# Tracking in Urban Traffic Scenes from Background Subtraction and Object Detection

## TL;DR

This paper presents a method for multi-object tracking in urban traffic scenes by combining background subtraction and object detection, improving tracking accuracy through data integration and trajectory prediction.

## Contribution

It introduces a novel approach that fuses background subtraction and multiclass object detection for enhanced multi-object tracking in complex urban environments.

## Key findings

- Achieved competitive performance on the Urban tracker dataset.
- Demonstrated the importance of integrating multiple detection sources.
- Highlighted challenges in detection data fusion affecting tracking quality.

## Abstract

In this paper, we propose to combine detections from background subtraction and from a multiclass object detector for multiple object tracking (MOT) in urban traffic scenes. These objects are associated across frames using spatial, colour and class label information, and trajectory prediction is evaluated to yield the final MOT outputs. The proposed method was tested on the Urban tracker dataset and shows competitive performances compared to state-of-the-art approaches. Results show that the integration of different detection inputs remains a challenging task that greatly affects the MOT performance.