Journal of Jilin University(Engineering and Technology Edition) ›› 2024, Vol. 54 ›› Issue (9): 2638-2645.doi: 10.13229/j.cnki.jdxbgxb.20230446

Previous Articles    

Object extraction of yellow catfish based on RGHS image enhancement and improved YOLOv5 network

Lu Li1,2(),Jun-qi Song1,Ming Zhu1,2,He-qun Tan1,2,Yu-fan Zhou1,Chao-qi Sun1,Cheng-yu Zhou1   

  1. 1.College of Engineering，Huazhong Agricultural University，Wuhan 430070，China
    2.Key Laboratory of Aquaculture Facilities Engineering，Ministry of Agriculture and Rural Affairs，Wuhan 430070，China
  • Received:2023-05-06 Online:2024-09-01 Published:2024-10-28

RICH HTML

 0   

PDF (PC)

74

Abstract:

Aiming at the problems of poor underwater visibility， low accuracy and slow speed of object extraction， a yellow catfish object extraction model based on RGHS algorithm and improved YOLOv5 was proposed. Firstly， in order to solve the image quality problems caused by uneven illumination and high noise， RGHS algorithm was used to enhance the brightness of yellow catfish image. Then， C3ghost and CA attention mechanisms were introduced into the YOLOv5 backbone network， and gnConv was used to replace the common convolution in the neck part， so as to establish an improved YOLOv5 model and improve the target extraction accuracy of yellow catfish. The results show that compared with YOLOv5， the AP value， accuracy rate and recall rate of the improved model are increased by 2.76%， 3.16% and 3.1 %respectively， the F1 value is increased by 0.03， the memory occupied by the improved model is reduced by 2.3 MB， and the reasoning time of a single image is reduced by 0.001 s. Meanwhile， compared with the YOLOv4， SSD， Faster-RCNN and YOLOx models， the AP values of the improved models are increased by 3.27%， 8.63%， 2.48% and 2.52% respectively. The improved YOLOv5 model based on RGHS image enhancement can significantly improve the target extraction accuracy of yellow catfish while maintaining a fast speed， which can provide useful reference for the study of fish status monitoring methods.

Key words: computer application, target extraction, brightness enhancement, attention mechanism, deep learning

CLC Number: 

  • TP391

Fig.1

Improved YOLOv5 model flowchart"

Fig.2

Modular structure"

Fig.3

Ghost Bottleneck information processing flow"

Fig.4

C3Ghost module information processing flow"

Fig.5

CA attention mechanism"

Fig.6

gnConv"

Fig.7

gnBlock"

Fig.8

gnC3 modules"

Fig.9

Image enhancement contrast diagram"

Fig.10

Loss function changes curve with training thesis"

Table 1

Comparison of YOLOv5 ablation tests"

模型ModelAP值/%准确率/%召回率/%调和均值F1模型所占内存/MB
YOLOv593.0792.5187.040.9014.4
YOLOv5+①91.3694.3882.820.8811.3
YOLOv5+①+②92.7995.3286.060.9011.3
YOLO5+①+②+③93.6994.3489.150.9211.4
YOLOv5+①+②+③+④（Improved-YOLOv5）95.8395.6790.140.9312.1

Fig.11

Visualization results of heat map before and after YOLOv5 improvement"

Table 2

Recognition effect of different models on the test set"

模型AP值/%准确率/%召回率/%参数量/M浮点运算量/G推理时间/s
YOLOv492.6595.1084.7964.3660.530.171
YOLOv593.0792.5187.047.0817.160.018
SSD87.2094.0075.0726.2962.750.014
Faster-RCNN93.3593.5089.15137.10370.210.153
YOLOx93.3186.9091.958.9726.930.090
Improved-YOLOv595.8395.6790.146.5116.380.017

Fig.12

Extraction results of yellow catfish from different models"

1 Jiao L C, Zhang R H, Liu F, et al. New generation deep learning for video object detection: a survey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(8): 3195-3215.
2 Zhang L, Li W, Liu C, et al. Automatic fish counting method using image density grading and local regression[J]. Computers and Electronics in Agriculture, 2020, 179: No.105844.
3 Aliyu I, Gana K J, Musa A A, et al. Incorporating recognition in catfish counting algorithm using artificial neural network and geometry[J]. KSII Transactions on Internet and Information Systems, 2020, 14(12): 4866-4888.
4 Garcia R, Prados R, Quintana J, et al. Automatic segmentation of fish using deep learning with application to fish size measurement[J]. ICES Journal of Marine Science, 2020, 77(4): 1354-1366.
5 Yu C, Liu Y, Hu Z, et al. Precise segmentation and measurement of inclined fish's features based on U-net and fish morphological characteristics[J]. Applied Engineering in Agriculture, 2022, 38(1): 37-48.
6 Yasruddin M L, Ismail M A H, Husin Z, et al. Feasibility study of fish disease detection using computer vision and deep convolutional neural network (dcnn) algorithm[C]∥2022 IEEE 18th International Colloquium on Signal Processing & Applications, Selangor, Malaysia, 2022: 272-276.
7 Zhang J, Pang H, Cai W, et al. Using image processing technology to create a novel fry counting algorithm[J]. Aquaculture and Fisheries, 2022, 7(4): 441-449.
8 Guillaud A, Troadec H, Benzinou A, et al. A multiagent system for edge detection and continuity perception on fish otolith images[J]. EURASIP Journal on Advances in Signal Processing, 2002, 7: 746-753.
9 Deka J, Laskar S. Comparative Analysis of FOD based prewitt, sobel & laplacian operators for edge detection on freshwater fish images[C]∥2020 International Conference on Emerging Smart Computing and Informatics, Madurai, India, 2020: 65-70.
10 Gao T S, Sheng D B, Nguyen T H, et al. Measurement of the fish body wound depth based on a depth map inpainting method[C]∥AETA 2016: Recent Advances in Electrical Engineering and Related Sciences: Theory and Application, Busan, Korea, 2017: 289-299.
11 Abdeldaim A M, Houssein E H, Hassanien A E. Color image segmentation of fishes with complex background in water[C]∥The International Conference on Advanced Machine Learning Technologies and Applications,Cairo, Egypt, 2018: 634-643.
12 Xu G, Chen Q, Yoshida T, et al. Detection of bluefin tuna by cascade classifier and deep learning for monitoring fish resources[C]∥Global Oceans 2020: Singapore-US Gulf Coast, Biloxi, MS, USA, 2020: 1-4.
13 谭鹤群,李玉祥,朱明,等. 通过图像增强与改进Faster-RCNN网络的重叠鱼群尾数检测[J]. 农业工程学报,2022,38(13):167-176.
TAN He-qun, Li Yu-xiang, ZHU Ming, et al. Detecting overlapping fish population using image enhancement and improved Faster-RCNN networks[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(13):167-176.
14 Zhang W, Dong L, Pan X, et al. Single image defogging based on multi-channel convolutional MSRCR[J]. IEEE Access, 2019, 7: 72492-72504.
15 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 Kun, Wang Kuo, Zhao Lu, 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.
16 Cai K, Miao X, Wang W, et al. A modified YOLOv3 model for fish detection based on MobileNetv1 as backbone[J]. Aquacultural Engineering, 2020, 91: No.102117.
17 Li J, Liu C, Lu X, et al. CME-YOLOv5: an efficient object detection network for densely spaced fish and small targets[J]. Water, 2022, 14(15): 2412.
18 Huang D, Wang Y, Song W, et al. Shallow-water image enhancement using relative global histogram stretching based on adaptive parameter acquisition[C]∥MultiMedia Modeling: 24th International Conference, Bangkok, Thailand, 2018: 453-465.
19 刘彦呈,董张伟,朱鹏莅,等. 基于特征解耦的无监督水下图像增强[J]. 电子与信息学报,2022,44(10):3389-3398.
Liu Yan-chen, Dong Zhang-wei, Zhu Peng-li, et al. Unsupervised underwater image enhancement based on feature decoupling[J]. Journal of Electronics & Information Technology, 2022, 44(10):3389-3398.
20 Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection[J/OL]. [2023-04-20].
21 Han K, Wang Y, Tian Q, et al. Ghostnet: more features from cheap operations[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle USA, 2020: 1580-1589.
22 Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Online Conference, 2021: 13713-13722.
23 Rao Y M, Zhao W L, Tang Y S, et al. Hornet: efficient high-order spatial interactions with recursive gated convolutions[J/OL]. [2023-04-22].
24 Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector[C]∥Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 2016: 21-37.
25 Ge Z, Liu S, Wang F, et al. Yolox: exceeding yolo series in 2021[J/OL]. [2023-04-22].
[1] Lei ZHANG,Jing JIAO,Bo-xin LI,Yan-jie ZHOU. Large capacity semi structured data extraction algorithm combining machine learning and deep learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(9): 2631-2637.
[2] Ping YU,Kang ZHAO,Jie CAO. Rolling bearing fault diagnosis based on optimized A-BiLSTM [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2156-2166.
[3] Hong-wei ZHAO,Hong WU,Ke MA,Hai LI. Image classification framework based on knowledge distillation [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2307-2312.
[4] Yun-zuo ZHANG,Yu-xin ZHENG,Cun-yu WU,Tian ZHANG. Accurate lane detection of complex environment based on double feature extraction network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(7): 1894-1902.
[5] Bai-you QIAO,Tong WU,Lu YANG,You-wen JIANG. A text sentiment analysis method based on BiGRU and capsule network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(7): 2026-2037.
[6] Xin-gang GUO,Ying-chen HE,Chao CHENG. Noise-resistant multistep image super resolution network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(7): 2063-2071.
[7] Li-ping ZHANG,Bin-yu LIU,Song LI,Zhong-xiao HAO. Trajectory k nearest neighbor query method based on sparse multi-head attention [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1756-1766.
[8] Ming-hui SUN,Hao XUE,Yu-bo JIN,Wei-dong QU,Gui-he QIN. Video saliency prediction with collective spatio-temporal attention [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1767-1776.
[9] Yan-feng LI,Ming-yang LIU,Jia-ming HU,Hua-dong SUN,Jie-yu MENG,Ao-ying WANG,Han-yue ZHANG,Hua-min YANG,Kai-xu HAN. Infrared and visible image fusion based on gradient transfer and auto-encoder [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1777-1787.
[10] Yu-kai LU,Shuai-ke YUAN,Shu-sheng XIONG,Shao-peng ZHU,Ning ZHANG. High precision detection system for automotive paint defects [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1205-1213.
[11] Yun-long GAO,Ming REN,Chuan WU,Wen GAO. An improved anchor-free model based on attention mechanism for ship detection [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1407-1416.
[12] Li-ming LIANG,Long-song ZHOU,Jiang YIN,Xiao-qi SHENG. Fusion multi-scale Transformer skin lesion segmentation algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(4): 1086-1098.
[13] Yun-zuo ZHANG,Wei GUO,Wen-bo LI. Omnidirectional accurate detection algorithm for dense small objects in remote sensing images [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(4): 1105-1113.
[14] Xiao-xu LI,Wen-juan AN,Ji-jie WU,Zhen LI,Ke ZHANG,Zhan-yu MA. Channel attention bilinear metric network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(2): 524-532.
[15] Guo-jun YANG,Ya-hui QI,Xiu-ming SHI. Review of bridge crack detection based on digital image technology [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(2): 313-332.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd