# An Attention-Based Deep Learning Architecture for Real-Time Monocular Visual Odometry: Applications to GPS-free Drone Navigation

arXiv: https://arxiv.org/abs/2404.17745 · HTML: https://mlsanity.com/paper/2404.17745/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 27 Apr 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry](https://mlsanity.com/paper/2003.01060/) (2020)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning](https://mlsanity.com/paper/1709.06841/) (2017)
- [VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry](https://mlsanity.com/paper/1804.08366/) (2018)
- [Deep Auxiliary Learning for Visual Localization and Odometry](https://mlsanity.com/paper/1803.03642/) (2018)
- [Bayesian Attention Modules](https://mlsanity.com/paper/2010.10604/) (2020)
- [Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias and Rolling Shutter Effect](https://mlsanity.com/paper/1705.04300/) (2017)
- [Geometric Consistency for Self-Supervised End-to-End Visual Odometry](https://mlsanity.com/paper/1804.03789/) (2018)
- [Global Pose Estimation with an Attention-based Recurrent Network](https://mlsanity.com/paper/1802.06857/) (2018)
- [Deep Global-Relative Networks for End-to-End 6-DoF Visual Localization and Odometry](https://mlsanity.com/paper/1812.07869/) (2018)

## Abstract (arXiv)

Drones are increasingly used in fields like industry, medicine, research, disaster relief, defense, and security. Technical challenges, such as navigation in GPS-denied environments, hinder further adoption. Research in visual odometry is advancing, potentially solving GPS-free navigation issues. Traditional visual odometry methods use geometry-based pipelines which, while popular, often suffer from error accumulation and high computational demands. Recent studies utilizing deep neural networks (DNNs) have shown improved performance, addressing these drawbacks. Deep visual odometry typically employs convolutional neural networks (CNNs) and sequence modeling networks like recurrent neural networks (RNNs) to interpret scenes and deduce visual odometry from video sequences. This paper presents a novel real-time monocular visual odometry model for drones, using a deep neural architecture with a self-attention module. It estimates the ego-motion of a camera on a drone, using consecutive video frames. An inference utility processes the live video feed, employing deep learning to estimate the drone's trajectory. The architecture combines a CNN for image feature extraction and a long short-term memory (LSTM) network with a multi-head attention module for video sequence modeling. Tested on two visual odometry datasets, this model converged 48% faster than a previous RNN model and showed a 22% reduction in mean translational drift and a 12% improvement in mean translational absolute trajectory error, demonstrating enhanced robustness to noise.