Research on Automatic Incident Detection Algorithm Based on Fusion of Freeway Mainline Information and Toll Collection information

2006 ◽  
Author(s):  
Xiangyuan Yin ◽  
Weiming Liu ◽  
Liping Guan
Keyword(s):  
Detection Algorithm ◽  
Incident Detection ◽  
Automatic Incident Detection ◽  
Toll Collection

scholarly journals Sensitivity Analysis Based SVM Application on Automatic Incident Detection of Rural Road in China

2018 ◽  
Vol 2018 ◽  
pp. 1-9
Author(s):  
Xingliang Liu ◽  
Jinliang Xu ◽  
Menghui Li ◽  
Jia Peng
Keyword(s):  
Sensitivity Analysis ◽  
Detection Algorithm ◽  
Vehicle Group ◽  
Incident Detection ◽  
Data Set ◽  
Rural Roads ◽  
Rural Road ◽  
Automatic Incident Detection ◽  
Accident Detection ◽  
Reaction Speed

Traditional automatic incident detection methods such as artificial neural networks, backpropagation neural network, and Markov chains are not suitable for addressing the incident detection problem of rural roads in China which have a relatively high accident rate and a low reaction speed caused by the character of small traffic volume. This study applies the support vector machine (SVM) and parameter sensitivity analysis methods to build an accident detection algorithm in a rural road condition, based on real-time data collected in a field experiment. The sensitivity of four parameters (speed, front distance, vehicle group time interval, and free driving ratio) is analyzed, and the data sets of two parameters with a significant sensitivity are chosen to form the traffic state feature vector. The SVM and k-fold cross validation (K-CV) methods are used to build the accident detection algorithm, which shows an excellent performance in detection accuracy (98.15% of the training data set and 87.5% of the testing data set). Therefore, the problem of low incident reaction speed of rural roads in China could be solved to some extent.

Comparison and Analysis Tool for Automatic Incident Detection

2005 ◽  
Vol 1925 (1) ◽  
pp. 58-65 ◽  
Author(s):  
Roger Browne ◽  
Simon Foo ◽  
Shawn Huynh ◽  
Baher Abdulhai ◽  
Fred Hall
Keyword(s):  
Field Evaluation ◽  
Detection Algorithm ◽  
Incident Detection ◽  
Analysis Tool ◽  
Test Bed ◽  
Traffic Video ◽  
Comparison And Analysis ◽  
Automatic Incident Detection ◽  
Advanced Traffic Management System ◽  
The Impact

A new test bed for automatic incident detection (AID) systems uses real-time traffic video and data feeds from the Ontario, Canada, Ministry of Transportation COMPASS advanced traffic management system. This new test bed, called the AID comparison and analysis tool (AID CAAT), consists largely of a data warehouse storing a significant amount of traffic video, the corresponding traffic data, and an accurate log of incident start and end times. Also presented is a proof-of-concept field evaluation whereby the AID CAAT is used to calibrate and then analyze the performance of three AID algorithms: California Algorithm 8, the McMaster algorithm, and the genetic adaptive incident detection algorithm. In the calibration and testing process, nuisance rate and false normal rate are introduced as two new performance measures to supplement the three traditional measures (detection rate, false alarm rate, and mean time to detection). Further, the pilot evaluation shows the considerable advantages of AID CAAT in its ability to investigate the impact of freeway geometry, traffic flow rate, and traffic sensor spacing on the performance of the three AID algorithms. This work represents the first stage in a series of further tests to develop a set of AID algorithm deployment guidelines.

Sign in / Sign up

Export Citation Format

Share Document