Online Vehicle Detection For Estimating Traffic Status

TL;DR

This paper introduces an unsupervised online vehicle detection system that estimates traffic congestion without background subtraction, using feature clustering and adaptive classification to handle various traffic scenes.

Contribution

The novel approach combines unsupervised clustering with online learning for real-time vehicle detection and traffic estimation without relying on background modeling.

Findings

System adapts to various traffic scenes

Accurate vehicle detection using clustering and online learning

Effective in real-time traffic congestion estimation

Abstract

We propose a traffic congestion estimation system based on unsupervised on-line learning algorithm. The system does not rely on background extraction or motion detection. It extracts local features inside detection regions of variable size which are drawn on lanes in advance. The extracted features are then clustered into two classes using K-means and Gaussian Mixture Models(GMM). A Bayes classifier is used to detect vehicles according to the previous cluster information which keeps updated whenever system is running by on-line EM algorithm. Experimental result shows that our system can be adapted to various traffic scenes for estimating traffic status.