A Robust Multiclass Vehicle Detection and Classification Algorithm for Traffic Surveillance System

The main goal of traffic surveillance systems (TSSs) is to extract useful traffic information by analyzing signals from cameras. This paper presents a system for vehicle detection and classification from static pole-mounted roadside surveillance cameras on busy streets in the presence of different kinds of vehicles. There has been considerable research to accommodate this subject since the 90s; but most studies have been only carried out in developed countries where traffic infrastructures are built around automobiles, whereas in developing countries, motorbikes are dominant. This paper proposes a method that robustly detects, classifies and counts vehicles into three classes: light (motorbikes, bikes, tricycles), medium (cars, sedans, SUV), heavy vehicle (trucks, buses), and a novel tracking algorithm designed to enable classification by majority voting to cope with motorbikes' sudden changes in direction. Extensive experiments with real-world data to evaluate the system's performance have shown promising results: a detection rate of 95.3% in daytime scenes.

I. Introduction

In recent years, there have been increasing interests in the area of traffic surveillance system (TSS), especially in Vietnam and other developing countries. The main goal of a TSS is to gain an understanding of traffic situations through an extraction of information (counts, speed, vehicle type, and density) from sensors' signals. So far, many studies have been carried out using cutting-edge TSSs. However, the detectors in use are costly, bulky and are difficult to maintain, while still providing limited information [1]. Perhaps for those reasons, video-based TSSs are becoming more popular. They are capable of providing more information about traffic conditions and can adapt to a wide range of view condition. They are characterized as low cost, less disruptive and more maintainable than others.