Land-based measurement method of underwater fish body length based on binocular vision

doi:10.13733/j.jcam.issn.20955553.2024.12.014

Abstract

Abstract:

The traditional manual measurement method not only makes the fish suffer from stress, but also has low measurement efficiency, and the non-contact measurement method can serve these shortcomings well. In this study, the top view images of underwater fish are collected by a binocular camera placed above the water surface. The GrabCut algorithm combined with contrast adaptive adjustment is used to achieve selective segmentation. Skeleton extraction method is used to straighten the fish bending of the fish body, and correct the influence of water refraction. Finally, the fish's body length measurement points after segmentation are extracted and measured. The experimental results show that compared with the original GrabCut algorithm, the proposed image segmentation algorithm improves the segmentation accuracy by 14.9%, reduces the over-segmentation rate by 23%, and improves the time efficiency by 11.6%. The average relative error in the final measurement of fish body length is 0.91%, which is an improvement of 0.37% over the accuracy without considering refraction. The non-contact land-based measurement method proposed in this study meets the measurement accuracy requirements. It is more accurate and convenient than the underwater fish body measurement method, and is more suitable for engineering implementation and application.

Key words: binocular vision, fish body length measurement, GrabCut segmentation, fish bending straightening, water refraction

摘要：

无接触式测量水中鱼类体长不会影响鱼类正常生长，测量效率高。通过置于水面之上的双目相机，采集水下鱼类的俯视图像，采用结合对比度自适应调整的GrabCut算法实现选择性分割，使用骨架提取方法对鱼体弯曲进行矫直，矫正水体折射的影响，最后提取分割后鱼类体长测量点进行体长测量。试验结果表明，图像分割算法较原始GrabCut算法在分割准度上提高14.9%，过分割率降低23%，时间效率提高11.6%。鱼体长测量的平均相对误差为0.91%，比未考虑折射情况下正确率提高0.37%。提出的无接触式陆基测量方法满足测量精度要求，比水下方式的鱼体测量方法更准确、便捷，也更适合于工程实施和应用。

关键词: 双目视觉, 鱼体长测量, GrabCut分割, 鱼体弯曲矫直, 水体折射

CLC Number:

S951.2

Shen Yang, , Shen Pingfeng, Zhu Hao, Zhou Minggang, , Wang Chongyu, Du Lingwei. Land-based measurement method of underwater fish body length based on binocular vision[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(12): 87-92.

申阳, 申平枫, 朱浩, 周明刚, 王冲宇, 都令炜. 基于双目视觉的水下鱼类体长陆基测量方法[J]. 中国农机化学报, 2024, 45(12): 87-92.

References

［1］　Balaban M O, Chombeau M, Cirban D, et al. Prediction of the weight of Alaskan pollock using image analysis ［J］. Journal of Food Science, 2010, 75(8): E552-E556.
［2］　余心杰，吴雄飞，王建平, 等. 基于机器视觉的大黄鱼形态参数快速检测方法［J］. 集成技术, 2014, 3(5): 45-51.
Yu Xinjie, Wu Xiongfei, Wang Jianping, et al. Rapid detecting method for pseudosciaena crocea morphologicalpa rameters based on the machine vision ［J］.Journal of Integration Technology, 2014, 3(5): 45-51.
［3］　Young B C, Alfaggeh R H, Almoutiri I. Growth, fry production, and cost analysis for sabaki tilapia production systems ［J］. North American Journal of Aquaculture, 2021, 83(4): 290-293.
［4］　Costa C, Antonucci F, Boglione C, et al. Automated sorting for size, sex and skeletal anomalies of cultured seabass using external shape analysis ［J］. Aquacultural Engineering, 2013, 52: 58-64.
［5］　张志强，牛智有，赵思明, 等. 基于机器视觉技术的淡水鱼质量分级［J］. 农业工程学报, 2011, 27(2): 350-354.
Zhang Zhiqiang, Niu Zhiyou, Zhao Siming, et al. Weight grading of freshwater fish based on computer vision ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2011, 27(2): 350-354.
［6］　Hufschmied P, Fankhauser T, Pugovkin D. Automatic stressfree sorting of sturgeons inside culture tanks using image processing ［J］. Journal of Applied Ichthyology, 2011, 27(2): 622-626.
［7］　Hu L, Zheng D, Qiao F, et al. Research on smart cast for fish cage aquaculture based on image processing ［C］. 2016 2nd Workshop on Advanced Research and Technology in Industry Applications (WARTIA-16). Atlantis Press, 2016: 1322-1327.
［8］　Bermejo S. Fish age classification based on length, weight, sex and otolith morphological features ［J］. Fisheries Research, 2007, 84(2): 270-274.
［9］　Hao M, Yu H, Li D. The measurement of fish size by machine visiona review ［C］. Computer and Computing Technologies in Agriculture IX: 9th IFIP WG 514 International Conference, CCTA 2015, Beijing, China, September 27-30, 2015, Revised Selected Papers, Part Ⅱ 9. Springer International Publishing, 2016: 15-32.
［10］　李振波，赵远洋，杨普, 等. 基于机器视觉的鱼体长度测量研究综述［J］. 农业机械学报， 2021， 52(S1):207-218.
Li Zhenbo, Zhao Yuanyang, Yang Pu, et al. Review of research on fish body length measurement based on machine vision ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(S1): 207-218.
［11］　段延娥，李道亮，李振波, 等. 基于计算机视觉的水产动物视觉特征测量研究综述［J］. 农业工程学报， 2015， 31(15): 1-11.
Duan Yane, Li Daoliang, Li Zhenbo， et al. Review on visual characteristic measurement research of aquatic animalsbased on computer vision ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(15): 1-11.
［12］　郭卜瑜，于佳，王姣姣, 等. 双目视觉用于鱼苗尺寸测量［J］. 光学技术， 2017， 43(2): 153-157.
Guo Buyu, Yu Jia, Wang Jiaojiao, et al. Stereo vision for measuring the size of fish ［J］. Optical Technique, 2017, 43 (2): 153-157.
［13］　杨杰超，许江淳，陆万荣, 等. 基于计算机视觉的大黄鱼体尺测算与体质量估测［J］. 中国农机化学报， 2018， 39(6): 66-70.

Yang Jiechao, Xu Jiangchun, Lu Wanrong, et al. Computer visionbased body size measurement and weight estimation of large yellow croaker ［J］. Journal of Chinese Agricultural Mechanization, 2018, 39(6): 66-70.

［14］　李艳君，黄康为，项基. 基于立体视觉的动态鱼体尺寸测量［J］. 农业工程学报, 2020, 36(21): 220-226.
Li Yanjun, Huang Kangwei, Xiang Ji, et al. Measurement of dynamic fish dimension based on stereoscopic vision ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(21): 220-226.
［15］　Savinov E, Ivashko E. Automatic contactless weighing of fish during experiments ［C］. 2021 Ivannikov Ispras Open Conference (ISPRAS), 2021: 134-139.
［16］　Abe K, Miyake K, Habe H. Method for measuring length of freeswimming farmed fry by 3D monitoring ［J］. Sensors & Materials, 32(11): 3595-3606.
［17］　李岩，吴孟男，薛兴伦. 应用于刹车盘复杂背景去除的改进GrabCut分割算法［J］. 机床与液压， 2022， 50(5): 74-79.
Li Yan, Wu Mengnan, Xue Xinglun. Improved GrabCut segmentation algorithm for removing thecomplex background of brake disc ［J］. Machine Tool & Hydraulics, 2022, 50(5): 74-79.
［18］　李帼，曹苏艳，钱婷婷，等. 基于改进GrabCut算法的黄瓜植株图像分割［J］. 中国农机化学报， 2021， 42(3): 159-165.
Li Guo， Cao Suyan， Qian Tingting， et al. Image segmentation of cucumber plants based on improved GrabCut algorithm ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(3): 159-165.
［19］　郭传鑫，李振波，乔曦, 等. 基于融合显著图与GrabCut算法的水下海参图像分割［J］. 农业机械学报， 2015， 46(S1): 147-152.
Guo Chuanxin, Li Zhenbo, Oiao Xi, et al. Image segmentation of underwater sea cucumber using GrabCut with saliency map ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(S1): 147-152.
［20］　Ye H, Liu C, Niu P. Cucumber appearance quality detection under complex background based on image processing ［J］. International Journal of Agricultural and Biological Engineering, 2018, 11(4): 193-199.
［21］　吴艳娟，王健，王云亮. 基于骨架提取算法的作物茎秆识别与定位方法［J］. 农业机械学报, 2022, 53(11): 334-340.
Wu Yanjuan, Wang Jian, Wang Yunliang. Crop stem recognition and localization based on skeleton extraction algorithm ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(11): 334-340.
［22］　Zhang T Y, Suen C Y. A fast parallel algorithm for thinning digital patterns ［J］. Communications of the ACM, 1984, 27(3): 236-239.
［23］　Zhang T Y, Suen C Y. A fast parallel algorithm for thinning digital patterns ［J］. Communications of the ACM, 1984, 27(3): 236-239.
［24］　梅启升，王敏，梁秀玲. 基于干涉条纹骨架的毛刺去除算法［J］. 应用光学， 2020， 41(2): 302-308.
Mei Qisheng, Wang Min, Liang Xiuling. Burr removal algorithm based on interference fringe skeleton ［J］. Journal of Applied Optics, 2020, 41(2): 302-308.
［25］　陈旭阳，贺昱曜，宗瑞良, 等. 基于光线折射模型的水下图像转换算法研究［J］. 西北工业大学学报, 2019, 37(3): 471-478.
Chen Xuyang, He Yuyao, Zhong Ruiliang, et al. Study on underwater image conversion algorithm based onlight refraction model ［J］. Journal of Northwestern Polytechnical University, 2019, 37(3): 471-478.