Recalibration of Structured-Light RGB-D Cameras with Parametric Depth Error Correction

Peng Yuan Kao, Sheng Wen Shih, Yi Ping Hung, Aye Mon Tun

研究成果: 書貢獻/報告類型會議貢獻

摘要

Structured-light RGB-D cameras have been widely used in various applications. However, due to the deformation of internal camera parts, their depth estimation accuracy degrades with time. While it is easy to calibrate the camera parameters, updating the calibrated parameters to the camera firmware is difficult. Therefore, existing methods compensate for the depth measurements with different error correction functions. At present, as there are no simple and accurate parametric error correction methods, non-parametric calibration methods must be used when accurate depth measurements are required. The main drawback of such nonparametric approaches is that they require a large number of calibration images to calibrate a large error correction lookup tables. In this paper, we propose a simple parametric depth error correction model based on Taylor-series approximation of depth measurement equations. Experimental results show that the proposed method outperforms other parametric approaches and achieves results comparable to the state-of-the-art nonparametric method although the proposed method uses only nine parameters.
原文英語
主出版物標題Proceedings - 4th International Conference on Multimedia Information Processing and Retrieval, MIPR 2021
發行者Institute of Electrical and Electronics Engineers Inc.
頁面111-117
頁數7
ISBN(電子)9781665418652
DOIs
出版狀態已發佈 - 2021
事件4th IEEE International Conference on Multimedia Information Processing and Retrieval, MIPR 2021 - Virtual, Online, 日本
持續時間: 9月 8 20219月 10 2021

出版系列

名字Proceedings - 4th International Conference on Multimedia Information Processing and Retrieval, MIPR 2021

會議

會議4th IEEE International Conference on Multimedia Information Processing and Retrieval, MIPR 2021
國家/地區日本
城市Virtual, Online
期間9/8/219/10/21

ASJC Scopus subject areas

  • 媒體技術
  • 電腦網路與通信
  • 訊號處理

指紋

深入研究「Recalibration of Structured-Light RGB-D Cameras with Parametric Depth Error Correction」主題。共同形成了獨特的指紋。

引用此