Unlock instant, AI-driven research and patent intelligence for your innovation.

Sar image vehicle detection method based on feature fusion sparse representation model

A technique of sparse representation and feature fusion, applied in the field of image processing

Active Publication Date: 2020-10-20
ZHEJIANG SCI-TECH UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to improve the accuracy of vehicle detection in SAR images in order to improve the accuracy of vehicle detection in SAR images, and propose a vehicle detection in SAR images based on feature fusion sparse representation model for the existing SAR image vehicle detection method. method
The residuals are then normalized and composed into a single residual series

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sar image vehicle detection method based on feature fusion sparse representation model
  • Sar image vehicle detection method based on feature fusion sparse representation model
  • Sar image vehicle detection method based on feature fusion sparse representation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings and embodiments, and the purpose and effect of the present invention will become more obvious.

[0035] The image is a SAR image provided by Sandia National Laboratories, such as image 3 As shown in , the image is mainly composed of areas of vehicles, buildings, roads, trees and other objects (such as rocks, helicopters and tanks, etc.). According to the flow chart of the technical solution of the present invention to this image figure 1 to process, in this example, figure 1 In N=4, the specific steps are as follows:

[0036] Step 1, preprocessing, that is, filtering the SAR image with a non-local mean method, and then performing image threshold segmentation;

[0037] Step 2, grayscale enhancement, that is, adjust low grayscale values ​​using linear transformation method. After stretching, [0,αμ x ] The gray value within is mapped to [0,βμ y ] so that these gray va...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a synthetic aperture radar (Synthetic Aperture Radar, SAR) image vehicle detection method based on a feature fusion sparse representation model. Accuracy of vehicle detection in SAR images. In this method, based on the relevant dictionary set of the training target data, a series of features extracted from each test target are sparsely reconstructed to generate a series of residuals. The residuals are then normalized and composed into a single residual series. Based on the residual sequence set of all the features collected, the best estimate of the target category is determined according to the linear fusion strategy, and the detection results of the test target are obtained accordingly. The invention fully utilizes the good resolution ability of the sparse representation model based on feature fusion, and considers the change of the scene complexity in the image, effectively improves the detection rate of the vehicle in the SAR image, and has higher accuracy.

Description

technical field [0001] The invention belongs to the technical field of image processing, and more specifically relates to a synthetic aperture radar (Synthetic Aperture Radar, SAR) image vehicle detection method based on a feature fusion sparse representation model. Background technique [0002] Vehicle detection is a challenging task in synthetic aperture radar image processing. Generally, vehicle detection consists of two stages: suspected region extraction and object classification. There are already many methods in the prior art that can deal with the problem of target detection in SAR images, among which, the representative ones are methods based on template matching and methods based on model design. The former depends on the matching degree of the target image or feature vector and the template on the data, while the latter depends on the statistical relationship of the model between the training sample and the test sample. By evaluating the class of parameters that...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/10G06T7/11G06T7/136G06K9/46
CPCG06T5/10G06T7/11G06T7/136G06T2207/10044G06V10/50G06V10/513G06V10/44
Inventor 吕文涛郭理鹏戴开燕任佳伟徐伟强
Owner ZHEJIANG SCI-TECH UNIV