Pixel-level alignment algorithm for color images to depth images of color depth camera

A pixel-level alignment, depth image technology, applied in image enhancement, image analysis, image data processing, etc., to improve the efficiency of information fusion

Active Publication Date: 2015-05-13
SHANGHAI INST OF TECHNICAL PHYSICS - CHINESE ACAD OF SCI
View PDF4 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Currently there are only alignment methods from depth images to color 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
  • Pixel-level alignment algorithm for color images to depth images of color depth camera
  • Pixel-level alignment algorithm for color images to depth images of color depth camera
  • Pixel-level alignment algorithm for color images to depth images of color depth camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The specific implementation method of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0056] 1) Determine the offset between the infrared image and the depth image. First, collect any scene image, and perform binarization on the infrared image and the depth image. Then the target object in the scene is segmented from the infrared image and the depth image respectively. Next, by comparing the shapes of the target object segmented from the infrared image and the depth image, the offset between the infrared image and the depth image is determined so that the two shapes can achieve the best alignment effect. According to the experimental results, this fixed offset is [u 0 ,v 0 ] = [3,3] (pixels).

[0057] 2) Calibrate the internal parameters of the infrared camera and the color camera respectively. In order to improve the fusion accuracy of the depth image and the color image, the internal p...

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 pixel-level alignment algorithm for color images to depth images of a color depth camera. The pixel-level alignment algorithm comprises the steps of 1) determining an offset between an infrared image and a depth image, 2) calibrating the internal parameters of an infrared camera and a color camera, respectively, 3) calibrating relative postures between the infrared camera and the color camera, 4) calibrating the parameters of a depth camera model, 5) starting from one pixel point of the color image, finding out corresponding pixel points on the depth image by use of the internal and external parameters of an infrared image and a color image, thereby determining the depth of the pixel points of the color image. According to the pixel-level alignment algorithm, the corresponding depth information is directly obtained from the color image, the alignment of the color information to the depth information can be realized, a fusion image of a larger size can be obtained, and the information is richer.

Description

technical field [0001] The alignment method from the color image to the depth image involved in the present invention specifically refers to a method based on epipolar constraints, starting from the pixel points on the color image of the color depth camera (Kinect), to find the corresponding pixel points on the depth image method. Background technique [0002] The imaging system combining infrared camera and color camera has been more and more applied to smart home, somatosensory games, 3D reconstruction, robot autonomous navigation and other fields. In order to give full play to the advantages of multi-sensor fusion, the first problem is how to better realize the fusion of different sensor information. Color Depth Camera (Kinect) is a typical imaging system combining an infrared camera and a color camera, and it has the characteristics of low price and good practical effect. It mainly consists of infrared transmitter, infrared camera and color camera. Moreover, the infra...

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): G06T7/00
CPCG06T2207/10024G06T2207/10028G06T2207/10048G06T2207/20221
Inventor 邹武合张雷戴宁
Owner SHANGHAI INST OF TECHNICAL PHYSICS - 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
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