Fusing moving average model and stationary wavelet decomposition for automatic incident detection: Case study of Tokyo Expressway

Liu, Qinghua, Chung, Edward, & Zhai, Liujia (2014) Fusing moving average model and stationary wavelet decomposition for automatic incident detection: Case study of Tokyo Expressway. Journal of Traffic and Transportation Engineering (English Edition), 1(6), pp. 404-414.

View at publisher (open access)


Traffic congestion is a growing problem in urban areas all over the world. The transport sector has been in full swing event study on intelligent transportation system for automatic detection. The functionality of automatic incident detection on expressways is a primary objective of advanced traffic management system. In order to save lives and prevent secondary incidents, accurate and prompt incident detection is necessary. This paper presents a methodology that integrates moving average (MA) model with stationary wavelet decomposition for automatic incident detection, in which parameters of layer coefficient are extracted from the difference between the upstream and downstream occupancy. Unlike other wavelet-based method presented before, firstly it smooths the raw data with MA model. Then it uses stationary wavelet to decompose, which can achieve accurate reconstruction of the signal, and does not shift the signal transfer coefficients. Thus, it can detect the incidents more accurately. The threshold to trigger incident alarm is also adjusted according to normal traffic condition with congestion. The methodology is validated with real data from Tokyo Expressway ultrasonic sensors. Experimental results show that it is accurate and effective, and that it can differentiate traffic accident from other condition such as recurring traffic congestion.

Impact and interest:

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

8 since deposited on 29 May 2016
8 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 95852
Item Type: Journal Article
Refereed: Yes
Keywords: automatic incident detection, moving average model, stationary wavelet decomposition, Tokyo Expressway
DOI: 10.1016/S2095-7564(15)30290-7
ISSN: 2095-7564
Subjects: Australian and New Zealand Standard Research Classification > ENGINEERING (090000) > CIVIL ENGINEERING (090500) > Transport Engineering (090507)
Divisions: Current > Schools > School of Civil Engineering & Built Environment
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: Copyright 2014 Periodical Offices of Chang’an University
Deposited On: 29 May 2016 22:53
Last Modified: 30 May 2016 22:31

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page