基于图像处理多算法融合的杂草检测方法及试验

doi:10.12133/j.smartag.2020.2.4.202010-SA006

摘要/Abstract

摘要：

自动化除草是现代精确农业科学领域的研究热点。已有的自动化除草解决方案中普遍存在鲁棒性不强、过度依赖大量样本等问题，针对上述问题，本研究提出了基于图像处理多算法融合的田间杂草检测方法，设计了一套田间杂草自动识别算法。首先通过设置颜色空间的阈值从图像中分割土壤背景。然后采用面积阈值、模板匹配和饱和度阈值三种方法对作物和杂草进行分类。最后基于投票的方式，综合权衡上述三种方法，实现对作物和杂草的精准识别与定位。以大豆田间除草为对象进行了试验研究，结果表明，使用融合多图像处理算法的投票方法进行作物和杂草识别定位，杂草识别平均错误率为1.79%，识别精度达到98.21%。相较单一的面积阈值、模板匹配和饱和度阈值方法，基于投票权重识别杂草的精度平均提升5.71%。同时，针对复杂多变的农业场景，进行了存在雨滴和阴影干扰的鲁棒性测试，实现了90%以上的作物识别结果，表明本研究方法具有较好的适应性和鲁棒性。本研究算法可为智能移动机器人除草作业等智慧农业领域应用提供技术支持。

关键词: 杂草检测, 投票权重, 算法融合, 图像处理, 自动识别

Abstract:

Automatic weeding is a hot research field of smart agriculture, which has many benefits such as achieving precise weed control, saving human cost, and avoiding damage on crops, etc. Recently, many researchers have focused on the research using the deep learning method, such as the convolutional neural network (CNN) and recurrent neural network (RNN) and have achieved decent outcomes related to the automatic weed detection. However, there are still generally problems of the projects such as weak robustness and excessive reliance on a large number of samples. To solve these problems, a recognition algorithm for automatic identification and weed removal was designed, and a soybean field weed detection and localization method based on the fusion of multiple image processing methods was proposed in this study. The images and video stream were obtained through the camera mounted on a mobile robot platform. Firstly, the soil background inside the image was segmented from the foreground (including the weeds and crops) by setting the threshold for a specific color space (hue). Then, three different methods including the area threshold method, template matching and saturation threshold method were used to classify the crops and weeds. Finally, based on a proposed innovative voting method, the three recognition methods were comprehensively weighed and fused to achieve more accurate recognition and localization results of the crops and weeds inside the image. Experimental validations were carried out using the samples obtained through the moving platform, and the experimental results showed that the average accuracy of the proposed weed detection algorithm was as high as 98.21%, while the recognition error was only 1.79%. Meanwhile, compared with each single method as the scale threshold, template matching and saturation threshold, the fused method based on the weighted voting has been able to raise the average accuracy by 5.71%. Even though the samples used in the validations were limited in covering different scenarios, the high recognition accuracy has proved the practicability of the proposed method. In addition, the robustness test that images with raindrop and shadow interference in the complex and unstructured agricultural scene was carried out, and satisfied results showed that above 90% of the plant were successfully detected, which verified the fine adaptability and robustness of the proposed method.

Key words: weed detection, vote weight, algorithm fusion, image processing, automatic detection

中图分类号:

S126

苗中华, 余孝有, 徐美红, 何创新, 李楠, 孙腾. 基于图像处理多算法融合的杂草检测方法及试验[J]. 智慧农业（中英文）, 2020, 2(4): 103-115.

MIAO Zhonghua, YU Xiaoyao, XU Meihong, HE Chuangxin, LI Nan, SUN Teng. Automatic Weed Detection Method Based on Fusion of Multiple Image Processing Algorithms[J]. Smart Agriculture, 2020, 2(4): 103-115.

参考文献

1	尚建伟, 蒋红海, 喻刚, 等. 基于深度学习的杂草识别系统[J]. 软件导刊, 2020, 19(7): 127-130.
1	SHANG J, JIANG H, YU G, et al. Weed recognition system based on deep learning[J]. Software Guide, 2020, 19(7): 127-130.
2	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.
2	HOU Y, CAO L, DING X, et al. Research on soybean weed identification based on edge detection and BP neural network[J]. Chinese Journal of Agricultural Mechanization, 2020, 41(7): 185-190.
3	ARAVIND R, DAMAN M, KARIYAPPA B S. Design and development of automatic weed detection and smart herbicide sprayer robot[C]// 2015 IEEE Recent Advances in Intelligent Computational Systems (RAICS). Piscataway, New York, USA: IEEE, 2015: 257-261.
4	任全会, 杨保海. 图像处理技术在田间杂草识别中应用研究[J]. 中国农机化学报, 2020, 41(6): 154-158.
4	REN Q, YANG B. Application of image processing technology in field weed identification[J]. Chinese Journal of Agricultural Mechanization, 2020, 41(6) :154-158.
5	SIDDIQI M H, AHMAD I, SULAIMAN S B. Weed recognition based on erosion and dilation segmentation algorithm[C]// 2009 International Conference on Education Technology and Computer. Piscataway, New York, USA: IEEE, 2009: 224-228.
6	LOTTES P, HOEFERLIN M, SANDER S, et al. An effective classification system for separating sugar beets and weeds for precision farming applications[C]// 2016 IEEE International Conference on Robotics and Automation (ICRA). Piscataway, New York, USA: IEEE, 2016: 5157-5163.
7	CICCO M D, POTENA C, GRISETTI G, et al. Automatic model based dataset generation for fast and accurate crop and weeds detection[C]// 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, New York, USA: IEEE, 2017: 5188-5195.
8	CZYMMEK V, HARDERS L O, KNOLL F J, et al. Vision-based deep learning approach for real-time detection of weeds in organic farming[C]// 2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). Piscataway, New York, USA: IEEE, 2019: 1-5.
9	彭文, 兰玉彬, 岳学军, 等. 基于深度卷积神经网络的水稻田杂草识别研究[J]. 华南农业大学学报, 2020(6): 75-81.
9	PENG W, LAN Y, YUE X, et al. Research on weed identification in rice paddy field based on deep convolutional neural network[J]. Journal of South China Agricultural University, 2020(6): 75-81.
10	魏靖, 王玉亭, 袁会珠, 等. 基于深度学习与特征可视化方法的草地贪夜蛾及其近缘种成虫识别[J]. 智慧农业(中英文), 2020, 2(3): 75-85.
10	WEI J, WANG Y, YUAN H, et al. Identification and morphological analysis of adult spodoptera frugiperda and its close related species using deep learning[J]. Smart Agriculture, 2020, 2(3): 75-85.
11	王璨, 武新慧, 李志伟. 基于卷积神经网络提取多尺度分层特征识别玉米杂草[J]. 农业工程学报, 2018, 34(5): 144-151.
11	WANG C, WU X, LI Z. Extraction of multi-scale layered features for identification of maize weeds based on convolutional neural network[J]. Transactions of the CSAE, 2012, 34(5): 144-151.
12	UTTAR_P. An experimental set up for utilizing convolutional neural network in automated weed detection[C]// 2019 4th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU). Ghaziabad, India: Department of CS, 2019: 1-6.
13	RIST Y, SHENDRYK I, DIAKOGIANNIS F, et al. Weed mapping using very high resolution satellite imagery and fully convolutional neural network[C]// IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. Yokohama, Japan: IGARSS, 2019: 9784-9787.
14	UMAMAHESWARI S, ARJUN R, MEGANATHAN D. Weed detection in farm crops using parallel image processing[C]// 2018 Conference on Information and Communication Technology (CICT). Jabalpur, India: CIC, 2018: 1-4.
15	CFAWAKHERJI M, YOUSSEF A, BLOISI D, et al. Crop and weeds classification for precision agriculture using context-independent pixel-wise segmentation[C]// 2019 Third IEEE International Conference on Robotic Computing (IRC). Piscataway, New York, USA: IEEE, 2019: 146-152.
16	VEDULA R, NANDA A, GOCHHAYAT S S, et al. Computer vision assisted autonomous intra-row weeder[C]// 2018 International Conference on Information Technology (ICIT). Bhubaneswar, India: ICIT, 2018: 79-84.
17	BABIKER I, XIE W, CHEN G. Recognition of dandelion weed via computer vision for a weed removal robot[C]// 2019 1st International Conference on Industrial Artificial Intelligence (IAI). Shenyang, China: Industrial and Aerospace Engineering Concordia University Montreal Quebec Canada, 2019: 1-6.
18	SARVINI T, SNEHA T, GOWTHAMI G S S, et al. Performance comparison of weed detection algorithms[C]// 2019 International Conference on Communication and Signal Processing (ICCSP). Piscataway, New York, USA: IEEE, 2019: 843-847.
19	BARRERO O, PERDOMO S A. RGB and multispectral UAV image fusion for Gramineae weed detection in rice fields[J]. Precision Agriculture, 2018, 19: 809-822.
20	TEJEDA A J I, CASTRO R C. Algorithm of weed detection in crops by computational vision[C]// 2019 International Conference on Electronics, Communications and Computers (CONIELECOMP). Cholula, Mexico: CONIELECOMP, 2019: 124-128.
21	BAH M D, HAFIANE A, CANALS R. Weeds detection in UAV imagery using SLIC and the Hough transform[C]// 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA). Piscataway, New York, USA: IEEE, 2017: 1-6.
22	BAKHSHIPOUR A, JAFARI A. Evaluation of support vector machine and artificial neural networks in weed detection using shape features[J]. Computers and Electronics in Agriculture, 2018, 145: 153-160.
23	TANG J, CHEN X, MIAO R, et al. Weed detection using image processing under different illumination for site-specific areas spraying[J]. Computers and Electronics in Agriculture, 2016, 122: 103-111.
24	WANG A, ZHANG W, WEI X. A Review on weed detection using ground-based machine vision and image processing techniques[J]. Computers and Electronics in Agriculture, 2019, 158: 226-240.
25	BAKHSHIPOUR A, JAFARI A, NASSIRI S M, et al. Weed segmentation using texture features extracted from wavelet sub-images[J]. Biosystems Engineering, 2017, 157: 1-12.
26	张燕, 李庆学, 吴华瑞. 基于核相互子空间法的番茄叶部病害快速识别模型[J]. 智慧农业(中英文), 2020, 2(3): 86-97.
26	ZHANG Y, LI Q, WU H. Rapid recognition model of tomato leaf diseases based on kernel mutual subspace method[J]. Smart Agriculture, 2020, 2(3): 86-97.
27	MCCOOL C S, BEATTIE J, FIRN J, et al. Efficacy of mechanical weeding tools: A study into alternative weed management strategies enabled by robotics[J]. IEEE Robotics and Automation Letters, 2018, 3(2): 1184-1190.

[1]	许骞, 蔡健荣, 杜灿, 孙力, 白竣文. 基于软X射线成像技术的柑橘内部浮皮和枯水检测[J]. 智慧农业(中英文), 2021, 3(4): 53-65.
[2]	李燕, 沈杰, 谢航, 高广垠, 刘建雄, 刘洁. 基于轮廓坐标系转换拟合的柚子果形检测分级方法[J]. 智慧农业(中英文), 2021, 3(1): 86-95.
[3]	周航, 张顺路, 翟毅豪, 王松, 张春龙, 张俊雄, 李伟. 天然橡胶割胶机器人视觉伺服控制方法与割胶试验[J]. 智慧农业（中英文）, 2020, 2(4): 56-64.
[4]	丁幼春, 王绪坪, 彭靖叶, 夏中州. 轮式谷物联合收获机视觉导航系统设计与试验[J]. 智慧农业（中英文）, 2020, 2(4): 89-102.
[5]	韩书庆, 张晶, 程国栋, 彭英琦, 张建华, 吴建寨. 奶牛跛行自动识别技术研究现状与挑战[J]. 智慧农业（中英文）, 2020, 2(3): 21-36.
[6]	FLORESPaulo, MATHEWJithin, JAHANNusrat, STENGERJohn. 利用图像和机器学习检测大豆作物幼苗期玉米杂苗[J]. 智慧农业（中英文）, 2020, 2(3): 61-74.
[7]	季云洲, 都盛佳, 纪同奎, 宋怀波. 基于嵌入式系统的小麦条锈病远程监测平台设计与试验[J]. 智慧农业, 2019, 1(3): 100-112.