Infrared small object single-frame detection method based on nerve network and morphology

A neural network, weak and small target technology, applied in the field of infrared weak and small target single-frame detection, can solve problems such as reducing the probability of false alarms and more residual noise points

Inactive Publication Date: 2006-11-29
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method overcomes the problem of too much background clutter and too many interference points caused by inaccurate background estimation in the past, and at the same time solves the problem of too many residual noise

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
  • Infrared small object single-frame detection method based on nerve network and morphology
  • Infrared small object single-frame detection method based on nerve network and morphology
  • Infrared small object single-frame detection method based on nerve network and morphology

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0047] In order to better understand the technical solutions of the present invention, the embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0048] The principle block diagram of the present invention based on neural network and morphology device for detecting weak and small infrared point targets is as follows figure 1 As shown, the filtering process is mainly divided into three parts: morphological filtering optimized by neural network, secondary threshold segmentation, and neural network classifier. The morphological filter is the beginning of the whole process, and the morphological filter can be decomposed into two basic problems of morphological operation and structural elements. When the morphological operation rules are determined, the final filtering performance of the morphological filter depends only on the selection of structural elements. The present invention uses a series of pre-obtained sample dat...

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

A single frame detection method of infrared weak object based on neural network and morphology includes collecting a training sample with various point object and background first, structuring neural network for optimizing said training element and combining it with revision morphology operator to structure morphological filter for making background estimation, using primary threshold to remove of interference point then using secondary threshold and neural network classifier to remove off noise point for achieving high detection probability and high false alarm probability.

Description

technical field [0001] The invention relates to a target detection method in the technical field of image processing, in particular to a single-frame detection method for weak infrared targets based on neural network and morphology. Background technique [0002] Based on the characteristics of infrared weak and small target detection, it is difficult for traditional methods to coordinate the contradiction between algorithm complexity and calculation speed. Among them, although the feature method and the optical flow field method can extract the three-dimensional shape and depth information of the moving target well in theory, there is no more general feature selection and matching algorithm, and the basic equation of the optical flow field is only used in special cases. The occasion is established. On the other hand, single-frame detection and multi-frame detection are two basic methods of infrared weak and small moving target detection. Due to the instability of the real-...

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): G06T7/00G06T5/00
Inventor 李建勋张鹏
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap