基于机器视觉的植物病虫害实时识别方法

doi:10.11924/j.issn.1000-6850.casb14120117

摘要/Abstract

摘要： 植物病虫灾害是中国三大自然灾害之一，其识别、监测、预警是防控工作的决策信息源头。联合国粮农组织的研究表明，仅农作物病虫害危害自然损失率就超过37%。中国是包括农作物在内的植物病虫害危害大国，若不采取防控措施，因病虫危害每年将损失粮食1500亿kg、果品与蔬菜1000亿kg、油料68亿kg、棉花1.9亿kg，潜在经济损失在5000亿元以上。通过植物病虫害的在线、实时、低廉、无损伤机器识别，不仅为植物病虫害防治防控提供了依据，赢得了防治时间，而且结合病虫害防治系统，最大限度地减少了经济损失，植物尤其是农产品品质得到了提升。对多种植物病虫害机器识别研究进行了综述与归纳，剖析了机器识别中的问题，认为未来的植物病虫害机器识别措施上应与病虫害监控、预测预报相结合；技术上融合机器视觉、声学、遥感、全球定位系统、地理信息系统、网络等技术；功能上进行草害信息、植物生长信息、生长环境信息自动识别等功能拓展。

关键词: 蒸发皿蒸发量, 蒸发皿蒸发量, 陕西省, Mann-Kendall突变检验, IDW插值法, 时空变化

Abstract: Plant diseases and pests is one of the three major natural disasters in China, its identification, monitoring and early warning is the information source of decision-making for prevention and control. The research results from Food and Agricultural Organization of United Nations show that natural loss rate of crop is more than 37% just because of crop diseases and pests. And China is a country with frequent and grave disasters of plant diseases and pests, without prevention and control measures against crop diseases and pests, about 150 billion kilograms of food crops, 6.8 billion kilograms of oil crops, 190 million kilograms of cotton, 100 billion kilograms of fruit and vegetables will be lost every year, and the economic loss will be more than 500 billion yuan. A low-cost nondestructive online real-time machine recognition system of plant diseases and pests will provide information for prevention and control of plant diseases and pests, set aside time for pest control system, minimize the economic loss, and improve quality and quantity of plants especially agricultural products. Research on machine recognition of plant diseases and pests is reviewed in this paper. Problems in recognition are summarized and analyzed, and solutions and future direction are presented, including recognition combined with prediction and pest control; fusion with remote sensing, global positioning system, geography information system, acoustics, machine vision, network technology; providing identification information about diseases and pests, plant growth and growth environment.

曹乐平. 基于机器视觉的植物病虫害实时识别方法[J]. 中国农学通报, 2015, 31(20): 244-249.

Cao Leping. The Research Progress on Machine Recognition of Plant Diseases and Insect Pests[J]. Chinese Agricultural Science Bulletin, 2015, 31(20): 244-249.

参考文献

[1] 江宜航.专家呼吁农作物病虫害防治立法[J]. 农药市场信息,2010,15(18):7.
[2] 陈兵,李少昆,王克如,等.基于TM影像光谱指数的棉花病害严重度估测[J]. 红外与毫米波学报,2011,30(5):451-457.
[3] 陈兵,王克如,李少昆,等.蚜虫胁迫下棉叶光谱特征及其遥感估测[J]. 光谱学与光谱分析,2010,30(11):3093-3097.
[4] 刘明辉,沈佐锐,高灵旺,等.基于WebGIS的农业病虫害预测预报专家系统[J]. 农业机械学报,2009,40(7):180-186.
[5] Zhao J H, Liu M H, Yao M Y. Study on Image Recognition of Insect Pest of Sugarcane Cotton Aphis Based on Rough Set and Fuzzy C-means Clustering[A]. 2009 Third International Symposium on Intelligent Information Technology Application[C], IEEE Transations,2009:553-555.
[6] 周龙.基于机器视觉的储粮害虫图像模糊检测方法研究[J].计算机应用与软件,2005,22(18):24-25.
[7] 陈月华,胡晓光,张长利.基于计算机视觉的小麦害虫分割算法研究[J].农业工程学报,2007,23(12):187-190.
[8] 黄星奕,林冬瑾,朱圣波,等.基于计算机视觉的鞘翅目害虫自动鉴定[J].微计算机信息,2008,24(3):303-305,111.
[9] 杨红珍,张建伟,李湘涛,等.基于图像的昆虫远程自动识别系统的研究[J].农业工程学报,2008,24(1):188-192.
[10] Paul B, Vincent M, Sabine M. A cognitive vision approach to early pest detection in greenhouse crops[J]. computers and electronics in agriculture,2008(62):81-93.
[11] Alireza A, Masood Amir-maafi. A Decision Support System For Management Of Sunn Pest (Eurygaster Integriceps Puton.) In Wheat[A]. Computers in Agriculture and Natural Resources, 4th World Congress Conference,Proceedings of the 24-26 July 2006 (Orlando, Florida USA)Publication Date 24 July 2006,ASABE Publication:413-417.
[12] Maghirang E B, Dowell F E, Baker J E, et al. Automated detection of single wheat kernels containing live or dead insects using near–infrared reflectance spectroscopy[J]. Transactions of the ASAE,2003,46(4):1277-1282.
[13] Abdul R M S, Yap Y A, Wong T H, et al. Automated Identification And Counting Of Pests In The Paddy Fields Using Image Analysis[A]. Computers in Agriculture and Natural Resources, 4th World Congress Conference[C], Proceedings of the 24-26 July 2006 (Orlando, Florida USA),ASABE Publication:759-764.
[14] Juan X, Daniel G. Detecting internal insect infestation in tart cherry using transmittance spectroscopy[J]. Postharvest Biology and Technology,2008(49):411-416.
[15] Maghirang E B, Dowell F E, Baker J E, et al. Detecting Single Wheat Kernels Containing Live or Dead Insects Using Near-Infrared Reflectance Spectroscopy[A]. 2002 ASAE Annual International Meeting / CIGR XVth World Congress Sponsored by ASAE and CIGR[C], Hyatt Regency Chicago,Chicago, Illinois, USA, July 28-July 31,2002:1-10.
[16] Murakami S, Homma K, Koike T. Detection of small pests on vegetable leaves using GLCM[A]. 2005 ASAE Annual International Meeting Sponsored by ASAE[C], Tampa Convention Center,Tampa, Florida,17-20 July 2005:1-9.
[17] Saleh A, Paul W, John S, et al. Identifying Pecan Weevils through Image Processing Techniques Based on Template Matching[A]. 2007 ASABE Annual International Meeting Sponsored by ASABE[c],Minneapolis Convention Center, Minneapolis, Minnesota,17-20 June 2007:1-14.
[18] Michio K, Francis J P, Douglas B W, et al. Laser Sensor-based Trunk Detection System for Targeted Pest Control in Vineyards[A]. 2009 ASABE Annual International Meeting Sponsored by ASABE[C],Grand Sierra Resort and Casino,Reno, Nevada,June 21-June 24, 2009:1-10.
[19] Daniel G, Diwan A, Bim S, et al. Opto-Electronic determination of insect presence in fruit[A]. 2006 ASABE Annual International Meeting Sponsored by ASABE[C], Oregon Convention Center,Portland, Oregon, 9-12 July 2006:1-21.
[20] Luis O Solis-Sánchez, Rodrigo Casta?eda-Miranda, Juan J García-Escalante, et al. Scale invariant feature approach for insect monitoring[J]. Computers and Electronics in Agriculture,2011(75):92-99.
[21] Van Li, Xia C L, Jangmyung Lee. Vision-based Pest Detection and Automatic Spray of Greenhouse Plant[A]. IEEE International Symposium on Industrial Electronics (ISlE 2009)[C], Seoul Olympic Parktel, Seoul, Korea, July 5-8, 2009:920-925.
[22] Sirisomboon P, Hashimoto Y, Tanaka M. Study on non-destructive evaluation methods for defect pods for green soybean processing by near-infrared Spectroscopy[J]. Journal of Food Engineering,2009(93):502-512.
[23] Wu D K, Xie C Y, Ma C W. The SVM Classification Leafminer-infected Leaves Based on Fractal Dimension[A].2008 International Conference on Computational Intelligence and Security[C], IEEE Transations,2008:147-151.
[24] 黎移新.柑橘病虫害疤痕的计算机视觉识别[J].食品与机械,2009,25(3):78-81.
[25] Wu D K, Ma C W. The Support Vector Machine (SVM) Based Near-Infrared Spectrum Recognition of Leaves Infected by the Leafminers[A]. Proceedings of the First International Conference on Innovative Computing, Information and Control (ICICIC'06)[C],IEEE Transactions,2006:1-4.
[26] Sena Jr D G, Pinto F A C, Queiroz D M, et al. Fall Armyworm Damaged Maize Plant Identification using Digital Images[J]. Biosystems Engineering,2003,85(4):449-454.
[27] Chandra B S, Digvir S J, Jitendra P, et al. White.Identification of insect-damaged wheat kernels using short-wave near-infrared hyperspectral and digital colour imaging[J]. Computers and Electronics in Agriculture,2010(73):118-125.
[28] Zandonadi R S, Pinto F A C, Sena D G, et al. Mantovani. Identification of Lesser Cornstalk Borer-attacked Maize Plants using Infrared Images[J]. Biosystems Engineering,2005,91(4):433-439.
[29] Zhao J H, Luo X W, Liu M H, et al. Application of BP Neural Network to Sugarcane Diseased Spots Classification[A]. Second International Symposium on Intelligent Information Technology Application[C], IEEE Transations,2008:422-425.
[30] Li J H, Gao L W, Shen Z R. Extraction and analysis of digital images feature of three kinds of wheat diseases[A]. 2010 3rd International Congress on Image and Signal Processing (CISP2010)[C], IEEE Transations,2010:2543-2548.
[31] 王守志,何东健,李文,等.基于核K-均值聚类算法的植物叶部病害识别[J].农业机械学报,2009,40(3):152-155.
[32] 赵玉霞,王克如,白中英,等.基于图像识别的玉米叶部病害诊断研究[J].中国农业科学,2007,40(4):698-703.
[33] 谭峰,马晓丹.基于叶片的植物病虫害识别方法[J].农机化研究,2009,31(6):41-43.
[34] Lai J C, Ming B, Li S K, et al. An Image-Based Diagnostic Expert System for Corn Diseases[J]. Agricultural Sciences in China,2010,9(8):1221-1229.
[35] Donahue D W, Sowell R S, Powell N T, et al. An expert system for diagnosing diseases of tobacco[J]. American Society of Agricultural Engineers,1991,7(4):499-503.
[36] Qin J W, Thomas F B, Dae G K, et al. Classification of Citrus Peel Diseases Using Color Texture Feature Analysis[A]. Food Processing Automation Conference CD-Rom[C]. Proceedings of the 28-29 June 2008 Conference (Providence, Rhode Island) Publication date 28 June 2008,ASABE Publication:1-9.
[37] Yutaka S, Masato S. Construction of the Automatic Diagnosis System ofPlant Disease Using Genetic Programming Which Paid Its Attention to Variety[A]. 2003 ASAE Annual International Meeting Sponsored by ASAE[C], Riviera Hotel and Convention Center Las Vegas, Nevada, USA,27- 30 July 2003,1-13.
[38] Qin J W, Thomas F B, Mark A R, et al. Detecting Citrus Canker by Hyperspectral Reflectance Imaging and Spectral Information Divergence[A]. 2008 ASABE Annual International Meeting Sponsored by ASABE[C],Rhode Island Convention Center Providence, Rhode Island June 29 – July 2, 2008,1-15.
[39] Polder G, van der Heijden G W A M, van Doorn J, et al. Detection of the tulip breaking virus (TBV) in tulips using optical sensors[J]. Precision Agriculture,2010(11):397-412.
[40] Zhao X, Burks T F, Qin J, et al. Digital microscopic imaging for citrus peel disease classification using color texture features[J]. Applied Engineering in Agriculture,2009,25(5):769-776.
[41] Pydipati R, Burks T F, Lee W S. Identification of citrus disease using color texture features and discriminant analysis[J]. Computers and Electronics in Agriculture,2006(52):49-59.
[42] Camargo A, Smith J S. Image pattern classification for the identification of disease causing agents in plants[J]. Computers and Electronics in Agriculture,2009(66):121-125.
[43] David S, Murat K, Chieri K, et al. Lettuce calcium deficiency detection with machine vision computed plant features in controlled environments[J]. Computers and Electronics in Agriculture,2010(74):238-243.
[44] Santanu P, Jaya S. Rice Disease Identification using Pattern Recognition Techniques[A]. Proceedings of 11th International Conference on Computer and Information Technology [C], 25-27 December, 2008, Khulna, Bangladesh,1-4.
[45] Pydipati R, Burks T F, Lee W S. Statistical and neural network classifiers for citrus disease detection using machine vision[J]. Transactions of the ASAE,2005,48(5):2007-2014.
[46] Spinelli F, Noferini M, Costa G. Near infrared spectroscopy (NIRs): Perspective of fire blight detection in asymptomatic plant material[A]. Proceeding of 10^th International Workshop on Fire Blight[C]. Acta Horticulturae,2006,704:87-90.
[47] Naidu R A, Perry E M, Pierce F J, et al. The potential of spectral reflectance technique for the detection of Grapevine leafroll-associated virus-3 in two red-berried wine grape cultivars[J]. Computers and Electronics in Agriculture 2009(66):38-45.
[48] Huang J F, Apan A. Detection of Sclerotinia rot disease on celery using hyperspectral data and partial least squares regression[J]. Journal of Spatial Science,2006,51(2):129-142.
[49] Wu D, Feng L, Zhang C, et al. Early detection of Botrytis cinerea on eggplant leaves based on visible and near-infrared spectroscopy[J]. Transactions of the ASABE,2008,51(3):1133-1139.
[50] Delalieux S, van Aardt J, Keulemans W, et al. Detection of biotic stress (Venturia inaequalis) in apple trees using hyperspectral data: Non-parametric statistical approaches and physiological implications. European[J]. Journal of Agronomy,2007,27(1):130-143.
[51] Moshou D, Bravo C, Wahlen S, et al. Simultaneous identification of plant stresses and diseases in arable crops using proximal optical sensing and self-organising maps[J]. Precision Agriculture,2006,7(3):149-164.
[52] Moshou D, Bravo C, Oberti R, et al. Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps[J]. Real-Time Imaging,2005,11(2):75-83.
[53] Camargo A, Smith J S. An image-processing based algorithm to automatically identify plant disease visual symptoms[J]. Biosystems engineering,2009(102):9-21.
[54] Zhao C J, Wu H R. Research on the Diagnosis Method of Crop Pests and Diseases Based on the Heuristic Search[A]. 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery[C], IEEE Transations,2009:349-356.
[55] 李华.模糊专家系统的研究及实现[D].贵阳:贵州大学,2006.
[56] Xin J, Beck H W, Halsey L A, et al. Development of a distance diagnostic and identification system for plant, insect,and disease problems[J]. Applied Engineering in Agriculture,2001,17(4):561-565.