D-InLoc++: Indoor Localization in Dynamic Environments

TL;DR

D-InLoc++ enhances indoor localization accuracy in dynamic environments by integrating real-time instance segmentation to filter out dynamic objects, improving robustness over traditional methods that struggle with repetitive structures and moving objects.

Contribution

The paper introduces a novel localization pipeline that combines instance segmentation with pose estimation, specifically addressing challenges posed by movable objects in indoor scenes.

Findings

Improved localization robustness in dynamic indoor environments.

Effective filtering of dynamic objects using YOLACT++ masks.

Enhanced simulation pipeline for environments with movable objects.

Abstract

Most state-of-the-art localization algorithms rely on robust relative pose estimation and geometry verification to obtain moving object agnostic camera poses in complex indoor environments. However, this approach is prone to mistakes if a scene contains repetitive structures, e.g., desks, tables, boxes, or moving people. We show that the movable objects incorporate non-negligible localization error and present a new straightforward method to predict the six-degree-of-freedom (6DoF) pose more robustly. We equipped the localization pipeline InLoc with real-time instance segmentation network YOLACT++. The masks of dynamic objects are employed in the relative pose estimation step and in the final sorting of camera pose proposal. At first, we filter out the matches laying on masks of the dynamic objects. Second, we skip the comparison of query and synthetic images on the area related to the moving object. This procedure leads to a more robust localization. Lastly, we describe and improve the mistakes caused by gradient-based comparison between synthetic and query images and publish a new pipeline for simulation of environments with movable objects from the Matterport scans. All the codes are available on github.com/dubenma/D-InLocpp .