Multiple Object Tracking with Kernelized Correlation Filters in Urban Mixed Traffic

TL;DR

This paper presents a multiple object tracking system that combines Kernelized Correlation Filters with background subtraction to improve robustness and accuracy in urban traffic videos, demonstrating competitive results with simpler data association.

Contribution

The paper introduces a novel integration of KCF with background subtraction for multiple object tracking, enhancing robustness against occlusion and fragmentation in urban environments.

Findings

Achieves competitive tracking performance on urban datasets.

Effectively handles occlusion and fragmentation issues.

Operates with a simpler data association method.

Abstract

Recently, the Kernelized Correlation Filters tracker (KCF) achieved competitive performance and robustness in visual object tracking. On the other hand, visual trackers are not typically used in multiple object tracking. In this paper, we investigate how a robust visual tracker like KCF can improve multiple object tracking. Since KCF is a fast tracker, many can be used in parallel and still result in fast tracking. We build a multiple object tracking system based on KCF and background subtraction. Background subtraction is applied to extract moving objects and get their scale and size in combination with KCF outputs, while KCF is used for data association and to handle fragmentation and occlusion problems. As a result, KCF and background subtraction help each other to take tracking decision at every frame. Sometimes KCF outputs are the most trustworthy (e.g. during occlusion), while in some other case, it is the background subtraction outputs. To validate the effectiveness of our system, the algorithm is demonstrated on four urban video recordings from a standard dataset. Results show that our method is competitive with state-of-the-art trackers even if we use a much simpler data association step.