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

Multi-binocular splicing intelligent analysis system based on GPU acceleration

An intelligent analysis, dual-purpose technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as loss of algorithm performance, misjudgment of intelligent analysis, unfavorable intelligent analysis, etc. Achieve the effect of resolution

Active Publication Date: 2017-06-23
ZHEJIANG ICARE VISION TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1) In order to save costs, many intelligent video analysis often use existing installed cameras, which are often not conducive to intelligent analysis in terms of shooting angle and imaging effect
[0004] 2) Ordinary 2D cameras cannot judge the distance between the target and the camera, resulting in overlapping and occlusion of targets at different distances on the same optical axis, which causes misjudgment by intelligent analysis
[0005] 3) The computing platform for intelligent analysis has limited capabilities, and algorithms often need to be optimized with performance loss to meet real-time processing

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
  • Multi-binocular splicing intelligent analysis system based on GPU acceleration
  • Multi-binocular splicing intelligent analysis system based on GPU acceleration
  • Multi-binocular splicing intelligent analysis system based on GPU acceleration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Below in conjunction with embodiment and accompanying drawing, the present invention will be further described:

[0032] The present invention adopts a binocular camera as a video acquisition device, and each binocular camera has two analog video signals, which respectively represent a left view and a right view. The binocular camera requires the ceiling to be installed on the ceiling and look down vertically to shoot the ground, so as to ensure that the captured targets do not occlude each other. When the scene range cannot be covered by a binocular camera, multiple cameras can be installed and spliced ​​to form a more visible range. The main principles are as follows:

[0033] For each pixel in each target area in each camera, project it onto the ground according to its depth information, and then use the pre-made multi-camera offset (dx, dy) calibration to associate the projected target, so that Realize multi-camera object detection on the global coordinate system ...

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 GPU acceleration-based multi-binocular splicing intelligent analysis system. a binocular camera is adopted to serve as a video acquisition device, the binocular camera is arranged on a ceiling for shooting the ground in a vertical over looking mode, and thus, shot targets can be ensured not to be mutually shielded. When a scene range can not be covered by one binocular camera, multiple binocular cameras are arranged, and a visual range is formed in a splicing mode. On the basis of a depth picture and a colorful picture shot vertically, various high-accuracy intelligent video analysis functions can be realized. Two paths of output videos of each binocular camera adopt GPU for parallel calculation so as to quicken the analysis result. Depth information is used, stability of target detection is greatly improved in combination with RGB information, and a good foundation is provided for future intelligent analysis.

Description

technical field [0001] The invention belongs to the technical field of video intelligent monitoring, and relates to a multi-binocular splicing intelligent analysis system based on GPU acceleration. Background technique [0002] At present, video-based intelligent analysis technology has been widely used in various industries, including banking, transportation, public security and so on. However, the actual results are often not satisfactory. The main reasons are as follows: [0003] 1) In order to save costs, many intelligent video analysis often use existing installed cameras, which are often not conducive to intelligent analysis in terms of shooting angle and imaging effect. [0004] 2) Ordinary 2D cameras cannot judge the distance between the target and the camera, resulting in overlapping and occlusion of targets at different distances on the same optical axis, which may cause misjudgment by intelligent analysis. [0005] 3) The computing platform for intelligent analy...

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 Patents(China)
IPC IPC(8): G06T7/292G06T7/50
CPCG06T7/35G06T2207/10016
Inventor 尚凌辉高勇王弘玥刘家佳余天明施展
Owner ZHEJIANG ICARE VISION TECH
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