Supercharge Your Innovation With Domain-Expert AI Agents!

A Subtle Target Detection Method in Large Scene SAR Images

A target detection and large scene technology, applied in scene recognition, neural learning methods, instruments, etc., can solve the problems of low accuracy, insensitivity of small target detection, slow detection speed of SAR image targets, etc. The effect of being slow and easy to learn

Active Publication Date: 2020-09-25
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention overcomes the problems of slow target detection speed, low accuracy rate and insensitivity to small target detection in large-scene SAR images in the prior art, and can realize accurate end-to-end detection of large-scene SAR image subtle targets

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
  • A Subtle Target Detection Method in Large Scene SAR Images
  • A Subtle Target Detection Method in Large Scene SAR Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0087] The present invention mainly adopts the method of simulation experiment for verification, and all steps and conclusions are verified correctly on tensorflow1.12.0. The specific implementation steps are as follows:

[0088] Step 1. Initialize and preprocess the SAR image of the large scene to be detected:

[0089] Large-scene SAR image preprocessing, including: initialize the SAR image to be detected as X, and the dimension of X is N 0 ×N 0 =5000×5000; initialize N=3 kinds of sliding window slices, and the dimensions of the sliding window slices are respectively M 1 × M 1 =600×600, M 2 × M 2 =800×800, M 3 × M 3 =1000×1000; N=3 kinds of sliding window slices are sorted according to the dimensions from small to large, and an N=3-layer image pyramid is obtained; the artificial targets to be detected in the SAR images to be detected are aircraft, ships, vehicles, buildings, and roads Carry out manual location and category labeling, and the total number of target cate...

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 proposes a method for detecting subtle targets in large-scene SAR images, which is based on the principle of convolutional neural network and YOLO algorithm target detection, transforms SAR image target detection into a regression problem, introduces a residual network structure and constructs a feature pyramid, and utilizes The 1×1 convolution kernel realizes the interaction of different feature layers and cross-scale prediction of SAR image targets, making the neural network more conducive to the feature extraction of large-scale SAR targets and real-time detection of small targets; The number of anchor boxes required for network training is less, the model representation ability is stronger, and the task is easier to learn. The invention has the advantages of simple implementation, high detection efficiency, high detection accuracy, fast detection speed and good applicability, and can realize accurate end-to-end detection of fine targets in SAR images of large scenes.

Description

technical field [0001] The invention belongs to the technical field of radar, in particular to the technical field of synthetic aperture radar (SAR) target detection. Background technique [0002] Synthetic Aperture Radar (SAR), as an all-weather, all-weather, and information-rich remote sensing imaging technology, has become an important means of earth observation today. Exploration and natural disaster monitoring and other national economic and military fields have been more and more widely used. For details, see the literature "Liu Guoxiang, Ding Xiaoli, Chen Yongqi, et al. A new technology for space earth observation with great potential-Synthetic aperture radar interferometry[J] . Advances in Earth Sciences, 2000, 15(6):734-740". With the continuous maturity of SAR technology and the continuous improvement of imaging resolution, the target detection technology through SAR images has received more and more attention. [0003] Object detection technology based on deep l...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/13G06N3/045G06F18/23213G06F18/24
Inventor 韦顺军苏浩闫敏周泽南王琛张晓玲师君
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com