# Probabilistic Segmentation for Robust Field of View Estimation

arXiv: https://arxiv.org/abs/2503.07375 · HTML: https://mlsanity.com/paper/2503.07375/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving](https://mlsanity.com/paper/1907.06826/) (2019)
- [Bayesian Neural Networks: An Introduction and Survey](https://mlsanity.com/paper/2006.12024/) (2020)
- [Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures](https://mlsanity.com/paper/2006.16974/) (2020)
- [Federated Learning for Connected and Automated Vehicles: A Survey of Existing Approaches and Challenges](https://mlsanity.com/paper/2308.10407/) (2023)
- [Security Analysis of Camera-LiDAR Fusion Against Black-Box Attacks on Autonomous Vehicles](https://mlsanity.com/paper/2106.07098/) (2021)
- [RadCloud: Real-Time High-Resolution Point Cloud Generation Using Low-Cost Radars for Aerial and Ground Vehicles](https://mlsanity.com/paper/2403.05964/) (2024)
- [Misbehavior Detection Using Collective Perception under Privacy Considerations](https://mlsanity.com/paper/2111.03461/) (2021)
- [MadRadar: A Black-Box Physical Layer Attack Framework on mmWave Automotive FMCW Radars](https://mlsanity.com/paper/2311.16024/) (2023)
- [Datasets, Models, and Algorithms for Multi-Sensor, Multi-agent Autonomy Using AVstack](https://mlsanity.com/paper/2312.04970/) (2023)
- [Bayesian Methods for Trust in Collaborative Multi-Agent Autonomy](https://mlsanity.com/paper/2403.16956/) (2024)
- [What Would Trojans Do? Exploiting Partial-Information Vulnerabilities in Autonomous Vehicle Sensing](https://mlsanity.com/paper/2303.03470/) (2023)
- [Polylidar3D -- Fast Polygon Extraction from 3D Data](https://mlsanity.com/paper/2007.12065/) (2020)
- [Learning-Based Vulnerability Analysis of Cyber-Physical Systems](https://mlsanity.com/paper/2103.06271/) (2021)

## Built on by (most cited first, 1 of 1)

- [Scaling Datasets for Multi-Sensor, Multi-Agent, and Multi-Domain Learning in Autonomous Systems](https://mlsanity.com/paper/2606.04444/) (2026)

## Abstract (arXiv)

Attacks on sensing and perception threaten the safe deployment of autonomous vehicles (AVs). Security-aware sensor fusion helps mitigate threats but requires accurate field of view (FOV) estimation which has not been evaluated autonomy. To address this gap, we adapt classical computer graphics algorithms to develop the first autonomy-relevant FOV estimators and create the first datasets with ground truth FOV labels. Unfortunately, we find that these approaches are themselves highly vulnerable to attacks on sensing. To improve robustness of FOV estimation against attacks, we propose a learning-based segmentation model that captures FOV features, integrates Monte Carlo dropout (MCD) for uncertainty quantification, and performs anomaly detection on confidence maps. We illustrate through comprehensive evaluations attack resistance and strong generalization across environments. Architecture trade studies demonstrate the model is feasible for real-time deployment in multiple applications.