GPU-accelerated Hierarchical Panoramic Image Feature Retrieval for Indoor Localization

TL;DR

This paper presents a GPU-accelerated method for indoor localization using panoramic image features, enabling real-time, robust positioning by modeling landmarks as multimedia retrieval tasks and employing multi-image strategies.

Contribution

It introduces a novel GPU-based parallel retrieval algorithm for indoor localization that leverages panoramic images and multi-image aggregation for improved accuracy and speed.

Findings

Achieves real-time localization at 14fps.

Demonstrates robustness in campus building experiments.

Provides accurate scene similarity estimation.

Abstract

Indoor localization has many applications, such as commercial Location Based Services (LBS), robotic navigation, and assistive navigation for the blind. This paper formulates the indoor localization problem into a multimedia retrieving problem by modeling visual landmarks with a panoramic image feature, and calculating a user's location via GPU- accelerated parallel retrieving algorithm. To solve the scene similarity problem, we apply a multi-images based retrieval strategy and a 2D aggregation method to estimate the final retrieval location. Experiments on a campus building real data demonstrate real-time responses (14fps) and robust localization.