Patent
Method for calibrating a depth camera
Mourad Boufarguine
- 29 Dec 2014
8
TL;DR: In this paper, a method for calibrating a depth camera comprising the steps of: (1) using depth camera (DC) to be calibrated for acquiring a plurality of depth maps (DMS) of a physical three-dimensional reference object (PO), corresponding to different positions of the depth camera relative to the is reference object; (2) computing a 3D reconstruction (3DR i ) of the reference object from said depth maps, depending on values assigned to a set of calibration parameters (SCP i ), and (3) computing an error (ERR i ) between the
read more
Abstract: A method for calibrating a depth camera comprising the steps of:
S1) using a depth camera (DC) to be calibrated for acquiring a plurality of depth maps (DMS) of a physical three-dimensional reference object (PO), corresponding to different positions of the depth camera relative to the is reference object; S2) computing a three-dimensional reconstruction (3DR i ) of the reference object from said depth maps, depending on values assigned to a set of calibration parameters (SCP i ) of the depth camera; S3) computing an error (ERR i ) between the three-dimensional reconstruction computed at step S2) and a predetermined digital model (RM) of the reference object; said steps S2) and S3) being iterated by assigning different values to said set of calibration parameters of the depth camera; and S4) choosing values (SCP) of said set of calibration parameters which minimize the error computed at step S3); said steps S2) to S4) being performed by a computer.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Automated collection and labeling of object data
Bryan J. Thibodeau,Michael Revow,Mihai Jalobeanu,Grigor Shirakyan +3 more
- 10 Apr 2015
TL;DR: In this article, a mechanical device is used to maneuver an object into different poses within a three-dimensional workspace in the real-world environment, while the object is in each different pose an image of the object was input from one or more sensors and data specifying the pose is input from the mechanical device.
17
Patent
Three-dimensional reconstruction method, apparatus and device and storage medium
TL;DR: In this article, a 3D reconstruction method for real-time 3D reconstructions of a target scene is presented. But the method is not suitable for the task of 3D image key frames.
5
Patent
Adaptive camera control and calibration for dynamic focus
Ingram Luke C,Baker Anthony W,Courter Brandon Michael +2 more
- 09 Apr 2020
TL;DR: In this paper, a camera vision system for creating 3D reconstructions of objects may include a camera, a distance sensor having a fixed spatial relationship with the camera, and a system controller.
Patent
Machine vision system with a computer generated virtual reference object
Leikas Esa
- 20 Jun 2019
TL;DR: In this paper, a machine vision system using a computer generated virtual reference object is disclosed, which is capable of measuring differences on an absolute scale when the exact measures of the virtual reference objects are known.
Patent
Machine vision system
Leikas Esa
- 11 Oct 2018
TL;DR: In this article, a machine vision system capable of measuring differences on an absolute scale is disclosed, where a reference object is accurately measured using a reference measurement arrangement, such as a coordinate measurement machine.
References
Accurately calibrate kinect sensor using indoor control field
Popo Gui,Qin Ye,Hongmin Chen,Tinghui Zhang,Chun Yang +4 more
- 11 Jun 2014
TL;DR: This article attempts to use indoor control field to calibrate Kinect sensor, and gets the accurate internal parameters of both cameras and their relative pose, and shows that the method can get high precision calibration parameters which projection mean square error lower than 0.5 pixels.
11
Patent
Information processing device and information processing method
Kazuhiko Kobayashi,一彦 小林,Daisuke Kotake,大輔 小竹,Keisuke Tateno,圭祐 立野 +5 more
- 18 Dec 2012
TL;DR: In this paper, a model point input unit 130 inputs a coordinate value of a point showing a geometric feature in a model, and a model-point coordinate conversion unit 180 converts the coordinate value showing the model point into a two-dimensional coordinate system of the index map image.
8
Patent
Information processor, information processing method, and computer program
Daisuke Watanabe,大輔 渡邊,Kazuhiko Kobayashi,一彦 小林 +3 more
- 04 Jun 2013
TL;DR: In this paper, an image including an object is acquired and an approximate position and attitude of the object is estimated on the basis of a result of the association, where a geometric feature of an object in an image is associated with at least one model among a plurality of models arranged in the approximate positions and attitudes.
5
3D reconstruction of a human body from multiple viewpoints
Koichiro Yamauchi,Hideto Kameshima,Hideo Saito,Yukio Sato +3 more
- 17 Dec 2007
TL;DR: The system configuration, calibration, morphable model and experimental results are described and it is proposed that data can be successfully obtained by a method using multiple rangefinders correctly.