一种图像增强及改进海洋生物图像检测算法

doi:10.3778/j.issn.1002-8331.2112-0556

摘要/Abstract

摘要： 为提高海洋生物图像的检测精度，采用优化的MSRCR对海洋生物图像进行增强，并基于ASFF和Focal Loss提出一种改进的YOLOv4算法（IYOLOv4）。针对光线在海水中传播，红光的强衰减性，导致海洋生物图像对比度低、出现色偏的问题，使用双边滤波代替传统的MSRCR中的高斯滤波，不仅能保留更多图像边界的特征，而且通过增益图像中的红色，解决了图像色偏问题，同时也提高了图像局域对比度。算法使用ASFF结构充分利用图像高层特征的语义信息与底层的细粒度特征，通过学习权重参数的方式来进行特征的充分融合，增强融合效果；将YOLOv4的分类损失中采用的BCE Loss替换为Focal Loss，来解决数据集中类别不均衡的问题，提高检测精度。实验结果表明，该算法与YOLOv4算法相比，海参、扇贝、海星、海胆四种类别的AP分别提高了10.35、9.13、2.22、0.14个百分点，mAP提高了5.45个百分点。

关键词: 图像检测, YOLOv4, 双边滤波, 自适应空间特征融合（ASFF）, 分类损失

Abstract: In order to improve the detection accuracy of marine biological images, this paper uses optimized MSRCR to enhance marine biological images, and proposes an improved YOLOv4 algorithm（IYOLOv4） based on ASFF and Focal Loss. First of all, for light propagating in seawater, the strong attenuation of red light leads to the problem of low contrast and color shift in marine biological images. It uses bilateral filtering instead of Gaussian filtering in the traditional MSRCR, which not only preserves more image boundary features, but also solves the problem of image color shift by increasing the red in the image, at the same time the local contrast of the image is also improved. Secondly, the algorithm uses the ASFF structure to make full use of the semantic information of the high-level features of the image and the fine-grained features of the bottom layer, and fully integrates the features by learning the weight parameters to enhance the fusion effect. Finally, the BCE Loss used in the classification loss of YOLOv4 is replaced with Focal Loss to solve the problem of unbalanced categories in the dataset and improve detection accuracy. The experimental results show that compared with the YOLOv4 algorithm, the four classes of AP of holohurian, scallop, starfish, and echinus increases by 10.35, 9.13, 2.22, 0.14 percentage points respectively, and mAP increases by 5.45 percentage points.

Key words: image detection, YOLOv4, bilateral filter, adaptively spatial feature fusion（ASFF）, classification loss

郭平秀, 李启南, 杨忠鹏. 一种图像增强及改进海洋生物图像检测算法[J]. 计算机工程与应用, 2023, 59(8): 208-216.

GUO Pingxiu, LI Qinan, YANG Zhongpeng. Image Enhancement and Improved Marine Biological Image Detection Algorithm[J]. Computer Engineering and Applications, 2023, 59(8): 208-216.

参考文献

[1] 阙华勇，陈勇，张秀梅，等.现代海洋牧场建设的现状与发展对策[J].中国工程科学，2016，18（3）：79-84.
QUE H Y，CHEN Y，ZHANG X M，et al.Modern marine ranching：status and development strategy[J].Strategic Study of CAE，2016，18（3）：79-84.
[2] 强伟，贺昱曜，郭玉锦，等.基于改进SSD的水下目标检测算法研究[J].西北工业大学学报，2020，38（4）：745-754.
QIANG W，HE Y Y，GUO Y J，et al.Exploring underwater target detection algorithm based on improved SSD[J].Journal of Northwestern Polytechnical University，2020，38（4）：745-754.
[3] 金维维，华臻，冯巍巍，等.基于改进多尺度retinex的水下图像增强研究[J].计算机应用与软件，2021，38（9）：239-243.
JING W W，HUA Z，FENG W W，et al.Research on underwater image enhancement based on improved multi-scale retinex[J].Computer Applications and Software，2021，38（9）：239-243.
[4] HU X.Underwater image enhancement method based on wavelet transform and retinex[C]//International Conference on Pattern Recognition and Artificial Intelligence（PRAI），2021：86-90.
[5] 林森，刘世本.基于多尺度生成对抗网络的水下图像增强[J].激光与光电子学进展，2021，58（16）：306-315.
LIN S，LIU S B.Underwater image enhancement based on multi-scale generative adversarial network[J].Laser & Optoelectronics Progress，2021，58（16）：306-315.
[6] 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 recognition algorithm based on improved YOLOv3 network[J].Application Research of Computers，2020，37（S1）：394-397.
[7] 郝琨，王阔，赵璐，等.基于图像增强与改进YOLOv3的水下生物检测算法[J].吉林大学学报（工学版），2022，52（5）：1088-1097.
HAO K，WANG K，ZHAO L，et al.Underwater biological detection algorithm based on image enhancement and improved YOLOv3[J].Journal of Jilin University（Engineering and Technology Edition），2022，52（5）：1088-1097.
[8] SONG S，ZHU J，LI X，et al.Integrate MSRCR and mask R-CNN to recognize underwater creatures on small sample datasets[J].IEEE Access，2020，8：172848-172858.
[9] WANG P，PENG Y.Research on underwater acoustic target recognition based on LOFAR spectrum and deep learning method[C]//International Conference on Automation，Control and Robotics Engineering（CACRE），2020.
[10] LIU S，QI L，QIN H，et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2018：8759-8768.
[11] LIU S，HUANG D，WANG Y.Learning spatial fusion for single-shot object detection[J].arXiv：1911.09516，2019.
[12] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2020，42（2）：318-327.
[13] 张彩珍，康斌龙，李颖，等.基于差异通道增益及改进Retinex的水下图像增强[J].激光与光电子学进展，2021，58（14）：148-155.
ZHANG C Z，KANG B L，LI Y，et al.Underwater image enhancement based on differential channel gain and improved Retinex[J].Laser & Optoelectronics Progress，2021，58（14）：148-155.
[14] 罗禹杰，张剑，陈亮，等.基于自适应空间特征融合的轻量化目标检测算法设计[J].激光与光电子学进展，2022，59（4）：310-320.
LUO Y J，ZHANG J，CHEN L，et al.Lightweight target detection algorithm based on adaptive spatial feature fusion[J].Laser & Optoelectronics Progress，2022，59（4）：310-320.
[15] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition.Piscatawy，NJ：IEEE Press，2014：580-587.
[16] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[17] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[18] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017.
[19] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017.
[20] REDMON J，FARHADI A.Yolov3：an incremental improvement[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018.
[21] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition，2020.
[22] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//Proceedings of European Conference on Computer Vision，2016：21-37.