Abstract
Polarimetric synthetic aperture radar (PolSAR) imagery can provide more intuitive and detailed SAR polarization information, and it is widely used in the classification and semantic segmentation of remote sensing. To bridge the PolSAR data and application, the 2020 Gaofen Challenge on Automated High-Resolution Earth Observation Image Interpretation provides a set of high-quality PolSAR semantic segmentation dataset. A series of preprocessing methods is first used to analyze the PolSAR images to improve the semantic segmentation performance of the PolSAR imagery. A special polarimetric decomposition method is used to extract the features, and the filter and the data truncation are implemented to enhance local and global information of images. And the random region matting method is proposed to expand the training samples. Finally, the DeepLabV3+ method with the ResNet101-V2 is employed to achieve the semantic segmentation. A variety of comparison experiments verifies the effectiveness of our methods. Simultaneously, compared with the classification methods of other groups in the competition, our methods have obvious advantages in the inference time and semantic segmentation accuracy. The proposed method achieved a frequency weighted intersection over union of 75.29% in the contest.
Highlights
O VER the last decade, the synthetic aperture radar (SAR) imagery has been widely used in the geographical survey, climate change research, and other applications due to its high resolution, day-and-night, and weather-independence
1) We designed a series of comparative experiments based on the classic segmentation method, and the results demonstrate the effectiveness of
The test data are composed of the 400 high-resolution fully polarimetric SAR (PolSAR) images, the image size ranges from 512 × 512 to 1500 × 1500, and the occupied memory of the test data is 1 GB
Summary
O VER the last decade, the synthetic aperture radar (SAR) imagery has been widely used in the geographical survey, climate change research, and other applications due to its high resolution, day-and-night, and weather-independence. It is a crucial research part of the image analysis and interpretation of SAR [1]–[3]. As a fundamental step in polarimetric SAR (PolSAR) image processing and applications, the semantic segmentation of PolSAR imagery can realize segmentation and categorization simultaneously, obtains smooth and fine-grained classification to assign one land cover category to each pixel [4]–[6]. It is beneficial in disaster monitoring, land cover classification, water identification, and so on. How to accurately segment PolSAR imagery to solve practical problems has become a hot topic, as well as one of the main topics in the Gaofen Challenge Contest
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
