Check patentability & draft patents in minutes with Patsnap Eureka AI!

Image saliency object detection method and system based on local feature weighting enhancement

A technology of object detection and local features, applied in the field of computer vision, can solve problems such as difficulty in detecting target objects

Active Publication Date: 2018-10-09
ZONGMU TECH SHANGHAI CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] When there is a situation where the detected object has a weak contrast in the overall environment but there are sub-regions that make the contrast relatively strong, it is difficult to detect the target object in the image using conventional saliency analysis methods such as contrast

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
  • Image saliency object detection method and system based on local feature weighting enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] Such as figure 1 as shown,

[0050] An image salient object detection method based on local feature weighted enhancement, comprising the following steps:

[0051] S1, the original image is divided into several sub-region original images; the sub-region original image is divided according to the position and size of the target object that may appear in the original image, and there is at least one sub-region in each sub-region original image, so that in this The target object in the sub-region forms a relatively strong contrast with the surrounding environment; when there is an overlapping area between the original images of the sub-region, further normalize the weight of the overlapping area;

[0052] S2, for each sub-region original image, obtain the sub-region saliency image corresponding to the sub-region original image, and map it to the range of 0-255 to obtain the sub-region saliency analysis image; traverse the sub-region saliency analysis image For each pixel,...

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 provides an image saliency object detection method based on local feature weighting enhancement. The method is characterized by dividing an original image into a plurality of subregion original images; and for each subregion original image, obtaining a subregion saliency analysis image and a subregion stretching image, and comparing the two to obtain a subregion binary image. The method can detect the object with not obvious contrast in the whole environment, can carry out weighting of each sub-image saliency characteristic value by utilizing a normalization coefficient of each sub-image saliency characteristic value and remap each sub-image saliency image to a range of 0-255, thereby preventing the problem that a real object is covered since the overlapped areas are overly reinforced, and effectively detecting the saliency object.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to an image salient object detection method and system based on local feature weighted enhancement. Background technique [0002] Visual salience is a concept from neuroscience and physiology that makes attention-grabbing areas stand out from a person's visual field. [0003] Detecting the same object in different contrast environments is a challenge for various current object detection methods based on saliency analysis. Since the detected target object always has a relatively high contrast with the surrounding environment in a local area. Similar to when humans observe a certain type of object in the environment, the object has a certain intensity of contrast in at least a certain local area, so that our visual system can recognize it from the surrounding environment. Conversely, if the contrast between the target object and the surrounding environment is very weak, and it cannot ...

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): G06T7/11G06T7/70
Inventor 吴子章王凡唐锐
Owner ZONGMU TECH SHANGHAI CO LTD
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