HPointLoc: Point-based Indoor Place Recognition using Synthetic RGB-D Images

TL;DR

This paper introduces HPointLoc, a new indoor place recognition dataset and a modular approach called PNTR that combines image retrieval, keypoint matching, and pose optimization, advancing indoor localization for robots.

Contribution

The paper presents a novel indoor place recognition dataset and a unique modular framework combining multiple techniques, not previously explored together.

Findings

PNTR outperforms existing methods on HPointLoc dataset

High potential for real-world robot localization applications

Dataset and framework are publicly available

Abstract

We present a novel dataset named as HPointLoc, specially designed for exploring capabilities of visual place recognition in indoor environment and loop detection in simultaneous localization and mapping. The loop detection sub-task is especially relevant when a robot with an on-board RGB-D camera can drive past the same place (``Point") at different angles. The dataset is based on the popular Habitat simulator, in which it is possible to generate photorealistic indoor scenes using both own sensor data and open datasets, such as Matterport3D. To study the main stages of solving the place recognition problem on the HPointLoc dataset, we proposed a new modular approach named as PNTR. It first performs an image retrieval with the Patch-NetVLAD method, then extracts keypoints and matches them using R2D2, LoFTR or SuperPoint with SuperGlue, and finally performs a camera pose optimization step with TEASER++. Such a solution to the place recognition problem has not been previously studied in existing publications. The PNTR approach has shown the best quality metrics on the HPointLoc dataset and has a high potential for real use in localization systems for unmanned vehicles. The proposed dataset and framework are publicly available: https://github.com/metra4ok/HPointLoc.