Color image and depth image multi-feature-based joint data association method

A depth image and color image technology, applied in the information field, can solve problems such as no occurrence, achieve the effects of expanding the perception range, improving estimation accuracy and execution efficiency, and improving robustness

Active Publication Date: 2016-11-16
SHANDONG UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Among them, related technologies on the joint data association based on multi-features of color images and depth images have not yet appeared.

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
  • Color image and depth image multi-feature-based joint data association method
  • Color image and depth image multi-feature-based joint data association method
  • Color image and depth image multi-feature-based joint data association method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention is described in detail below in conjunction with accompanying drawing:

[0039] Such as image 3 As shown, the joint data association method based on multi-features of color images and depth images, which is aimed at multi-target tracking, includes:

[0040] System parameter initialization;

[0041] Multi-model interaction;

[0042] JPDA based on linear information filter and JPDA based on central difference information filter;

[0043] Send local information to neighboring sensor nodes;

[0044] Receive information from nearby sensor nodes;

[0045] Data association based on Mahalanobis distance;

[0046] The distributed information consensus algorithm realizes the fusion of multi-model results.

[0047] When estimating the consistency of distributed information, the details are:

[0048] By building a dynamic distributed RGBD sensor network, the distributed processing of data and the distributed fusion of information are realized. There is...

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 color image and depth image multi-feature-based joint data association method. The method comprises the steps of performing data association between a tracking target and target observation for the first time by local sensor nodes through adopting a joint probabilistic data association (JPDA) algorithm; performing data association on the tracking target between the sensor nodes for the second time by a Mahalanobis distance-based Hungarian algorithm; and during the data association for the first time, establishing three thresholds (gamma z, gamma c, gamma d) by utilizing joint point position observation information z, a color image gradient orientation histogram characteristic hc and a depth image gradient orientation histogram characteristic hd by a multi-feature-based target observation candidate set adjustment mechanism to define the size of an observation set. According to the method, the estimation precision and executive efficiency of the JPDA algorithm can be improved.

Description

technical field [0001] The invention relates to the field of information technology, in particular to a joint data association method based on multi-features of color images and depth images. Background technique [0002] Human behavior recognition based on multiple RGBD cameras has attracted extensive attention from researchers, and has been applied to human behavior detection in operating rooms, factory workshops, automobile assembly, indoor monitoring and other environments, effectively solving the problem of human occlusion and possible human- The robot collision problem has important application value. [0003] At present, human behavior perception based on multiple RGBD sensors is still in a centralized stage, requiring one or more data fusion centers to fuse 3D data and human skeleton joint point data, which requires high computing power and robustness for data fusion centers , weak resistance to network instability and low scalability. [0004] When there are multi...

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): G06K9/00
CPCG06V40/20
Inventor 刘国良田国会
Owner SHANDONG UNIV
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