Dark and dim point target detection method in infrared image

A target detection and infrared image technology, applied in the field of infrared detection, can solve the problems of limited number of candidate targets and high probability of missed detection, and achieve the effect of easy real-time implementation, low complexity and high detection probability

Inactive Publication Date: 2017-11-07
CHANGCHUN INST OF OPTICS FINE MECHANICS & PHYSICS CHINESE ACAD OF SCI
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional top-hat algorithm only uses one structural element, ignoring the differences in point target details in different directions, so the number of candidate targets detected by it is limited, which may result in a greater probability of missed detection

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
  • Dark and dim point target detection method in infrared image
  • Dark and dim point target detection method in infrared image
  • Dark and dim point target detection method in infrared image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0102] The present invention adopts self-constructed equipment to collect infrared weak point target image sequences, and the 5 frames of images in the sequence are shown in image 3 . The image contains a large number of complex cloud backgrounds, and there are many fixed or random noises in the background. These noises seriously interfere with the detection of small targets and easily cause a large false alarm rate.

[0103] The present invention first adopts Top-hat, Bottom-hat transformation combined operation, namely original image adds top-hat transformation result and subtracts bottom-hat transformation result again, adopts the structural element of design 8 directions here, extracts image in all Point target regions of interest that may be distributed, and then combine these extracted regions of interest. Next, apply adaptive threshold to the image of the above-mentioned processing results and adopt constant false alarm threshold processing to obtain candidate targets...

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 discloses a dark and dim point target detection method in an infrared image. 8 structure elements with 5*5 dimension of a direction are employed to extract all possible targets with different scales; obtaining a target interest area, through adaptive threshold processing so as to effectively improve the target signal to noise ratio; employing the decision criterion of distribution of a background edge point-to-point target at a local neighborhood, and rejecting residual background edge points; and rejecting noisy points according to an interframe matching relation and obtaining a target movement locus. The dark and dim point target detection method in the infrared image is not high in algorithm complexity and satisfies timeliness requirements; and the target detection probability is high, the false alarm rate is low, and the dark and dim point target detection method in the infrared image has important application values.

Description

technical field [0001] The invention belongs to the technical field of infrared detection, and in particular relates to a method for detecting dark spots in infrared images, which is suitable for detecting dark spots in infrared images with a signal-to-noise ratio of about 2 to 3 under complex backgrounds. Background technique [0002] Infrared dark spot target detection technology is of great significance to the development of infrared search system, precision guidance and other fields. The working distance is an important index to measure the infrared search and tracking system. The imaging size of the long-distance low signal-to-noise ratio point target changes between 1×1 to 3×3 pixels during the movement, and its shape information changes with the distance and imaging distance. The difference in angle is constantly changing. In fact, the image formed by the point target on the detector seldom occupies 1 pixel, and more often it will spread into 2 pixels in the horizont...

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 Applications(China)
IPC IPC(8): G06T3/40G06T7/13G06T7/20G06K9/32
CPCG06T3/4038G06T7/13G06T7/20G06T2207/10048G06V10/25G06V2201/07
Inventor 王德江刘让贾平车鑫
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