LoopNet: A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM

TL;DR

LoopNet introduces a multitasking few-shot learning approach for real-time loop closure detection in large-scale SLAM, utilizing online retraining and distinctive keypoint descriptors to improve accuracy and efficiency on embedded hardware.

Contribution

The paper presents LoopNet, a novel multitasking deep learning architecture with online retraining for loop closure detection, and introduces LoopDB, a new benchmark dataset for SLAM evaluation.

Findings

LoopNet outperforms traditional handcrafted features in diverse conditions.

The approach achieves real-time performance on embedded devices.

LoopNet demonstrates improved loop closure detection accuracy.

Abstract

One of the main challenges in the Simultaneous Localization and Mapping (SLAM) loop closure problem is the recognition of previously visited places. In this work, we tackle the two main problems of real-time SLAM systems: 1) loop closure detection accuracy and 2) real-time computation constraints on the embedded hardware. Our LoopNet method is based on a multitasking variant of the classical ResNet architecture, adapted for online retraining on a dynamic visual dataset and optimized for embedded devices. The online retraining is designed using a few-shot learning approach. The architecture provides both an index into the queried visual dataset, and a measurement of the prediction quality. Moreover, by leveraging DISK (DIStinctive Keypoints) descriptors, LoopNet surpasses the limitations of handcrafted features and traditional deep learning methods, offering better performance under varying conditions. Code is available at https://github.com/RovisLab/LoopNet. Additinally, we introduce a new loop closure benchmarking dataset, coined LoopDB, which is available at https://github.com/RovisLab/LoopDB.