基于深度学习的农作物病害图像识别技术进展
|
摘要
农作物病害的无损检测和早期识别是精准农业和生态农业发展的关键。随着图像采集和图像处理技术的进步,高光谱成像等先进成像探测技术和基于深度学习的图像分析技术越来越多地应用于农作物病虫害的无损检测中。本文首先简单介绍了以深度学习为代表的图像识别技术的基本原理,然后系统地阐述了基于深度学习的先进成像技术和先进图像识别分析技术在农作物病害检测识别中的国内外研究现状,分析了其在农作物病害检测识别上存在的优缺点,如具有快速、准确率高等优点以及数据量过大处理不便等缺点,并进一步指出,利用高光谱成像和热红外成像与深度学习相结合,将成为今后研究农作物病虫害早期检测的主要发展方向。
The non-destructive testing and early identification of crop diseases is the key to the development of precision agriculture and ecological agriculture. With the progress of image acquisition and image processing technologies, advanced imaging detection technologies such as hyperspectral imaging and image analysis technologies based on deep learning were increasingly used in non-destructive testing of crop pests and diseases. This article first briefly introduced the basic principles of the new non-destructive testing technology represented by near-infrared thermal imaging technology and hyperspectral imaging technology and the image recognition technology represented by deep learning, and then systematically elaborated new imaging technologies and advanced image recognition and analysis technologies. The domestic and foreign research status in crop disease detection and identification was demonstrated, and its advantages and disadvantages in disease detection and identification were analyzed, with the advantages of rapidity and high accuracy, but the disadvantage of too large data volume to handle. The research trends and development directions of non-destructive testing of crop diseases were further pointed out, indicating that the combination of hyperspectral imaging with thermal infrared imaging and deep learning will be the development direction for the early detection of crop pests and diseases.
The non-destructive testing and early identification of crop diseases is the key to the development of precision agriculture and ecological agriculture. With the progress of image acquisition and image processing technologies, advanced imaging detection technologies such as hyperspectral imaging and image analysis technologies based on deep learning were increasingly used in non-destructive testing of crop pests and diseases. This article first briefly introduced the basic principles of the new non-destructive testing technology represented by near-infrared thermal imaging technology and hyperspectral imaging technology and the image recognition technology represented by deep learning, and then systematically elaborated new imaging technologies and advanced image recognition and analysis technologies. The domestic and foreign research status in crop disease detection and identification was demonstrated, and its advantages and disadvantages in disease detection and identification were analyzed, with the advantages of rapidity and high accuracy, but the disadvantage of too large data volume to handle. The research trends and development directions of non-destructive testing of crop diseases were further pointed out, indicating that the combination of hyperspectral imaging with thermal infrared imaging and deep learning will be the development direction for the early detection of crop pests and diseases.
引文
[1] 李真,史智兴, 王成, 等.红外热成像技术在作物胁迫检测方面的应用[J].农机化研究,2016,38(1):232-237.LI Z, SHI Z X, WANG C, et al. The application progress of infrared thermography for crop stress detection[J]. Journal of Agricultural Mechanization Research, 2016, 38(1):232-237. (in Chinese with English abstract)
[2] ZHAO Y R, LI X L, YU K Q, et al. Hyperspectral imaging for determining pigment contents in cucumber leaves in response to angular leaf spot disease[J].Scientific Reports, 2016,6: 27790.
[3] WANG Y J, HU X, HOU Z W, et al. Discrimination of nitrogen fertilizer levels of tea plant (Camellia sinensis) based on hyperspectral imaging[J]. Journal of the Science of Food and Agriculture, 2018,98(12):4659-4664.
[4] PANDEY P, GE Y F, STOERGER V, et al. High throughput in vivo analysis of plant leaf chemical properties using hyperspectral imaging[J]. Frontiers in Plant Science, 2017, 8: 1348.
[5] NOURI M, GORRETTA N, VAYSSE P, et al. Near infrared hyperspectral dataset of healthy and infected apple tree leaves images for the early detection of apple scab disease[J].Data in Brief, 2018,16: 967-971.
[6] 杨燕.基于高光谱成像技术的水稻稻瘟病诊断关键技术研究[D].杭州:浙江大学,2012.YANG Y. The key diagnosis technology of rice blast based on hyper-spectral imaging[D].Hangzhou: Zhejiang University,2012.(in Chinese with English abstract)
[7] ALBASHISH D, BRAIK M, BANI-AHMAD S. A framework for detection and classification of plant leaf and stem diseases[C]//2010 Internatinal Conference on Signal and Image Processing, Chennai, India, 2010.
[8] GUO C H, SONG K, SU H, et al. A research of maize disease image recognition of corn based on BP networks[C]//2011 Third International Conference on Measuring Technology and Mechatronics Automation. IEEE, 2011: 246-249.
[9] MOHANTY S P, HUGHES D P, SALATHé M. Using deep learning for image-based plant disease detection[J]. Frontiers in Plant Science, 2016,7: 1419.
[10] WANG G, SUN Y, WANG J X. Automatic image-based plant disease severity estimation using deep learning[J]. Computational Intelligence and Neuroscience, 2017, 2017: 2917536.
[11] RAMCHARAN A, BARANOWSKI K, MCCLOSKEY P, et al. Deep learning for image-based cassava disease detection[J]. Frontiers in Plant Science, 2017, 8: 1852.
[12] HOLMES L, LAHURD A, WASSON E, et al. Racial and ethnic heterogeneity in the association between total cholesterol and pediatric obesity[J]. International Journal of Environmental Research and Public Health, 2015,13(1): ijerph13010019.
[13] 张善文, 谢泽奇, 张晴晴. 卷积神经网络在黄瓜叶部病害识别中的应用[J]. 江苏农业学报, 2018, 34(1): 56-61.ZHANG S W, XIE Z Q, ZHANG Q Q. Application research on convolutional neural network for cucumber leaf disease recognition[J]. Jiangsu Journal of Agricultural Sciences, 2018, 34(1): 56-61.(in Chinese with English abstract)
[14] 刘阗宇,冯全,杨森.基于卷积神经网络的葡萄叶片病害检测方法[J].东北农业大学学报,2018,49(3):73-83.LIU T Y, FENG Q, YANG S. Detecting grape diseases based on convolutional neural network[J].Journal of Northeast Agricultural University,2018,49(3):73-83. (in Chinese with English abstract)
[15] RAZA S E A, PRINCE G, CLARKSON J P, et al. Automatic detection of diseased tomato plants using thermal and stereo visible light images[J].PLoS One, 2015,10(4):e0123262.
[16] ZHU H Y, CHU B Q, ZHANG C, et al. Hyperspectral imaging for presymptomatic detection of tobacco disease with successive projections algorithm and machine-learning classifiers[J]. Scientific Reports,2017, 7: 4125.
[17] 黄双萍,孙超,齐龙,等.基于深度卷积神经网络的水稻穗瘟病检测方法[J].农业工程学报,2017,33(20):169-176. HUANG S P, SUN C, QI L, et al. Rice panicle blast identification method based on deep convolution neural network[J].Transactions of the Chinese Society of Agricultural Engineering, 2017,33(20):169-176. (in Chinese with English abstract)
[18] 甘海明,岳学军,洪添胜,等.基于深度学习的龙眼叶片叶绿素含量预测的高光谱反演模型[J].华南农业大学学报,2018,39(3):102-110.GAN H M, YUE X J, HONG T S, et al. A hyperspectral inversion model for predicting chlorophyll content of Longan leaves based on deep learning[J].Journal of South China Agricultural University,2018,39(3):102-110. (in Chinese with English abstract)
[2] ZHAO Y R, LI X L, YU K Q, et al. Hyperspectral imaging for determining pigment contents in cucumber leaves in response to angular leaf spot disease[J].Scientific Reports, 2016,6: 27790.
[3] WANG Y J, HU X, HOU Z W, et al. Discrimination of nitrogen fertilizer levels of tea plant (Camellia sinensis) based on hyperspectral imaging[J]. Journal of the Science of Food and Agriculture, 2018,98(12):4659-4664.
[4] PANDEY P, GE Y F, STOERGER V, et al. High throughput in vivo analysis of plant leaf chemical properties using hyperspectral imaging[J]. Frontiers in Plant Science, 2017, 8: 1348.
[5] NOURI M, GORRETTA N, VAYSSE P, et al. Near infrared hyperspectral dataset of healthy and infected apple tree leaves images for the early detection of apple scab disease[J].Data in Brief, 2018,16: 967-971.
[6] 杨燕.基于高光谱成像技术的水稻稻瘟病诊断关键技术研究[D].杭州:浙江大学,2012.YANG Y. The key diagnosis technology of rice blast based on hyper-spectral imaging[D].Hangzhou: Zhejiang University,2012.(in Chinese with English abstract)
[7] ALBASHISH D, BRAIK M, BANI-AHMAD S. A framework for detection and classification of plant leaf and stem diseases[C]//2010 Internatinal Conference on Signal and Image Processing, Chennai, India, 2010.
[8] GUO C H, SONG K, SU H, et al. A research of maize disease image recognition of corn based on BP networks[C]//2011 Third International Conference on Measuring Technology and Mechatronics Automation. IEEE, 2011: 246-249.
[9] MOHANTY S P, HUGHES D P, SALATHé M. Using deep learning for image-based plant disease detection[J]. Frontiers in Plant Science, 2016,7: 1419.
[10] WANG G, SUN Y, WANG J X. Automatic image-based plant disease severity estimation using deep learning[J]. Computational Intelligence and Neuroscience, 2017, 2017: 2917536.
[11] RAMCHARAN A, BARANOWSKI K, MCCLOSKEY P, et al. Deep learning for image-based cassava disease detection[J]. Frontiers in Plant Science, 2017, 8: 1852.
[12] HOLMES L, LAHURD A, WASSON E, et al. Racial and ethnic heterogeneity in the association between total cholesterol and pediatric obesity[J]. International Journal of Environmental Research and Public Health, 2015,13(1): ijerph13010019.
[13] 张善文, 谢泽奇, 张晴晴. 卷积神经网络在黄瓜叶部病害识别中的应用[J]. 江苏农业学报, 2018, 34(1): 56-61.ZHANG S W, XIE Z Q, ZHANG Q Q. Application research on convolutional neural network for cucumber leaf disease recognition[J]. Jiangsu Journal of Agricultural Sciences, 2018, 34(1): 56-61.(in Chinese with English abstract)
[14] 刘阗宇,冯全,杨森.基于卷积神经网络的葡萄叶片病害检测方法[J].东北农业大学学报,2018,49(3):73-83.LIU T Y, FENG Q, YANG S. Detecting grape diseases based on convolutional neural network[J].Journal of Northeast Agricultural University,2018,49(3):73-83. (in Chinese with English abstract)
[15] RAZA S E A, PRINCE G, CLARKSON J P, et al. Automatic detection of diseased tomato plants using thermal and stereo visible light images[J].PLoS One, 2015,10(4):e0123262.
[16] ZHU H Y, CHU B Q, ZHANG C, et al. Hyperspectral imaging for presymptomatic detection of tobacco disease with successive projections algorithm and machine-learning classifiers[J]. Scientific Reports,2017, 7: 4125.
[17] 黄双萍,孙超,齐龙,等.基于深度卷积神经网络的水稻穗瘟病检测方法[J].农业工程学报,2017,33(20):169-176. HUANG S P, SUN C, QI L, et al. Rice panicle blast identification method based on deep convolution neural network[J].Transactions of the Chinese Society of Agricultural Engineering, 2017,33(20):169-176. (in Chinese with English abstract)
[18] 甘海明,岳学军,洪添胜,等.基于深度学习的龙眼叶片叶绿素含量预测的高光谱反演模型[J].华南农业大学学报,2018,39(3):102-110.GAN H M, YUE X J, HONG T S, et al. A hyperspectral inversion model for predicting chlorophyll content of Longan leaves based on deep learning[J].Journal of South China Agricultural University,2018,39(3):102-110. (in Chinese with English abstract)