Utilizing High-level Visual Feature for Indoor Shopping Mall Navigation

TL;DR

This paper introduces a learning-based indoor navigation system that uses high-level visual features from storefront images to accurately localize users and generate maps in shopping malls, enhancing navigation robustness.

Contribution

It proposes a novel feature fusion scheme (FusionNet) for store recognition and a method to convert indicator maps into topological maps for improved indoor navigation.

Findings

Achieves robust localization in real shopping malls

Enables precise map generation from user-captured images

Demonstrates effectiveness through experimental results

Abstract

Towards robust and convenient indoor shopping mall navigation, we propose a novel learning-based scheme to utilize the high-level visual information from the storefront images captured by personal devices of users. Specifically, we decompose the visual navigation problem into localization and map generation respectively. Given a storefront input image, a novel feature fusion scheme (denoted as FusionNet) is proposed by fusing the distinguishing DNN-based appearance feature and text feature for robust recognition of store brands, which serves for accurate localization. Regarding the map generation, we convert the user-captured indicator map of the shopping mall into a topological map by parsing the stores and their connectivity. Experimental results conducted on the real shopping malls demonstrate that the proposed system achieves robust localization and precise map generation, enabling accurate navigation.