Multiple-Vehicle Tracking in the Highway Using Appearance Model and Visual Object Tracking

TL;DR

This paper presents a novel multiple-vehicle tracking approach using appearance and motion models, comparing deep neural network features with traditional features, and evaluates performance on the UA-DETRACK benchmark.

Contribution

The paper introduces a new vehicle tracking method combining appearance and motion models, and compares deep learning features with traditional features for improved accuracy.

Findings

Deep neural network features achieved 58.9% accuracy.

Traditional features achieved up to 15.9% accuracy.

Results demonstrate potential for further improvement with more distinguishable features.

Abstract

In recent decades, due to the groundbreaking improvements in machine vision, many daily tasks are performed by computers. One of these tasks is multiple-vehicle tracking, which is widely used in different areas such as video surveillance and traffic monitoring. This paper focuses on introducing an efficient novel approach with acceptable accuracy. This is achieved through an efficient appearance and motion model based on the features extracted from each object. For this purpose, two different approaches have been used to extract features, i.e. features extracted from a deep neural network, and traditional features. Then the results from these two approaches are compared with state-of-the-art trackers. The results are obtained by executing the methods on the UA-DETRACK benchmark. The first method led to 58.9% accuracy while the second method caused up to 15.9%. The proposed methods can still be improved by extracting more distinguishable features.