Noise Models in Feature-based Stereo Visual Odometry

TL;DR

This paper evaluates various noise models in feature-based stereo visual odometry, demonstrating that adaptable noise models improve accuracy in structure and motion estimation.

Contribution

It provides a comparative analysis of different noise models specifically for stereo visual odometry, highlighting the importance of adaptability for better performance.

Findings

Adaptive noise models outperform fixed models in accuracy.

Stereo visual odometry benefits from noise models tailored to noise variability.

Evaluation on KITTI and Tsukuba datasets confirms the effectiveness of adaptable models.

Abstract

Feature-based visual structure and motion reconstruction pipelines, common in visual odometry and large-scale reconstruction from photos, use the location of corresponding features in different images to determine the 3D structure of the scene, as well as the camera parameters associated with each image. The noise model, which defines the likelihood of the location of each feature in each image, is a key factor in the accuracy of such pipelines, alongside optimization strategy. Many different noise models have been proposed in the literature; in this paper we investigate the performance of several. We evaluate these models specifically w.r.t. stereo visual odometry, as this task is both simple (camera intrinsics are constant and known; geometry can be initialized reliably) and has datasets with ground truth readily available (KITTI Odometry and New Tsukuba Stereo Dataset). Our evaluation shows that noise models which are more adaptable to the varying nature of noise generally perform better.