Unlock instant, AI-driven research and patent intelligence for your innovation.

Depth restoration method based on binocular kinect depth camera system

A technology of depth camera and depth restoration, which is applied in the field of computer vision, can solve problems such as not considering the relationship, and achieve the effect of ensuring accuracy and sharpness, eliminating overcompensation, and being easy to implement

Active Publication Date: 2018-10-16
TIANJIN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods do not consider the relationship between the various viewpoints in the system, or only use a simple fusion method to fuse images from different viewpoints.

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
  • Depth restoration method based on binocular kinect depth camera system
  • Depth restoration method based on binocular kinect depth camera system
  • Depth restoration method based on binocular kinect depth camera system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The new depth image repair framework based on the binocular depth camera acquisition system of the present invention will be described in detail below in conjunction with the embodiments and the accompanying drawings.

[0042] The present invention proposes a new depth restoration framework based on a binocular depth camera acquisition system to obtain high-quality depth images. First, two Kinect v2 cameras are used to build a binocular depth camera acquisition system; from the perspective of system error, the system characteristics are analyzed and described, and an edge-oriented depth image fusion strategy based on system error compensation is proposed, which makes full use of the depth compensation information of dual viewpoints. On the basis of eliminating the interference of the system error on the fusion accuracy, the fused depth image is obtained; finally, the color edge-oriented depth diffusion method is used to fill the fused image. The specific method includes...

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 field of computer vision, and relates to a depth recovery method based on a double-eye Kinect depth camera system to fully utilize double-viewpoint depth supplementary information and obtain a high-quality depth image by filling low-quality depth images. According to the technical scheme, the depth recovery method based on the double-eye Kinect depth camera system comprises the following steps: establishing an acquiring system based on a double-eye depth camera at first, and analyzing on the basis of correlativity between cameras and error characteristics of the system; fusing viewpoints through an edge guided fusing strategy and error compensation of the system to supplement depth information among the viewpoints; and finally finishing diffusion filling of depth images by using an edge guided filtering mode to obtain a depth image. The depth recovery method based on the double-eye Kinect depth camera system is mainly used for picture processing places.

Description

technical field [0001] The invention belongs to the field of computer vision and relates to the establishment of a binocular depth camera system and the restoration of a depth map. Background technique [0002] In recent years, stereoscopic displays and stereoscopic 3D applications have become increasingly popular in the consumer market. As an important part of 3D applications, the acquisition of high-quality depth images has become a hot research field. At present, the acquisition of depth images is mainly divided into two categories, one of which is passive acquisition, such as stereo matching and 2D-3D conversion technology. However, these methods are all based on inference, estimating the depth from the structural information of the color image instead of directly measuring the depth, which often produces wrong depth estimation results. The other is an active way, namely: directly acquire the depth image. In 2011, Microsoft launched the first-generation Kinect depth c...

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): H04N13/239H04N13/271
CPCH04N13/122H04N13/128H04N13/271
Inventor 杨敬钰柏井慧侯春萍
Owner TIANJIN UNIV