Uncovering the Background-Induced bias in RGB based 6-DoF Object Pose Estimation

TL;DR

This paper investigates how artificial markers in datasets influence 6-DoF pose estimation accuracy, revealing biases in neural network focus and proposing methods to mitigate marker-induced effects for more robust real-world applications.

Contribution

The study uncovers the bias introduced by ArUco markers in the Linemod dataset and proposes a new dataset and mitigation strategies to improve pose estimation robustness.

Findings

Markers significantly influence neural network focus during pose estimation.

Presence of markers can bias the model, reducing real-world applicability.

Data augmentation can help mitigate marker-induced bias.

Abstract

In recent years, there has been a growing trend of using data-driven methods in industrial settings. These kinds of methods often process video images or parts, therefore the integrity of such images is crucial. Sometimes datasets, e.g. consisting of images, can be sophisticated for various reasons. It becomes critical to understand how the manipulation of video and images can impact the effectiveness of a machine learning method. Our case study aims precisely to analyze the Linemod dataset, considered the state of the art in 6D pose estimation context. That dataset presents images accompanied by ArUco markers; it is evident that such markers will not be available in real-world contexts. We analyze how the presence of the markers affects the pose estimation accuracy, and how this bias may be mitigated through data augmentation and other methods. Our work aims to show how the presence of these markers goes to modify, in the testing phase, the effectiveness of the deep learning method used. In particular, we will demonstrate, through the tool of saliency maps, how the focus of the neural network is captured in part by these ArUco markers. Finally, a new dataset, obtained by applying geometric tools to Linemod, will be proposed in order to demonstrate our hypothesis and uncovering the bias. Our results demonstrate the potential for bias in 6DOF pose estimation networks, and suggest methods for reducing this bias when training with markers.