Traffic vehicle behavior prediction using hidden markov models

Authors:
Jian Wu;Zhi-ming Cui;Peng-peng Zhao;Jian-ming Chen
Affiliations:
The Institute of Intelligent Information Processing and Application, Soochow University, Suzhou, China,State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China;The Institute of Intelligent Information Processing and Application, Soochow University, Suzhou, China;The Institute of Intelligent Information Processing and Application, Soochow University, Suzhou, China;The Institute of Intelligent Information Processing and Application, Soochow University, Suzhou, China
Venue:
AICI'12 Proceedings of the 4th international conference on Artificial Intelligence and Computational Intelligence
Year:
2012

Citing 3
Cited 0

A feature-based tracking algorithm for vehicles in intersections

CRV '06 Proceedings of the The 3rd Canadian Conference on Computer and Robot Vision
Traffic monitoring and accident detection at intersections

IEEE Transactions on Intelligent Transportation Systems
Object Trajectory-Based Activity Classification and Recognition Using Hidden Markov Models

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper intends to focus on vehicles steering by analyzing the trajectory. The target values we need to measure are the vehicle's speed and turning angle. These two values are needed to be quantified to certain levels. To create the Hidden Markov Model, HMM learning algorithm and the two values above are used. In HMM, turning left, going straight and turning right are the hidden states and data from the video are used to compute the parameters. HMM can be used to analyze vehicles' driving and to predicate the probable steering in time. The experimental results show that in the case of getting good vehicle trajectory, it is pretty suitable to use HMM to predicate vehicle behavior.