Mining Minimal Map-Segments for Visual Place Classifiers

TL;DR

This paper introduces a novel map segmentation algorithm that mines minimal, important map segments for visual place classifiers, reducing map size and maintenance while maintaining recognition performance.

Contribution

It formulates map segmentation as a video segmentation problem and demonstrates its effectiveness across multiple visual place classifier types.

Findings

Minimal map segments suffice for effective VPR.

The proposed method reduces map size and maintenance costs.

Improved VPR performance on the NCLT dataset.

Abstract

In visual place recognition (VPR), map segmentation (MS) is a preprocessing technique used to partition a given view-sequence map into place classes (i.e., map segments) so that each class has good place-specific training images for a visual place classifier (VPC). Existing approaches to MS implicitly/explicitly suppose that map segments have a certain size, or individual map segments are balanced in size. However, recent VPR systems showed that very small important map segments (minimal map segments) often suffice for VPC, and the remaining large unimportant portion of the map should be discarded to minimize map maintenance cost. Here, a new MS algorithm that can mine minimal map segments from a large view-sequence map is presented. To solve the inherently NP hard problem, MS is formulated as a video-segmentation problem and the efficient point-trajectory based paradigm of video segmentation is used. The proposed map representation was implemented with three types of VPC: deep convolutional neural network, bag-of-words, and object class detector, and each was integrated into a Monte Carlo localization algorithm (MCL) within a topometric VPR framework. Experiments using the publicly available NCLT dataset thoroughly investigate the efficacy of MS in terms of VPR performance.