3D Object Localization Using 2D Estimates for Computer Vision Applications

Taha Hasan Masood Siddique; Yawar Rehman; Tahira Rafiq; Malik Zohaib Nisar; Muhammad Sohail Ibrahim; Muhammad Usman

doi:10.1109/MAJICC53071.2021.9526270

3D Object Localization Using 2D Estimates for Computer Vision Applications

Taha Hasan Masood Siddique^*
, Yawar Rehman
, Tahira Rafiq
, Malik Zohaib Nisar
, Muhammad Sohail Ibrahim
, Muhammad Usman

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

Computer vision based applications have received notable attention globally due to the interaction with the physical world. In this paper, a novel method for object localization based on camera calibration and pose estimation is discussed. The 3-dimensional (3D) coordinates are computed by taking multiple 2-dimensional (2D) images from different view that meets the requirement in camera calibration process. Several number of steps are involved in camera calibration including estimation of intrinsic and extrinsic parameters for the removal of lens distortion, estimation of object's size and camera location. Besides, a technique to estimate the 3D pose using 2D images is proposed and the results of camera parameters and localization are applied for the 3D reconstruction. The hardware implementation of the proposed approach is implemented on HP core i5 with the MATLAB support packages and experimental results are validated for both camera calibration and pose estimation.

Original language	English
Title of host publication	Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665424134
DOIs	https://doi.org/10.1109/MAJICC53071.2021.9526270
State	Published - 15 Jul 2021
Externally published	Yes
Event	1st Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021 - Karachi, Pakistan Duration: 15 Jul 2021 → 17 Jul 2021

Publication series

Name	Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021

Conference

Conference	1st Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021
Country/Territory	Pakistan
City	Karachi
Period	15/07/21 → 17/07/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Camera calibration
camera localization
checkerboard detection
pose estimation

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition
Health Informatics

Access to Document

10.1109/MAJICC53071.2021.9526270

Cite this

Siddique, T. H. M., Rehman, Y., Rafiq, T., Nisar, M. Z., Ibrahim, M. S., & Usman, M. (2021). 3D Object Localization Using 2D Estimates for Computer Vision Applications. In Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021 (Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MAJICC53071.2021.9526270

Siddique, Taha Hasan Masood ; Rehman, Yawar ; Rafiq, Tahira et al. / 3D Object Localization Using 2D Estimates for Computer Vision Applications. Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021).

@inproceedings{1051a0da22a44b93bec57860cf426ea7,

title = "3D Object Localization Using 2D Estimates for Computer Vision Applications",

abstract = "Computer vision based applications have received notable attention globally due to the interaction with the physical world. In this paper, a novel method for object localization based on camera calibration and pose estimation is discussed. The 3-dimensional (3D) coordinates are computed by taking multiple 2-dimensional (2D) images from different view that meets the requirement in camera calibration process. Several number of steps are involved in camera calibration including estimation of intrinsic and extrinsic parameters for the removal of lens distortion, estimation of object's size and camera location. Besides, a technique to estimate the 3D pose using 2D images is proposed and the results of camera parameters and localization are applied for the 3D reconstruction. The hardware implementation of the proposed approach is implemented on HP core i5 with the MATLAB support packages and experimental results are validated for both camera calibration and pose estimation.",

keywords = "Camera calibration, camera localization, checkerboard detection, pose estimation",

author = "Siddique, \{Taha Hasan Masood\} and Yawar Rehman and Tahira Rafiq and Nisar, \{Malik Zohaib\} and Ibrahim, \{Muhammad Sohail\} and Muhammad Usman",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 1st Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021 ; Conference date: 15-07-2021 Through 17-07-2021",

year = "2021",

month = jul,

day = "15",

doi = "10.1109/MAJICC53071.2021.9526270",

language = "English",

series = "Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021",

address = "United States",

}

Siddique, THM, Rehman, Y, Rafiq, T, Nisar, MZ, Ibrahim, MS & Usman, M 2021, 3D Object Localization Using 2D Estimates for Computer Vision Applications. in Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021. Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021, Institute of Electrical and Electronics Engineers Inc., 1st Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021, Karachi, Pakistan, 15/07/21. https://doi.org/10.1109/MAJICC53071.2021.9526270

3D Object Localization Using 2D Estimates for Computer Vision Applications. / Siddique, Taha Hasan Masood; Rehman, Yawar; Rafiq, Tahira et al.
Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - 3D Object Localization Using 2D Estimates for Computer Vision Applications

AU - Siddique, Taha Hasan Masood

AU - Rehman, Yawar

AU - Rafiq, Tahira

AU - Nisar, Malik Zohaib

AU - Ibrahim, Muhammad Sohail

AU - Usman, Muhammad

PY - 2021/7/15

Y1 - 2021/7/15

N2 - Computer vision based applications have received notable attention globally due to the interaction with the physical world. In this paper, a novel method for object localization based on camera calibration and pose estimation is discussed. The 3-dimensional (3D) coordinates are computed by taking multiple 2-dimensional (2D) images from different view that meets the requirement in camera calibration process. Several number of steps are involved in camera calibration including estimation of intrinsic and extrinsic parameters for the removal of lens distortion, estimation of object's size and camera location. Besides, a technique to estimate the 3D pose using 2D images is proposed and the results of camera parameters and localization are applied for the 3D reconstruction. The hardware implementation of the proposed approach is implemented on HP core i5 with the MATLAB support packages and experimental results are validated for both camera calibration and pose estimation.

AB - Computer vision based applications have received notable attention globally due to the interaction with the physical world. In this paper, a novel method for object localization based on camera calibration and pose estimation is discussed. The 3-dimensional (3D) coordinates are computed by taking multiple 2-dimensional (2D) images from different view that meets the requirement in camera calibration process. Several number of steps are involved in camera calibration including estimation of intrinsic and extrinsic parameters for the removal of lens distortion, estimation of object's size and camera location. Besides, a technique to estimate the 3D pose using 2D images is proposed and the results of camera parameters and localization are applied for the 3D reconstruction. The hardware implementation of the proposed approach is implemented on HP core i5 with the MATLAB support packages and experimental results are validated for both camera calibration and pose estimation.

KW - Camera calibration

KW - camera localization

KW - checkerboard detection

KW - pose estimation

UR - https://www.scopus.com/pages/publications/85115718074

U2 - 10.1109/MAJICC53071.2021.9526270

DO - 10.1109/MAJICC53071.2021.9526270

M3 - Conference contribution

AN - SCOPUS:85115718074

T3 - Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021

BT - Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021

Y2 - 15 July 2021 through 17 July 2021

ER -

Siddique THM, Rehman Y, Rafiq T, Nisar MZ, Ibrahim MS, Usman M. 3D Object Localization Using 2D Estimates for Computer Vision Applications. In Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021). doi: 10.1109/MAJICC53071.2021.9526270

3D Object Localization Using 2D Estimates for Computer Vision Applications

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this