帮助 关于我们

返回检索结果

基于深度学习AlexNet的遥感影像地表覆盖分类评价研究
Study on the Evaluation of Land Cover Classification using Remote Sensing Images Based on AlexNet

查看参考文献22篇

党宇 1   张继贤 1 *   邓喀中 1   赵有松 2   余凡 3  
文摘 地表覆盖分类信息是反映自然、人工地表覆盖要素的综合体,包含植被、土壤、冰川、河流、湖泊、沼泽湿地及各类人工构筑物等元素,侧重描述地球表面的自然属性,具有明确的时间及空间特性。地表覆盖分类信息数据量大、现势性强、人工评价费时,其自动化评价长期以来存在许多技术难点。本文基于面向对象的图斑分类体系,引入深度卷积神经网络对现有地理国情普查-地表覆盖分类数据进行分类评价,并通过试验利用AlexNet模型实现地表覆盖分类评价验证。试验结果表明,该方法可有效判读耕地、房屋2类图斑,正确分类隶属度优于99%,而由于数据较少、训练不充分,林地、水体图斑正确分类隶属度不高,分别为62.73%和43.59%。使用本文方法,经过大量数据充分微调的深度学习AlexNet可有效地计算图斑的地类隶属度,并实现自动地表覆盖分类图斑量化评价。
其他语种文摘 As one of the important outcomes of the National Geographic Census of China, the land cover classification reveals the information of both natural and artificial coverage elements, including vegetation, soil, glaciers, rivers, lakes, marsh wetlands and various artificial structures. Obviously, it mainly focuses on profiling the natural characters of the land surface with temporal and distribution attributes, which has an obviously different classification system from other scene classification applications. In recent years, more and more high-resolution remote sensing platforms become available, it is possible to update and evaluate land cover classification quickly with the advantage of huge volume of data and more frequent data updates. Meanwhile, in practice we face with more and more challenges of the huge data. In this paper, we propose a novel approach for evaluating the land cover classification results by combining the object-oriented method with the Deep Convolutional Neural Network (D-CNN) model. With deeper structure and wilder receptive field, the deep neural network has the capability of abstract description from low-level features, and the deep learning has become one of the latest development trends in the artificial neural network field. The deep learning shows a completely different possibility in many fields, and it has been applied to the speech recognition, image recognition, information retrieval and so on. The newly-developed method of image recognition based on deep leaning has been preliminarily verified in the scene classification field. Traditionally, the land cover classification method is established on the pixel-based classifying. The latest improved method of the object-oriented classification frame has been proposed, but this new frame is hard to be achieved because of the lack of supports from efficient methods and algorithms. Nowadays, the deep neural network provides us an effective tool to achieve the object-oriented classification by clipping image spots from original images and inputting the clipped image spots to D-CNN. The D-CNN model can convolute and pool the image spots to realize the object-oriented classification of the land cover. By the combination of the object-oriented classification with the deep learning, the proposed method can extract more and better abstract features than the pixel-based approach, while the pixel-based method requires more manual interventions. When applying the deep learning method to land cover classification recognition, the prepared image spots as appropriate inputs will be automatically scored to its belonging classes. Thus, the score represent the degree of membership of the image spot matching to the corresponding class. By fine-tuning the D-CNN, we can obtain a new approach of judging the quality of the samples, in order to assure the reliability of the proposed approach. The fine-tuned D-CNN is required to be sufficiently robust, and we verify its robustness in the following experiment by employing the AlexNet. The experimental results show that the image spots of arable land and building can be recognized with the membership degree of 99.95% and 99.41%, but those of woodland and water area can be recognized only with the membership degree of 62.73% and 43.59%. Obviously, the proposed model can achieve the promising reliability that is related to the qualified and sufficient data set of the image spots which is used for fine-tuning of the net. The reason for poor robustness of the fine-tuned AlexNet in classifying the woodland and water area may be the insufficient size of data-set of these two classes. It shows that a fine-tuned deep convolutional neural network as a new model can be utilized in evaluating the land cover classification with high reliability.
来源 地球信息科学学报 ,2017,19(11):1530-1537 【核心库】
DOI 10.3724/SP.J.1047.2017.01530
关键词 深度学习 ; 地理国情普查 ; 地表覆盖分类 ; 质量评价 ; AlexNet
地址

1. (徐州)中国矿业大学, 徐州, 221116  

2. 国家测绘产品质量检验测试中心, 北京, 100830  

3. 中国测绘科学研究院, 北京, 100830

语种 中文
文献类型 研究性论文
ISSN 1560-8999
学科 测绘学
基金 国家自然科学基金项目
文献收藏号 CSCD:6117761

参考文献 共 22 共2页

1.  胡艳. 多方法的地理国情地表覆盖分类研究. 地理空间信息,2014(1):6-9 CSCD被引 3 次    
2.  Luo B. Robust autodual morphological profiles for the classification of high-resolution satellite images. IEEE Transactions on Geoscience and Remote Sensing,2014,52(2):1451-1462 CSCD被引 10 次    
3.  Hinton G E. Reducing the dimensionality of data with neural networks. Science,2006,313(5786):504-507 CSCD被引 1782 次    
4.  Krizhevsky A. Image Net classification with deep convolutional neural networks. International Conference on Neural Information Processing Systems,2012:1097-1105 CSCD被引 279 次    
5.  陈军. 全球地表覆盖高分辨率遥感制图. 地理信息世界,2011,9(2):12-14 CSCD被引 49 次    
6.  Li X F. Influence of land cover data on regional forest leaf area index inversion. Journal of Remote Sensing,2010,14(5):974-989 CSCD被引 2 次    
7.  曹云刚. 多时相ASAR数据的地表覆盖分类研究. 测绘科学,2007,32(5):103-105 CSCD被引 9 次    
8.  谢宏全. 面向地理国情普查的地表覆盖分类方法研究. 测绘通报,2014(s2):245-247 CSCD被引 2 次    
9.  汪权方. 基于地表覆盖物光谱特征的土地覆被分类系统——以鄱阳湖流域为例. 地理学报,2006,61(4):359-368 CSCD被引 21 次    
10.  翁中银. 基于决策树分类的地表覆盖遥感信息提取. 地理空间信息,2012,10(2):110-112 CSCD被引 7 次    
11.  高志宏. 地理国情普查中容易混分地表覆盖类型定量统计与分析. 测绘通报,2015(6):32-34 CSCD被引 7 次    
12.  陈利军. 30m全球地表覆盖遥感分类方法初探. 测绘通报,2012(s1):350-353 CSCD被引 10 次    
13.  Cheng G. Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Transactions on Geoscience & Remote Sensing,2016,54(12):7405-7415 CSCD被引 105 次    
14.  Hu F. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery. Remote Sensing,2015,7(11):14680-14707 CSCD被引 91 次    
15.  Yu D. Deep learning and its applications to signal and information processing. IEEE Signal Processing Magazine,2011,28(1):145-154 CSCD被引 45 次    
16.  Jones N. The learning machines. Nature,2014,505(7842):146-148 CSCD被引 10 次    
17.  余凯. 深度学习的昨天、今天和明天. 计算机研究与发展,2013,50(9):1799-1804 CSCD被引 204 次    
18.  Qin Q. On the data augmentation algorithm for bayesian multivariate linear regression with non-gaussian errors. Statistics,2015 CSCD被引 1 次    
19.  周星宇. 高分辨率遥感影像下沿海地区地表覆盖信息的提取. 测绘通报,2017(2):19-24 CSCD被引 5 次    
20.  高常鑫. 基于深度学习的高分辨率遥感影像目标检测. 测绘通报,2014(s1):108-111 CSCD被引 22 次    
引证文献 24 篇

1 孙钰 基于深度学习的森林虫害无人机实时监测方法 农业工程学报,2018,34(21):74-81
CSCD被引 34 次

2 郭燕 基于高分二号数据的小麦快速识别与精度分析 河南农业科学,2018,47(10):143-148
CSCD被引 3 次

显示所有24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