Discriminative Map Retrieval Using View-Dependent Map Descriptor

TL;DR

This paper enhances map retrieval by incorporating spatial information through a unique viewpoint determined by scene parsing, improving discriminative power in large map collections for autonomous navigation.

Contribution

It introduces a novel method to model a unique, invariant viewpoint using scene parsing and Manhattan world grammar, extending bag-of-words map retrieval with spatial context.

Findings

Improved map retrieval accuracy on the radish dataset.

Robustness to clutter, occlusions, and viewpoint changes.

Effective scene structure detection using Manhattan world grammar.

Abstract

Map retrieval, the problem of similarity search over a large collection of 2D pointset maps previously built by mobile robots, is crucial for autonomous navigation in indoor and outdoor environments. Bag-of-words (BoW) methods constitute a popular approach to map retrieval; however, these methods have extremely limited descriptive ability because they ignore the spatial layout information of the local features. The main contribution of this paper is an extension of the bag-of-words map retrieval method to enable the use of spatial information from local features. Our strategy is to explicitly model a unique viewpoint of an input local map; the pose of the local feature is defined with respect to this unique viewpoint, and can be viewed as an additional invariant feature for discriminative map retrieval. Specifically, we wish to determine a unique viewpoint that is invariant to moving objects, clutter, occlusions, and actual viewpoints. Hence, we perform scene parsing to analyze the scene structure, and consider the "center" of the scene structure to be the unique viewpoint. Our scene parsing is based on a Manhattan world grammar that imposes a quasi-Manhattan world constraint to enable the robust detection of a scene structure that is invariant to clutter and moving objects. Experimental results using the publicly available radish dataset validate the efficacy of the proposed approach.