RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Features for Indoor Localization

TL;DR

RaP-Net is a novel feature extraction network that predicts region-wise and point-wise reliability to improve indoor localization accuracy, trained on a new dataset with diverse indoor scene appearances.

Contribution

The paper introduces RaP-Net, a new network architecture that considers both region and point reliability for robust feature extraction in indoor localization.

Findings

RaP-Net outperforms state-of-the-art feature algorithms in indoor localization.

The OpenLORIS-Location dataset effectively trains the network for invariability in indoor scenes.

RaP-Net achieves excellent performance in feature matching tasks.

Abstract

Feature extraction plays an important role in visual localization. Unreliable features on dynamic objects or repetitive regions will interfere with feature matching and challenge indoor localization greatly. To address the problem, we propose a novel network, RaP-Net, to simultaneously predict region-wise invariability and point-wise reliability, and then extract features by considering both of them. We also introduce a new dataset, named OpenLORIS-Location, to train the proposed network. The dataset contains 1553 images from 93 indoor locations. Various appearance changes between images of the same location are included and can help the model to learn the invariability in typical indoor scenes. Experimental results show that the proposed RaP-Net trained with OpenLORIS-Location dataset achieves excellent performance in the feature matching task and significantly outperforms state-of-the-arts feature algorithms in indoor localization. The RaP-Net code and dataset are available at https://github.com/ivipsourcecode/RaP-Net.