基于图像处理和Deeplabv3+模型的小麦赤霉病识别

doi:10.13733/j.jcam.issn.2095-5553.2021.09.29

摘要/Abstract

摘要： 赤霉病是影响小麦产量和品质的主要病害之一。为快速、有效地监测小麦赤霉病的发生情况,利用数码相机对人工接种赤霉病菌的小麦田进行RGB图像获取,在图像预处理基础上,对Deeplabv3+网络模型进行调参和训练。以轻量化网络MobileNet V2为网络编码模块,利用空洞卷积技术建立基于深度学习网络的小麦赤霉病发病麦穗的识别与检测模型,并用实测数据对模型进行验证和评价。结果表明,该模型的平均精度为0.969 2,损失函数Loss为0.103 0,平均交并比MIoU为0.793,模型识别与检测效果较好。上述结果为小麦赤霉病的检测与识别提供新的手段。

关键词: 小麦, 赤霉病, Deeplabv3+模型, 深度学习, 图像识别

Abstract: Fusarium head blight is one of the main diseases affecting wheat yield and quality. In order to monitor the occurrence of fusarium head blight in wheat rapidly and effectively, RGB images were acquired by using a digital camera in wheat fields with artificially inoculated Fusarium graminearum in this study, and Deeplabv3+ network model parameters were adjusted and trained on the basis of image preprocessing. Using the lightweight network MobileNet V2 as the network coding module, an identification, and detection model of the wheat ear caused by fusarium head blight was established using the hollow convolution technology based on a deep learning network, and the model was verified and evaluated using the measured data. The results showed that the average accuracy of the model was 0969 2, the Loss value of loss function was 0.103 0, and the mean intersection over union (MIoU) was 0793. The model has a good recognition and detection effect. These results provide a new method for the detection and identification of wheat fusarium head blight.

Key words: wheat, Fusariumhead blight, deeplabv3+ model, deep learning, image recognition

中图分类号:

戴雨舒, 仲晓春, 孙成明, 杨俊, 刘涛, 刘升平, . 基于图像处理和Deeplabv3+模型的小麦赤霉病识别[J]. 中国农机化学报, 2021, 42(9): 209-215.

Dai Yushu, Zhong Xiaochun, Sun Chengming, Yang Jun, Liu Tao, Liu Shengping.. Identification of fusarium head blight in wheatbased on image processing and Deeplabv3+ model[J]. Journal of Chinese Agricultural Mechanization, 2021, 42(9): 209-215.

参考文献

［１］　
鲍文霞, 孙庆, 胡根生, 等. 基于多路卷积神经网络的大田小麦赤霉病图像识别［J］. 农业工程学报, 2020, 36(11): 174-181.

Bao Wenxia, Sun Qing, Hu Gensheng, et al. Image recognition of field wheat scab based on multiway convolutional neural network ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(11): 174-181.

［2］　
张健, 崔继承, 刘晓梅, 等. 短波红外成像光谱技术在小麦赤霉病检测中的应用［J］. 光学技术, 2019, 45(5): 552-556.

Zhang Jian, Cui Jicheng, Liu Xiaomei, et al. The technology of shortwave infrared imaging spectroscopy applied to detecting wheat scab ［J］.Optical Technique, 2019, 45(5): 552-556.

［3］　
梁琨, 杜莹莹, 卢伟, 等. 基于高光谱成像技术的小麦籽粒赤霉病识别［J］. 农业机械学报, 2016, 47(2): 309-315.

Liang Kun, Du Yingying, Lu Wei, et al. Identification of fusarium head blight wheat based on hyperspectral imaging technology ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(2): 309-315.

［4］　
刘爽, 谭鑫, 刘成玉, 等. 高光谱数据处理算法的小麦赤霉病籽粒识别［J］. 光谱学与光谱分析, 2019, 39(11): 3540-3546.

Liu Shuang, Tan Xin, Liu Chengyu, et al. Recognition of fusarium head blight wheat grain based on hyperspectral data processing algorithm ［J］. Spectroscopy and Spectral Analysis, 2019, 39(11): 3540-3546.

［5］　
Barbedo J G A, Tibola C S, Fernandes J M C. Detecting Fusarium head blight in wheat kernels using hyperspectral imaging ［J］. Biosystems Engineering, 2015, 131: 65-76.

［6］　
Ropelewska E, Zapotoczny P. Classification of Fusariuminfected and healthy wheat kernels based on features from hyperspectral images and flatbed scanner images: A comparative analysis ［J］. European Food Research & Technology, 2018, 244(8): 1453-1462.

［7］　
Bauriegel E, Giebel A, Geyer M, et al. Early detection of fusarium infection in wheat using hyperspectral imaging ［J］. Computers & Electronics in Agriculture, 2011, 75(2): 304-312.

［8］　
Jin X, Jie L, Wang S, et al. Classifying wheat hyperspectral pixels of healthy heads and fusarium head blight disease using a deep neural network in the wild field ［J］. Remote Sensing, 2018, 10(3): 395.

［9］　
刁智华, 袁万宾, 罗雅雯, 等. 基于图像处理的小麦白粉病病斑生长模型构建［J］. 中国农机化学报, 2019, 40(6): 158-161.

Diao Zhihua, Yuan Wanbin, Luo Yawen, et al. Construction of wheat powdery mildew lesion growth model based on image processing ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(6): 158-161.

［10］　
张开兴, 吕高龙, 贾浩, 等. 基于图像处理和BP神经网络的玉米叶部病害识别［J］. 中国农机化学报, 2019, 40(8): 122-126.

Zhang Kaixing, Lü Gaolong, Jia Hao, et al. Identification of corn leaf disease based on image processing and BP neural network ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(8): 122-126.

［11］　
顾博, 邓蕾蕾, 李巍, 等. 基于GrabCut算法的玉米病害图像识别方法研究［J］. 中国农机化学报, 2019, 40(11): 143-149.

Gu Bo, Deng Leilei, Li Wei, et al. Researvh on maize disease image recognition method based on GrabCut algorithms ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(11): 143-149.

［12］　
Qiu Ruicheng, Yang Ce, Moghimi A, et al. Detection of fusarium head blight in wheat using a deep neural network and color imaging ［J］. Remote Sensing, 2019, 11(22): 2658.

［13］　
王云艳, 罗冷坤, 王重阳. Deeplab网络的极化合成孔径雷达图像分类［J］. 测绘科学, 2020, 45(6): 110-117.

Wang Yunyan, Luo Lengkun, Wang Chongyang. PolSAR image classification based on Deeplab network ［J］. Science of Surveying Mapping, 2020, 45(6): 110-117.

［14］　
王云艳, 罗冷坤, 周志刚. 改进型DeepLab的极化SAR果园分类［J］. 中国图象图形学报, 2019, 24(11): 2035-2044.

Wang Yunyan, Luo Lengkun, Zhou Zhigang. Polarized SAR orchard classification based on improved DeepLab ［J］. Journal of Image and Graphics, 2019, 24(11): 2035-2044.

［15］　
刘文祥, 舒远仲, 唐小敏, 等. 采用双注意力机制Deeplabv3+算法的遥感影像语义分割［J］. 热带地理, 2020, 40(2): 303-313.

Liu Wenxiang, Shu Yuanzhong, Tang Xiaomin, et al. Remote sensing image segmentation using dual attention mechanism Deeplabv3+ algorithm ［J］. Tropical Geography, 2020, 40(2): 303-313.

［16］　
袁立, 袁吉收, 张德政. 基于DeepLabv3+的遥感影像分类［J］. 激光与光电子学进展, 2019, 56(15): 1-8.

Yuan Li, Yuan Jishou, Zhang Dezheng. Remte sensing image classification based on DeepLabv3+ ［J］. Laser & Optoelectronics Progress, 2019, 56(15): 1-8.

［17］　
刘文雅, 岳安志, 季珏, 等. 基于DeepLabv3+语义分割模型的GF-2影像城市绿地提取［J］. 国土资源遥感, 2020, 32(2): 120-129.

Liu Wenya, Yue Anzhi, Ji Jue, et al. Urban green space extraction from GF-2 remote sensing image based on DeepLabv3+ semantic segmentation model ［J］. Remote Sensing for Land and Resource, 2020, 32(2): 120-129.

［18］　
王振华, 钟元芾, 何婉雯, 等. 改进Deeplab网络的遥感影像海岛岸线分割［J］. 中国图象图形学报, 2020, 25(4): 768-778.

Wang Zhenhua, Zhong Yuanfei, He Wanwen, et al. Island shoreline segmentation in remote sensing image based on improved Deeplab network ［J］. Journal of Image and Graphics, 2020, 25(4): 768-778.

［19］　
任凤雷, 何昕, 魏仲慧, 等. 基于DeepLabV3+与超像素优化的语义分割［J］. 光学精密工程, 2019, 27(12): 2722-2729.

Ren Fenglei, He Xin, Wei Zhonghui, et al. Semantic segmentation based on DeepLabV3+ and superpixel optimization ［J］. Optics and Precision Engineering, 2019, 27(12): 2722-2729.

［20］　
丁串龙. 基于高光谱数据的小麦赤霉病遥感监测［D］. 合肥: 安徽大学, 2020.

Ding Chuanlong. Remote sensing monitoring of wheat scab based on hyperspectral data ［D］. Hefei: Anhui University, 2020.

［21］　
Zhang N, Pan Y, Feng H, et al. Development of Fusarium head blight classification index using hyperspectral microscopy images of winter wheat spikelets ［J］. Biosystems Engineering, 2019, 186: 83-99.

[1]	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.
[2]	冒辛平, 金建新, 何振嘉. 宁夏引黄灌区滴灌条件下春小麦干物质转移与灌浆特征[J]. 中国农机化学报, 2022, 43(9): 174-181.
[3]	金建新, 李株丹, 黄建成, 何进勤, 何振嘉. 宁夏引黄灌区不同灌水处理下春小麦光响应曲线模型研究[J]. 中国农机化学报, 2022, 43(9): 182-190.
[4]	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.
[5]	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.
[6]	冯继克, 郑颖, 李平, 李艳翠, 张自阳, 郭晓娟. 基于特征选择的小麦籽粒品种识别研究[J]. 中国农机化学报, 2022, 43(7): 116-123.
[7]	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.
[8]	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.
[9]	于雪莹, 高继勇, 王首程, 李庆盛, 王志强. 基于生成对抗网络和混合注意力机制残差网络的苹果病害识别[J]. 中国农机化学报, 2022, 43(6): 166-174.
[10]	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.
[11]	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.
[12]	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.
[13]	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.
[14]	南风, 曹光乔, 李亦白, 陈聪, 刘东. 基于小麦收割机作业路线行走方向的调度优化研究[J]. 中国农机化学报, 2022, 43(4): 98-105.
[15]	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.