Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

SAR Target Recognition Method Based on Cooperative Representation of Multi-scale Features

A multi-scale feature and collaborative representation technology, which is applied in scene recognition, character and pattern recognition, instruments, etc., can solve the problems of complicated target recognition processing process and low recognition processing efficiency, and solve the problem that the target recognition processing process is relatively complicated and efficient. Accuracy of target recognition and high efficiency of recognition processing

Active Publication Date: 2019-04-26
CHONGQING UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above-mentioned problems existing in the prior art, the present invention provides a SAR target recognition method based on multi-scale feature cooperative representation, which can ensure that SAR images have While having good target recognition accuracy, it can effectively improve the recognition processing efficiency, so as to solve the problems of complicated target recognition processing process and low recognition processing efficiency in the existing SAR target recognition technology

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 Target Recognition Method Based on Cooperative Representation of Multi-scale Features
  • SAR Target Recognition Method Based on Cooperative Representation of Multi-scale Features
  • SAR Target Recognition Method Based on Cooperative Representation of Multi-scale Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0094] This embodiment uses the MSTAR database to do the experiment, which is the measured data obtained by the X-band SAR system of the San Diego National Laboratory in the United States. It has a resolution of 0.3m × 0.3m, and is respectively at the pitch angle of 15 degrees and 17 degrees. acquired. In this embodiment, three types of targets, BMP2 (infantry tank), BTR70 (armored personnel carrier), and T72 (T-72 main station tank) in the MSTAR database are used for experiments. The visible light images of BMP2, BTR70, and T72 three different types of radar targets are as follows: figure 2 (2a), (2b), (2c), and the SAR images of three different types of radar targets BMP2, BTR70, and T72 are as follows image 3 In (3a), (3b), (3c) shown. It can be seen that these military or civilian vehicle targets are similar in size and easily confused when identifying them. The pixel density of each SAR image in the MSTAR database is 128 rows × 128 columns. In this embodiment, the SA...

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 present invention provides a SAR target recognition method based on multi-scale feature collaborative representation, which utilizes multi-scale features of SAR images, combined with a collaborative representation classification and recognition method, adopts a regularized least mean square collaborative representation model, and L1 norm constraints Compared with the sparse representation recognition algorithm under , it can make full use of the information of all categories of training samples, and the computational complexity is greatly reduced; while the multi-scale feature significantly reduces the feature dimension, and retains the discriminative feature information in the original SAR target image; Experimental results show that the correct recognition rate of the recognition method of the present invention can reach 96.93%, which can ensure good target recognition accuracy for SAR images, and the recognition processing efficiency of the recognition method of the present invention is very high, and the entire recognition process The time-consuming is much lower than the sparse representation classification recognition method, which can effectively improve the recognition processing efficiency while ensuring the recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of radar target recognition, in particular to a SAR target recognition method based on multi-scale feature cooperative representation. Background technique [0002] Synthetic Aperture Radar (SAR) technology is a pulse radar technology that uses mobile radar mounted on satellites or aircraft to obtain radar target images in high-precision geographic areas. Synthetic aperture radar is an active microwave imaging system, which can provide high-resolution images of the target area by irradiating the target area with electromagnetic waves and analyzing the echo signals. It has all-weather, all-day working ability and certain penetration ability. In view of its advantages, it is widely used in fields such as mineral exploration, marine environment monitoring and military defense. In the field of military defense, the research on target recognition is the most extensive, so the research on SAR Automatic Target Re...

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): G06K9/00G06K9/62
CPCG06V20/13G06F18/24
Inventor 张新征刘苗苗王亦坚
Owner CHONGQING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products