SAR (Synthetic Aperture Radar) sea ice image segmentation method adopting SRGB-RMRF

Abstract

The invention discloses a segmentation method for SAR (Synthetic Aperture Radar) sea ice images. The segmentation method is mainly used for solving the problem that segmentation results cannot actually reflect the distribution condition of earth surface sea ice due to the fact that the SAR sea ice images are severely affected by coherent speckle noises. The segmentation method comprises the implementation procedures: (1) filtering the SAR sea ice images by adopting a two-sided filter; (2) carrying out initialized segmentation by adopting improved edge weight computation model and intra-regional differences; (3) constructing a regional MRF model based on an initialized segmentation structural element region adjacency graph; (4) integrating an inter-regional intensity difference penalty function into MRF; (5) erasing edge pixels, thereby obtaining a final segmentation result. According to the segmentation method, the performance of segmentation of the SAR sea ice images is remarkably improved.

Description

technical field [0001] The invention relates to the field of image segmentation methods, in particular to a SAR sea ice image segmentation method using SRGB-RMRF. Background technique [0002] In sea areas covered by sea ice, sea ice information is very important for ship route design. As the global climate gradually warms and the polar glaciers melt, sea ice information is also of great significance in the field of climate research. Synthetic Aperture Radar (SAR), as a high-resolution microwave remote sensing imaging radar, has the characteristics of all-weather, all-time, multi-band, multi-polarization, variable viewing angle, and strong penetrability, making it widely used. applied to sea ice monitoring. SAR sea ice image segmentation, as one of the key technologies in this field, has attracted more and more attention. [0003] The classic SAR sea ice image segmentation methods mainly include: threshold method, hybrid method combined with edge detection and region mergi...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a SAR sea ice image segmentation method using SRGB-RMRF to solve the problem that the SAR sea ice image is seriously affected by coherent speckle noise, and to provide subsequent regional MRF with the SRGB method with stronger coherent speckle suppression ability. A more accurate initial segmentation area, and a penalty function for inter-regional intensity differences is introduced in the MRF model to obtain more accurate segmentation results

Images