基于图像处理的蟹塘水草图像导航线拟合方法

doi:10.13733/j.jcam.issn.2095-5553.2023.07.020

摘要/Abstract

摘要： 针对河蟹养殖中水草清理是以人工完成为主，存在费工费时、劳动效率低、成本高等问题，提出一种图像处理的蟹塘水草图像导航线拟合方法。首先通过采集水草RGB图像，并转换为HSV颜色空间，并选用H分量二值分割，对分割图像进行填充处理；其次根据水草图像面积差异，设定参数删除非目标区域，进行形态学运算，保留目标区域；再按列查找二值图像非零像素点的中点位置，得到水草图像形态特征曲线；最后根据查找的特征曲线，利用最小二乘法拟合出导航线。试验结果表明本文方法拟合导航线相对误差在0.498%以内，平均相对误差绝对值为0.247%，平均耗时为0.005s。本文方法能够较好地满足水草图像导航线拟合的准确性和实时性，可为智能化水草清理作业船的研制奠定理论与技术基础。

关键词: 水草图像, HSV颜色空间, 图像分割, 导航线拟合

Abstract: In response to the challenges of laborintensive and timeconsuming manual aquatic plant cleaning in crab farming, a method for imageguided navigation line fitting of water grass in crab ponds is proposed. The proposed approach involves several steps. First, RGB images of aquatic plants are read and converted into HSV color space. The H component is selected for binary segmentation, and the segmented image is then filled. Secondly, based on the differences in the water grass image area, parameters are set to delete the small area parts, and the processed image is processed by morphology to retain the target area. Then, the midpoint of nonzero pixels in the binary image is searched by column to obtain the morphological characteristic curve of the aquatic plant image. Finally, based on the characteristic curve, the navigation line is fitted using the least square method. The experimental results show that the relative error of the fitted navigation line is within 0.498%. The average absolute value of the relative error is 0.247%. The average processing time is 0.005s. The method proposed in this paper shows good accuracy and realtime performance in fitting navigation lines for aquatic plant images, which can lay a theoretical and technical foundation for the development of visually guided aquatic plant cleaning workboats.

Key words: aquatic plant image, HSV color space, image segmentation, navigation line fitting

中图分类号:

阮承治, 林根深, 陈旭, 孙月平, 杨君, 赵德安. 基于图像处理的蟹塘水草图像导航线拟合方法[J]. 中国农机化学报, 2023, 44(7): 147-153.

Ruan Chengzhi, Lin Genshen, Chen Xu, Sun Yueping, Yang Jun, Zhao Dean. Navigation line fitting method of crab pond aquatic plant image based on image processing[J]. Journal of Chinese Agricultural Mechanization, 2023, 44(7): 147-153.

参考文献

［1］　赵德安, 曹硕, 孙月平, 等. 基于联动扩展神经网络的水下自由活蟹检测器研究［J］. 农业机械学报, 2020, 51（9）: 163-174.
Zhao Dean, Cao Shuo, Sun Yueping, et al. Smallsized efficient detector for underwater freely live crabs based on compound scaling neural network ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51（9）: 163-174.
［2］　吴波, 赵德安, 孙月平, 等. 一种河蟹养殖用自动化水草清理作业船［J］. 中国农机化学报, 2016, 37（9）: 88-91.
Wu Bo, Zhao Dean, Sun Yueping, et al. Automatic aquatic cleaning ship for river crabs breeding ［J］. Journal of Chinese Agricultural Mechanization, 2016, 37（9）: 88-91.
［3］　阮承治, 赵德安, 刘晓洋, 等. 基于IPSOUKF的水草清理作业船组合导航定位方法［J］. 农业机械学报, 2017, 48（7）: 38-45.
Ruan Chengzhi, Zhao Dean, Liu Xiaoyang, et al. Integrated navigation positioning method based on IPSOUKF for aquatic plants cleaning workboat ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48（7）: 38-45.
［4］　Ruan Chengzhi, Zhao Dean, Zhao Dejie, et al. Aquatic image segmentation based on PSOPCNN in crab farming ［J］. International Agricultural Engineering Journal, 2017, 26（1）: 199-211.
［5］　罗锡文, 廖娟, 胡炼, 等. 提高农业机械化水平促进农业可持续发展［J］. 农业工程学报, 2016, 32（1）: 1-11.
Luo Xiwen, Liao Juan, Hu Lian, et al. Improving agricultural mechanization level to promote agricultural suatainable development ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32（1）: 1-11.
［6］　Kristoffer R S, Morten O A, Jo A A. Modelling and simulation of rotary feed spreaders with application to sea cage aquacultureA study of common and alternative designs ［J］. Aquacultural Engineering, 2018, 82（8）: 1-11.
［7］　孟良宇, 赖贤声. 一种新型河道水草清理机器［J］. 农家参谋, 2020, （4）: 213.
［8］　郭祥雨, 薛新宇. 基于机器视觉的水稻制种田导航线提取方法［J］. 中国农机化学报, 2021, 42（5）: 197-201.
Guo Xiangyu, Xue Xinyu. Extraction of navigation lines for rice seed farming based on machine vision ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42（5）: 197-201.
［9］　阮承治. 水草清理自动作业船视觉/GPS组合导航定位方法研究［D］. 镇江: 江苏大学, 2018.
Ruan Chengzhi. Research on visual/GPS integrated navigation positioning method for aquatic plants cleaning automatic workboat ［D］. Zhenjiang: Jiangsu University, 2018.
［10］　张勤, 陈建敏, 李彬, 等. 基于RGBD信息融合和目标检测的番茄串采摘点识别定位方法［J］. 农业工程学报, 2021, 37（18）: 143-152.
Zhang Qin, Chen Jianmin, Li Bin, et al. Method for recognizing and locating tomato cluster picking points based on RGBD information fusion and target detection ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37（18）: 143-152.
［11］　李贵宾, 李长勇, 陈立新. 利用圆预处理RGB图像对葡萄图像分割影响研究［J］. 中国农机化学报, 2021, 42（7）: 162-169.
Li Guibin, Li Changyong, Chen Lixin. Research on the influence of circle preprocessing RGB image on grape image segmentation ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42（7）: 162-169.
［12］　赵宇峰. 基于光场成像的行人检测方法研究［D］. 天津: 天津理工大学, 2021.
Zhao Yufeng. Research on pedestrian detection using light filed imaging ［D］. Tianjin: Tianjin University of Technology, 2021.
［13］　彭明阳, 王建华, 闻祥鑫, 等. 结合HSV空间的水面图像特征水岸线检测［J］. 中国图象图形学报, 2018, 23（4）: 526-533.
Peng Mingyang, Wang Jianhua, Wen Xiangxin, et al. Shoreline detection method by combining HSV spatial water image feature ［J］. Journal of Image and Graphics, 2018, 23（4）: 526-533.
［14］　赵静, 曹佃龙, 兰玉彬, 等. 基于FCN的无人机玉米遥感图像垄中心线提取［J］. 农业工程学报, 2021, 37（9）: 72-80.
Zhao Jing, Cao Dianlong, Lan Yubin, et al. Extraction of maize field ridge centerline based on FCN with UAV remote sensing images ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37（9）: 72-80.
［15］　廖娟, 汪鹞, 尹俊楠, 等. 基于分区域特征点聚类的秧苗行中心线提取［J］. 农业机械学报, 2019, 50（11）: 34-41.
Liao Juan, Wang Yao, Yin Junnan, et al. Detection of seedling row centerlines based on subregional feature points clustering ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50（11）: 34-41.
［16］　李云红, 张秋铭, 周小计, 等. 基于形态学及区域合并的分水岭图像分割算法［J］. 计算机工程与应用, 2020, 56（2）: 190-195.

[1]	葛翔, 陆军, 曹冬林, 金天澍. 基于轮廓固性与分水岭算法的叶片粘连雾滴图像分割[J]. 中国农机化学报, 2023, 44(6): 182-191.
[2]	周文静, 赵康, 马晓晓, 田志芳. 基于改进红绿色差和Otsu的葡萄果穗图像分割[J]. 中国农机化学报, 2023, 44(1): 172-177.
[3]	王珊, 薛新宇, 郭祥雨. 基于机器视觉的油菜菌核病分级检测研究[J]. 中国农机化学报, 2022, 43(5): 47-53.
[4]	李金阳, 张伟, 康烨, 许秀英, 亓立强, 石文强, . 基于无人机遥感技术的大豆苗数估算研究[J]. 中国农机化学报, 2022, 43(4): 83-89.
[5]	王梁, 侯义锋, 贺杰. 基于Mask-RCNN的自然场景下油茶果目标识别与检测[J]. 中国农机化学报, 2022, 43(12): 148-154.
[6]	王鹤树, 曹丽英, . 基于全卷积神经网络的植物叶片自动分割及表型解析[J]. 中国农机化学报, 2021, 42(8): 161-168.
[7]	李贵宾;李长勇;陈立新;. 利用圆预处理RGB图像对葡萄图像分割影响研究[J]. 中国农机化学报, 2021, 42(7): 162-169.
[8]	施滢;夏春华;. 基于棋盘格的可变参照物叶面积测量方法研究[J]. 中国农机化学报, 2021, 42(5): 191-196.
[9]	李帼;曹苏艳;钱婷婷;陆声链;. 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.
[10]	卜小东;张馨月;黄可京;郭辉;. 基于机器视觉的玉米苗期土壤湿度检测试验研究[J]. 中国农机化学报, 2020, 41(7): 150-156.
[11]	林楠;王娜;李卓识;陈晓旭;张波;田霞;. 基于机器视觉的野生食用菌特征提取识别研究[J]. 中国农机化学报, 2020, 41(5): 111-119.
[12]	刘哲;张善文;黄文准;李瑞洋;崔倩;. 基于双远心镜头的高精度叶面积测量方法研究[J]. 中国农机化学报, 2020, 41(4): 138-145.
[13]	李睿;张伟;王訢丞;符海霸;于丽娟;张平;. 叶面雾滴沉积分布直接检测算法研究[J]. 中国农机化学报, 2020, 41(3): 74-78.
[14]	顾博;邓蕾蕾;李巍;吕博;. 基于GrabCut算法的玉米病害图像识别方法研究[J]. 中国农机化学报, 2019, 40(11): 143-149.
[15]	齐锐丽;陈曼龙;杨宗浩;丁敏;. 基于HSV模型与改进的OTSU算法花椒图像分割[J]. 中国农机化学报, 2019, 40(11): 155-160.