LoopDB: A Loop Closure Dataset for Large Scale Simultaneous Localization and Mapping

TL;DR

LoopDB is a comprehensive, publicly available dataset with over 1000 high-resolution images from diverse environments, designed for benchmarking and training loop closure algorithms in SLAM systems.

Contribution

It introduces a large-scale, diverse loop closure dataset with ground truth for SLAM benchmarking and deep learning training.

Findings

Provides accurate ground truth for over 1000 images

Enables benchmarking of loop closure algorithms

Supports training of neural network-based methods

Abstract

In this study, we introduce LoopDB, which is a challenging loop closure dataset comprising over 1000 images captured across diverse environments, including parks, indoor scenes, parking spaces, as well as centered around individual objects. Each scene is represented by a sequence of five consecutive images. The dataset was collected using a high resolution camera, providing suitable imagery for benchmarking the accuracy of loop closure algorithms, typically used in simultaneous localization and mapping. As ground truth information, we provide computed rotations and translations between each consecutive images. Additional to its benchmarking goal, the dataset can be used to train and fine-tune loop closure methods based on deep neural networks. LoopDB is publicly available at https://github.com/RovisLab/LoopDB.