Depth estimation from monocular vision using image edge complexity

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Autonomous robotic arm motion requires the use of a control system in order to prevent collisions with the targeted object. Generally, in translational motion, as the camera approaches an object, the degree of complexity of the edges of the object image will change. This principle can be used to estimate the distance to a targeted object. This work introduces a novel statistical method, named Moment of Zoomed-Algorithm Kurtosis (MoZAK), which is based on the I-kaz method, as an indicator for motion system control. The MoZAK parameter, Lc which represents the degree of complexity of image edges, is used to indicate if further actuation of the motor, or otherwise, is required. The method is compared to conventional statistical methods (standard deviation and kurtosis). Results indicate that the MoZAK method presents a viable distance estimator compared to conventional statistical methods.

Original languageEnglish
Title of host publicationIEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
Pages868-873
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2011 - Budapest
Duration: 3 Jul 20117 Jul 2011

Other

Other2011 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2011
CityBudapest
Period3/7/117/7/11

Fingerprint

Statistical methods
Control systems
Robotic arms
Cameras

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications
  • Software

Cite this

Mohamed Haris, S., Zakaria, M. K., & Nuawi, M. Z. (2011). Depth estimation from monocular vision using image edge complexity. In IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM (pp. 868-873). [6027091] https://doi.org/10.1109/AIM.2011.6027091

Depth estimation from monocular vision using image edge complexity. / Mohamed Haris, Sallehuddin; Zakaria, Muhammad Khalid; Nuawi, Mohd. Zaki.

IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. 2011. p. 868-873 6027091.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mohamed Haris, S, Zakaria, MK & Nuawi, MZ 2011, Depth estimation from monocular vision using image edge complexity. in IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM., 6027091, pp. 868-873, 2011 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2011, Budapest, 3/7/11. https://doi.org/10.1109/AIM.2011.6027091
Mohamed Haris S, Zakaria MK, Nuawi MZ. Depth estimation from monocular vision using image edge complexity. In IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. 2011. p. 868-873. 6027091 https://doi.org/10.1109/AIM.2011.6027091
Mohamed Haris, Sallehuddin ; Zakaria, Muhammad Khalid ; Nuawi, Mohd. Zaki. / Depth estimation from monocular vision using image edge complexity. IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. 2011. pp. 868-873
@inproceedings{48c1b71958614f7d9927b883c2008ccc,
title = "Depth estimation from monocular vision using image edge complexity",
abstract = "Autonomous robotic arm motion requires the use of a control system in order to prevent collisions with the targeted object. Generally, in translational motion, as the camera approaches an object, the degree of complexity of the edges of the object image will change. This principle can be used to estimate the distance to a targeted object. This work introduces a novel statistical method, named Moment of Zoomed-Algorithm Kurtosis (MoZAK), which is based on the I-kaz method, as an indicator for motion system control. The MoZAK parameter, Lc which represents the degree of complexity of image edges, is used to indicate if further actuation of the motor, or otherwise, is required. The method is compared to conventional statistical methods (standard deviation and kurtosis). Results indicate that the MoZAK method presents a viable distance estimator compared to conventional statistical methods.",
author = "{Mohamed Haris}, Sallehuddin and Zakaria, {Muhammad Khalid} and Nuawi, {Mohd. Zaki}",
year = "2011",
doi = "10.1109/AIM.2011.6027091",
language = "English",
isbn = "9781457708381",
pages = "868--873",
booktitle = "IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM",

}

TY - GEN

T1 - Depth estimation from monocular vision using image edge complexity

AU - Mohamed Haris, Sallehuddin

AU - Zakaria, Muhammad Khalid

AU - Nuawi, Mohd. Zaki

PY - 2011

Y1 - 2011

N2 - Autonomous robotic arm motion requires the use of a control system in order to prevent collisions with the targeted object. Generally, in translational motion, as the camera approaches an object, the degree of complexity of the edges of the object image will change. This principle can be used to estimate the distance to a targeted object. This work introduces a novel statistical method, named Moment of Zoomed-Algorithm Kurtosis (MoZAK), which is based on the I-kaz method, as an indicator for motion system control. The MoZAK parameter, Lc which represents the degree of complexity of image edges, is used to indicate if further actuation of the motor, or otherwise, is required. The method is compared to conventional statistical methods (standard deviation and kurtosis). Results indicate that the MoZAK method presents a viable distance estimator compared to conventional statistical methods.

AB - Autonomous robotic arm motion requires the use of a control system in order to prevent collisions with the targeted object. Generally, in translational motion, as the camera approaches an object, the degree of complexity of the edges of the object image will change. This principle can be used to estimate the distance to a targeted object. This work introduces a novel statistical method, named Moment of Zoomed-Algorithm Kurtosis (MoZAK), which is based on the I-kaz method, as an indicator for motion system control. The MoZAK parameter, Lc which represents the degree of complexity of image edges, is used to indicate if further actuation of the motor, or otherwise, is required. The method is compared to conventional statistical methods (standard deviation and kurtosis). Results indicate that the MoZAK method presents a viable distance estimator compared to conventional statistical methods.

UR - http://www.scopus.com/inward/record.url?scp=80053962246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053962246&partnerID=8YFLogxK

U2 - 10.1109/AIM.2011.6027091

DO - 10.1109/AIM.2011.6027091

M3 - Conference contribution

AN - SCOPUS:80053962246

SN - 9781457708381

SP - 868

EP - 873

BT - IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM

ER -