# Road Scene Understanding by Occupancy Grid Learning from Sparse Radar Clusters using Semantic Segmentation

arXiv: https://arxiv.org/abs/1904.00415 · HTML: https://mlsanity.com/paper/1904.00415/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2019.

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

- [Place recognition survey: An update on deep learning approaches](https://mlsanity.com/paper/2106.10458/) (2021)
- [Quantification of Uncertainties in Deep Learning-based Environment Perception](https://mlsanity.com/paper/2306.03018/) (2023)
- [Deep learning for radar data exploitation of autonomous vehicle](https://mlsanity.com/paper/2203.08038/) (2022)
- [Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time](https://mlsanity.com/paper/2306.06126/) (2023)

## Abstract (arXiv)

Occupancy grid mapping is an important component in road scene understanding for autonomous driving. It encapsulates information of the drivable area, road obstacles and enables safe autonomous driving. Radars are an emerging sensor in autonomous vehicle vision, becoming more widely used due to their long range sensing, low cost, and robustness to severe weather conditions. Despite recent advances in deep learning technology, occupancy grid mapping from radar data is still mostly done using classical filtering approaches.In this work, we propose learning the inverse sensor model used for occupancy grid mapping from clustered radar data. This is done in a data driven approach that leverages computer vision techniques. This task is very challenging due to data sparsity and noise characteristics of the radar sensor. The problem is formulated as a semantic segmentation task and we show how it can be learned using lidar data for generating ground truth. We show both qualitatively and quantitatively that our learned occupancy net outperforms classic methods by a large margin using the recently released NuScenes real-world driving data.