| 基于波段增强的DeepLabv3+多光谱影像葡萄种植区识别 |
| |
| 引用本文： | 孙志同,朱珊娜,高郑杰,古明扬,张国良,张宏鸣.基于波段增强的DeepLabv3+多光谱影像葡萄种植区识别[J].农业工程学报,2022,38(7):229-236. |
| |
| 作者姓名： | 孙志同 朱珊娜 高郑杰 古明扬 张国良 张宏鸣 |
| |
| 作者单位： | 1. 西北农林科技大学信息工程学院，杨凌 712100;;1. 西北农林科技大学信息工程学院，杨凌 712100; 2. 宁夏智慧农业产业技术协同创新中心，银川 750004; |
| |
| 基金项目： | 国家重点研发计划项目（2020YFD1100601） |
| |
| 摘 要： | 精准获取葡萄种植区分布信息对其精细化管理和优质基地建设具有重要意义，通常大区域种植区识别主要基于遥感影像完成，但葡萄种植区空间位置的分散性和背景环境的复杂性，使得种植区识别的精度不高。该研究基于DeepLabv3+网络，改进网络输入通道数使其能够接受更多的光谱信息，同时构建波段信息增强模块（Band Information Enhancement，BIE），利用各波段特征图之间的相关性生成综合特征，提出了波段信息增强的葡萄种植区识别方法（BIE-DeepLabv3+）。在2016和2019年高分二号影像葡萄种植区数据集上训练网络，在2020年影像上测试其性能，结果表明，改进模型输出结果的平均像素精度和平均交并比分别为98.58%和90.27%，识别效果好于机器学习SVM算法，在深度学习DeepLabv3+模型的基础上分别提高了0.38和2.01个百分点，比SegNet分别提高了0.71和4.65个百分点。BIE-DeepLabv3+模型拥有更大的感受野和捕获多尺度信息特征的同时放大了地物间的差异，能够解决影像中葡萄种植区存在类间纹理相似性、背景和环境复杂等问题，在减少模型参数的同时预测出的葡萄种植区更加完整，且边缘识别效果良好，为较大区域内背景复杂的遥感图像葡萄种植区识别提供了有效方法。
|
| 关 键 词： | 深度学习 语义分割 DeepLabv3+ 多光谱影像 葡萄种植区 |
| 收稿时间： | 2021/8/29 0:00:00 |
| 修稿时间： | 2022/2/19 0:00:00 |
Recognition of grape growing areas in multispectral images based on band enhanced DeepLabv3+ |
| |
| Sun Zhitong,Zhu Shann,Gao Zhengjie,Gu Mingyang,Zhang Guoliang,Zhang Hongming.Recognition of grape growing areas in multispectral images based on band enhanced DeepLabv3+[J].Transactions of the Chinese Society of Agricultural Engineering,2022,38(7):229-236. |
| |
| Authors: | Sun Zhitong Zhu Shann Gao Zhengjie Gu Mingyang Zhang Guoliang Zhang Hongming |
| |
| Affiliation: | 1. College of Information Engineering, Northwest A&F University, Yangling 712100, China;; 1. College of Information Engineering, Northwest A&F University, Yangling 712100, China; 2. Ningxia Smart Agricultural Industry Technology Collaborative Innovation Center, Yinchuan 750004, China; |
| |
| Abstract: | Accurate and rapid identification has been of great importance to obtain the spatial distribution of grape growing areas in recent years. The spatial information can be used to guide the fine management of planting areas and high-quality base construction in an orchard. Recognition of large-scale crop growing areas has been usually implemented using remote sensing images. However, the low accuracy of planting area recognition can be induced by the dispersed patches and the complex background. Fortunately, the convolution operation in deep learning can effectively extract the texture features of images. Among them, semantic segmentation has been one of the most important processing for remote sensing images. In this study, an improved band enhancement DeepLabv3+ (BIE-DeepLabv3+) was proposed for the multispectral image recognition of grape planting areas. An encoder-decoder structure was employed in the DeepLabv3+. Atrous convolution was then applied to encode the multi-scale contextual information in the encoder module. The decoder module was used to effectively capture the sharp object boundaries for the gradual recovery of spatial information. As such, the DeepLabv3+ model was used to require the key features suitable for the high recognition accuracy of grape growing areas with different area sizes and scattered spatial locations. Since the combination of various bands reflected the differences between features, the DeepLabv3+ model was modified to concurrently handle four bands of remote sensing images. In addition, the band enhancement module was also built to determine the interdependencies between the band channel maps. All spectral bands of features were weighted to clarify the semantic dependency relationship among the spectral band feature maps. The ground features were distinguished to fully utilize the spectral information in each band. The dataset was generated through labeling the grape growing areas in the GaoFen-2 remote sensing images taken in 2016 and 2019. Then the model is trained on this dataset. The testing was also performed to verify the improved model using the dataset from the remote sensing images taken in 2020. Experimental results show that the improved model achieved the best classification accuracy, where the mean pixel accuracy and mean intersection over union were 98.58% and 90.27%, respectively. The recognition performance of the improved model was much better than that of the SVM algorithm. Specifically, the mean pixel accuracy and mean intersection over union were improved by 0.38 and 2.01 percentage points on the basis of DeepLabv3+, and the improvement over SegNet were 0.71 and 4.65 percentage points, respectively. More complete grape growing regions were predicted for better edge recognition with the reduced model parameters. Therefore, the BIE-Deeplabv3+ network model can be used to achieve the high accurate segmentation of grape growing areas. The detailed information of the image can also be collected for the spatial correlation of pixels in a large range, particularly for the various planting area sizes and regional dispersion in the grape growing areas. The multi-bands input and BIE module can be used to fully utilize the band information for highlighting differences between the objects. The recognition accuracy of images was significantly improved with similar texture features. Anyway, the effective recognition can be widely expected for the grape planting areas in the remote sensing image with the complex background in a large area. |
| |
| Keywords: | deep learning semantic segmentation DeepLabv3+ multispectral imagery grape growing areas |
|
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
|
点击此处可从《农业工程学报》下载全文 |
|
