Into the Fog: Evaluating Robustness of Multiple Object Tracking

TL;DR

This paper introduces a physics-based fog simulation for evaluating the robustness of multiple object tracking methods under adverse weather conditions, revealing their limitations in foggy environments.

Contribution

It presents a novel fog simulation technique for MOT datasets and provides a comprehensive benchmark assessing tracker performance in foggy scenarios.

Findings

Trackers perform poorly under foggy conditions.

The new simulation reveals limitations of current MOT methods.

Benchmark results highlight need for more robust tracking algorithms.

Abstract

State-of-the-art Multiple Object Tracking (MOT) approaches have shown remarkable performance when trained and evaluated on current benchmarks. However, these benchmarks primarily consist of clear weather scenarios, overlooking adverse atmospheric conditions such as fog, haze, smoke and dust. As a result, the robustness of trackers against these challenging conditions remains underexplored. To address this gap, we introduce physics-based volumetric fog simulation method for arbitrary MOT datasets, utilizing frame-by-frame monocular depth estimation and a fog formation optical model. We enhance our simulation by rendering both homogeneous and heterogeneous fog and propose to use the dark channel prior method to estimate atmospheric light, showing promising results even in night and indoor scenes. We present the leading benchmark MOTChallenge (third release) augmented with fog (smoke for indoor scenes) of various intensities and conduct a comprehensive evaluation of MOT methods, revealing their limitations under fog and fog-like challenges.