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

GPU-based acceleration method of image feature extraction algorithm

A technology of image feature extraction and algorithm, which is applied to the details of image processing hardware, processor architecture/configuration, etc. It can solve problems such as complex algorithms, limited processing speed, and inability to meet real-time needs of users

Inactive Publication Date: 2016-05-04
FUDAN UNIV
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because this algorithm not only needs to process a huge amount of data, but also the algorithm itself is very complex, so the processing speed is greatly limited, and in some applications it cannot meet the real-time needs of users.

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
  • GPU-based acceleration method of image feature extraction algorithm
  • GPU-based acceleration method of image feature extraction algorithm
  • GPU-based acceleration method of image feature extraction algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technology in the present invention will be described in detail below in conjunction with the accompanying drawings and source codes in the program of the present invention. The present invention mainly uses the CUDA programming model to map the local feature extraction algorithm in the image feature extraction algorithm to the calculation on the GPU in a fine-grained parallel manner, and further optimize the algorithm on the GPU through the characteristics of the GPU and the cooperative working mode of the GPU and the CPU. realization. The local feature retrieval algorithm selected by the present invention is the current mainstream retrieval algorithm SURF (Speeded-UpRobustFeatures). Below we will describe the specific implementation of this technology in detail and test the performance of this technology.

[0027] (1) Fine-grained GPU implementation

[0028] The invention maps the two stages of feature detection and feature description in the image retrieval alg...

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 parallel processor technical field and relates to a GPU-based acceleration method of an image feature extraction algorithm. According to the GPU-based acceleration method of the invention, fine-granularity parallel implementation of existing main image feature extraction algorithms is performed on GPUs, and optimized acceleration can be performed according to the features of the GPUs; collaborative work mechanisms of asynchronous assembly lines are adopted to make the GPUs perform collaborative calculation; as indicated by a test result, when hardware is configured as an Intel Q8300 CPU and a GTX260 GPU, the speed of the algorithm is 172.33 frames per second, and is 67 times of the speed of a serial algorithm; and when the hardware is configured as an IntelI7 CPU and a GTX295 GPU, the speed of the algorithm is as high as 340.47 frames per second; and therefore, the requirements of real-time processing can be better satisfied.

Description

technical field [0001] The invention belongs to the technical field of parallel processors, and in particular relates to an acceleration method for an image feature extraction algorithm. Background technique [0002] As human beings enter the digital age, a large amount of data from different fields is generated every day. Among them, multimedia data types, such as images, videos, etc., have become one of the main data types. How to effectively filter information in the increasing image / video data has received more and more research attention. Compared with traditional text-based applications, applications centered on multimedia data, such as search engines, filtering systems, copy detection, etc., have more and more practical requirements. Among them, the image feature extraction algorithm is an important basic algorithm for image / video information retrieval and screening, which can effectively extract the key frame information in the image or video for comparison between...

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): G06T1/20
CPCG06T1/20G06T2200/28
Inventor 张为华鲁云萍
Owner FUDAN 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