Bio-inspired top-down visual attention method

A top-down, bio-inspired technology applied in the field of computer vision, which can solve the problem of poor visual attention

Inactive Publication Date: 2010-11-24
HUAZHONG UNIV OF SCI & TECH
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] These two existing top-down visual attention methods are both related to the background where the object is located, so when the background where the object is located changes, that is, when the object in the to-be-attention image does not always appear in the background of the training image, Or when the combination of the object and its background in the image to be noticed is very different from the combination of the object and its background in the training image, the visual attention effect of the existing method will become poor

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
  • Bio-inspired top-down visual attention method
  • Bio-inspired top-down visual attention method
  • Bio-inspired top-down visual attention method

Examples

Experimental program
Comparison scheme
Effect test

example

[0120]The present invention uses the Itti model, the VOCUS top-down model Navalpakkam model and the model of the present invention respectively act on the same image to be noticed and the learning graph. Among the 50 sets of experiments, there are 24 natural scenes, including 20 single-object scenes and 4 multi-object scenes, in addition to 26 synthetic scenes, including 17 single-object scenes and 9 multi-object scenes. The experiment has two forms, one is to know the feature type to pay attention to, for example, if the task of the present invention is to find a horizontal red target, then the first feature type red and the sixth feature type 0° are relevant at this time Feature type, so let μ(1)=1, σ(1)=0, μ(6)=1, σ(6)=0, and the rest of the mean and variance are zero, the experimental results are as follows Figure 4 shown. Another method is to not know the type of features to pay attention to. Taking a natural scene as an example, Figure 5 and Figure 6 are the experi...

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 discloses a bio-inspired top-down visual attention method, which comprises the following steps of: (1) extracting the characteristics of all learning maps; (2) representing all the learning maps of the same type with mean vectors and standard deviation vectors; (3) acquiring a top-down map prominent map and a bottom-up prominent map of a map to which attention is to be paid; (4) acquiring a final prominent map; (5) performing a winner-take-all method; (6) performing inhibition of return, and setting pixel values of areas where most prominent points in the final prominent map to be zero to obtain a new final prominent map; and (7) performing attention selection. In the method, in the presentation of a learning target, only own characteristics of the learning target are utilized and the background of the learning target is not taken into account, so the representation of the target has stronger robustness and relatively better visual effect is achieved.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a biologically motivated top-down visual attention method. Background technique [0002] Visual attention methods mainly address the problem of data screening in images. In computer graphics, the content of the task is usually only a small part of the image, so it is necessary to assign different processing priorities to different image regions, which can reduce the complexity of the processing process and reduce unnecessary computational waste. In human visual information processing, a few salient objects are always quickly selected for priority processing, and other non-salient objects are ignored or discarded, so that the present invention can selectively allocate computing resources, thereby greatly improving visual information processing. processing efficiency, the process is called visual attention. [0003] Psychological research has found that not only those ...

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): G06T7/00G06T5/00
Inventor 桑农魏龙生王岳环高常鑫左峥嵘杨卫东胡静
Owner HUAZHONG UNIV OF SCI & TECH
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