A SAR Image Sample Block Selection Method Based on Aggregation Characteristics of Sketch Line Segments

Abstract

The invention discloses a SAR image sample block selection method based on the aggregation characteristics of sketch line segments, which mainly solves the problem of too many redundant samples in the SAR image mixed aggregation structure ground object pixel subspace division separated by 1 sliding window sample set in the prior art. The implementation plan is: extract the sketch map according to the sketch model of the SAR image; regionalize the sketch map to obtain a region map, and obtain the extremely heterogeneous area of ​​the SAR image according to the region map; extract all Sketch line segments, solve the rectangular block set formed by these sketch line segments and K-nearest neighbor sketch line segments; sample and expand in the corresponding extremely heterogeneous area according to the coordinates of the rectangular block in the rectangular block set, and obtain the sample block set. The invention can construct the sample set of the extremely heterogeneous region of the SAR image, and the constructed sample set can more comprehensively represent the structural characteristics of the extremely heterogeneous region.

Description

Technical field [0001] The present invention belongs to the field of image processing technology, particularly relates to a SAR image sample block selection method based on the aggregation characteristics of sketch line segments, applied to the determination of the training sample set of the inconsistency of the intercommunicated extremely heterogeneous region in the synthetic aperture radar SAR image mixed pixel subspace, further for the characteristic learning of the extremely heterogeneous region in the SAR image. Background [0002] Synthetic aperture radar SAR is an important advance in remote sensing technology to acquire high-resolution images of the Earth's surface. Compared with other types of imaging technologies, SAR is particularly suitable for large-area landmark imaging, which can penetrate clouds, rain and snow, and has the ability to work around the clock. With the rapid development of SAR image technology, more and more SAR image data is obtained, and automatic ...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that when learning the structural features of the disconnected areas in the aggregation area, the sample blocks sent to the deconvolution learning network are not selected, which makes the sample size large, resulting in network training time Long, and the space complexity is high, making the cost of network learning features larger

The disadvantage of this method is that when performing feature learning on highly heterogeneous regions that are not connected to each other in the pixel subspace of mixed aggregation structure features, this method is to collect every extremely heterogeneous region with a sliding window Random selection of the sample blocks obtained by the machine learning model makes the features learned by the machine learning model random, that is, it may be necessary to select random samples multiple times and learn features multiple times before it is possible to learn the extreme Good feature representation in heterogeneous regions affects the accuracy of pixel subspace segmentation of SAR images with mixed aggregation structures and increases training costs

Images