Target detection method based on multi-source sensor fusion

A target detection and source sensor technology, applied in instrumentation, image analysis, image enhancement, etc., can solve the problem of detecting low, small and slow targets that cannot cope with fast scene changes, achieve wide practicability, improve accuracy and reliability, high The effect of accuracy

Active Publication Date: 2022-04-26
CHANGCHUN INST OF OPTICS FINE MECHANICS & PHYSICS CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a target detection method based on multi-source sensor fusion to solve the problem that existing target detection methods cannot cope with rapid scene changes or detect low, small and slow targets in complex backgrounds

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
  • Target detection method based on multi-source sensor fusion
  • Target detection method based on multi-source sensor fusion
  • Target detection method based on multi-source sensor fusion

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0047] Specific implementation mode 1. Combination Figure 1 to Figure 8 Describe this embodiment, the target detection method based on multi-source sensor fusion;

[0048] Step 1, extracting regions of interest from infrared images and visible light images;

[0049] Obtain an infrared image, use Weighted Moving Mean background modeling (Weighted Moving Mean) to carry out foreground extraction to the infrared image, and complete the positioning of the infrared image region of interest;

[0050] The specific process is: the following formula is used to represent the weighted average value of the image pixels:

[0051]

[0052]

[0053] In the formula, weighted_mean is the weighted average of image pixels, weight is the weight, and image_f is the input image;

[0054] Infrared image imaging conforms to the laws of thermodynamics, and the one-dimensional information entropy of the infrared image is calculated as a threshold to distinguish the front and back backgrounds, amo...

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 target detection method based on multi-source sensor fusion, relates to the technical field of image processing automatic detection, and solves the problem that existing target detection methods cannot cope with rapid scene changes or detect low, small and slow targets in complex backgrounds. Extract the region of interest of the image; perform image fusion based on rolling guided filtering and weighted least squares optimization function to obtain the fused image F; input the fused image of the region of interest, and complete the detection of small slow objects through the background modeling method. The invention adopts the method of multi-sensor image fusion to detect the target, which is different from traditional algorithms such as VIBE and PBAS, and uses the information complementation between the visible light camera and the infrared camera to improve the accuracy and reliability of the detection, and the fused image has obvious The texture features and high resolution input into the static background modeling framework can resist the influence of illumination, special weather, and object occlusion to achieve all-weather work.

Description

technical field [0001] The invention relates to the technical field of image processing automatic detection, in particular to a "low, small and slow" target detection method based on multi-source sensor fusion. Background technique [0002] At present, the "low, small and slow" target detection technology is a key technology for precision guidance, infrared search and tracking, and reconnaissance and warning systems. Small targets have always been a challenging research topic in the field of target detection, and their detection performance directly determines the operating distance and detection sensitivity of the system. The traditional "low, small and slow" target detection VIBE algorithm and PBAS algorithm cannot cope with special occasions such as rapid scene changes or complex backgrounds, so they cannot work stably. Contents of the invention [0003] The present invention provides a target detection method based on multi-source sensor fusion in order to solve the p...

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): G06T7/00G06T7/136G06T5/50
CPCG06T7/0002G06T5/50G06T7/136G06T2207/20104G06T2207/10048
Inventor 孙海江吴言枫
Owner CHANGCHUN INST OF OPTICS FINE MECHANICS & PHYSICS CHINESE ACAD OF SCI
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