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

Background modeling acceleration method based on CUDA (Compute Unified Device Architecture) technology

A background model and algorithm technology, applied in the field of pattern recognition, can solve the problem that the background modeling algorithm cannot reach the running speed

Inactive Publication Date: 2010-11-10
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, when there are many monitoring devices, a large amount of image data will be generated, and the existing background modeling algorithm cannot achieve real-time running speed

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
  • Background modeling acceleration method based on CUDA (Compute Unified Device Architecture) technology
  • Background modeling acceleration method based on CUDA (Compute Unified Device Architecture) technology
  • Background modeling acceleration method based on CUDA (Compute Unified Device Architecture) technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] The acceleration method of background modeling algorithm based on CUDA technology includes three processes: acceleration of image preprocessing and denoising, acceleration of background modeling algorithm and OpenGL rendering. In order to demonstrate the effect of improving the algorithm operation speed of the invention and explain its universal applicability, here we select two videos with a large difference in traffic flow, and use the graphics card NVIDIA tesla c1060 and CPUIntel Core 2DUOT71001.8GHz to implement them respectively. The first video is from the monitoring video of the park of the Institute of Automation, Chinese Academy of Sciences, and the traffic flow is small; the second video is from the monitoring video of a highway, and the traffic flow is relatively large. The specific parameters of the video are shown in Table 1.

[0045] Table 1

[0046]

Duration (seconds)

width (pixels)

height (pixels)

video 1

720

320

24...

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 relates to a background modeling acceleration method which comprises the following steps of: filtering an image imported into a CUDA (Compute Unified Device Architecture); establishing Gaussian models for corresponding pixels by each thread, wherein the parameter data of the Gaussian model required by a current thread block is written into a shared memory, and after calculation is finished, a calculation result is written into a global memory from the shared memory. The method has universal applicability, and no matter for a scene with a large traffic flow or a scene with a small traffic flow, consistent acceleration can be obtained basically. The method is applied to the field of intelligent video monitoring for improving the efficiency of a background modeling algorithm so as to ensure that a system can guarantee to be run in real time while facing a larger data volume; and moreover, superfluous resources can be assigned to other algorithms, which provides a certain space for improving other functions. The method is applied to object clustering in the field of computer vision for accelerating a clustering process of objects and reducing a large quantity of waiting time.

Description

technical field [0001] The present invention relates to pattern recognition, and more particularly to video-based acceleration of background modeling. Background technique [0002] With the improvement of people's safety awareness, video surveillance systems have been more and more used in various occasions, such as banks, subways, stadiums, traffic supervision and prisons and other places. Traditional video surveillance systems often require a lot of manpower and material resources, and require video surveillance personnel to continuously monitor the video for a long time, analyze the abnormal situation in the video, record and store the abnormal information, and make corresponding decisions to deal with the abnormal situation. This work is characterized by tediousness and continuity. After working for a long time, monitors are prone to physical and mental fatigue, which will lead to a large number of missed and false positives, and pose a great challenge to safety. There...

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): G06T7/00H04N7/18
Inventor 谭铁牛黄凯奇饶超
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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

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