Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image significance object detection method based on multiscale low-rank decomposition and with sensitive structural information

A low-rank decomposition and structural information technology, applied in image enhancement, image analysis, image data processing, etc.

Inactive Publication Date: 2014-04-02
BEIHANG UNIV
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention is to generate a brand-new feature space by adopting the geometric diffusion method in graphics, which can effectively combine local information and global information to distinguish salient objects and non-salient backgrounds; Based on this feature space, a multi-scale low-rank decomposition method is used to perform complete and accurate detection of salient objects

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 significance object detection method based on multiscale low-rank decomposition and with sensitive structural information
  • Image significance object detection method based on multiscale low-rank decomposition and with sensitive structural information
  • Image significance object detection method based on multiscale low-rank decomposition and with sensitive structural information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0033] figure 1 The overall processing flow of the image salient object detection method based on multi-scale low-rank decomposition and sensitive to the result information is given.

[0034] This paper invents an image salient object detection method based on multi-scale low-rank decomposition and sensitive to the result information. The main steps are as follows:

[0035] 1. Formation of 3D volume data

[0036] (1) Superpixel decomposition

[0037] This method first decomposes the original two-dimensional image into a superpixel map with superpixels as the smallest unit through SLIC superpixel decomposition. The SLIC superpixel decomposition parameter sigma_s is set to 60, and sigma_r is set to 0.01. The superpixel decomposition results are as follows: attached figure 2 (b) shown.

[0038] (2) Delaunay triangulation

[0039] Based on t...

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 an image significance object detection method based on multiscale low-rank decomposition and with sensitive structural information. The method comprises the following steps of: a three-dimensional volume data generation stage: performing superpixel decomposition and DT (Delaunay Triangulation) on a two-dimensional image to form three-dimensional volume data corresponding to the two-dimensional image, a Biharmonic distribution calculation stage: obtaining a Biharmonic diffusion result of each superpixel point, a subgeneration description stage: performing histogram statistics on L2 distances between sampling points on Biharmonic isolines of the superpixel points to form shape description of the isolines, and a multiscale low-rank decomposition stage: obtaining a final significance object detection result by differencing sparse matrixes obtained by the low-rank decomposition under different scales and performing residual error matrix summation based on the shape description of the Biharmonic isoline of each superpixel point. The method is based on GPU (Graphics Processing) parallel implementation, can detect one or more significance objects in the image, and has the characteristics of high detection precision of the significance object, complete detection of the significance object, good noise resistance and the like.

Description

technical field [0001] The invention relates to an image salient object detection method based on multi-scale and low-rank decomposition of image thermal diffusion information of image superpixel points. Background technique [0002] Since the late 1990s, the research on salient object detection has been developed for nearly 15 years. This field involves the detection of single and multiple salient objects in a single image with complex backgrounds. Salient object detection is usually used in the preprocessing stage of the image, which can help follow-up work to guide relatively meaningful objects in the image scene, and is usually used in image relocation, image compression, video conferencing, etc. In recent years, with the gradual understanding of the characteristics of salient objects, the accuracy of salient object detection has been greatly improved, and it has gradually become one of the most influential research methods in the field of image vision. [0003] Common...

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): G06T7/00G06T5/40
Inventor 郝爱民陈程立诏李帅
Owner BEIHANG UNIV
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
Eureka Blog
Learn More
PatSnap group products