# Data-Efficient Collaborative Decentralized Thermal-Inertial Odometry

arXiv: https://arxiv.org/abs/2209.06588 · HTML: https://mlsanity.com/paper/2209.06588/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 35 references that are in the map.
- First posted on arXiv 14 Sep 2022.

## Builds on (most cited first, 9 of 9)

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Visual-Inertial Navigation: A Concise Review](https://mlsanity.com/paper/1906.02650/) (2019)
- [Data-Efficient Decentralized Visual SLAM](https://mlsanity.com/paper/1710.05772/) (2017)
- [Visual-Inertial Odometry of Aerial Robots](https://mlsanity.com/paper/1906.03289/) (2019)
- [COVINS: Visual-Inertial SLAM for Centralized Collaboration](https://mlsanity.com/paper/2108.05756/) (2021)
- [Keyframe-based Direct Thermal-Inertial Odometry](https://mlsanity.com/paper/1903.00798/) (2019)
- [Online Photometric Calibration of Automatic Gain Thermal Infrared Cameras](https://mlsanity.com/paper/2012.14292/) (2020)
- [xVIO: A Range-Visual-Inertial Odometry Framework](https://mlsanity.com/paper/2010.06677/) (2020)
- [Distributed Visual-Inertial Cooperative Localization](https://mlsanity.com/paper/2103.12770/) (2021)

## Built on by (most cited first, 4 of 4)

- [Long-range UAV Thermal Geo-localization with Satellite Imagery](https://mlsanity.com/paper/2306.02994/) (2023)
- [Fieldscale: Locality-Aware Field-based Adaptive Rescaling for Thermal Infrared Image](https://mlsanity.com/paper/2405.15395/) (2024)
- [STHN: Deep Homography Estimation for UAV Thermal Geo-localization with Satellite Imagery](https://mlsanity.com/paper/2405.20470/) (2024)
- [Data Efficient Visual Place Recognition Using Extremely JPEG-Compressed Images](https://mlsanity.com/paper/2209.08343/) (2022)

## Abstract (arXiv)

We propose a system solution to achieve data-efficient, decentralized state estimation for a team of flying robots using thermal images and inertial measurements. Each robot can fly independently, and exchange data when possible to refine its state estimate. Our system front-end applies an online photometric calibration to refine the thermal images so as to enhance feature tracking and place recognition. Our system back-end uses a covariance-intersection fusion strategy to neglect the cross-correlation between agents so as to lower memory usage and computational cost. The communication pipeline uses Vector of Locally Aggregated Descriptors (VLAD) to construct a request-response policy that requires low bandwidth usage. We test our collaborative method on both synthetic and real-world data. Our results show that the proposed method improves by up to 46 % trajectory estimation with respect to an individual-agent approach, while reducing up to 89 % the communication exchange. Datasets and code are released to the public, extending the already-public JPL xVIO library.