Detection of Road Images Containing a Counterlight Using Multilevel Analysis
In this paper, a method for detecting real-time images that include counterlight produced by the sun, is proposed. It involves applying a multistep analysis of the size, location, and distribution of bright areas in the image. In general, images containing counterlight have a symmetrically high brig...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/13/11/2210 |
_version_ | 1797508410004996096 |
---|---|
author | JongBae Kim |
author_facet | JongBae Kim |
author_sort | JongBae Kim |
collection | DOAJ |
description | In this paper, a method for detecting real-time images that include counterlight produced by the sun, is proposed. It involves applying a multistep analysis of the size, location, and distribution of bright areas in the image. In general, images containing counterlight have a symmetrically high brightness value at a specific location spread over an extremely large region. In addition, the distribution and change in brightness in that specific region have a symmetrically large difference compared with other regions. Through a multistep analysis of these symmetrical features, it is determined whether counterlight is included in the image. The proposed method presents a processing time of approximately 0.7 s and a detection accuracy of 88%, suggesting that the approach can be applied to a safe driving support system for autonomous vehicles. |
first_indexed | 2024-03-10T05:01:42Z |
format | Article |
id | doaj.art-f4d47b98e95a417d91aee7c86fc5ac51 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-10T05:01:42Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-f4d47b98e95a417d91aee7c86fc5ac512023-11-23T01:47:02ZengMDPI AGSymmetry2073-89942021-11-011311221010.3390/sym13112210Detection of Road Images Containing a Counterlight Using Multilevel AnalysisJongBae Kim0Department of Software Engineering, Sejong Cyber University, Seoul 05000, KoreaIn this paper, a method for detecting real-time images that include counterlight produced by the sun, is proposed. It involves applying a multistep analysis of the size, location, and distribution of bright areas in the image. In general, images containing counterlight have a symmetrically high brightness value at a specific location spread over an extremely large region. In addition, the distribution and change in brightness in that specific region have a symmetrically large difference compared with other regions. Through a multistep analysis of these symmetrical features, it is determined whether counterlight is included in the image. The proposed method presents a processing time of approximately 0.7 s and a detection accuracy of 88%, suggesting that the approach can be applied to a safe driving support system for autonomous vehicles.https://www.mdpi.com/2073-8994/13/11/2210counterlight detectionmultilevel analysisITSsafe driving support systems |
spellingShingle | JongBae Kim Detection of Road Images Containing a Counterlight Using Multilevel Analysis Symmetry counterlight detection multilevel analysis ITS safe driving support systems |
title | Detection of Road Images Containing a Counterlight Using Multilevel Analysis |
title_full | Detection of Road Images Containing a Counterlight Using Multilevel Analysis |
title_fullStr | Detection of Road Images Containing a Counterlight Using Multilevel Analysis |
title_full_unstemmed | Detection of Road Images Containing a Counterlight Using Multilevel Analysis |
title_short | Detection of Road Images Containing a Counterlight Using Multilevel Analysis |
title_sort | detection of road images containing a counterlight using multilevel analysis |
topic | counterlight detection multilevel analysis ITS safe driving support systems |
url | https://www.mdpi.com/2073-8994/13/11/2210 |
work_keys_str_mv | AT jongbaekim detectionofroadimagescontainingacounterlightusingmultilevelanalysis |