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

A Synergistic Saliency Detection Method

A detection method, a remarkable technology, applied in the field of image processing and stereo vision, can solve the problems of lack of joint optimization graph method, lack of multi-scale relationship acquisition method between graphs, etc., to achieve good consistency and suppress the effect of complex background areas

Active Publication Date: 2021-06-04
TIANJIN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The methods in the prior art usually lack a multi-scale inter-graph relationship acquisition method; the existing methods often lack the method of jointly optimizing the intra-graph and inter-graph saliency

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 Synergistic Saliency Detection Method
  • A Synergistic Saliency Detection Method
  • A Synergistic Saliency Detection Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] In order to accurately and completely extract the common saliency objects of the RGBD image group, the embodiment of the present invention designs a collaborative saliency detection method, see figure 1 and figure 2 , the specific implementation steps are as follows:

[0040] 101: Segment the RGB image through the superpixel segmentation method to obtain a uniform and consistent superpixel area, and use the RGBD saliency detection based on the depth confidence measure and multi-cue fusion to fuse the compact saliency and the foreground saliency to obtain Significance value in the graph;

[0041] 102: Based on similarity constraints, saliency consistency constraints, and clustering constraints, express the corresponding relationship between multi-image superpixels as a matching relationship under multiple constraints, and then obtain the matching relationship label between superpixels;

[0042] 103: Fuse the distances calculated by multiple features through an adaptiv...

Embodiment 2

[0047] The scheme in embodiment 1 is further introduced below in conjunction with specific calculation formulas and examples, see the following description for details:

[0048] 201: superpixel segmentation;

[0049] Suppose there are N RGB color images in the image group Its corresponding depth map is Using SLIC (simple linear iterative clustering) superpixel segmentation method to image I iCarry out segmentation, and obtain N after segmentation i A uniform and consistent superpixel region, denoted as Among them, D i is the i-th depth map; is the superpixel region.

[0050] 202: In-graph saliency calculation;

[0051] The intra-graph saliency model is used to calculate the saliency map of a single image in an image group, without involving the relationship between graphs. In a single image, salient objects usually exhibit distinct appearance characteristics from background regions, thereby making salient objects stand out. In addition, depth information, as a sup...

Embodiment 3

[0096] Combine below figure 1 and figure 2 , carry out feasibility verification to the scheme in embodiment 1 and 2, see the following description for details:

[0097] figure 1 The visual detection results of this method are given. The first row is the original RGB color image, the second row is the corresponding depth map, the third row is the ground truth image, and the fourth row is the co-saliency detection result obtained by this method.

[0098] From figure 1 It can be seen from the figure that this method can effectively extract the common saliency target of the image group, that is, the blonde cartoon character, and can effectively suppress the complex background area to obtain a more complete and consistent saliency target.

[0099] Those skilled in the art can understand that the accompanying drawing is only a schematic diagram of a preferred embodiment, and the serial numbers of the above-mentioned embodiments of the present invention are for description only,...

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 collaborative saliency detection method, comprising: segmenting an RGB image through a superpixel segmentation algorithm, and fusing compact saliency and foreground saliency to obtain a saliency value in the image; based on similarity constraints, saliency consistency Constraints and clustering constraints, the corresponding relationship between multi-image superpixels is expressed as a matching relationship under multiple constraints, and then the matching relationship label between superpixels is obtained; the distance calculated by multiple features is calculated by an adaptive weighting strategy Perform fusion to obtain a measure of similarity between two images; the inter-image saliency value of a superpixel is the weighted sum of the single-image saliency values ​​of corresponding superpixels in other images, and the weighted value is obtained by the inter-image similarity measure Coefficients to obtain the significance value between graphs; use cross-label propagation to jointly optimize the significance value in the graph and between graphs; carry out weighted fusion of the initial graph and graph significance value, the optimized graph and graph significance value to get Final co-salience results.

Description

technical field [0001] The invention relates to the technical fields of image processing and stereo vision, in particular to a collaborative saliency detection method. Background technique [0002] As a cutting-edge technology in the field of artificial intelligence and computer vision, visual saliency detection technology has been widely used in many visual tasks such as image retrieval, compression, perceptual enhancement, and image redirection. With the advent of the big data era, collaborative saliency detection technology is in the ascendant, and its purpose is to simultaneously detect common salient objects in multiple images. [0003] Different from traditional single-image saliency detection models, co-saliency detection models aim to discover common salient objects from image groups containing two or more related images, and the categories, intrinsic features, and locations of these objects are often different. is unknown. Therefore, the co-saliency target needs t...

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): G06K9/46
CPCG06V10/443G06V10/56G06V10/462
Inventor 雷建军丛润民侯春萍张静范晓婷彭勃
Owner TIANJIN UNIV
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