# DeepLocalization: Landmark-based Self-Localization with Deep Neural Networks

arXiv: https://arxiv.org/abs/1904.09007 · HTML: https://mlsanity.com/paper/1904.09007/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2019.

## Built on by (most cited first, 9 of 9)

- [Anomaly Detection in Multi-Agent Trajectories for Automated Driving](https://mlsanity.com/paper/2110.07922/) (2021)
- [Lightweight Monocular Depth Estimation through Guided Decoding](https://mlsanity.com/paper/2203.04206/) (2022)
- [Extrinsic Camera Calibration with Semantic Segmentation](https://mlsanity.com/paper/2208.03949/) (2022)
- [Image Patch-Matching with Graph-Based Learning in Street Scenes](https://mlsanity.com/paper/2311.04617/) (2023)
- [Attention-based Vehicle Self-Localization with HD Feature Maps](https://mlsanity.com/paper/2107.07787/) (2021)
- [Landmark Stereo Dataset for Landmark Recognition and Moving Node Localization in a Non-GPS Battlefield Environment](https://mlsanity.com/paper/2402.12320/) (2024)
- [Landmark-based Localization using Stereo Vision and Deep Learning in GPS-Denied Battlefield Environment](https://mlsanity.com/paper/2402.12551/) (2024)
- [Secure Navigation using Landmark-based Localization in a GPS-denied Environment](https://mlsanity.com/paper/2402.14280/) (2024)
- [SafeNav: Safe Path Navigation using Landmark Based Localization in a GPS-denied Environment](https://mlsanity.com/paper/2505.01956/) (2025)

## Abstract (arXiv)

We address the problem of vehicle self-localization from multi-modal sensor information and a reference map. The map is generated off-line by extracting landmarks from the vehicle's field of view, while the measurements are collected similarly on the fly. Our goal is to determine the autonomous vehicle's pose from the landmark measurements and map landmarks. To learn this mapping, we propose DeepLocalization, a deep neural network that regresses the vehicle's translation and rotation parameters from unordered and dynamic input landmarks. The proposed network architecture is robust to changes of the dynamic environment and can cope with a small number of extracted landmarks. During the training process we rely on synthetically generated ground-truth. In our experiments, we evaluate two inference approaches in real-world scenarios. We show that DeepLocalization can be combined with regular GPS signals and filtering algorithms such as the extended Kalman filter. Our approach achieves state-of-the-art accuracy and is about ten times faster than the related work.