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

Embedded parallel optimization method for image salient region detection

A technology of area detection and optimization method, which is applied in image enhancement, image analysis, image data processing, etc., can solve the problem of low calculation efficiency, achieve the effects of improving calculation performance, accelerating detection, and reducing multiplication and division operations

Inactive Publication Date: 2015-04-08
JIANGNAN UNIV
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Mikolajczyk proposed to use the affine invariant Harris operator for local fitting, and obtain the affine transformation parameters of the detected area through iterative calculation, but the calculation efficiency of this method is not high

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
  • Embedded parallel optimization method for image salient region detection
  • Embedded parallel optimization method for image salient region detection
  • Embedded parallel optimization method for image salient region detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0021] attached figure 1 It is the overall flow chart of image salient region detection in the present invention.

[0022] The process includes the sorting of grayscale image pixels, the detection of extreme value regions, the determination of the largest stable extreme value region, and the fitting of the largest stable extreme value region. The specific steps are as follows:

[0023] Sorting of Grayscale Image Pixels

[0024] The first step: set the image pixel as R[0], R[1], ..., R[i], ..., R[PixelNumbers-1], PixelNumbers is the number of pixels, and each pixel records The pixel gray value R[i].key, the x coordinate R[i].x and the y coordinate R[i].y of the pixel in the image. According to the BinSort algorithm, the...

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 embedded parallel optimization method for image salient region detection. The method realizes the extraction of salient region characteristics in an image by adopting a maximally stable extremum region algorithm, based on a Cortex-A8 machine vision system, and meets the requirement of an image processing algorithm on high real-time performance on the embedded machine vision system. The computation based on the parallel processing structure optimization extremum region change rate of an NEON unit accelerates the detection of a maximally stable extremum region. The computation based on the parallel processing structure optimization region geometry first moment and center matrix of the NEON unit simplifies the computation of oval long and short half axes, long axis direction angle and center coordinate, and accelerates the fitting of a characteristic region oval. Setting program level optimization ensures that a program is more suitable for compiler vectorization processing, reduces program redundancy expenditure, and enhances the program operating efficiency.

Description

technical field [0001] The invention belongs to the field of image salient area detection in an embedded machine vision system, and specifically refers to a machine vision system based on Cortex-A8, an optimization acceleration method for real-time image salient area detection. Background technique [0002] Correctly extracting key regions in an image can greatly improve the efficiency and accuracy of image processing, so salient region detection has always been a popular research topic in image processing. Salient region detection technology is widely used in image segmentation, compression and content-based image retrieval and other fields. In the area detection technology, Lowe and Bay et al. respectively proposed highly efficient SIFT and SURF algorithms, which are invariant to scale and rotation, but not affine invariant. Mikolajczyk proposed to use the affine invariant Harris operator for local fitting, and obtain the affine transformation parameters of the detected a...

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
IPC IPC(8): G06T7/00G06T7/60G06K9/46G06F9/46
CPCG06T2207/20164
Inventor 白瑞林马敏锐
Owner JIANGNAN 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com