| |
| |
| |
| |
| |
| |
| |
|
|
| |
| |
|
|
| <!DOCTYPE html> |
| <html> |
|
|
| <head> |
| <title>页面标题</title> |
| <meta charset="UTF-8"> |
| <meta name="viewport" content="width=device-width, initial-scale=1"> |
| <style> |
| * { |
| box-sizing: border-box; |
| } |
| |
| |
| body { |
| font-family: Arial; |
| margin: 0; |
| } |
| |
| |
| .header { |
| padding: 10px; |
| text-align: center; |
| < !-- background: url(2.jpg) no-repeat; |
| -->< !-- background: #1abc9c; |
| -->color: white; |
| } |
| |
| |
| .header h1 { |
| font-size: 40px; |
| } |
| |
| |
| .navbar { |
| overflow: hidden; |
| background-color: #333; |
| } |
| |
| |
| .navbar a { |
| float: left; |
| display: block; |
| color: white; |
| text-align: center; |
| padding: 14px 20px; |
| text-decoration: none; |
| } |
| |
| |
| .navbar a.right { |
| float: right; |
| } |
| |
| |
| .navbar a:hover { |
| background-color: #ddd; |
| color: black; |
| } |
| |
| |
| .row { |
| display: -ms-flexbox; |
| |
| display: flex; |
| -ms-flex-wrap: wrap; |
| |
| flex-wrap: wrap; |
| } |
| |
| |
| |
| .side { |
| -ms-flex: 20%; |
| |
| flex: 20%; |
| background-color: #f1f1f1; |
| padding: 20px; |
| } |
| |
| |
| .main { |
| -ms-flex: 60%; |
| |
| text-align: justify; |
| flex: 60%; |
| background-color: white; |
| padding: 10px; |
| } |
| |
| |
| .side { |
| -ms-flex: 20%; |
| |
| flex: 20%; |
| background-color: #f1f1f1; |
| padding: 20px; |
| } |
| |
| |
| .img { |
| < !-- background-color: #aaa; |
| -->< !-- width: 40%; |
| -->< !-- text-align: center; |
| -->padding: 20px; |
| } |
| |
| |
| .footer { |
| padding: 20px; |
| text-align: center; |
| background: #ddd; |
| } |
| |
| |
| @media screen and (max-width: 700px) { |
| .row { |
| flex-direction: column; |
| } |
| } |
| |
| |
| @media screen and (max-width: 400px) { |
| .navbar a { |
| float: none; |
| width: 100%; |
| } |
| } |
| </style> |
| </head> |
|
|
| <body> |
|
|
| <div class="header"> |
| <h1>Airborne Multi-Dimensional SAR Land Cover Dataset and <br> |
| Fusion Classification Method</h1> |
| <p>Nai-Rong Zheng<sup>1</sup>, Zi-An Yang<sup>1</sup>, Xian-Zheng Shi<sup>1</sup>, |
| Hong Yang<sup>2,3</sup>, Yue Sun<sup>2</sup>, Feng Wang<sup>1*</sup><br> |
| 1. Key Laboratory of Information Science of Electromagnetic Waves(MoE), <br> |
| Fudan University, Shanghai 200433, China <br> |
| 2. Aerospace Information Research Institute, Chinese Academy of Sciences, <br> |
| Beijing 100094, China.<br> |
| 3.School of Electronics and Information, Northwestern Polytechnical University, <br> |
| Xi’an 710129, China. |
| </p> |
| </div> |
|
|
| <div class="row"> |
| <div class="side"> |
| </div> |
|
|
| <div class="main"> |
|
|
| <h2>Abstract</h2> |
| <p> With the development of Synthetic Aperture Radar (SAR) imaging and deep learning, the use of deep |
| learning to classify land cover in SAR images has received extensive attention and applied research. In |
| this paper, a high-resolution airborne multi-dimensional SAR land cover classification dataset is |
| constructed based on the high-resolution airborne data of the Chinese Aeronautic Remote Sensing System |
| (CARSS) for Earth observation, whose name is AIR-MDSAR-Map (Airborne Multi-Dimensional Synthetic |
| Aperture Radar Mapping Dataset). <br> |
| The original data are obtained by CARSS, and the platform is a modified Xinzhou 60 remote sensing |
| aircraft. SAR images and optical images are generated according to the standard data production process. |
| AIR-MDSAR-Map contains polarization SAR images in bands of C, Ka, L, P, and S and high-resolution |
| optical images in Wanning, Hainan, and Sheyang, Jiangsu, with the spatial resolution ranging from 0.2 m |
| to 1 m depending on the band. It divides the land cover into nine categories and generates fine |
| pixel-level labels through a semi-automatic labeling algorithm. In this paper, the classical semantic |
| segmentation methods in deep learning, such as UNet, SegNet, Deeplab, and HRNet, are used to verify the |
| classification of AIR-MDSAR-Map. At the same time, we also test the classification sensitivity of |
| different band images to all kinds of land cover objects.<br> |
| This dataset includes multi-dimensional SAR images of the same place and time, which can be used for |
| fusion classification research. In this paper, multi-dimensional SAR data are fused and classified |
| through different fusion strategies, model fusion classifies land cover by selectively fusing the models |
| of each band, and the priori fusion uses the prior information of the classification results in each |
| band to distinguish land cover on defining the priority of objects. These two fusion methods outperform |
| the single-band in the performance of some types of land cover, and improve the FWIoU and PA by 10~15%, |
| the FWIoU reaches 69%, and PA is 81%.<br> |
| AIR-MDSAR-Map can satisfy the research and application requirements of different users and can be used |
| to study the characteristics of the same land cover object with different resolutions, bands, and |
| polarizations. Moreover, it can provide a strong promotion for the development of multi-dimensional SAR |
| applications. The AIR-MDSAR-Map and our algorithm are available at |
| <strong>github.com/NairongZheng/AIR-MDSAR-Map</strong>. |
| </p> |
|
|
| <h2> Citation </h2> |
| <p>@article{, <br> |
| title={Airborne Multi-Dimensional SAR Land Cover Dataset and Fusion Classification Method}, <br> |
| author={Nai-Rong Zheng, Zi-An Yang, Xian-Zheng Shi, Hong Yang, Yue Sun, Feng Wang}, <br> |
| journal={National Remote Sensing Bulletin}, <br> |
| year={2023} <br> |
| } |
| </p> |
|
|
| <h2>AIR-MDSAR-Map</h2> |
| <p>AIR-MDSAR-Map contains polarization SAR images in bands of P, L, S, C, and Ka and high-resolution optical |
| images in Wanning, Hainan, and Sheyang, Jiangsu. Land cover objects are divided into water, bare soil, |
| road, industry, vegetation, residence, plantation, farms, and other. Each class is labeled with |
| different colors, i.e. water in the blue, vegetation in green. |
| <br> |
| The advantages of the dataset include: <br> |
| (1) Accurate masks of 9 categories. <br> |
| (2) Including SAR images of different bands and optical images at the same place and time period. <br> |
| (3) Difference in features of the same category in the same or different patch images. <br> |
| </p> |
|
|
|
|
| <div class="img" style="height:450px;" align="center"> |
| <img src="example_1.jpg" width="965px" height="456px" /> |
| </div> |
|
|
|
|
|
|
| <strong> |
| <p>Information of polSAR images used to generate AIR-MDSAR-Map: </p> |
| </strong> |
| <div class="img" style="height:420px;" align="center"> |
| <img src="source_images_info.png" width="947px" height="459px" /> |
| </div> |
| <br> |
| <br> |
| <strong> |
| <p>AIR-MDSAR-Map can be downloaded from Baidudrive: </p> |
| </strong> |
| <a href="https://pan.baidu.com/s/1Zqb-JSFNAv-d0xSv54xvfA"> AIR-MDSAR-Map </a> <span> (extraction code:cbg4 ) </span> <br> |
| <a href="https://pan.baidu.com/s/1xpCEgr0FO8poYUZhsAUlDQ"> the raw data of AIR-MDSAR-Map </a> <span> (extraction code:myzn ) </span> |
|
|
| <strong> |
| <p>Contact </p> |
| </strong> |
| <p> E-mail: fengwang@fudan.edu.cn、nrzheng20@fudan.edu.cn</p> |
|
|
| </div> |
|
|
| <div class="side"> |
| </div> |
|
|
| </div> |
|
|
| </body> |
|
|
| </html> |
