Depth-Based Object Tracking Using a Robust Gaussian Filter

TL;DR

This paper introduces a robust Gaussian filter approach for 3D object tracking using depth images, effectively handling fat-tailed noise and high-dimensional data, outperforming standard filters and matching particle filter performance.

Contribution

The paper presents a novel robust Gaussian filter method tailored for depth-based object tracking, addressing noise robustness and computational efficiency challenges.

Findings

Outperforms standard Gaussian filter in real data experiments.

Achieves comparable efficiency to particle filters with better accuracy.

Provides smoother and more accurate tracking estimates.

Abstract

We consider the problem of model-based 3D-tracking of objects given dense depth images as input. Two difficulties preclude the application of a standard Gaussian filter to this problem. First of all, depth sensors are characterized by fat-tailed measurement noise. To address this issue, we show how a recently published robustification method for Gaussian filters can be applied to the problem at hand. Thereby, we avoid using heuristic outlier detection methods that simply reject measurements if they do not match the model. Secondly, the computational cost of the standard Gaussian filter is prohibitive due to the high-dimensional measurement, i.e. the depth image. To address this problem, we propose an approximation to reduce the computational complexity of the filter. In quantitative experiments on real data we show how our method clearly outperforms the standard Gaussian filter. Furthermore, we compare its performance to a particle-filter-based tracking method, and observe comparable computational efficiency and improved accuracy and smoothness of the estimates.