請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74834
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 李明穗 | |
dc.contributor.author | Bo-Sheng Jhu | en |
dc.contributor.author | 朱柏昇 | zh_TW |
dc.date.accessioned | 2021-06-17T09:08:30Z | - |
dc.date.available | 2025-03-13 | |
dc.date.copyright | 2020-03-13 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-11-07 | |
dc.identifier.citation | [1] Branko Karan, “Calibration of Kinect-Type RGB-D Sensors for Robotic Applications,” FME Transactions, Vol. 43, pp. 47-54, 2015.
[2] Daniel Herrera, Juho Kannala, and Janne Heikkilä, “Joint Depth and Color Camera Calibration with Distortion Correction,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34.10, pp. 2058-2064, 2012. [3] Wei Xiang, et al., “A Review and Quantitative Comparison of Methods for Kinect Calibration,” the 2nd International Workshop on Sensor-Based Activity Recognition and Interaction, 2015. [4] V. Villena-Martínez, A. Fuster-Guilló, J. Azorín-López, M. Saval-Calvo, J. Mora-Pascual, J. Garcia-Rodriguez, and A. Garcia-Garcia, “A Quantitative Comparison of Calibration Methods for RGB-D Sensors Using Different Technologies,” Sensors, vol. 17, no. 2, p. 243, 2017. [5] N. Burrus, Kinect RGB Demo. Manctl Labs. June 2013. http://rgbdemo.org/. [6] Alex Teichman, Stephen Miller, and Sebastian Thrun, “Unsupervised Intrinsic Calibration of Depth Sensors via SLAM,” in Robotics: Science and Systems, vol. 248, 2013, p. 3. [7] J.Y. Bouguet, Camera Calibration Toolbox for Matlab. 2004. Available online:https://www.vision.caltech.edu/bouguetj/calib_doc/ [8] Martin Fischler, Robert C. Bolles, ”Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, 1981, 24.6: 381-395. [9] Cha Zhang, Zhengyou Zhang, “Calibration between depth and color sensors for commodity depth cameras,” Computer vision and machine learning with RGB-D sensors. Springer, Cham, 2014. p. 47-64. [10] Zhengyou Zhang, ”A flexible new technique for camera calibration. IEEE Transactions on pattern analysis and machine intelligence, 2000, 22. [11] Jan Smisek, Michal Jancosek, and Tomas Pajdla, “3D with Kinect,” in IEEE International Conference on Computer Vision Workshop, 2011. [12] ScarossoMedia. SCAROSSO bespoke shoe using 3D technology by Volumental [Video file]. Retrieved from https://www.youtube.com/watch?v=kSOFWOgx6pM, 2015, March 20. [13] Duane C. Brown, “Close-range camera calibration,” Photogramm. Eng, 1971, 37.8: 855-866. [14] Vangos Pterneas. BODY TRACKING USING ORBBEC ASTRA + NUITRACK (KINECT ALTERNATIVE) Retrieved from https://pterneas.com/2018/04/30/orbbec-astra-nuitrack/, 2018, April 30. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74834 | - |
dc.description.abstract | 過去機器因為缺乏深度資訊無法識別物體為平面或立體。深度攝影機的問世使機器擁有準確估測物體距離的能力,可以完成過去做不到的事情,例如:可以藉由深度資訊重建三維的人臉來達到更準確的人臉辨識。但是使用深度資訊重建3D模型時,如果深度攝影機深度值之估測不夠準確,會導致建造的3D模型失真,因此為提高3D模型重建準確度,許多研究提出深度值修正方法以提高準確度。但目前已有的深度值修正方法尚有改進空間,例如:Karan提出的線性模型太過簡略,Herrera的方法在非線性最佳化時沒有包含IR攝影機內在參數的約束,因此本篇論文對Karan以及Herrera的方法進行修改,欲更進一步降低深度攝影機的量測誤差。實驗結果顯示現有的方法經過我們的修改後,Karan的方法估測誤差減少22%,Herrera的方法減少26%。 | zh_TW |
dc.description.abstract | In the past, machines lacked depth information and could not accurately identify the object as a plane or a solid. The advent of the depth camera allows the machine to accurately estimate the distance of the object, and can do things that were not possible in the past. For example, people can reconstruct 3D face by using depth information to achieve more accurate face recognition. However, when using depth information to reconstruct the 3D models, if the estimation of depth camera’s depth value is not accurate enough, the 3D model of the construction will be distorted. Therefore, in order to improve the accuracy of 3D model reconstruction, many studies have proposed the depth correction methods to improve the accuracy. However, there is still room for improvement in the existing depth correction methods. For example, the linear model proposed by Karan is too brief. Herrera method does not contain IR camera intrinsic parameter constraints in nonlinear optimization. This paper modified the Karan and Herrera methods to further reduce the depth camera measurement error. The experimental results show that the measurement errors of the modified methods have been reduced, modified Karan method reduces the estimated error by 22%, and modified Herrera method reduces it by 26%. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T09:08:30Z (GMT). No. of bitstreams: 1 ntu-108-R06944041-1.pdf: 3900285 bytes, checksum: fc4d225e6a04cc14a4aad528a7d3fff6 (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vi LIST OF TABLES xi Chapter 1 Introduction 1 1.1 RGB-D cameras 1 1.2 Applications using RGB-D Cameras 2 1.3 Motivation 3 Chapter 2 Related Work 5 2.1 Review of Depth Correction Methods 6 2.2 Comparison of Different RGB-D Camera Calibration Methods 8 Chapter 3 RGB-D Camera Calibration 10 3.1 Calibration of Color Camera and Depth Camera 10 3.2 Depth Correction 13 3.2.1 Review of Karan Method 15 3.2.2 Modified Karan Method 16 3.2.3 Review of Herrera Method 17 3.2.4 Modified Herrera Method 20 Chapter 4 Experiments 21 4.1 Devices and Data Acquisition 21 4.2 Depth Accuracy Evaluation 23 4.3 Experiment 1: Depth Accuracy Deterioration 24 4.3.1 Experimental Design 24 4.3.2 Results 25 4.4 Experiment 2: Calibration with Experimental Data from Different Distances 28 4.4.1 Experimental Design 28 4.4.2 Results 29 4.5 Experiment 3: Comparison of Four Methods 45 Chapter 5 Conclusions 48 REFERENCES 50 | |
dc.language.iso | en | |
dc.title | 基於結構光的RGB-D攝影機之深度修正 | zh_TW |
dc.title | Depth Correction of Structured-Light RGB-D Cameras | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-1 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 洪一平 | |
dc.contributor.oralexamcommittee | 石勝文 | |
dc.subject.keyword | 基於結構光的RGB-D攝影機,深度值修正,攝影機校正, | zh_TW |
dc.subject.keyword | Structured-Light RGB-D Cameras,Depth Correction,Camera Calibration, | en |
dc.relation.page | 51 | |
dc.identifier.doi | 10.6342/NTU201904263 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-11-07 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 3.81 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。