Semantic Segmentation of Wheat Stripe Rust Images Using Deep Learning
Semantic Segmentation of Wheat Stripe Rust Images Using Deep Learning
复制标题
DOI：
10.3390/agronomy12122933
复制
发表时间：
2022-12-01
期刊：
影响因子：
3.7
通讯作者：
Yao, Qiang
中科院分区：
文献类型：
--
作者：
Li, Yang;Qiao, Tianle;Yao, Qiang
小麦条锈病叶片的自动病情指数计算面临着挑战，包括孢子和斑点之间的高度相似性，以及难以区分边缘轮廓。在实际现场应用中，调查人员依靠肉眼判断病情程度，主观性强，准确度低，本质上是定性的。针对上述问题，本研究开展了基于深度学习的小麦条锈病图像语义分割研究。针对小麦条锈病图像数据集小的问题，通过田间和温室图像的采集、筛选、过滤和人工标注，构建了青海省首个大规模的小麦条锈病图像开放数据集。我们的数据集中有33,238幅图像，大小为512 x 512像素。定义了一种新的分割范式。将无法区分的孢子和斑点分成不同的类别，研究了背景、叶片(含斑点)和孢子的准确分割任务。为了给高频特征和低频特征赋予不同的权重，我们使用了Octave-UNET模型，它用U网模型中的倍频程卷积代替了原来的卷积运算。在四种模型(PSPNet、DeepLabv3、U-Net、Octave-UNET)中，Octave-UNET模型获得了最好的基准结果，Octave-UNET模型的并集上的平均交集为83.44%，平均像素精度为94.58%，精度为96.06%。结果表明，最新的Octave-UNET模型能够更好地表示和识别小区域内的语义信息，提高了我们构建的数据集中孢子、叶片和背景的分割精度。
Wheat stripe rust-damaged leaves present challenges to automatic disease index calculation, including high similarity between spores and spots, and difficulty in distinguishing edge contours. In actual field applications, investigators rely on the naked eye to judge the disease extent, which is subjective, of low accuracy, and essentially qualitative. To address the above issues, this study undertook a task of semantic segmentation of wheat stripe rust damage images using deep learning. To address the problem of small available datasets, the first large-scale open dataset of wheat stripe rust images from Qinghai province was constructed through field and greenhouse image acquisition, screening, filtering, and manual annotation. There were 33,238 images in our dataset with a size of 512 x 512 pixels. A new segmentation paradigm was defined. Dividing indistinguishable spores and spots into different classes, the task of accurate segmentation of the background, leaf (containing spots), and spores was investigated. To assign different weights to high- and low-frequency features, we used the Octave-UNet model that replaces the original convolutional operation with the octave convolution in the U-Net model. The Octave-UNet model obtained the best benchmark results among four models (PSPNet, DeepLabv3, U-Net, Octave-UNet), the mean intersection over a union of the Octave-UNet model was 83.44%, the mean pixel accuracy was 94.58%, and the accuracy was 96.06%, respectively. The results showed that the state-of-art Octave-UNet model can better represent and discern the semantic information over a small region and improve the segmentation accuracy of spores, leaves, and backgrounds in our constructed dataset.