，ZHANG G，MA S.Deep learning[J].International Journal of Semantic Computing，2016，10（3）：417-439.
[6] LECUN Y，BENGIO Y，HINTON G.Deep learning[J].Nature，2015，521（7553）：436-444.
[7] SCHMIDHUBER J.Deep learning in neural networks：an overview[J].Neural Networks，2015，61：85-117.
[8] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（6）：1137-1149.
[9] HE K，GKIOXARI G，PIOTR D，et al.MaskR-CNN[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017：2961-2969.
[10] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[11] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[J].arXiv：1512.02325，2015.
[12] 李庆忠，李宜兵，牛炯.基于改进YOLO和迁移学习的水下鱼类目标实时检测[J].模式识别与人工智能，2019，32（3）：193-203.
LI Q Z，LI Y B，NIU J.Real-time detection of underwater fish based on improved YOLO and transfer learning[J].Pattern Recognition and Artificial Intelligence，2019，32（3）：193-203.
[13] 朱世伟，杭仁龙，刘青山.基于类加权YOLO网络的水下目标检测[J].南京师大学报（自然科学版），2020，43（1）：129-135.
ZHU S W，HANG R L，LIU Q S.Underwater object detection based on the class-weighted YOLO net[J].Journal of Nanjing Normal University（Natural Science Edition），2020，43（1）：129-135.
[14] 刘萍，杨鸿波，宋阳.改进YOLOv3网络的海洋生物识别算法[J].计算机应用研究，2020，37（S1）：394-397.
LIU P，YANG H B，SONG Y.Marine biometric algorithm based on improved YOLOv3 network[J].Application Research of Computers，2020，37（S1）：394-397.
[15] HE K，ZHANG X，REN S，et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，37（9）：1904-1916.
[16] GUO Y，LI H，ZHUANG P.Underwater image enhancement using a multiscale dense generative adversarial network[J].IEEE Journal of Oceanic Engineering，2019，45（3）：862-870.
[17] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[18] ZHANG H，CISSE M，DAUPHIN Y N，et al.Mixup：beyond empirical risk minimization[J].arXiv：1710.09412，2017.
[19] ZHENG Z，WANG P，LIU W，et al.Distance-IoU loss：faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：12993-13000.
[20] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[21] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.