scispace - formally typeset
Search or ask a question
Topic

Image conversion

About: Image conversion is a research topic. Over the lifetime, 2490 publications have been published within this topic receiving 19077 citations.


Papers
More filters
Patent
26 Mar 2014
TL;DR: In this paper, a monitoring device and a monitoring system using a 3D image and a method using the same method are presented, provided that the monitoring device is an interface unit interlocked with a plurality of PTZ cameras.
Abstract: Provided are a monitoring device and a monitoring system using a 3D image and a method using the same The monitoring device using a 3D image according to one embodiment of the present invention includes: an interface unit interlocked with a plurality of PTZ cameras; an image obtaining unit obtaining 2D images photographed by the PTZ cameras through the interface unit; and an image conversion unit composing at least two images among the 2D images obtained by the image obtaining unit and converting the composed image into the 3D image [Reference numerals] (210) Interface unit; (220) Image obtaining unit; (230) Image conversion unit; (250) Location tracing unit; (300) Database; (340) Information processing unit

3 citations

Patent
03 Feb 2016
TL;DR: In this article, a tower type crane load stereo pendulum angle vision detection method is presented, which comprises steps of left and right camera calibration, image acquisition, image conversion for gray scale images, filtering and denoising, image binaryzation, edge detection, lifting rope linear detection, white mark point plane coordinate point calculation and three-dimensional swing angle calculation.
Abstract: The invention provides a tower type crane load stereo pendulum angle vision detection method. The method comprises steps of left and right camera calibration, image acquisition, image conversion for gray scale images, filtering and denoising, image binaryzation, edge detection, lifting rope linear detection, white mark point plane coordinate point calculation, white mark point three-dimensional coordinate calculation and three-dimensional swing angle calculation. Through the method, an acceleration gauge and a gyroscope having expensive prices are prevented from being used, and high detection precision and relatively good application prospects are realized.

3 citations

Patent
16 Dec 2015
TL;DR: In this paper, the baseline length of each camera on the left and right sides is set to be smaller than or equal to one half of a result that the product of the background depth value ZB and the length LB of a background portion is divided by the difference of the ZB value and a foreground depth value; in this way, the intermediate view has no cavity, and therefore, the quality of the synthetic image is guaranteed to a certain extent.
Abstract: The invention discloses an intermediate view synthesis method without generating a cavity. In a given shooting scene, the baseline length of each of two cameras on the left and right sides is set to be smaller than or equal to one half of a result that the product of a background depth value ZB and the length LB of a background portion is divided by the difference of the background depth value ZB and a foreground depth value; in this way, three-dimensional image conversion is performed on two reference images obtained by the left and right two cameras and depth images corresponding to the two reference images by use of a two-way DIBR technique to obtain two virtual views at a video terminal, and the two virtual views are fused to obtain an intermediate view of a central eye position; the intermediate view has no cavity, and therefore, the quality of the synthetic image is guaranteed to a certain extent and the cavity filling time complexity is avoided.

3 citations

Patent
21 Dec 2006
TL;DR: In this paper, the authors proposed a manufacturing method of a radiological image conversion panel capable of reducing occurrence of image noise and obtaining a high-quality image, and they used a flattening process of flattening only a projecting part existing on the surface of the phosphor layer 3.
Abstract: PROBLEM TO BE SOLVED: To provide a manufacturing method of a radiological image conversion panel capable of reducing occurrence of image noise and obtaining a high-quality image, and the radiological image conversion panel. SOLUTION: In the manufacturing method of the radiological image conversion panel, after a vapor deposition process, a phosphor plate comprising a support body 2 and a phosphor layer 3 formed on the support body 2 is formed. This method has a flattening process of flattening only a projecting part existing on the surface of the phosphor layer 3. COPYRIGHT: (C)2007,JPO&INPIT

3 citations

Patent
30 Jun 2014
TL;DR: In this paper, the problem of providing a display system for production control and a display method thereof configured to reliably display machining information, work information, or assembling information of components constituting a mold, in a production line of the mold to be manufactured through a plurality of machining or working processes is addressed.
Abstract: PROBLEM TO BE SOLVED: To provide a display system for production control and a display method thereof configured to reliably display machining information, work information, or assembling information of components constituting a mold, in a production line of the mold to be manufactured through a plurality of machining or working processes.SOLUTION: A display system for production control includes: an image conversion server 2 which prepares display data on the basis of information on a mold production control device 1, and converts the display data into at least master image data and multiple pieces of image data including mirror data of the master image data; and a Web server 3 which stores the image data converted by the image conversion server 2, transmits the mirror image data of the image data to a work signboard 5, and updates a display screen of the work signboard 5.

3 citations


Network Information
Related Topics (5)
Image processing
229.9K papers, 3.5M citations
84% related
Feature (computer vision)
128.2K papers, 1.7M citations
83% related
Pixel
136.5K papers, 1.5M citations
82% related
Feature extraction
111.8K papers, 2.1M citations
80% related
Image segmentation
79.6K papers, 1.8M citations
79% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202132
202074
2019117
2018115
2017100
2016107