Clustering learning model of CCTV image pattern for producing road hazard meteorological information

Jiwan Lee; Bonghee Hong; Sunghoon Jung; Victor Chang

doi:10.1016/j.future.2018.03.022

Clustering learning model of CCTV image pattern for producing road hazard meteorological information

Jiwan Lee
, Bonghee Hong^*
, Sunghoon Jung
, Victor Chang

^*Corresponding author for this work

International Business School Suzhou

Pusan National University

Research output: Contribution to journal › Article › peer-review

19 Citations (Scopus)

Abstract

A method for real-time estimation of weather, especially the amount of rainfall, by analyzing CCTV images, is much cheaper than one using the existing expensive weather observation equipment. In this paper, we propose a method to find an estimation model function whose input is CCTV images and output is the amount of rainfall. Using CCTV images, we propose an algorithm for selecting the number and size of the region of interest optimized for rainfall estimation, generating a data pattern graph showing a clear distinction from the number of regions of interest, clustering the pattern data graphs, and estimating the amount of rainfall. Experiments using real CCTV images show that the estimation accuracy is greater than 80%.

Original language	English
Pages (from-to)	1338-1350
Number of pages	13
Journal	Future Generation Computer Systems
Volume	86
DOIs	https://doi.org/10.1016/j.future.2018.03.022
Publication status	Published - Sept 2018

Access to Document

10.1016/j.future.2018.03.022

Cite this

@article{89ea6e1a5b3e4132b6d78a3766a4229b,

title = "Clustering learning model of CCTV image pattern for producing road hazard meteorological information",

abstract = "A method for real-time estimation of weather, especially the amount of rainfall, by analyzing CCTV images, is much cheaper than one using the existing expensive weather observation equipment. In this paper, we propose a method to find an estimation model function whose input is CCTV images and output is the amount of rainfall. Using CCTV images, we propose an algorithm for selecting the number and size of the region of interest optimized for rainfall estimation, generating a data pattern graph showing a clear distinction from the number of regions of interest, clustering the pattern data graphs, and estimating the amount of rainfall. Experiments using real CCTV images show that the estimation accuracy is greater than 80\%.",

author = "Jiwan Lee and Bonghee Hong and Sunghoon Jung and Victor Chang",

note = "Publisher Copyright: {\textcopyright} 2018 Elsevier B.V.",

year = "2018",

month = sep,

doi = "10.1016/j.future.2018.03.022",

language = "English",

volume = "86",

pages = "1338--1350",

journal = "Future Generation Computer Systems",

issn = "0167-739X",

}

TY - JOUR

T1 - Clustering learning model of CCTV image pattern for producing road hazard meteorological information

AU - Lee, Jiwan

AU - Hong, Bonghee

AU - Jung, Sunghoon

AU - Chang, Victor

PY - 2018/9

Y1 - 2018/9

N2 - A method for real-time estimation of weather, especially the amount of rainfall, by analyzing CCTV images, is much cheaper than one using the existing expensive weather observation equipment. In this paper, we propose a method to find an estimation model function whose input is CCTV images and output is the amount of rainfall. Using CCTV images, we propose an algorithm for selecting the number and size of the region of interest optimized for rainfall estimation, generating a data pattern graph showing a clear distinction from the number of regions of interest, clustering the pattern data graphs, and estimating the amount of rainfall. Experiments using real CCTV images show that the estimation accuracy is greater than 80%.

AB - A method for real-time estimation of weather, especially the amount of rainfall, by analyzing CCTV images, is much cheaper than one using the existing expensive weather observation equipment. In this paper, we propose a method to find an estimation model function whose input is CCTV images and output is the amount of rainfall. Using CCTV images, we propose an algorithm for selecting the number and size of the region of interest optimized for rainfall estimation, generating a data pattern graph showing a clear distinction from the number of regions of interest, clustering the pattern data graphs, and estimating the amount of rainfall. Experiments using real CCTV images show that the estimation accuracy is greater than 80%.

UR - https://www.scopus.com/pages/publications/85046757272

U2 - 10.1016/j.future.2018.03.022

DO - 10.1016/j.future.2018.03.022

M3 - Article

AN - SCOPUS:85046757272

SN - 0167-739X

VL - 86

SP - 1338

EP - 1350

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

ER -

Clustering learning model of CCTV image pattern for producing road hazard meteorological information

Abstract

Access to Document

Other files and links

Fingerprint

Cite this