Fault-Diagnosing SLAM for Varying Scale Change Detection

TL;DR

This paper introduces a fault diagnosis-based method for visual SLAM change detection that effectively handles varying object scales by reorganizing bag-of-words representations, avoiding the need for map memorization or up-to-date anomaly detectors.

Contribution

It proposes a novel fault diagnosis approach utilizing restructured BoW image representations to detect scale-varying changes without map memorization or dedicated anomaly detectors.

Findings

Effective detection of significant changes across varying scales.

No need for memorizing map images or maintaining up-to-date detectors.

Validated through experimental results with different change detection methods.

Abstract

In this paper, we present a new fault diagnosis (FD) -based approach for detection of imagery changes that can detect significant changes as inconsistencies between different sub-modules (e.g., self-localizaiton) of visual SLAM. Unlike classical change detection approaches such as pairwise image comparison (PC) and anomaly detection (AD), neither the memorization of each map image nor the maintenance of up-to-date place-specific anomaly detectors are required in this FD approach. A significant challenge that is encountered when incorporating different SLAM sub-modules into FD involves dealing with the varying scales of objects that have changed (e.g., the appearance of small dangerous obstacles on the floor). To address this issue, we reconsider the bag-of-words (BoW) image representation, by exploiting its recent advances in terms of self-localization and change detection. As a key advantage, BoW image representation can be reorganized into any different scaling by simply cropping the original BoW image. Furthermore, we propose to combine different self-localization modules with strong and weak BoW features with different discriminativity, and to treat inconsistency between strong and weak self-localization as an indicator of change. The efficacy of the proposed approach for FD with/without AD and/or PC was experimentally validated.