Maximum cohesiveness super-pixel gridding method and super-pixel-level image processing method

An image processing and superpixel technology, which is used in image data processing, image analysis, instrumentation, etc.

Inactive Publication Date: 2013-12-25
TIANJIN UNIV
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complexity of natural image texture, brightness, and shadows, as well as the irregular segmentation methods of superpixel methods (including the size, shape, and irregular distribution of superpixels), there is no single algorithm that can handle all types of images. The images have ideal segmentation and target detection results

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
  • Maximum cohesiveness super-pixel gridding method and super-pixel-level image processing method
  • Maximum cohesiveness super-pixel gridding method and super-pixel-level image processing method
  • Maximum cohesiveness super-pixel gridding method and super-pixel-level image processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to regularize any irregular superpixel structure, this algorithm first uses the superpixel segmentation results of the target image, and dynamically places each superpixel in a virtual rectangular grid based on its coordinates: the grid The structure should preserve the overall coherence of the original superpixel structure, the connectivity between superpixels, local and global features as much as possible; at the same time, since the number of superpixels is not enough to occupy all the virtual grid nodes, We play the role of occupying the grid position and transferring energy by introducing pseudo-nodes. Then, we use a cascaded dynamic programming algorithm to rearrange the positions of the pseudo-nodes in the virtual grid to maximize the cohesion of the superpixel grid. Finally, the obtained maximum cohesive superpixel grid can be applied to many computer vision tasks, including target recognition and detection, target collaborative segmentation, etc.

[0...

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 belongs to the field of computer vision and media calculation. According to the technical scheme, in order to achieve the purpose that regularized arrangement is carried out on any irregular super-pixel structures, a maximum cohesiveness super-pixel gridding method and a super-pixel-level image processing method comprise the following steps that (1) each super-pixel is placed into a virtual rectangular grid in a dynamic mode on the basis of coordinates of the super-pixels according to a super-pixel division result of a target image, wherein the structure of the grid needs to reserve integral coherence of an original super-pixel structure, connection among super-pixels, local features and global features to the maximum extent; (2) the effect of occupation of the positions of the grids and the effect of energy transmission are achieved through introduction of fake nodes; (3) the positions of the fake nodes in the virtual grids are rearranged through a stacking type dynamic programming algorithm to achieve the purpose that cohesiveness of the super-pixel grids is maximized. The maximum cohesiveness super-pixel gridding method and the super-pixel-level image processing method are mainly used for carrying out regularized arrangement on any irregular super-pixel structures.

Description

technical field [0001] The invention belongs to the field of computer vision and media computing, and specifically relates to a maximum cohesion superpixel gridding method and a superpixel-level image processing framework. technical background [0002] In recent years, in order to pursue more efficient and accurate image analysis effects, many computer vision algorithms are based on super-pixels. Superpixels can aggregate adjacent pixels with the same or similar feature attributes in an image, and combine adjacent similar pixels into a processing unit. This segmentation method can better reflect human perception and is more in line with natural reality. At present, there are a large number of computer vision processing methods that replace pixels with superpixels, which are applied in fields such as image analysis, image segmentation, collaborative segmentation, and object positioning. Therefore, when performing tasks such as image target detection and segmentation, collabo...

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): G06K9/00G06T7/00
Inventor 冯伟万亮张加万李亮张诚
Owner TIANJIN 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
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