联合收获机水稻破碎籽粒及杂质在线识别方法

陈进; 张帅; 李耀明; 朱林军; 夏慧; 朱亚辉

doi:10.13733/j.jcam.issn.2095-5553.2021.06.22

联合收获机水稻破碎籽粒及杂质在线识别方法

1. 江苏大学机械工程学院;
2. 江苏大学农业工程学院;
3. 江苏沃得农业机械股份有限公司

基金项目:

国家重点研发计划(2016YFD0702004)

镇江市重点研发计划(NY2019009)

详细信息

作者简介:
陈进,女,1959年生,江苏盐城人,博士,教授,博导,研究方向为农业装备信息感知及智能控制技术。E-mail:chenjinjd126@126.com

中图分类号: S225.4
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 收稿日期: 2021-03-31
- 刊出日期: 2021-06-14

Research on online identification system of rice broken impurities in combine harvester

1. School of Mechanical Engineering, Jiangsu University;
2. College of Agricultural Engineering,Jiangsu University;
3. Jiangsu World Agricultural Machinery Co., Ltd.

摘要

摘要: 在联合收获机作业过程中,含杂率或破碎率过高往往是由于收获机作业参数设置不当引起,需要对收获机作业参数实时调整,而对收获的水稻成分进行在线识别可以为驾驶员提供合理的调整依据。基于此,提出一种联合收获机水稻破碎籽粒及杂质在线识别方法,采用采集流动中的水稻图像的方案,研制图像采集装置,实时采集流动状态下的水稻图像,然后利用OpenCV进行图像处理,根据水稻中完整籽粒、破碎籽粒、杂质的颜色特征以及面积特征差异进行识别分类。在水稻田间试验中随机采集200张图片,其中20张图片用于进行特征差异研究,其余图片用于测试验证。测试结果表明:破碎籽粒、稻秆杂质以及稻梗杂质的综合评价指标分别达到92.92%、90.65%和90.52%,且单幅图片的平均处理周期约为1.86 s,研究的谷物图像采集装置及水稻破碎杂质在线识别算法可以在线识别水稻中完整籽粒、破碎籽粒、稻秆稻梗等杂质,为水稻联合收获机作业参数在线自动调控提供技术支撑。
- 水稻 /
- 联合收获机 /
- 含杂率 /
- 破碎率 /
- 在线识别 /
- RGB
Abstract: In the process of combined harvester operation, the high impurity content or crushing rate was often caused by improper setting of harvester operation parameters, which needs to be adjusted in real-time. Therefore, online monitoring and identification of rice components in harvest could provide a reasonable basis for adjusting harvester operation parameters. In this paper, an online recognition method of broken rice impurities based on image features was proposed. The scheme of collecting rice images in the flow was adopted, and an image acquisition device was developed. The rice images in the flow state were collected in real-time, and then OpenCV was used for image processing. According to the differences of color features and area features of complete grains, broken grains, and impurities in rice, the image processing performed the outline identification classification. In the field experiment of rice, 200 images were randomly collected, 20 of which were used for feature difference study, and the rest were used for test validation. The test results showed that the comprehensive evaluation indexes of complete grain, broken grain, and impurity reached the standard 92.92%, 90.65%, and 90.52%. The average processing cycle of a single image was about 1.86 s. The grain image acquisition device and the online identification algorithm of broken rice impurities studied in this paper could identify the impurities in rice online, such as complete grain, broken grain, rice stalk, and rice stem, and provide technical support for automatic online control of operation parameters of rice harvester.
- rice /
- combine harvester /
- impurity rate /
- crushing rate /
- online identification /
- RGB

HTML全文

参考文献(19)

[1]	董先伟.农业机械发展概况及思考[J].农机使用与维修,2021(2):135-136.
[2]	王晓.对新时期农机化发展的思考[J].农业装备技术,2020,46(4):12,25.
[3]	夏鼎宽,邓干然,何冯光,等.农田作业机械监测技术发展现状与趋势[J].现代农业装备,2020,41(6):10-16,28. Xia Dingkuan,Deng Ganran,He Fengguang,et al.Current situation and trend of monitoring technology of farm working machinery [J].Modern Agricultural Equipment,2020,41(6):10-16,28.
[4]	冯振水,刘建华.我国农业机械行业现状分析和前景展望[J].农业技术与装备,2020(7):37-38. Feng Zhenshui,Liu Jianhua.Current situation analysis and prospect of agricultural machinery industry in China [J].Agricultural Technology & Equipment,2020(7):37-38.
[5]	李海涛.国内外智能化农机的发展现状[J].农家参谋,2020(6):93.
[6]	陈进,韩梦娜,练毅,等.基于U-Net模型的含杂水稻籽粒图像分割[J].农业工程学报,2020,36(10):174-180. Chen Jin,Han Mengna,Lian Yi,et al.Segmentation of impurity rice grain images based on U-Net model [J].Transactions of the Chinese Society of Agricultural Engineering,2020,36(10):174-180.
[7]	李栋.基于ARM嵌入式的图像处理研究[D].石家庄:河北科技大学,2010. Li Dong.Theremote control system of video based on web service in embedded linux environment [D].Shijiazhuang:Hebei University of Science and Technology,2010.
[8]	许美珍.嵌入式图像处理系统研究[D].呼和浩特:内蒙古工业大学,2016. Xu Meizhen.Research on embedded image processing system [D].Hohhot:Inner Mongolia University of Technology,2016.
[9]	梁振伟,李耀明,徐立章.一种粮箱籽粒含杂率、破碎率监测装置[P].中国专利:CN206223641U,2017-06-06.
[10]	葛杰,曹晨晨,李光.基于机器视觉的图像形状特征提取方法研究进展[J].包装学报,2015,7(1):54-60. Ge Jie,Cao Chenchen,Li Guang.Research progress in shape feature extraction methods based on machine vision [J].Packaging Journal,2015,7(1):54-60.
[11]	韩丁,武佩,张强,等.基于颜色矩的典型草原牧草特征提取与图像识别[J].农业工程学报,2016,32(23):168-175. Han Ding,Wu Pei,Zhang Qiang,et al.Feature extraction and image recognition of typical grassland forage based on color moment [J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(23):168-175.
[12]	张亚秋,吴文福,王刚.基于逐步改变阈值方法的玉米种子图像分割[J].农业工程学报,2011,27(7):200-204. Zhang Yaqiu,Wu Wenfu,Wang Gang.Separation of corn seeds images based on threshold changed gradually [J].Transactions of the Chinese Society of Agricultural Engineering,2011,27(7):200-204.
[13]	张晴晴,张云龙,齐国红.基于最大类间方差法的黄瓜病害叶片分割[J].安徽农业科学,2017,45(12):193-195,234. Zhang Qingqing,Zhang Yunlong,Qi Guohong.Segmentation of cucumber disease leaves based on Otsu method [J].Journal of Anhui Agricultural Sciences,2017,45(12):193-195,234.
[14]	朱言江,韩震,和思海,等.基于最大类间方差法和数学形态学的遥感图像潮沟提取方法[J].上海海洋大学学报,2017,26(1):146-153. Zhu Yanjiang,Han Zhen,He Sihai,et al.Remote sensing image extraction of tidal channels based on Otsu and mathematical morphology [J].Journal of Shanghai Ocean University,2017,26(1):146-153.
[15]	闫磊,刘芷宁,林剑辉,等.一种粘连谷物图像分割及杂质识别算法开发[J].吉林农业科学,2012,37(4):72-76. Yan Lei,Liu Zhining,Lin Jianhui,et al.Development of splitting and identification algorithm of touching kernels in digital images [J].Journal of Jilin Agricultural Sciences,2012,37(4):72-76.
[16]	苏忆楠.基于机器视觉和高光谱图像技术的粮食水分检测及杂质与不完善粒识别方法研究[D].杭州:浙江大学,2011. Su Yinan.Research on grain water content detection and impurities recognition method based on machine vision and hyperspectral image technique [D].Hangzhou:Zhejiang University,2011.
[17]	黄玉斌,范朝元,钟志强,等.一种测试仪的功率测量自动校准设计与实现[J].电子测试,2021(1):21-23.
[18]	Jin Y,Chen Y,Chen W,et al.Experimental demonstration of filter parameters’ effect on the performance of all-optical thresholding [J].Optics Communications,2021,491:126961.
[19]	张启轩,袁明辉.基于OpenCV的物体图像边缘缺陷识别研究[J].软件导刊,2021,20(4):231-235.

施引文献(15)

期刊类型引用(10)

1.	林燕翔，沈印，李光林. 基于改进InceptionV3算法的小麦杂质识别研究. 中国农机化学报. 2024(04): 108-116 . 本站查看
2.	周思理，李玲，王系林，代叶，颜彬，刘海涛，何冯光，孙昌东. 机收作物含杂率检测方法研究进展. 农业开发与装备. 2024(06): 149-153 . 百度学术
3.	李边豪，张国良，李鹏程，赵宏亮，闫飞宇，黄志炜，牛远，齐波，张林青，范松. 机器视觉在稻种识别和分类上的应用进展. 中国农学通报. 2024(31): 152-158 . 百度学术
4.	陈满，金诚谦，莫恭武，刘士坤，徐金山. 基于改进U-Net模型的小麦收获含杂率在线检测方法. 农业机械学报. 2023(02): 73-82 . 百度学术
5.	刘士坤，金诚谦，陈满，杨腾祥，徐金山. 基于DeepLabV3+网络的机收大豆破碎率在线检测方法. 中国农机化学报. 2023(05): 170-175 . 本站查看
6.	付永民，范磊，李长进，吴庆华. 基于计算机视觉与机器学习的烟丝杂质图像级联检测方法. 轻工学报. 2023(04): 113-121 . 百度学术
7.	陈旭，关卓怀，李海同，沐森林，张敏，吴崇友. 油菜联合收获机含杂率在线检测系统设计与试验. 中国农机化学报. 2022(10): 127-134 . 本站查看
8.	王修善，谢方平，刘大为，陈子林，钟嘉雄. 基于深度学习的稻谷内部损伤无损检测装置. 实验技术与管理. 2022(12): 112-117 . 百度学术
9.	裴凤雀，杨开伟，王淼，童一飞. 智能制造在农业机械领域的应用现状分析（英文）. 智能化农业装备学报(中英文). 2022(01): 7-19 . 百度学术
10.	罗锡文，廖娟，胡炼，周志艳，张智刚，臧英，汪沛，何杰. 我国智能农机的研究进展与无人农场的实践. 华南农业大学学报. 2021(06): 8-17+5 . 百度学术