Exploiting Points and Lines in Regression Forests for RGB-D Camera Relocalization

TL;DR

This paper introduces a novel RGB-D camera relocalization method that jointly exploits points and lines within uncertainty-driven regression forests, improving robustness and accuracy in challenging environments.

Contribution

It proposes integrating point and line features into regression forests for camera relocalization, addressing limitations of random pixel sampling methods.

Findings

Outperforms several state-of-the-art baselines on public datasets.

Demonstrates robustness in poorly textured and motion-blurred environments.

Achieves superior or comparable accuracy across multiple error metrics.

Abstract

Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure and loop closure detection. Recent random forests based methods exploit randomly sampled pixel comparison features to predict 3D world locations for 2D image locations to guide the camera pose optimization. However, these image features are only sampled randomly in the images, without considering the spatial structures or geometric information, leading to large errors or failure cases with the existence of poorly textured areas or in motion blur. Line segment features are more robust in these environments. In this work, we propose to jointly exploit points and lines within the framework of uncertainty driven regression forests. The proposed approach is thoroughly evaluated on three publicly available datasets against several strong state-of-the-art baselines in terms of several different error metrics. Experimental results prove the efficacy of our method, showing superior or on-par state-of-the-art performance.