Frontiers in Plant Science | |
A novel method for maize leaf disease classification using the RGB-D post-segmentation image data | |
Plant Science | |
Chao Wang1  Wude Yang1  Fei Nan2  Yang Song3  Yadong Liu3  Chenwei Nie3  Dameng Yin3  Dongxiao Zou3  Xun Yu3  Yali Bai3  Xiuliang Jin3  | |
[1] College of Agriculture, Shanxi Agricultural University, Taigu, Shanxi, China;College of Agriculture, Shanxi Agricultural University, Taigu, Shanxi, China;Institute of Crop Sciences, Chinese Academy of Agricultural Sciences/Key Laboratory of Crop Physiology and Ecology, Ministry of Agriculture, Beijing, China;National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China;Institute of Crop Sciences, Chinese Academy of Agricultural Sciences/Key Laboratory of Crop Physiology and Ecology, Ministry of Agriculture, Beijing, China;National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China; | |
关键词: leaf spot; disease classification; deep learning; convolutional neural network; depth camera; image processing; smart agriculture; crop breeding; | |
DOI : 10.3389/fpls.2023.1268015 | |
received in 2023-07-27, accepted in 2023-09-11, 发布年份 2023 | |
来源: Frontiers | |
【 摘 要 】
Maize (Zea mays L.) is one of the most important crops, influencing food production and even the whole industry. In recent years, global crop production has been facing great challenges from diseases. However, most of the traditional methods make it difficult to efficiently identify disease-related phenotypes in germplasm resources, especially in actual field environments. To overcome this limitation, our study aims to evaluate the potential of the multi-sensor synchronized RGB-D camera with depth information for maize leaf disease classification. We distinguished maize leaves from the background based on the RGB-D depth information to eliminate interference from complex field environments. Four deep learning models (i.e., Resnet50, MobilenetV2, Vgg16, and Efficientnet-B3) were used to classify three main types of maize diseases, i.e., the curvularia leaf spot [Curvularia lunata (Wakker) Boedijn], the small spot [Bipolaris maydis (Nishik.) Shoemaker], and the mixed spot diseases. We finally compared the pre-segmentation and post-segmentation results to test the robustness of the above models. Our main findings are: 1) The maize disease classification models based on the pre-segmentation image data performed slightly better than the ones based on the post-segmentation image data. 2) The pre-segmentation models overestimated the accuracy of disease classification due to the complexity of the background, but post-segmentation models focusing on leaf disease features provided more practical results with shorter prediction times. 3) Among the post-segmentation models, the Resnet50 and MobilenetV2 models showed similar accuracy and were better than the Vgg16 and Efficientnet-B3 models, and the MobilenetV2 model performed better than the other three models in terms of the size and the single image prediction time. Overall, this study provides a novel method for maize leaf disease classification using the post-segmentation image data from a multi-sensor synchronized RGB-D camera and offers the possibility of developing relevant portable devices.
【 授权许可】
Unknown
Copyright © 2023 Nan, Song, Yu, Nie, Liu, Bai, Zou, Wang, Yin, Yang and Jin
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO202310127659884ZK.pdf | 18111KB | download |