SkillAgentSearch skills...

SRLCD

fast loop closure detection (online visual place recognition) via saliency re-identification IROS 2020

Install / Use

/learn @wh200720041/SRLCD
About this skill

Quality Score

0/100

Supported Platforms

Universal

README

SRLCD

Online Visual Place Recognition via Saliency Re-identification IROS 2020

Author: Wang Han, Nanyang Technological University, Singapore

Comparison approach can be found at https://github.com/wh200720041/VRP_Comparison

1. Evaluation

1.1. Example on public dataset (KITTI dataset, TUM dataset, Oxford RobotCar dataset)

<p align='center'> <img src="https://github.com/wh200720041/SRLCD/blob/master/img/detection_examples.png"/> </p>

1.2. Performance Evaluation

<p align='center'> <img src="https://github.com/wh200720041/SRLCD/blob/master/img/precision_recall.png" width = 45% /> </p>

1.3. Comparison

<p align='center'> <img src="https://github.com/wh200720041/SRLCD/blob/master/img/metrics_comparison.png" width = 60% /> </p>

2. Prerequisites

2.1 Platform

Microsoft Visual Studio 2017

2.2 Opencv

Follow Opencv installation.

2.3. Eigen

Follow Eigen Installation.

3. Citation

If you use this work for your research, you may want to cite

@inproceedings{wang2020online,
  author={H. {Wang} and C. {Wang} and L. {Xie}},
  booktitle={2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
  title={Online Visual Place Recognition via Saliency Re-identification}, 
  year={2020},
  volume={},
  number={},
  pages={5030-5036},
  doi={10.1109/IROS45743.2020.9341703}
}
View on GitHub
GitHub Stars99
CategoryDevelopment
Updated6mo ago
Forks17

Languages

C++

Security Score

92/100

Audited on Sep 4, 2025

No findings