A Foreground Detection Method Based on Fusion of Depth Image and Visible Light Image

A depth image and foreground detection technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problem of inaccurate detection, improve the accuracy, improve the foreground detection performance, and overcome the effect of slight jitter.

Active Publication Date: 2015-08-19
HUNAN SURE SECURE INTELLIGENCE CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a foreground detection method based on the fusion of depth images and visible light images to solve the problem of foreground detection by using visible light images or depth images alone. Detect possible inaccurate detection problems; improve the accuracy of foreground detection based on depth images

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
  • A Foreground Detection Method Based on Fusion of Depth Image and Visible Light Image
  • A Foreground Detection Method Based on Fusion of Depth Image and Visible Light Image
  • A Foreground Detection Method Based on Fusion of Depth Image and Visible Light Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The concrete realization steps of the present invention are as follows:

[0018] Step 1: Depth Image Background Modeling

[0019] After the system is turned on and running stably, continuously select N frames of depth images, count the number of effective depth values ​​on each pixel, and store them in the matrix Time validate , while accumulating the sum of the effective depth values ​​and storing them in the matrix depth acc , using matrix point division, Get the average effective depth value at each pixel. At the same time, the relative variance matrix of the effective depth value on the entire image is calculated And calculate the probability of occurrence of effective depth value where var represents the matrix formed by the variance of the effective value on each pixel. In this way, the probability of whether the depth value of the relevant pixel can be obtained effectively, as well as the mean value and relative variance of the obtained effective depth va...

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 a foreground detection method based on fusion of a depth image and a visible image. The foreground detection method includes performing background modeling on the visible image and the depth image, performing modeling for a depth value and an effectiveness probability of the depth value in the background modeling of the depth image, sampling randomly in the visible image by means of time-space domain mixing to acquire a background model, and fusing a detected foreground. The foreground detection method has the advantages that the visible image and the depth image are organically fused, and the problem of possible detection inaccuracy caused by the fact that the visual image or the depth image is individually utilized for foreground detection is solved.

Description

technical field [0001] The invention relates to the field of foreground detection in video images, in particular to a foreground detection method based on fusion of depth images and visible light images. Background technique [0002] Foreground detection in video images is the most basic and important part of computer vision visualization application systems. At present, there are many foreground detection schemes in academia and industry, but they are basically using visible light images. The foreground detection is basically divided into three categories: inter-frame difference, background subtraction, and optical flow method. Since the color information of visible light images is not stable, changes in illumination, shadows, reflections, swaying leaves, camera shake, etc. will cause image changes, reduce the accuracy of foreground detection that only relies on color information, and affect the accuracy of subsequent analysis of the system Therefore, accurate foreground d...

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): G06T7/00
CPCG06T2207/10016G06T2207/10028
Inventor 不公告发明人
Owner HUNAN SURE SECURE INTELLIGENCE CO LTD
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