Recently, cameras are equipped on cars in order to assist their drivers. These cameras often have a severe radial distortion because of their wide view angle, and sometimes it is necessary to compensate it in a fully automatic way in the field. We have proposed such a method, which uses the entropy of the histogram of oriented gradient (HOG) to evaluate the goodness of the compensation. Its performance was satisfactory, but the computational burden was too heavy to be executed by drive assistance devices. In this report, we discuss a method to speed up the algorithm, and obtain a new light algorithm feasible for such devices. We also show more comprehensive performance evaluation results then those in the previous reports.
Yuta KANUKI
Gunma University
Naoya OHTA
Gunma University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yuta KANUKI, Naoya OHTA, "Speeding Up and Performance Evaluation of a Fully Automatic Radial Distortion Compensation Algorithm for Driving Assistance Cameras" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 10, pp. 1892-1895, October 2015, doi: 10.1587/transinf.2015EDL8071.
Abstract: Recently, cameras are equipped on cars in order to assist their drivers. These cameras often have a severe radial distortion because of their wide view angle, and sometimes it is necessary to compensate it in a fully automatic way in the field. We have proposed such a method, which uses the entropy of the histogram of oriented gradient (HOG) to evaluate the goodness of the compensation. Its performance was satisfactory, but the computational burden was too heavy to be executed by drive assistance devices. In this report, we discuss a method to speed up the algorithm, and obtain a new light algorithm feasible for such devices. We also show more comprehensive performance evaluation results then those in the previous reports.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8071/_p
Copy
@ARTICLE{e98-d_10_1892,
author={Yuta KANUKI, Naoya OHTA, },
journal={IEICE TRANSACTIONS on Information},
title={Speeding Up and Performance Evaluation of a Fully Automatic Radial Distortion Compensation Algorithm for Driving Assistance Cameras},
year={2015},
volume={E98-D},
number={10},
pages={1892-1895},
abstract={Recently, cameras are equipped on cars in order to assist their drivers. These cameras often have a severe radial distortion because of their wide view angle, and sometimes it is necessary to compensate it in a fully automatic way in the field. We have proposed such a method, which uses the entropy of the histogram of oriented gradient (HOG) to evaluate the goodness of the compensation. Its performance was satisfactory, but the computational burden was too heavy to be executed by drive assistance devices. In this report, we discuss a method to speed up the algorithm, and obtain a new light algorithm feasible for such devices. We also show more comprehensive performance evaluation results then those in the previous reports.},
keywords={},
doi={10.1587/transinf.2015EDL8071},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Speeding Up and Performance Evaluation of a Fully Automatic Radial Distortion Compensation Algorithm for Driving Assistance Cameras
T2 - IEICE TRANSACTIONS on Information
SP - 1892
EP - 1895
AU - Yuta KANUKI
AU - Naoya OHTA
PY - 2015
DO - 10.1587/transinf.2015EDL8071
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2015
AB - Recently, cameras are equipped on cars in order to assist their drivers. These cameras often have a severe radial distortion because of their wide view angle, and sometimes it is necessary to compensate it in a fully automatic way in the field. We have proposed such a method, which uses the entropy of the histogram of oriented gradient (HOG) to evaluate the goodness of the compensation. Its performance was satisfactory, but the computational burden was too heavy to be executed by drive assistance devices. In this report, we discuss a method to speed up the algorithm, and obtain a new light algorithm feasible for such devices. We also show more comprehensive performance evaluation results then those in the previous reports.
ER -