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

A texture saliency-based object detection method for low-light images

A low-light image and target detection technology, applied in the field of image processing, can solve the problems of low contrast, poor target contour, high false alarm rate, etc.

Active Publication Date: 2016-12-28
NANJING UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since low-light images have no color information and low contrast, these methods are often applied to low-light image target detection, with low hit rate, high false alarm rate, and poor target contour

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 texture saliency-based object detection method for low-light images
  • A texture saliency-based object detection method for low-light images
  • A texture saliency-based object detection method for low-light images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] Such as figure 1 As shown, the present invention is a low-light image target detection method based on texture saliency, comprising the following steps:

[0055] Step 1: Extract the image roughness feature map as follows:

[0056] 1.1 Calculate the average gray value of the pixels in the active window whose size is 4k×4k in the image,

[0057] A k ( x , y ) = Σ i = x - 2 k x + 2 k - 1 Σ j = y - 2 k y + 2 k - ...

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 invention relates to a low-light image object detection method based on texture saliency. This method first extracts the image roughness feature map, performs binarization feature processing, merges the same target area, calculates the global saliency, local saliency and position saliency respectively, and then calculates the texture saliency to obtain the texture saliency map, and finally uses Texture saliency maps for image object detection. Its core content is to use the characteristics of the large difference between the target texture and the background of the low-light image to detect the target through the texture saliency. By using the method of the invention to detect low-light image targets, the target outline is good and the hit rate is high.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a low-light image target detection method based on texture saliency. Background technique [0002] Low-light technology is an important part of night vision technology. The low-light imaging system uses the natural radiation of night sky light and the reflection of objects to obtain images under the action of an image intensifier, which improves the observation ability of the human eye under weak light conditions. However, unlike ordinary visible light images, it is formed after multiple photoelectric conversions and electron multiplications, and has the characteristics of low contrast, low signal-to-noise ratio, and limited gray scale. These characteristics make the low-light image target suffer from noise interference, the contrast with the surrounding environment is low, the target is not obvious, and the automatic detection of the target is difficult. With the continu...

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): G06T7/00G06K9/46
CPCG06T7/13G06V10/60
Inventor 柏连发张毅金左轮韩静岳江陈钱顾国华
Owner NANJING UNIV OF SCI & TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com