SAR Image Accumulation Region Extraction Method Based on One-sided Accumulation Line Segment

Abstract

The invention discloses an SAR (Synthetic Aperture Radar) image gathering area extraction method based on single-sided gathering line segments. The method mainly solves the problems that an arc appears at the border and the speed is low in the method based on a circular operator acquisition gathering area. The method comprises the steps of: 1, finding the single-sided gathering line segments thatcan produce a border according to a topological relation of line segments in a gathering line segment set, and adding the single-sided gathering line segments into a border line segment set; 2, generating a straight line according to the situation that the number of line segments in the border line segment set is different to form a closed initial polygonal area; and 3, seeking a line segment endpoint satisfying the condition in the gathering line segment set according to the spatial position relation between the line segment endpoint and the initial polygonal area, adding the line segment endpoint into the polygon, and performing gradual inward approximationto obtain a polygonal gathering area. The method realizes accurate and quick extraction of the SAR image gathering area, and can be used for semantic segmentation and target recognition of an SAR image.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a method for extracting a SAR image gathering area, which can be used for SAR image semantic segmentation and target recognition. Background technique [0002] Synthetic aperture radar (SAR) is an important direction in the field of remote sensing technology, which is used to obtain high-resolution images of the earth's surface. Compared with other types of imaging technology, SAR imaging technology has very important advantages. It is not affected by atmospheric conditions such as clouds, rain or heavy fog, and light intensity, and can obtain high-resolution remote sensing data all day and all day. The interpretation technology of SAR images has important guiding significance for many fields such as military affairs, agriculture, and geography. SAR image segmentation is one of the key issues of SAR image interpretation, and it is also the basis and premise of SAR image...

AI Technical Summary

Problems solved by technology

The use of the center operator to extract clustered regions proposed in the SAR image segmentation based on Sketch Map and semantic information classification avoids the unsupervised SAR image segmentation method based on pixels or superpixels on SAR images that cannot merge pixels or superpixels to form connected regions. The difficulty is to use the center operator to extract the aggregated area through expansion and erosion operations in an aggregated line segment set generated by the seed line segment. However, this method of extracting the aggregated area is not only slow, but the boundary of the aggregated area appears arc-shaped, resulting in The boundary of the gathering area is inaccurate and does not conform to the actual object shape, and the circle center operator does not use the sketch line segment as the primitive to extract the gathering area, resulting in a slow extraction speed of the gathering area

Images