# DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor Fusion

## TL;DR

DFR-FastMOT is a fast, sensor-fusion based multi-object tracking method that improves occlusion handling and long-term object recovery, outperforming current benchmarks in accuracy and speed.

## Contribution

It introduces a novel algebraic formulation for object association and fusion, enabling long-term memory and real-time performance in multi-object tracking.

## Key findings

- Achieves about 3-4% higher MOTA than recent benchmarks.
- Processes 7,763 frames in 1.48 seconds, seven times faster than recent methods.
- Performs well under various detection distortion levels.

## Abstract

Persistent multi-object tracking (MOT) allows autonomous vehicles to navigate safely in highly dynamic environments. One of the well-known challenges in MOT is object occlusion when an object becomes unobservant for subsequent frames. The current MOT methods store objects information, like objects' trajectory, in internal memory to recover the objects after occlusions. However, they retain short-term memory to save computational time and avoid slowing down the MOT method. As a result, they lose track of objects in some occlusion scenarios, particularly long ones. In this paper, we propose DFR-FastMOT, a light MOT method that uses data from a camera and LiDAR sensors and relies on an algebraic formulation for object association and fusion. The formulation boosts the computational time and permits long-term memory that tackles more occlusion scenarios. Our method shows outstanding tracking performance over recent learning and non-learning benchmarks with about 3% and 4% margin in MOTA, respectively. Also, we conduct extensive experiments that simulate occlusion phenomena by employing detectors with various distortion levels. The proposed solution enables superior performance under various distortion levels in detection over current state-of-art methods. Our framework processes about 7,763 frames in 1.48 seconds, which is seven times faster than recent benchmarks. The framework will be available at https://github.com/MohamedNagyMostafa/DFR-FastMOT.