帮助 关于我们

返回检索结果

CNN影像输入尺寸和分辨率对川西针叶林植被分类精度的影响
Effects of image input size and resolution by CNN on the classification accuracy for coniferous forest vegetation in western Sichuan

查看参考文献34篇

石伟博 1   廖小罕 2,3,4 *   王绍强 1,5,6   岳焕印 2,3,4   王东亮 2,3  
文摘 川西亚高山针叶林位于中国西南地区,受多云、多雨、多雾的影响,难以通过卫星影像进行植被分类的研究。为了解决这一难题,本研究选取川西亚高山针叶林的典型区域王朗自然保护区作为研究区,使用多旋翼无人机获取研究区域北部高分辨率RGB影像,结合卷积神经网络进行植被分类;为进一步挖掘卷积神经网络在无人机遥感影像上的潜力,选择语义分割方法(U-Net)进行分类,并根据不同分辨率的无人机影像和不同尺寸下的样本集构建植被分类模型,建立森林指纹库。结果表明:(1)结合无人机可见光影像和CNN模型进行分类能够获得高精度分类结果。在空间分辨率为5 cm,尺寸为256×256像素的情况下达到最优,总体精度为93.21%,Kappa系数为0.90;(2)选择合适的尺寸大小能够提高模型的分类精度。在5 cm的空间分辨率下,尺寸为128×128像素的模型总体精度为82.30%,Kappa系数为0.76;尺寸为256×256像素的模型总体精度为93.21%, Kappa系数为0.90;(3)超高空间分辨率的升高对模型精度的提升是有限的。当空间分辨率从10 cm升到5 cm时,模型的总体精度提高了0.02,Kappa系数提高了0.03,模型的分类精度并没有明显提升。(4)对于区域内代表性不足的植被类型来说,受空间分辨率和尺寸大小的影响要远高于区域内优势树种,特别是空间分辨率的影响最大。在20 cm的空间分辨率下落叶灌木的生产者精度和用户精度均低于70%。综上,利用无人机高分辨率RGB影像结合CNN模型对川西亚高山针叶林的植被分类能够取得高精度分类结果,本研究可为该区域植被分类提供一种自动、准确的方法。
其他语种文摘 The subalpine coniferous forest in west Sichuan is located in southwest China, which is affected by cloudy, rainy, and foggy conditions. Thus, conducting vegetation classification in the area by using satellite images is difficult. (Objective) Therefore, this work selects Wanglang Nature Reserve, which is a typical area of subalpine coniferous forest in western Sichuan, as the study area. A multi-rotor UAV is used to acquire high-resolution RGB images of the northern part of the study area, and it is combined with a convolutional neural network model for vegetation classification. (Method) This study selects the semantic segmentation method (U-Net) for classification, constructs vegetation classification models based on UAV images of different spatial resolutions and sample sets under different tile sizes, and establishes a forest fingerprint library to further explore the potential of convolutional neural networks on UAV remote sensing images. (Result) (1) The combination of UAV visible images and convolutional neural network model for classification can obtain classification results of high accuracy, which reached the optimum at a spatial resolution of 5 cm and a size of 256×256. The overall accuracy was 93.21%, and the kappa coefficient was 0.90. (2) The increase in ultrahigh spatial resolution had limited improvement on the model accuracy. When the spatial resolution was increased from 10 cm to 5 cm, the overall accuracy of the model improved by 0.02 and the Kappa coefficient improved by 0.03, and the classification accuracy of the model did not improve significantly. (3) Choosing the appropriate size can improve the classification accuracy of the model. Under the spatial resolution of 5 cm, the overall accuracy of the model with the size of 128×128 was 82.30% and the kappa coefficient was 0.76, and the overall accuracy of the model with the size of 256×256 was 93.21% and the kappa coefficient was 0.90. (4) For the vegetation types that were underrepresented in the region, the influence of spatial resolution and tile size was much higher than that of the dominant tree species, especially the influence of spatial resolution was the highest. The producer and user accuracies for deciduous shrubs at a spatial resolution of 20 cm were below 70%. (Conclusion) This study shows that vegetation classification of subalpine coniferous forests in western Sichuan using UAV high-resolution RGB images combined with convolutional neural networks can achieve high-precision classification results. The effects of UAV spatial resolution and tile sizes on the accuracy of convolutional neural network models are explored, which further details the potential of convolutional neural networks on UAV high-resolution RGB images to provide an automatic and accurate research method for vegetation classification in this region.
来源 遥感学报 ,2023,27(11):2640-2652 【核心库】
DOI 10.11834/jrs.20221868
关键词 无人机RGB影像 ; 卷积神经网络 ; 川西亚高山针叶林 ; 植被分类 ; 输入尺寸 ; 空间分辨率
地址

1. 中国地质大学(武汉)地理与信息工程学院区域生态过程与环境演变实验室, 武汉, 430074  

2. 中国科学院地理科学与资源研究所, 资源与环境信息系统国家重点实验室, 北京, 100101  

3. 中国科学院无人机应用与管控研究中心, 北京, 100101  

4. 中国民航局低空地理信息与航路重点实验室, 中国民航局低空地理信息与航路重点实验室, 北京, 100101  

5. 中国科学院地理科学与资源研究所, 中国科学院生态系统网络观测与模拟重点实验室, 北京, 100101  

6. 中国科学院大学资源与环境学院, 北京, 100049

语种 中文
文献类型 研究性论文
ISSN 1007-4619
学科 测绘学
基金 中国科学院战略性先导科技专项 ;  中国地质大学（武汉）基金
文献收藏号 CSCD:7610839

参考文献 共 34 共2页

1.  曹忠. 低空无人机森林资源调查与监测应用现状与展望. 林业建设,2016(6):1-5 CSCD被引 4 次    
2.  Colomina I. Unmanned aerial systems for photogrammetry and remote sensing: a review. ISPRS Journal of Photogrammetry and Remote Sensing,2014,92:79-97 CSCD被引 118 次    
3.  戴鹏钦. 基于FCN的无人机可见光影像树种分类. 激光与光电子学进展,2020,57(10):101001 CSCD被引 7 次    
4.  杜志. 西南高山林区森林资源特点及保护利用对策探讨. 林业资源管理,2014(Z1):27-31 CSCD被引 3 次    
5.  Fassnacht F E. Review of studies on tree species classification from remotely sensed data. Remote Sensing of Environment,2016,186:64-87 CSCD被引 35 次    
6.  顾人和. 王朗自然保护区的大自然景观类型分析与评价. 生物学杂志,2005,22(3):1-4 CSCD被引 4 次    
7.  Hao Z B. Automated tree-crown and height detection in a young forest plantation using mask region-based convolutional neural network (Mask R-CNN). ISPRS Journal of Photogrammetry and Remote Sensing,2021,178:112-123 CSCD被引 12 次    
8.  何诚. 旋翼无人机林火点定位技术研究. 测绘通报,2014(12):24-27 CSCD被引 5 次    
9.  He K M. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2016:770-778 CSCD被引 630 次    
10.  黄华毅. Fast R-CNN深度学习和无人机遥感相结合在松材线虫病监测中的初步应用研究. 环境昆虫学报,2021,43(5):1295-1303 CSCD被引 4 次    
11.  Iverson L R. Ecosystem services from forest landscapes: where we are and where we go. Ecosystem Services from Forest Landscapes,2018:249-258 CSCD被引 1 次    
12.  贾莉. 地形校正对U-Net深度神经网络分类器分类精度的影响. 遥感学报,2022,26(4):698-710 CSCD被引 2 次    
13.  Kattenborn T. Review on Convolutional Neural Networks (CNN) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing,2021,173:24-49 CSCD被引 40 次    
14.  廖亮林. 2005-2013年中国新增造林植被生物量碳库固碳潜力分析. 地理学报,2016,71(11):1939-1947 CSCD被引 10 次    
15.  廖小罕. 无人机遥感:大众化与拓展应用发展趋势. 遥感学报,2019,23(6):1046-1052 CSCD被引 35 次    
16.  廖小罕. 无人机遥感众创时代. 地球信息科学学报,2016,18(11):1439-1447 CSCD被引 34 次    
17.  林志玮. 基于DenseNet的无人机光学图像树种分类研究. 遥感技术与应用,2019,34(4):704-711 CSCD被引 7 次    
18.  刘庆. 中国西南亚高山针叶林的生态学问题. 世界科技研究与发展,2001,23(2):63-69 CSCD被引 51 次    
19.  刘清旺. 无人机激光雷达与摄影测量林业应用研究进展. 林业科学,2017,53(7):134-148 CSCD被引 26 次    
20.  Maes W H. Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture. Trends in Plant Science,2019,24(2):152-164 CSCD被引 33 次    
引证文献 1 篇

1 徐祖平 基于GEE的香格里拉草地分类及其生物量遥感估算 草业科学,2024,41(10):2250-2262
CSCD被引 0 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号