传统图像分割算法在农作物籽粒考种应用中的研究进展

doi:10.13733/j.jcam.issn.2095-5553.2024.02.040

摘要/Abstract

摘要： 传统图像分割算法以时间、空间复杂度低等优点在农作物籽粒考种领域中有着广泛的应用。对传统分割算法在农作物表型获取过程中的应用进行研究,首先阐述Otsu、分水岭、边缘检测、SLIC算法以及凹点分析算法的算法原理,对种皮颜色灰度均匀、形状不同的农作物籽粒,以“问题—方法”的模式阐述不同算法在应用中存在的问题以及相应的解决方法;接着将算法基于阈值、区域、边缘、聚类、凹点整合为五大类,对算法的分割效果、优缺点及其适用范围进行比较研究;最后,剖析农作物籽粒图像分割应用研究存在农作物种类覆盖度不够宽泛、图像分割精度不高、技术通用性不高等问题,并从算法精度提高、重叠遮挡处理等方面对未来的研究进行展望,以期为农作物籽粒考种过程中的图像分割研究提供参考。

关键词: 考种, 籽粒表型, 信息获取, 图像处理, 图像分割

Abstract: Traditional image segmentation algorithm has been widely used in the field of crop seed testing because of its low complexity in time and space. The application of traditional segmentation algorithm in the crop phenotype extraction was studied in this paper. Firstly, the algorithm principles of Otsu, watershed, edge detection, SLIC and concave point analysis algorithm were expounded. For crop seeds with uniform seed coat color and different shapes, the problems in the application of different algorithms and the corresponding solutions were described in the model of ‘problem-method’. Then the algorithms were integrated into five categories based on threshold, region, edge, cluster and concave point, and the segmentation effect, advantages and disadvantages and application range of the algorithm were compared. Finally, the problems in the application of crop seed image segmentation were analyzed, and the future research directions were prospected from algorithm accuracy improvement and overlapping occlusion processing, in order to provide reference for the research of image segmentation in the process of crop seed testing.

Key words: seed testing, seed phenotype, information acquisition, image processing, image segmentation

中图分类号:

TP391: S375

张伟进, 王福顺, , 孙小华, 王军皓, 刘宏权, 王鑫鑫, . 传统图像分割算法在农作物籽粒考种应用中的研究进展[J]. 中国农机化学报, 2024, 45(2): 280-287.

Zhang Weijin, Wang Fushun, , Sun Xiaohua, Wang Junhao, Liu Hongquan, Wang Xinxin, . Research progress of traditional image segmentation algorithm in seed testing of crops[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 280-287.

参考文献

［1］　Jiang Ziqi, Zou Feng, Chen Debao, et al. An improved teaching-learning-based optimization for multilevel thresholding image segmentation ［J］. Arabian Journal for Science and Engineering, 2021, 46(9): 8371-8396.
［2］　Sawant A. Flower recognition system based on image segmentation algorithms ［J］. International Journal of Innovative Technology and Exploring Engineering, 2020, 9(3): 685-688.
［3］　Jung S, Cho Y, Lee K T, et al. Moving object detection with single moving camera and IMU sensor using mask R-CNN instance image segmentation ［J］. International Journal of Precision Engineering and Manufacturing, 2021, 22(6): 1049-1059.
［4］　Kotaridis I, Lazaridou M. Remote sensing image segmentation advances: A meta-analysis ［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 173: 309-322.
［5］　Divyameena S, Mangaleswaran M. A study on various image segmentation algorithms ［J］. International Journal of Scientific Research in Science, Engineering and Technology, 2018: 272-276.
［6］　Koh J, Hayden M, Daetwyler H, et al. Estimation of crop plant density at early mixed growth stages using UAV imagery ［J］. Plant Methods, 2019, 15(1): 1-9.
［7］　吴文华. 基于图像的油菜表型参数测量方法研究［D］. 杭州: 浙江大学, 2019.
Wu Wenhua. Study on measurement method of rapeseed phenotypic parameters based on image ［D］. Hangzhou: Zhejiang University, 2019.
［8］　Cui Dandan, Cui Guoxian, Yang Ruifang, et al. Phenotypic characteristics of ramie (Boehmeria nivea L.) germplasm resources based on UAV remote sensing ［J］. Genetic Resources and Crop Evolution, 2020, 68(2): 1-16.
［9］　宋鹏, 张晗, 王成, 等. 玉米高通量自动考种装置设计与试验［J］. 农业工程学报, 2017, 33(16): 41-47.
Song Peng, Zhang Han, Wang Cheng, et al. Design and experiment of high throughput automatic measuring device for corn ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(16): 41-47.
［10］　明雨阳. 基于图像处理的作物表型参量测量及生长状态监测方法研究［D］. 西安: 西安理工大学, 2020.
Ming Yuyang. Research on method of crop phenotypic parameter measurement and growth status monitoring based on image processing ［D］. Xian: Xian University of Technology, 2020.
［11］　杨晓雪, 史晓刚. 计算机图像处理技术及其在农业工程中的应用［J］. 数字通信世界, 2021(10): 45-46, 50.
Yang Xiaoxue, Shi Xiaogang. Computer image processing technology and its application in agricultural engineering ［J］. Digital Communication World, 2021(10): 45-46, 50.
［12］　Mahajan S, Mittal N, Salgotra R, et al. An efficient adaptive SALP swarm algorithm using type Ⅱ fuzzy entropy for multilevel thresholding image segmentation ［J］. Computational and Mathematical Methods in Medicine, 2022.
［13］　Ju Aiyun, Wang Zhongli. A novel fully convolutional network based on marker-controlled watershed segmentation algorithm for industrial soot robot target segmentation ［J］. Evolutionary Intelligence, 2022, 16(3): 1-18.
［14］　Qiao Shuang, Yu Qinghan, Zhao Zhengwei, et al. Edge extraction method for medical images based on improved local binary pattern combined with edge-aware filtering ［J］. Biomedical Signal Processing and Control, 2022, 74: 103490.
［15］　Vera J F, Macías R. On the behaviour of K-means clustering of a dissimilarity matrix by means of full multidimensional scaling ［J］. Psychometrika, 2021, 86(2): 489-513.
［16］　Sun Aiyun, Jia Wenbao, Hei Daqian,et al. Application of concave point matching algorithm in segmenting overlapping coal particles in X-ray images ［J］. Minerals Engineering, 2021, 171: 107096.
［17］　肖乐意. Otsu图像分割法的改进与应用研究［D］. 长沙: 湖南大学, 2020.
Xiao Leyi. Improvement and application of Otsu image segmentation method ［D］. Changsha: Hunan University, 2020.
［18］　刘杰, 安博文. 基于动态阈值分割的目标提取技术［J］. 红外技术, 2008, 30(12): 706-708, 712.
Liu Jie, An Bowen. Object extraction technique based on dynamic threshold segmentation ［J］. Infrared Technology, 2008, 30(12): 706-708, 712.
［19］　Otsu N. A threshold selection method from gray-level histograms ［J］. IEEE Transactions on Systems Man & Cybernetics, 2007, 9(1): 62-66.
［20］　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.
Li Yunhong, Zhang Qiuming, Zhou Xiaoji, et al. Watershed image segmentation algorithm based on morphology and region merging ［J］. Computer Engineering and Applications, 2020, 56(2): 190-195.
［21］　潘雄. 基于区域合并的图像分割算法研究［D］. 福州: 福建农林大学, 2020.
Pan Xiong. Research on image segmentation algorithm based on region merging ［D］. Fuzhou: Fujian Agriculture and Forestry University, 2020.
［22］　陈斌斌, 范九伦, 雷博, 等. 基于SLIC超像素粒化的粗糙熵图像分割算法［J］. 传感器与微系统, 2022, 41(2): 105-107.
Chen Binbin, Fan Jiulun, Lei Bo, et al. SLIC superpixel granulation-based rough entropy image segmentation algorithm ［J］. Transducer and Microsystem Technologies, 2022, 41(2): 105-107.
［23］　Wang Yuting, Liao Zhouyu. A method for object extraction from crop image based on visual saliency ［J］. Journal of Physics: Conference Series, 2022, 2171(1): 012007.
［24］　黄鹏, 郑淇, 梁超. 图像分割方法综述［J］. 武汉大学学报(理学版), 2020, 66(6): 519-531.
Huang Peng, Zheng Qi, Liang Chao. Overview of image segmentation methods ［J］. Journal of Wuhan University (Natural Science Edition), 2020, 66(6): 519-531.
［25］　张轩, 张新峰. 粘连颗粒图像分割方法综述［J］. 图像与信号处理, 2018, 7(3): 113-118.
Zhang Xuan, Zhang Xinfeng. Summarization of image segmentation methods for adhesive particles ［J］. Journal of Image and Signal Processing, 2018, 7(3): 113-118.
［26］　高辉, 甄彤, 李智慧. 粘连颗粒图像的分割方法综述［J］. 中国粮油学报, 2022, 37(3): 186-194.
Gao Hui, Zhen Tong, Li Zhihui. A review of segmentation methods for adhesive particle images ［J］. Chinese Journal of Cereals and Oils, 2022,37(3):186-194.
［27］　韩明芮, 杨玺. 基于图像处理的包装缺陷检测方法综述［J］. 中国储运, 2019(9): 110-112.
［28］　马佳佳, 王克强, 郑奕雄, 等. 基于机器视觉的花生种子外观品质检测与分类方法研究［J］. 安徽农业科学, 2021, 49(10): 225-227, 231.
Ma Jiajia, Wang Keqiang, Zheng Yixiong, et al. Research on the appearance quality detection and classification of peanut seeds based on machine vision ［J］. Journal of Anhui Agricultural Sciences, 2021, 49(10): 225-227, 231.
［29］　王建宇. 基于卷积神经网络的玉米籽粒精选系统研制［D］. 哈尔滨: 东北农业大学, 2019.
Wang Jianyu. Development of corn kernel sorting system based on convolutional neural network ［D］. Harbin: Northeast Agricultural University, 2019.
［30］　张博. 基于深度学习的小麦外观品质机器视觉检测研究［D］. 杨凌: 西北农林科技大学, 2019.
Zhang Bo. Machine vision detection of wheat appearance quality based on deep learning ［D］. Yangling: Northwest A & F University, 2019.
［31］　祝保林. 基于机器视觉的小桐子种子识别分类研究［D］. 开封: 河南大学, 2020.
Zhu Baolin. Study on seed recognition and classification of Jatropha seed based on machine vision ［D］. Kaifeng: Henan University, 2020.
［32］　陈进, 顾琰, 练毅, 等. 基于机器视觉的水稻杂质及破碎籽粒在线识别方法［J］. 农业工程学报, 2018, 34(13): 187-194.
Chen Jin, Gu Yan, Lian Yi, et al. Online recognition method of impurities and broken paddy grains based on machine vision ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(13): 187-194.
［32］　Xue Yongan, Zhao Jinling, Zhang Mingmei. A watershed-segmentation-based improved algorithm for extracting cultivated land boundaries ［J］. Remote Sensing, 2021, 13(5): 939.
［34］　Sun Quan, Zheng Junxing, Li Cheng. Improved watershed analysis for segmenting contacting particles of coarse granular soils in volumetric images ［J］. Powder Technology, 2019, 356(C): 295-303.
［35］　Cao Wenxuan, Qiao Zeyu, Gao Zeyu,et al. Use of unmanned aerial vehicle imagery and a hybrid algorithm combining a watershed algorithm and adaptive threshold segmentation to extract wheat lodging ［J］. Physics and Chemistry of the Earth, 2021, 123: 103016.
［36］　Gamarra M, Zurek E, Escalante H J,et al. Split and merge watershed: A two-step method for cell segmentation in fluorescence microscopy images ［J］. Biomedical Signal Processing and Control, 2019, 53: 101575.
［37］　Zhao Min, Wu Wen Fu, Zhang Ya Qiu. The corn seed image segmentation and measurement of the geometrical features based on image analysis ［J］. Applied Mechanics and Materials, 2011, 1326(66-68): 1100-1105.
［38］　Kuang Fangjun, Xu Weihong, Wang Yanhua. Novel watershed algorithm for touching rice image segmentation ［J］. Advanced Materials Research, 2011, 1290(271-273): 1-6.
［39］　蒋霓, 段凌凤, 杨万能, 等. 基于并行处理技术的谷物粒型快速测量算法［J］. 光电工程, 2012, 39(3): 66-71.
Jiang Ni, Duan Lingfeng, Yang Wanneng, et al. Fast grain shape determination algorithm based on parallel processing ［J］. Opto-Electronic Engineering, 2012, 39(3): 66-71.
［40］　李锦明. 基于机器视觉的玉米考种技术研究［D］. 杭州: 杭州电子科技大学, 2019.
Li Jinming. Research on maize seed examination technology based on machine vision ［D］. Hangzhou: Hangzhou Dianzi University, 2019.
［41］　孙晓婷, 陈江红, 陈庆周. 基于H-Dome重构的大豆图像分割［J］. 大豆科学, 2013, 32(6): 821-824.
Sun Xiaoting, Chen Jianghong, Chen Qingzhou.Image segmentation of soybean based on H-Dome ［J］. Soybean Science, 2013, 32(6): 821-824.
［42］　Berggren M, Caiazza S, Chera M,et al. Kinematic edge detection using finite impulse response filters ［J］. Nuclear Inst and Methods in Physics Research, 2021, 1010: 165555.
［43］　Xu Hongyun, Xu Xiaoli, Zuo Yunbo. Applying morphology to improve Canny operators image segmentation method ［J］. The Journal of Engineering, 2019, 2019(23): 8816-8819.
［44］　侯雨, 曹丽英, 丁小奇, 等. 基于边缘检测和BP神经网络的大豆杂草识别研究［J］. 中国农机化学报, 2020, 41(7): 185-190.
Hou Yu, Cao Liying, Ding Xiaoqi, et al. Research on soybean weed recognition based on edge detection and BP neural network ［J］. Journal of Chinese Agricultural Mechanization, 2020, 41(7): 185-190.
［45］　Achanta R, Shaji A, Smith K, et al. SLIC superpixels compared to state-of-the-art superpixel methods ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.
［46］　Yadav D P. A method for human burn diagnosis using machine learning and SLIC superpixels based segmentation ［J］. IOP Conference Series: Materials Science and Engineering, 2021, 1116(1): 012186.
［47］　Shakir U, Naeem B, Muhammad Z. Adaptive tuning of SLIC parameter K ［J］. Multimedia Tools and Applications, 2021, 80(17): 25649-25672.
［48］　郑金云. 基于聚类的超像素分割方法研究［D］. 桂林: 桂林电子科技大学, 2021.
Zheng Jinyun. Research on superpixel segmentation method based on clustering ［D］. Guilin: Guilin University of Electronic Technology, 2021.
［49］　何红霞. 基于机器视觉的小麦种子品种分类模型研究［D］. 合肥: 安徽农业大学, 2018.
He Hongxia. Research on wheat seed variety classification model based on machine vision ［D］. Hefei: Anhui Agricultural University, 2018.
［50］　李咏豪. 基于超像素的粘连谷粒分割算法［J］. 数字技术与应用, 2021, 39(4): 110-112.
Li Yonghao. Superpixel based adhesive grain kernel segmentation algorithm ［J］. Digital Technology & Application, 2021, 39(4): 110-112.
［51］　张宝全, 陆辉山, 王福杰, 等. 基于凹点分析法的粘连鸡体分割方法研究［J］. 中国农机化学报, 2021, 42(2): 164-170, 183.
Zhang Baoquan, Lu Huishan, Wang Fujie, et al. Research on the segmentation method of adhesive chicken body based on concave point analysis ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(2): 164-170, 183.
［52］　王小鹏, 姚丽娟, 文昊天, 等. 形态学多尺度重建结合凹点匹配分割枸杞图像［J］. 农业工程学报, 2018, 34(2): 212-218.
Wang Xiaopeng, Yao Lijuan, Wen Haotian, et al. Wolfberry image segmentation based on morphological multi-scale reconstruction and concave points matching ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(2): 212-218.
［53］　武威. 基于机器视觉技术的稻麦籽粒外观品质评测研究［D］. 扬州: 扬州大学, 2021.
Wu Wei. Evaluation of grain appearance quality of rice and wheat based on machine vision technology ［D］. Yangzhou: Yangzhou University, 2021.
［54］　孙志恒. 基于深度学习的稻米垩白识别算法研究与应用［D］. 成都: 电子科技大学, 2019.
Sun Zhiheng. Research and application of rice chalkiness recognition algorithm based on deep learning ［D］. Chengdu: University of Electronic Science and Technology of China, 2019.
［55］　刘宰豪. 基于凹点和重心检测的粘连类圆形目标图像分割［D］. 西安: 西安电子科技大学, 2019.
Liu Zaihao. Image segmentation of conglutination circular target based on concave point and center of gravity detection ［D］. Xian: Xidian University, 2019.
［56］　樊蒙蒙. 基于PCNN和凹点的粘连大米图像分割［D］. 郑州: 河南工业大学, 2019.
Fan Mengmeng. Image segmentation of bonded rice based on PCNN and concave point ［D］. Zhengzhou: Henan University of Technology, 2019.
［57］　Lin P, Chen Y M, He Y, et al. A novel matching algorithm for splitting touching rice kernels based on contour curvature analysis ［J］. Computers and Electronics in Agriculture, 2014, 109: 124-133.
［58］　布芳. 基于卷积神经网络的小目标检测与分割算法研究［D］. 西安: 西安电子科技大学, 2019.
Bu Fang. Research on small target detection and segmentation algorithm based on convolutional neural network ［D］. Xian: Xidian University, 2019.

[1]	董娅兰, 胡国玉, 刘广, 古丽巴哈尔·托乎提. 基于Mask R-CNN模型的葡萄藤关键结构分割方法[J]. 中国农机化学报, 2024, 45(2): 207-214.
[2]	黄家才, 汪涛, 张铎, 唐安, 高芳征. 基于改进YOLOv4的草莓果柄叶识别与定位[J]. 中国农机化学报, 2023, 44(9): 205-213.
[3]	李航, 廖映华, 黄波. 基于改进DQN算法的茶叶采摘机械手路径规划[J]. 中国农机化学报, 2023, 44(8): 198-205.
[4]	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.
[5]	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.
[6]	周显沁, 韩震宇, 刘成源. 基于改进卷积神经网络与图像处理的蚕茧识别方法[J]. 中国农机化学报, 2023, 44(5): 100-106.
[7]	周鹏飞, 蒙贺伟, , , 梁荣庆, 张炳成, 坎杂, , . 基于OpenCV-Python的土壤颗粒动态休止角试验[J]. 中国农机化学报, 2023, 44(5): 214-222.
[8]	王恒, 张维懿, 李成松, 王沛, 王丽红, . 基于图像处理的果树滴水线导航路径检测方法研究[J]. 中国农机化学报, 2023, 44(3): 183-190.
[9]	任浩, 李丽, 卢世博, 陈静姚, 张云峰, . 基于深度学习的复杂自然环境下桑树枝干识别方法[J]. 中国农机化学报, 2023, 44(2): 182-188.
[10]	沈中华, 夏爱强, 董志康, 陈万委, 曹卫华. 复杂环境下蔗梢图像分割方法研究[J]. 中国农机化学报, 2023, 44(12): 113-118.
[11]	秦昌友, 杨艳山, 顾峰玮, 陈盼阳, 秦维彩. 现代农业领域中计算机视觉技术的运用与发展[J]. 中国农机化学报, 2023, 44(12): 119-128.
[12]	朱路生, 徐敏雅, 王爱臣, 张东凤, 钱伟豪, 李川. 基于改进DeepLabV3+的成熟期水稻生长密度检测研究[J]. 中国农机化学报, 2023, 44(12): 186-192.
[13]	杨霄, 王朕, , 赵伟, 徐晶, 文玲梅, 徐敏. 鱼病实时检测系统的研制与试验[J]. 中国农机化学报, 2023, 44(11): 130-137.
[14]	王冬, , 段炼, 赵闰, 顾华兵, , 黎寿丰, 赵振华. 基于图像处理的鸡冠面积和色级测定方法研究[J]. 中国农机化学报, 2023, 44(10): 152-158.
[15]	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.