Improved YOLOv3 Shallow Sea Underwater Biological Target Detection

doi:10.3778/j.issn.1002-8331.2205-0211

Abstract

Abstract: Aiming at the low accuracy of shallow underwater biology target detection caused by color distortion, coarse image, local overexposure and large size difference of shallow underwater image, a detection and recognition method of shallow underwater biological target based on YOLOv3 network is proposed. Firstly, the residual attention module is used to solve the problem of local overexposure caused by weak light and artificial light in shallow sea, and improve the feature extraction ability of target. Then, cross-stage local feature extraction is used to improve the detection accuracy, solve the problems of image color distortion and image roughness that affect the detection and recognition effect of shallow underwater biological targets, enhance feature extraction ability and avoid information redundancy. Finally, the calculation function of the total intersection ratio loss is used to solve the problem of large size difference caused by the same species spatial position, which improves the robustness of target detection. The experimental verification proves that the improved YOLOv3 can effectively improve the accuracy and reduce the rate of missed detection in shallow sea underwater biological target detection and recognition task.

Key words: shallow sea underwater biology, target detection, YOLOv3, cross stage partial characteristics, precision

摘要： 针对浅海水下图像存在颜色失真、图像毛糙、局部过曝和尺寸差异大等导致的浅海水下生物目标检测精确度低的问题，提出一种基于YOLOv3网络的浅海水下生物目标检测识别方法。针对浅海中光线弱和使用人造光源导致的局部过曝问题，在YOLOv3网络中加入残差注意力模块，增强对目标的特征提取能力；针对浅海中图像色彩失真和图像毛糙等影响浅海水下生物目标检测识别效果的问题，采用跨阶段局部特征提取提高检测精确度，增强特征提取能力的同时避免信息冗余；针对同一物种由于空间位置造成的尺寸差异大的问题，采用完全交并比损失计算函数，提高目标检测的鲁棒性。通过实验验证证明了改进后的YOLOv3在浅海水下生物目标检测识别任务中能够有效提高精确度，降低漏检率。

关键词: 浅海水下生物, 目标检测, YOLOv3, 跨阶段局部特征, 精确度

CHEN Yuliang, DONG Shaojiang, ZHU Sunke, SUN Shizheng, HU Xiaolin. Improved YOLOv3 Shallow Sea Underwater Biological Target Detection[J]. Computer Engineering and Applications, 2023, 59(18): 190-197.

陈宇梁, 董绍江, 朱孙科, 孙世政, 胡小林. 改进的YOLOv3浅海水下生物目标检测[J]. 计算机工程与应用, 2023, 59(18): 190-197.

References

[1] 郭威，张有波，周悦，等.应用于水下机器人的快速深海图像复原算法[J].光学学报，2022，42（4）：53-67.
GUO W，ZHANG Y B，ZHOU Y，et al.Rapid deep-sea image restoration algorithm applied to unmanned underwater vehicles[J].Acta Optica Sinica，2022，42（4）：53-67.
[2] 张立艺，武文红，牛恒茂，等.深度学习中的安全帽检测算法应用研究综述[J].计算机工程与应用，2022，58（16）：1-17.
ZHANG L Y，WU W H，NIU H M，et al.Summary of application research on helmet detection algorithm based on deep learning[J].Computer Engineering and Applications，2022，58（16）：1-17.
[3] 周清松，董绍江，罗家元，等.改进YOLOv3的桥梁表观病害检测识别[J].重庆大学学报，2022，45（6）：121-130.
ZHOU Q S，DONG S J，LUO J Y，et al.Bridge apparent disease based on improved YOLOv3[J].Journal of Chong-
qing University，2022，45（6）：121-130.
[4] 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 & Machine Intelligence，2017，39（6）：1137-1149.
[5] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//IEEE Conference on Computer Vision & Pattern Recognition，2016.
[6] LIU W，ANFUELOY D，ERLAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[7] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[8] 袁利毫，昝英飞，钟声华，等.基于YOLOv3的水下小目标自主识别[J].海洋工程装备与技术，2018，5（S1）：118-123.
YUAN L H，ZAN Y F，ZHONG S H，et al.Small underwater target recognition based on YOLOv3[J].Ocean Engineering Equipment and Technology，2018，5（S1）：118-123.
[9] 高英杰.基于“SSD”模型的水下目标检测网络设计与实现[J].电子世界，2019（8）：110-111.
GAO Y J.Design and implementation of underwater target detection network based on SSD model[J].Electronics World，2019（8）：110-111.
[10] 赵德安，刘晓洋，孙月平，等.基于机器视觉的水下河蟹识别方法[J].农业机械学报，2019，50（3）：151-158.
ZHAO D A，LIU X Y，SUN Y P，et al.Detection of underwater crabs based on machine vision[J].Transactions of the Chinese Society for Agricultural Machinery，2019，50（3）：151-158.
[11] 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.Improved marine biometrics identification algorithm for YOLOv3 network[J].Application Research of Computers，2020，37（S1）：394-397.
[12] 邢晋超，潘广贞.改进YOLOv5s的手语识别算法研究[J].计算机工程与应用，2022，58（16）：194-203.
XING J C，PAN G Z.Research on improved YOLOv5s sign language recognition algorithm[J].Computer Engineering and Applications，2022，58（16）：194-203.
[13] 董绍江，刘伟，蔡巍巍，等.基于分层精简双线性注意力网络的鱼类识别[J].计算机工程与应用，2022，58（5）：186-192.
DONG S J，LIU W，CAI W W，et al.Fish recognition based on hierarchical compact bilinear attention network[J].Computer Engineering and Applications，2022，58（5）：186-192.
[14] REZATOFIGHI H，TSOI N，GWAK J Y，et al.Generalized intersection over union：a metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：658-666.
[15] WANG C Y，LIAO H Y M，WU Y H，et al.CSPNet：a new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2020：390-391.
[16] 农元君，王俊杰.基于嵌入式的遥感目标实时检测方法[J].光学学报，2021，41（10）：179-186.
NONG Y J，WANG J J.Real-time object detection in remote sensing images based on embedded system[J].Acta Optica Sinica，2021，41（10）：179-186.
[17] WOO S，PARK J，LEE J Y，et al.Cbam：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：3-19.
[18] YU J，JIANG Y，WANG Z，et al.Unitbox：an advanced object detection network[C]//Proceedings of the 24th ACM International Conference on Multimedia，2016：516-520.
[19] PEDERSEN M，BRUSLUND HAURUM J，GADE R，et al.Detection of marine animals in a new underwater dataset with varying visibility[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2019：18-26.
[20] ZHOU X，WANG D，KRAHENBUHL P.Objects as points[J].arXiv：1904.07850，2019.