Use of Unmanned Aerial Vehicle Imagery and Deep Learning UNet to Extract Rice Lodging

Rice lodging severely affects harvest yield. Traditional evaluation methods and manual on-site measurement are found to be time-consuming, labor-intensive, and cost-intensive. In this study, a new method for rice lodging assessment based on a deep learning UNet (U-shaped Network) architecture was proposed. The UAV (unmanned aerial vehicle) equipped with a high-resolution digital camera and a three-band multispectral camera synchronously was used to collect lodged and non-lodged rice images at an altitude of 100 m. After splicing and cropping the original images, the datasets with the lodged and non-lodged rice image samples were established by augmenting for building a UNet model. The research results showed that the dice coefficients in RGB (Red, Green and Blue) image and multispectral image test set were 0.9442 and 0.9284, respectively. The rice lodging recognition effect using the RGB images without feature extraction is better than that of multispectral images. The findings of this study are useful for rice lodging investigations by different optical sensors, which can provide an important method for large-area, high-efficiency, and low-cost rice lodging monitoring research.

[1]  Marcel Salathé,et al.  Using Deep Learning for Image-Based Plant Disease Detection , 2016, Front. Plant Sci..

[2]  C. Jordan.  Derivation of leaf-area index from quality of light on the forest floor , 1969 .

[3]  Guillermo Kemper,et al.  Automatic Segmentation of Mauritia flexuosa in Unmanned Aerial Vehicle (UAV) Imagery Using Deep Learning , 2018, Forests.

[4]  Ming-Der Yang,et al.  Spatial and Spectral Hybrid Image Classification for Rice Lodging Assessment through UAV Imagery , 2017, Remote. Sens..

[5]  Andreas Burkart,et al.  Quantifying Lodging Percentage and Lodging Severity Using a UAV-Based Canopy Height Model Combined with an Objective Threshold Approach , 2019, Remote. Sens..

[6]  John A. Gamon,et al.  Assessing leaf pigment content and activity with a reflectometer , 1999 .

[7]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[8]  G. Meyer,et al.  Color indices for weed identification under various soil, residue, and lighting conditions , 1994 .

[9]  Weijia Li,et al.  Deep Learning Based Oil Palm Tree Detection and Counting for High-Resolution Remote Sensing Images , 2016, Remote. Sens..

[10]  Yang Xu,et al.  Weed identification based on K-means feature learning combined with convolutional neural network , 2017, Comput. Electron. Agric..

[11]  C. Daughtry,et al.  Evaluation of Digital Photography from Model Aircraft for Remote Sensing of Crop Biomass and Nitrogen Status , 2005, Precision Agriculture.

[12]  Seth C. Murray,et al.  UAS imaging for automated crop lodging detection: a case study over an experimental maize field , 2017, Commercial + Scientific Sensing and Imaging.

[13]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[14]  Koichi Amaha,et al.  Canopy height measurement by photogrammetric analysis of aerial images: Application to buckwheat (Fagopyrum esculentum Moench) lodging evaluation , 2012 .

[15]  Vijay Kumar,et al.  Counting Apples and Oranges With Deep Learning: A Data-Driven Approach , 2017, IEEE Robotics and Automation Letters.

[16]  Konstantinos P. Ferentinos,et al.  Deep learning models for plant disease detection and diagnosis , 2018, Comput. Electron. Agric..

[17]  Farid Melgani,et al.  A Deep Learning Approach to UAV Image Multilabeling , 2017, IEEE Geoscience and Remote Sensing Letters.

[18]  Tarmo Lipping,et al.  Crop Lodging Analysis from Uas Orthophoto Mosaic, Sentinel-2 Image and Crop Yield Monitor Data , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[19]  王 善本,et al.  Studies on Lodging in Rice Plants. , 1991 .

[20]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[21]  Guijun Yang,et al.  Monitoring model of corn lodging based on Sentinel-1 radar image , 2017, 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA).

[22]  Rubens Augusto Camargo Lamparelli,et al.  Height estimation of sugarcane using an unmanned aerial system (UAS) based on structure from motion (SfM) point clouds , 2017 .

[23]  L. D. Miller,et al.  Remote mapping of standing crop biomass for estimation of the productivity of the shortgrass prairie, Pawnee National Grasslands, Colorado , 1972 .

[24]  A. J. Richardsons,et al.  DISTINGUISHING VEGETATION FROM SOIL BACKGROUND INFORMATION , 1977 .

[25]  B. O. Juliano,et al.  Rice in human nutrition. , 1993 .

[26]  Chen Jingbo,et al.  Inversion method of flora growth parameters based on machine vision. , 2014 .

[27]  Seth C. Murray,et al.  Assessing Lodging Severity over an Experimental Maize (Zea mays L.) Field Using UAS Images , 2017, Remote. Sens..

[28]  Zhang Zhong-xu.  Effect of Lodging Resistance on Yield and Its Relationship with Stalk Physical Characteristics , 1999 .

[29]  George E. Meyer,et al.  Machine vision detection parameters for plant species identification , 1999, Other Conferences.

[30]  Xiaodong Yang,et al.  Effects of Lodging at Different Filling Stages on Rice Yield and Grain Quality , 2012 .

[31]  Stefano Bianchi,et al.  Seed-per-pod estimation for plant breeding using deep learning , 2018, Comput. Electron. Agric..

[32]  Shuai Wang,et al.  Classifying Wheat Hyperspectral Pixels of Healthy Heads and Fusarium Head Blight Disease Using a Deep Neural Network in the Wild Field , 2018, Remote. Sens..

[33]  S. K. McFeeters.  The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features , 1996 .

[34]  E. V. Laureles,et al.  Lodging reduces yield of rice by self-shading and reductions in canopy photosynthesis , 1997 .

[35]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.