Forests play an important role in the global carbon cycle and natural air conditioning. Monitoring and mapping of forest distribution are of great significance. With the successive launch of new synthetic aperture radar (SAR) sensors, microwave remote sensing data acquisition methods have been developed from single-band, single-polarization and single-angle to multi-frequency, multi-polarization, multi-angle, multi-temporal and so on. That provides an unprecedented potential and opportunity for SAR in the research and application of forest identification. In this paper, the data source mainly included the quad-polarization C-band GaoFen-3(GF-3) and dual-polarization L-band ALOS-1 PALSAR. First, the single-look complex (SLC) data was preprocessed with multi-look, filtering, radiation calibration, geocoding, registration and clipping. Three polarization characteristic parameters of entropy (H), scattering angle (α) and anisotropy (A) were obtained by using Cloude-Pottier polarization decomposition, and three texture features of the mean (MEAN), variance (VAR) and dissimilarity (DIS) were extracted based on the gray-level co-occurrence matrix(GLCM). Combined with the advantages of GF-3 high-resolution quad-polarization and PALSAR L-band, multi-dimensional information including frequency, polarization, temporal and texture features was used synthetically. Then support vector machine (SVM) supervised classifier was used to obtain the four classification results, including coniferous forest, broad-leaved forest, mixed broadleaf-conifer forest and others. The experimental result shows that proposed method achieved a better classification result based on multi-dimensional POLSAR, the overall accuracy of forest type identification is approximately 89.47% and the Kappa coefficient is 0.85.
Crop classification can accurately estimate crop area, structure, and spatial distribution, as well as provide important input parameters for crop yield models. The crop yield information is an important basis for the country to formulate food policies and economic plans, so the study of crop classification is of great significance. Traditional optical remote sensing is susceptible to sunlight and clouds, and Synthetic Aperture Radar (SAR) can be used all-time and all-weather. Compared to single- polarization SAR, full-polarization SAR has more abundant information. In this paper, C-band GF- 3(GaoFen-3) satellite data and multi-temporal Sentinel-1 data were used as data sources. Changchun City in northeastern China is selected as the experimental area and the scattering characteristics of typical crops in this area are analyzed. Firstly, the GF-3 and multi-temporal Sentinel-1 SAR data were preprocessed. Then, polarization decomposition of GF-3 data was performed to obtain three polarization characteristics: scattering angle, entropy and anisotropy (H/α/A). The Supports vector machine (SVM) algorithm was implemented as the classifier. Polarization characteristics, multi-source and multi-temporal SAR were used for classification features. The overall accuracy reached 91.9537%, nearly 10% higher than using full-polarization information alone, and the kappa coefficient was 0.8827. It shows that multi-source and multi-temporal SAR has obvious advantages in crop identification.
With the development of space satellites, a large number of high-resolution remote sensing images have been produced, so the analysis and application of high-resolution remote sensing images are very important. Recently deep learning provides a new method to increase the accuracy of land-cover classification. This study aims to propose a classification framework based on convolutional neural network (CNN) to carry out remote sensing scene classification. After remote sensing images are trained by CNN, a model which can extract complex characteristic from the image for classification is created. In this paper, GaoFen-2(GF-2) satellite data is used as data sources and Jilin province of China is selected as the study area. Firstly, the preprocessed images are made into a GF-2 satellite data sets. Secondly, CaffeNet is used to train the data sets through Caffe platform and the classification result is obtained. The CNN overall accuracy is 89.88%, the Kappa coefficient is 0.8026. Compared with the traditional BP neural network classification result, it is obviously find the CNN is more suitable for remote sensing image classification.
Snow accumulation has a very important influence on the natural environment and human activities. Meanwhile, improving the estimation accuracy of passive microwave snow depth (SD) retrieval is a hotspot currently. Northeastern China is a typical snow study area including many different land cover types, such as forest, grassland and farmland. Especially, there is relatively stable snow accumulation in January every year. The brightness temperatures which are observed by the Advanced Microwave Scanning Radiometer 2 (AMSR2) on GCOM-W1 and FengYun3B Microwave Radiation Imager (FY3B-MWRI) in the same period in 2013 are selected as the study data in the research. The results of snow depth retrieval using AMSR2 standard algorithm and Jiang’s FY operational algorithm are compared in the research. Moreover, to validate the accuracy of the two algorithms, the retrieval results are compared with the SD data observed at the national meteorological stations in Northeastern China. Furthermore, the retrieval SD is also compared with AMSR2 and FY standard SD products, respectively. The root mean square errors (RMSE) results using AMSR2 standard algorithms and FY operational algorithm are close in the forest surface, which are 6.33cm and 6.28cm, respectively. However, The FY operational algorithm shows a better result than the AMSR2 standard algorithms in the grassland and farmland surface. The RMSE results using FY operational algorithm in the grassland and farmland surface are 2.44cm and 6.13cm, respectively.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.