高光照条件下的大豆行线提取方法研究

doi:10.13304/j.nykjdb.2022.0217

摘要/Abstract

摘要：

针对中国南方大豆田间环境复杂，光照强度高，常用的作物特征提取算法适应性差的问题，对高光照条件下的大豆行线提取方法进行研究。通过超绿特征（2G-R-B）算法，提取大豆植株绿色特征；对灰度图进行形态学处理、小面积去噪，去除图像背景和图像中的噪声；根据SUSAN角点检测算法，提取出大豆田间作物特征点；利用特征点的位置特征自动归类特征点，采用MLESAC算法对离散点进行拟合，得到作物行线。结果表明，该算法具有较强的抗噪性能，可以准确地提取大豆苗带上的特征点，利用特征点的位置特征自动归类特征点，提取出垄上两侧的大豆苗带行线，大豆苗带行线提取准确率为93%，可以为田间导航作业提供研究基础。研究结果为大豆苗期除草、追肥等田间自主导航作业提供了一种可靠的导航方法。

关键词: 大豆, SUSAN角点, MLESAC算法, 行线

Abstract:

A study of soybean row line extraction methods under high light conditions was conducted to address the problems of complex soybean field environment， high light intensity and poor adaptability of commonly used crop feature extraction methods in southern China. Using the 2G-R-B algorithm， this study extracted green features from soybean plants， and performed morphological processing， small area denoising of the grayscale image to remove the image background and noise from the image. This study extracted soybean field crop feature points based on the SUSAN corner point detection algorithm，and then used the location features of the feature points to automatically categorise the feature points， and the MLESAC algorithm was used to fit the discrete points to obtain the crop row lines. The results show that the algorithm had a strong noise immunity performance. Using this algorithm could accurately extract the feature points on the soya bean seedling strip， and use the location features of the feature points to automatically categorise the feature points and extract the soya bean seedling strip line on both sides of the monopoly. The accuracy of soya bean seedling strip line extraction was 93%， which could provide a research basis for field navigation operations.This results provided a reliable navigation method for autonomous field navigation operations such as weeding and fertilisation of soybean seedlings.

Key words: soybean, SUSAN corner point, MLESAC algorithm, lines

中图分类号:

S565.1

胡健, 车刚, 万霖, 周慧茹, 李光. 高光照条件下的大豆行线提取方法研究[J]. 中国农业科技导报, 2023, 25(5): 106-111.

Jian HU, Gang CHE, Lin WAN, Huiru ZHOU, Guang LI. Study of Soybean Row Line Extraction Method Under High Light Conditions[J]. Journal of Agricultural Science and Technology, 2023, 25(5): 106-111.

图/表 7

图1 提取流程

Fig. 1 Extraction process

图2 灰度化图像A：原始图像； B ：YCrCg灰度化；C：2G?R?B灰度化

Fig. 2 Grayscale imagesA：Original image；B ：YCrCg grayscale；C：2G?R?B grayscale

图3 图像二值化A：原二值化处理； B：形态学膨胀处理； C：形态学膨胀与小面积去噪处理

Fig. 3 Binary imageA：Original binarization processing； B：Morphological expansion treatment； C：Morphological expansion and denoising of small areas

图4 角点检测注：红色点为图像检测的特征点。

Fig. 4 Corner point detectionNote：Red dots are feature points for image detection.

图5 大豆苗带特征点检测效果注：图中蓝色点提取左右苗带特征点。

Fig. 5 Detection effect of soybean seedlings with characteristic pointsNote：Blue dots in the figure extract the left and right seedling band feature points.

图6 大豆苗带检测效果

Fig. 6 Soybean seedling belt detection effect

图7 大豆苗带检测准确性曲线A：左侧苗带检测结果； B：右侧苗带检测结果

Fig. 7 Soybean seedling belt detection accuracy curveA：Left seedling band test results； B：Right seedling band test results

参考文献 21

1	梁习卉子,陈兵旗,姜秋慧,等.基于图像处理的玉米收割机导航路线检测方法[J].农业工程学报,2016,32(22):43-49.
	LIANGXI H Z, CHEN B Q, JIANG Q H, et al.. Detection method of navigation route of corn harvester based on image processing [J]. Trans. Chin. Soc. Agric. Eng., 2016,32(22): 43-49.
2	朱弘亮,马兆敏,胡波,等.农业机器人田间导航参照点测距的新方法[J].农机化研究,2016,38(8):68-71, 76.
	ZHU H L, MA Z M, HU B, et al.. A new method for ranging the reference point of field navigation of agricultural robots [J]. Agric. Mechan. Res., 2016, 38(8):68-71, 76.
3	郭飘扬. 履带式联合收割机自主导航系统开发[D]. 南京:南京农业大学,2017.
	GUO P Y. Development of autonomous navigation system for crawler combine harvester [D]. Nanjing:Nanjing Agricultural University, 2017.
4	彭顺正,坎杂,李景彬.矮化密植枣园收获作业视觉导航路径提取[J].农业工程学报,2017,33(9):45-52.
	PENG S Z, KAN Z, LI J B. Extraction of visual navigation path for harvesting operations in dwarfed dense jujube orchards [J]. Trans. Chin. Soc. Agric. Eng., 2017, 33(9):45-52.
5	李景彬,彭顺正,温宝琴,等. 针对矮化密植枣园田管作业视觉导航路径提取方法:CN108509928A[P]. 2018-09-07.
6	胡波. 一种田间近景图像的导航线提取方法:CN109948543A[P].2019-06-28.
7	饶秀勤,林洋洋,张延宁,等. 一种作物封垄后田间导航线的检测方法:CN112146646A[P]. 2020-12-29.
8	廖娟,陈民慧,张锴,等. 一种田间农业机械视觉导航系统及方法:CN113587946A[P]. 2021-11-02.
9	陈娇,姜国权,杜尚丰,等.基于垄线平行特征的视觉导航多垄线识别[J].农业工程学报,2009,25(12):107-113.
	CHEN J, JIANG G Q, DU S F, et al..Visual navigation multi-ridge line recognition based on ridge parallel features [J].Trans. Chin. Soc. Agric. Eng., 2009, 25(12):107-113.
10	刁智华,赵明珍,宋寅卯,等. 基于机器视觉的玉米精准施药系统作物行识别算法及系统实现[J].农业工程学报,2015,31(7):47-52.
	DIAO Z H, ZHAO M Z, SONG Y M, et al.. Crop row recognition algorithm and system implementation of maize precision pesticide application system based on machine vision [J].Trans. Chin. Soc. Agric. Eng., 2015, 31(7): 47-52.
11	宋宇,刘永博,刘路,等.基于机器视觉的玉米根茎导航基准线提取方法[J].农业机械学报,2017,48(2):38-44.
	SONG Y, LIU Y B, LIU L, et al.. Extraction method of maize rhizome navigation base line base donmachine vision [J]. Trans. Chin. Soc. Agric. Machin., 2017,48(2): 38-44.
12	王祥祥,宫金良,张彦斐.基于机器视觉的玉米行导航线提取方法[J].山东理工大学学报(自然科学版),2021,35(2):19-22, 27.
	WANG X X, GONG J L, ZHANG Y F. Maize row navigation line extraction method based on machine vision [J]. J. Shandong Univ.Technol. (Nat. Sci.),2021,35(2):19-22, 27.
13	关卓怀,陈科尹,丁幼春,等.水稻收获作业视觉导航路径提取方法[J].农业机械学报,2020,51(1):19-28.
	GUAN Z H, CHEN K Y, DING Y C, et al.. Extraction method of visual navigation path for rice harvest operation [J].Trans. Chin. Soc. Agric. Machin., 2020, 51(1):19-28.
14	GARCÍA-SANTILLÁN I, GUERRERO J M, MONTALVO M, et al.. Curved and straight crop row detection by accumulation of green pixels from images in maize fields [J]. Precision Agric., 2018,19(1):18-41.
15	NADEEM F, KHUSHBAKHT R. Integration of remote sensing and GIS to extract plantation rows from a drone-based image point cloud digital surface model [J/OL]. ISPRS Int. J. Geo-Inf., 2020, 9(3):151 [2022-02-23]. .
16	BASSO M, FREITAS E P D. A UAV guidance system using crop row detection and line follower algorithms [J]. J. Intellig. Robotic Syst.,2020,97(3):605-621.
17	国家统计局. 2021中国统计年鉴(EB/OL).(2021-09-01) [2022-02-23]. .
18	SMITH S M, BRADY J M. SUSAN - a new approach to low level image processing [J]. Int. J. Computer Vision,1997,23(1):45-78.
19	WOEBBECHE D M, MEYER G E, BARGEN K V, et al.. Color indices for weed identification under various soil, residue, and lighting conditions [J]. Trans. ASABE,1995,38(1): 259-269.
20	孟庆宽,何洁,仇瑞承,等.基于机器视觉的自然环境下作物行识别与导航线提取[J].光学报,2014,34(7):180-186.
	MENG Q K, HE J, QIU R C, et al.. Crop row recognition and navigation line extraction in natural environment based on machine vision [J]. Acta Optica Sin., 2014,34(7):180-186.
21	TORR P H S, ZISSERMAN A. MLESAC: a new robust estimator with application to estimating image geometry [J]. Computer Vision Image Understand.,2000,78(1): 138-156.

[1]	杨占武, 杜汇, 邢馨竹, 李文龙, 孔佑宾, 李喜焕, 张彩英. 大豆细胞色素P450家族GmCYP78A71固氮功能解析[J]. 中国农业科技导报, 2023, 25(1): 50-57.
[2]	田振祥, 丁伟, 程茁, 戴航宇. 大豆内生细菌的分离及其作用效果研究[J]. 中国农业科技导报, 2022, 24(6): 47-57.
[3]	陈奎元, 刘卉, 丁伟. 草甘膦对大豆田土壤养分及其功能酶活性的影响[J]. 中国农业科技导报, 2022, 24(5): 180-188.
[4]	秦宁, 李俊茹, 田蕊, 邵振启, 李喜焕, 张彩英. 大豆籽粒生育酚遗传位点发掘及候选基因筛选[J]. 中国农业科技导报, 2022, 24(3): 48-56.
[5]	王凯强, 杨雪, 李常风, 段晓, 彭晴, 乔宇, 石波. 响应面法优化低聚木糖诱导大豆抗毒素合成条件[J]. 中国农业科技导报, 2022, 24(10): 208-217.
[6]	邢馨竹, 杨占武, 孔佑宾, 李文龙, 杜汇, 李喜焕, 张彩英. 大豆类胡萝卜素裂解双加氧酶GmCCD8固氮功能解析[J]. 中国农业科技导报, 2022, 24(1): 46-53.
[7]	范文华, 戴建军, 张树山, 孙玲伟, 吴彩凤, 张德福. 大豆卵磷脂稀释液中添加原花青素对山羊冻精效果的影响#br#[J]. 中国农业科技导报, 2021, 23(9): 78-86.
[8]	陈士亮, 孙亚倩, 邵振启, 李文龙, 孔佑宾, 杜汇, 李喜焕, 张彩英. 大豆鲜荚籽粒上位性QTL及其互作效应分析[J]. 中国农业科技导报, 2021, 23(8): 25-36.
[9]	张永芳，高志慧，史鹏清，韩志平*. 基于不同大豆品种农艺性状及品质性状的适应性分析[J]. 中国农业科技导报, 2020, 22(8): 25-32.
[10]	李智，王宏富*，王钰云，杨净，鱼冰星，黄珊珊. 谷子大豆间作对作物光合特性及产量的影响[J]. 中国农业科技导报, 2020, 22(6): 168-175.
[11]	金林雪1,唐红艳1*,武荣盛1,王惠贞1,刘林春2. 内蒙古大豆干旱灾害风险分析与区划[J]. 中国农业科技导报, 2020, 22(1): 106-115.
[12]	白玉哲1,马钰聪1,孟一泽1,廉瑞娇1,王莹1,李喜焕1,张彩英2. 大豆籽粒蛋白与脂肪含量上位性QTLs分析[J]. 中国农业科技导报, 2019, 21(6): 36-42.
[13]	张丽梅,马欣,韩宝吉,石磊*. 大豆-油菜轮作中不同硼肥及后效对作物产量的影响[J]. 中国农业科技导报, 2019, 21(10): 133-139.
[14]	曹慧方,李新新,张玥琦,石鹏君,柏映国,姚斌. 来源于脂环酸芽孢杆菌的GH1家族β-葡萄糖苷酶的葡萄糖耐受性分子改造[J]. 中国农业科技导报, 2018, 20(5): 26-33.
[15]	耿金剑,王春艳*,程婉莹,杨雪玲,李茂松. 极早熟区大豆冠层受光量及其对产量的影响[J]. 中国农业科技导报, 2018, 20(5): 111-123.