SAR image ship target identification method based on multi-level feature depth fusion

Abstract

The invention discloses an SAR (Synthetic Aperture Radar) image ship target identification method based on multi-level feature deep fusion. The SAR image ship target identification method comprises the following steps: (1) processing an SAR image sample by adopting a Haar-like feature template and reducing dimensions to obtain low-level Haar-like features; (2) processing the SAR image sample by using a convolutional neural network to obtain high-level depth features; (3) fusing the low-level Haar-like features and the high-level depth features by using a multi-level deep learning network to obtain a multi-level feature weight coefficient, and then obtaining an optimal SVM classifier through learning training; and (4) identifying the input SAR image sample slice to be identified by using the multi-level feature weight coefficient and the SVM classifier. According to the method, the detection performance of the SAR image ship target can be effectively improved, and the method has high engineering application value.

Description

technical field [0001] The invention relates to the technical field of SAR image target recognition, in particular to a SAR image ship target identification method based on deep fusion of multi-level features. Background technique [0002] Synthetic Aperture Radar (SAR) is a high-resolution imaging radar with all-weather and all-weather observation capabilities. The research and technology development of ship target identification and surveillance using SAR images has been highly valued in the field of marine remote sensing, and it is a research hotspot in the marine application of SAR images at this stage. [0003] So far, a large number of feature extraction algorithms based on edge textures have been proposed and applied in the field of target identification, including Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), Competitive Local Binary Patterns (CompletedLocal Binary Patterns, CLBP), Multi-ScaleCompleted Local Binary Patterns (MS-CLBP), Gray Leve...

AI Technical Summary

Problems solved by technology

However, when the traditional deep learning network performs target feature extraction and identification, it will cause the loss of low-level features such as the edge texture of the ship target. The accuracy of ship target identification in SAR images with low resolution and small samples is not high, which limits its direct Applied to SAR image ship identification

Especially in complex environments such as multiple targets, the lack of samples and edge features reduces the target discrimination rate of traditional deep learning networks.

Images