深度学习在杂草识别领域的研究现状与展望

doi:10.13733/j.jcam.issn.20955553.2022.09.019

摘要/Abstract

摘要： 使用深度学习精准识别杂草实现使用农药减量、增效、安全的目标受到研究人员的广泛关注。因此综述近年来国内外使用深度学习算法对不同作物的杂草进行识别检测的研究进展，重点从数据获取、算法选择、优化部分、识别效果等方面总结研究现状，指出其在数据集建立费时费力、田间识别精度低、算法设备部署困难、实时性与准确率不能兼得等方面的问题，并提出解决方案，同时展望数据集建立简易和准确，算法模型结构轻量和鲁棒性强，便于部署移动设备的发展趋势以及未来应用的方法，为后续杂草精准化清除研究提供参考。

关键词: 精准化, 深度学习, 杂草识别, 数据获取, 模型优化

Abstract: The use of deep learning to accurately identify weeds to achieve the goals of pesticide reduction, efficiency and safety has been widely concerned by researchers. Therefore, the research progress of using deep learning algorithms to identify and detect weeds of different crops in recent years is reviewed at home and abroad. The review status is summarized from the aspects of data acquisition, algorithm selection, optimization and recognition effect. It points out that the problems of timeconsuming and laborious data set establishment, low accuracy of field recognition, algorithm equipment deployment difficulty, realtime performance and accuracy cannot be both, and also proposes solutions. Meanwhile, it prospects the development trend of easy and accurate data set establishment, lightweight and robust algorithm model structure, and easy deployment of mobile devices, and methods for future applications., which will provide a reference for the subsequent research on precise weed removal.

Key words: precision, deep learning, weed recognition, data collection, model optimization

中图分类号:

TP391.4

李东升, 胡文泽, 兰玉彬, 范明洪, 李翠云, 朱俊科. 深度学习在杂草识别领域的研究现状与展望[J]. 中国农机化学报, 2022, 43(9): 137-144.

Li Dongsheng, Hu Wenze, Lan Yubin, Fan Minghong, Li Cuiyun, Zhu Junke.. Research status and prospect of deep learning in weed recognition[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(9): 137-144.

参考文献

［1］　
强胜. 我国杂草学研究现状及其发展策略［J］. 植物保护, 2010, 36(4): 1-5.

Qiang Sheng. Current status and development strategy for weed science in China ［J］. Plant Protection, 2010, 36(4): 1-5.

［2］　
陈德润, 王书茂, 王秀. 农田杂草识别技术的现状与展望［J］. 中国农机化, 2005(2): 35-38.

Chen Derun, Wang Shumao, Wang Xiu. Status and prospect for recognition technology of farm weeds ［J］. Chinese Agricultural Mechanization, 2005(2): 35-38.

［3］　
李香菊. 近年我国农田杂草防控中的突出问题与治理对策［J］. 植物保护, 2018, 44(5): 77-84.

Li Xiangju. Main problems and management strategies of weeds in agricultural fields in China recent year ［J］. Plant Protection, 2018, 44(5): 77-84.

［4］　
马志艳, 朱熠, 杨磊. 基于视觉的苗期作物株间除草关键技术研究现状［J］. 中国农机化学报, 2020, 41(2): 32-38.

Ma Zhiyan, Zhu Yi, Yang Lei. Research status of key techniques of interplant weeding in seedling crops based on vision ［J］. Journal of Chinese Agricultural Mechanization, 2020, 41(2): 32-38.

［5］　
杨峰山, 孙丛, 鲍霞霞, 等. 5类化学除草剂在作物中残留分析的研究进展［J］. 中国农学通报, 2021, 37(10): 136-141.

Yang Fengshan, Sun Cong, Bao Xiaxia, et al. Residue analysis of five chemical herbicides in crops: Research progress ［J］. Chinese Agricultural Science Bulletin, 2021, 37(10): 136-141.

［6］　
Champ J, MoraFallas A, Goau H, et al. Instance segmentation for the fine detection of crop and weed plants by precision agricultural robots ［J］. Applications in Plant Sciences, 2020, 8(7).

［7］　
Hasan A, Sohel F, Diepeveen D, et al. A survey of deep learning techniques for weed detection from images ［J］. Computers and Electronics in Agriculture, 2021, 184(3): 106067.

［8］　
Hong J, Lan Y, Yue X, et al. Adaptive target spray system based on machine vision for plant protection UAV ［J］. International Journal of Precision Agricultural Aviation, 2018, 1(1): 65-71.

［9］　
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.

Ren Quanhui, Yang Baohai. Application of image processing technology in weed recognition in field ［J］. Journal of Chinese Agricultural Mechanization, 2020, 41(6): 154-158.

［10］　
李扬. 机器学习在农业领域应用现状与前景［J］. 安徽农学通报, 2021, 27(1): 164-165, 174.

Li Yang. Application status and prospect of machine learning in agriculture ［J］. Anhui Agricultural Science Bulletin, 2021, 27(1): 164-165, 174.

［11］　
吕盛坪, 李灯辉, 冼荣亨. 深度学习在我国农业中的应用研究现状［J］. 计算机工程与应用, 2019, 55(20): 24-33, 51.

Lü Shengping, Li Denghui, Xian Rongheng. Research status of deep learning in agriculture of China ［J］. Computer Engineering and Applications, 2019, 55(20): 24-33, 51.

［12］　
Dos Santos Ferreira A, Freitas D M, Da Silva G G, et al. Unsupervised deep learning and semiautomatic data labeling in weed discrimination ［J］. Computers and Electronics in Agriculture, 2019, 165: 104963.

［13］　
李志伟. 机器学习发展及几种学习方式［J］. 产业与科技论坛, 2016, 15(10): 198-199.

［14］　
陈嘉博. 机器学习算法研究及前景展望［J］. 信息通信, 2017(6): 5-6.

［15］　
孙志军, 薛磊, 许阳明, 等. 深度学习研究综述［J］. 计算机应用研究, 2012, 29(8): 2806-2810.

Sun Zhijun, Xue Lei, Xu Yangming, et al. Overview of deep learning ［J］. Application Research of Computers, 2012, 29(8): 2806-2810.

［16］　
谭笑枫, 李广帅. 深度学习发展综述［A］. 中国地球物理学会国家安全地球物理专业委员会、陕西省地球物理学会军事地球物理专业委员会. 国家安全地球物理丛书（十五）——丝路环境与地球物理［C］. 中国地球物理学会国家安全地球物理专业委员会、陕西省地球物理学会军事地球物理专业委员会: 中国地球物理学会, 2019.

［17］　
Lecun Y, Bottou L. Gradientbased learning applied to document recognition ［J］. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

［18］　
Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets ［J］. Neural Computation, 2006, 18(7): 1527-1554.

［19］　
邓向武, 齐龙, 马旭, 等. 基于多特征融合和深度置信网络的稻田苗期杂草识别［J］. 农业工程学报, 2018, 34(14): 165-172.

Deng Xiangwu, Qi Long, Ma Xu, et al. Recognition of weeds at seedling stage in paddy fields using multifeature fusion and deep belief networks ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(14): 165-172.

［20］　
Goodfellow I, PougetAbadie J, Mirza M, et al. Generative adversarial nets ［J］. Advances in neural information processing systems, 2014, 27: 2672-2680.

［21］　
Fawakherji M, Potena C, Prevedello I, et al. Data augmentation using GANs for crop/weed segmentation in precision farming ［C］. 2020 IEEE Conference on Control Technology and Applications (CCTA). IEEE, 2020: 279-284.

［22］　
周飞燕, 金林鹏, 董军. 卷积神经网络研究综述［J］. 计算机学报, 2017, 40(6): 1229-1251.

Zhou Feiyan, Jin Linpeng, Dong Jun. Review of convolutional neural networks ［J］. Chinese Journal of Computers, 2017, 40(6): 1229-1251.

［23］　
陈辉东, 丁小燕, 刘艳霞. 基于深度学习的目标检测算法综述［J］. 北京联合大学学报, 2021, 35(3): 39-46.

Chen Huidong, Ding Xiaoyan, Liu Yanxia. Review of target detection algorithm based on deep learning ［J］. Journal of Beijing Union University, 2021, 35(3): 39-46.

［24］　
Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation ［J］. IEEE Computer Society, 2013.

［25］　
Girshick R. Fast R-CNN ［J］. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015.

［26］　
Ren Shaoqing, He Kaiming, Ross Girshick, et al. Faster R-CNN: Towards realtime object detection with region proposal networks ［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149.

［27］　
Redmon J, Farhadi A. YOLOv3: An incremental improvement ［J］. arXiv eprints, 2018.

［28］　
Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, realtime object detection ［C］. Computer Vision & Pattern Recognition. IEEE, 2016.

［29］　
Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector ［C］. European conference on computer vision. Springer, Cham, 2016: 21-37.

［30］　
卢旭, 刘钊. 基于深度学习的图像语义分割技术综述［J］. 软件导刊, 2021, 20(1): 242-244.

Lu Xu, Liu Zhao. A review of image semantic segmentation based on deep learning ［J］. Software Guide, 2021, 20(1): 242-244.

［31］　
黄旭, 张世义, 李军. 图像分割技术研究综述［J］. 装备机械, 2021(2): 6-9.

［32］　
Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation ［C］. Proceedings of the IEEE conference on computer vision and pattern recognition, 2015: 3431-3440.

［33］　
Badrinarayanan V, Kendall A, Cipolla R. Segnet: A deep convolutional encoderdecoder architecture for image segmentation ［J］. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(12): 2481-2495.

［34］　

Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation ［C］. International Conference on Medical Image Computing and ComputerAssisted Intervention, 2015.

［35］　
赵小虎, 李晓. 基于语义分割的农作物病害识别综述研究［J］. 现代计算机, 2021(18): 122-126.

Zhao Xiaohu, Li Xiao. Survey of crop disease recognition based on semantic segmentation ［J］. Modern Computer, 2021(18): 122-126.

［36］　
He Kaiming, Gkioxari G, Dolla＇r P, et al. Mask R-CNN ［C］. IEEE Transactions on Pattern Analysis & Machine Intelligence. IEEE, 2017.

［37］　
刘钦. 乡村振兴战略背景下我国蔬菜产业发展分析［J］. 北方园艺, 2020(4): 142-147.

Liu Qin. Analysis of vegetable industry development under the background of rural revitalization strategy ［J］. Northern Horticulture, 2020(4): 142-147.

［38］　
Osorio K, Puerto A, Pedraza C, et al. A deep learning approach for weed detection in lettuce crops using multispectral images ［J］. Agri Engineering, 2020, 2(3): 471-488.

［39］　
Gao J, French A P, Pound M P, et al. Deep convolutional neural networks for imagebased Convolvulus sepium detection in sugar beet fields ［J］. Plant Methods, 2020, 16(1): 1-12.

［40］　
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.

Shang Jianwei, Jiang Honghai, Yu Gang, et al. Weed identification system based on deep learning ［J］. Software Guide, 2020, 19(7): 127-130.

［41］　
喻刚, 蒋红海, 孙腾飞, 等. 基于深度学习的白菜田杂草分割［J］. 软件, 2020, 41(4): 211-215.

Yu Gang, Jiang Honghai, Sun Tengfei, et al. Weed identification in cabbage field based on deep learning ［J］. Computer Engineering & Software, 2020, 41(4): 211-215.

［42］　
EspejoGarcia B, Mylonas N, Athanasakos L, et al. Combining generative adversarial networks and agricultural transfer learning for weeds identification ［J］. Biosystems Engineering, 2021, 204: 79-89.

［43］　
张宋超, 薛新宇, 孙涛, 等. 植保无人飞机油菜杂草防治与效果评估研究［J］. 中国农机化学报, 2019, 40(9): 48-53, 59.

Zhang Songchao, Xue Xinyu, Sun Tao, et al. Study on weed control of plant protection UAV and effect evaluation in rape filed ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(9): 48-53, 59.

［44］　
张乐, 金秀, 傅雷扬, 等. 基于Faster R-CNN深度网络的油菜田间杂草识别方法［J］. 激光与光电子学进展, 2020, 57(2): 304-312.

Zhang Le, Jin Xiu, Fu Leiyang, et al. Recognition method for weeds in rapeseed field based on Faster R-CNN deep network ［J］. Laser & Optoelectronics Progress, 2020, 57(2): 304-312.

［45］　
Abdalla A, Cen H, Wan L, et al. Finetuning convolutional neural network with transfer learning for semantic segmentation of groundlevel oilseed rape images in a field with high weed pressure ［J］. Computers and Electronics in Agriculture, 2019, 167: 105091.

［46］　
Asad M H, Bais A. Weed detection in canola fields using maximum likelihood classification and deep convolutional neural network ［J］. Information Processing in Agriculture, 2020, 7(4): 535-545.

［47］　
Partel V, Kakarla S C, Ampatzidis Y. Development and evaluation of a lowcost and smart technology for precision weed management utilizing artificial intelligence ［J］. Computers and Electronics in Agriculture, 2019, 157: 339-350.

［48］　
卢秀茹, 贾肖月, 牛佳慧. 中国棉花产业发展现状及展望［J］. 中国农业科学, 2018, 51(1): 26-36.

Lu Xiuru, Jia Xiaoyue, Niu Jiahui. The present situation and prospects of cotton industry development in China ［J］. Scientia Agricultura Sinica, 2018, 51(1): 26-36.

［49］　
EspejoGarcia B, Mylonas N, Athanasakos L, et al. Towards weeds identification assistance through transfer learning ［J］. Computers and Electronics in Agriculture, 2020, 171: 105306.

［50］　
许燕, 温德圣, 周建平, 等. 基于Faster R-CNN的新疆棉花幼苗与杂草识别方法［J］. 排灌机械工程学报, 2021, 39(6): 602-607.

Xu Yan, Wen Desheng, Zhou Jianping, et al. Identification method of cotton seedlings and weeds in Xinjiang based on Faster R-CNN ［J］. Journal of Drainage and Irrigation Machinery Engineering, 2021, 39(6): 602-607.

［51］　
彭明霞, 夏俊芳, 彭辉. 融合FPN的Faster R-CNN复杂背景下棉田杂草高效识别方法［J］. 农业工程学报, 2019, 35(20): 202-209.

Peng Mingxia, Xia Junfang, Peng Hui. Efficient recognition of cotton and weed in field based on Faster R-CNN by integrating FPN ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(20): 202-209.

［52］　
Chen D, Lu Y, Li Z, et al. Performance evaluation of deep transfer learning on multiclass identification of common weed species in cotton production systems［J］. Computers and Electronics in Agriculture, 2022, 198: 107091.

［53］　
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, 41(6): 75-81.

Peng Wen, Lan Yubin, Yue Xuejun, et al. Research on paddy weed recognition based on deep convolutional neural network ［J］. Journal of South China Agricultural University, 2020, 41(6): 75-81.

［54］　
Huang Huasheng, Lan Yubin, Yang Aqing, et al. Deep learning versus objectbased image analysis (OBIA) in weed mapping of UAV imagery ［J］. International Journal of Remote Sensing, 2020, 41(9): 3446-3479.

［55］　
Zhang Rufei, Wang Cong, Hu Xiaoping, et al. Weed location and recognition based on UAV imaging and deep learning ［J］. International Journal of Precision Agricultural Aviation, 2018, 1(1): 25-31.

［56］　
Kumar J R D, Babu C G, Priyadharsini K. An experimental investigation to spotting the weeds in rice field using deepnet ［J］. Materials Today: Proceedings, 2021, 45(12): 8041-8053.

［57］　
Ma Xu, Deng Xiangwu, Qi Long, et al. Fully convolutional network for rice seedling and weed image segmentation at the seedling stage in paddy fields ［J］. PLoS ONE, 2019, 14(4).

［58］　
崔爱民, 张久刚, 张虎, 等. 我国玉米生产现状及发展变革［J］. 中国农业科技导报, 2020, 22(7): 10-19.

Cui Aimin, Zhang Jiugang, Zhang Hu, et al. Preliminary exploration on current situation and development of maize production in China ［J］. Journal of Agricultural Science and Technology, 2020, 22(7): 10-19.

［59］　
徐艳蕾, 何润, 翟钰婷, 等. 基于轻量卷积网络的田间自然环境杂草识别方法［J/OL］. 吉林大学学报(工学版): 1-10［2021-09-03］.

［60］　
Mads Dyrmann, Henrik Karstoft, Henrik Skov Midtib. Plant species classification using deep convolutional neural network ［J］. Biosystems Engineering, 2016, 151: 72-80.

［61］　
权龙哲, 吴冰, 毛首人. 基于Mask R-CNN农田杂草实例分割与叶龄识别方法［J］. 东北农业大学学报, 2021, 52(4): 65-76.

Quan Longzhe, Wu Bing, Mao Shouren. Method for segmentation and leaf age recognition of farmland weeds based on Mask R-CNN ［J］. Journal of Northeast Agricultural University, 2021, 52(4): 65-76.

［62］　
Wang Aichen, Zhang Wen, Wei Xinhua. A review on weed detection using groundbased machine vision and image processing techniques ［J］. Computers and Electronics in Agriculture, 2019, 158: 226-240.

[1]	王晓婷, , 赵展, , 王阳, 李林, . 基于改进Mask R-CNN的植物表型智能检测算法[J]. 中国农机化学报, 2022, 43(8): 151-157.
[2]	孙逸飞, , , 柳平增, , , 张艳, , , 宋长青, , , 张大雷, 马学文. 基于Sentinel-2A遥感影像的潍坊市冬小麦种植面积提取研究[J]. 中国农机化学报, 2022, 43(7): 98-105.
[3]	张三林, 张立萍, 郑威强, 郭壮, 付子强. 基于YOLOv5的核桃品种识别与定位[J]. 中国农机化学报, 2022, 43(7): 167-172.
[4]	史方青, 王虎林, 黄华. 基于卷积神经网络的马铃薯芽眼检测识别研究[J]. 中国农机化学报, 2022, 43(6): 159-165.
[5]	曹金凤, 沈大港, 郭继鸿, 刘鹏, 李策, 兰添贺. 基于CNN和SVM分类优化的大蒜鳞芽朝向识别研究[J]. 中国农机化学报, 2022, 43(5): 134-139.
[6]	雷雪梅, 张光强, 姚旗, 刘伟渭, 邱帅. 基于卷积神经网络的农机图像自动识别研究[J]. 中国农机化学报, 2022, 43(5): 140-147.
[7]	陈国防, , 陈兆英, , 王玉亮, , 王金星, , 范国强, , 李汉卿, . 基于数据增强深度学习的苹果花检测方法研究[J]. 中国农机化学报, 2022, 43(5): 148-155.
[8]	李贤哲, 张辉, 徐立友, 刘孟楠, , 闫祥海, , 张明柱. 液力机械复合传动拖拉机动力系统匹配特性研究[J]. 中国农机化学报, 2022, 43(4): 46-52.
[9]	张燕斌, , 杜健民, 王圆, , 皮伟强, 高新超. 基于无人机高光谱遥感和3D-ResNet的荒漠草原地物分类[J]. 中国农机化学报, 2022, 43(4): 66-73.
[10]	何颖, 陈丁号, 彭琳. 基于改进YOLOv5模型的经济林木虫害目标检测算法研究[J]. 中国农机化学报, 2022, 43(4): 106-115.
[11]	项新建, 宋晓敏, 郑永平, 王海波, 方政洋. 基于MobileNet-YOLO的嵌入式人脸检测研究#br# #br# [J]. 中国农机化学报, 2022, 43(4): 124-130.
[12]	董萍, 卫梦华, 时雷, 郭伟. 迁移学习在玉米叶片病害识别中的研究与应用[J]. 中国农机化学报, 2022, 43(3): 146-152.
[13]	张继成, 李德顺. 基于深度残差学习的成熟草莓识别方法[J]. 中国农机化学报, 2022, 43(2): 136-142.
[14]	陈启, 陈慈发, 邓向武, 袁单飞. 基于移动端轻量模型的杂草分类方法研究[J]. 中国农机化学报, 2022, 43(2): 163-170.
[15]	陈继清, 韦德鹏, 龙腾, 罗天, 王桦彬. 基于卷积神经网络的害虫分类[J]. 中国农机化学报, 2022, 43(11): 188-194.