# Certified Control for Train Sign Classification

arXiv: https://arxiv.org/abs/2311.09778 · HTML: https://mlsanity.com/paper/2311.09778/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 5 of 5)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [OSDaR23: Open Sensor Data for Rail 2023](https://mlsanity.com/paper/2305.03001/) (2023)
- [Certified Control: An Architecture for Verifiable Safety of Autonomous Vehicles](https://mlsanity.com/paper/2104.06178/) (2021)
- [Model Checking Spatial Logics for Closure Spaces](https://mlsanity.com/paper/1609.06513/) (2016)

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

- [Using Formal Models, Safety Shields and Certified Control to Validate AI-Based Train Systems](https://mlsanity.com/paper/2411.14374/) (2024)

## Abstract (arXiv)

There is considerable industrial interest in integrating AI techniques into railway systems, notably for fully autonomous train systems. The KI-LOK research project is involved in developing new methods for certifying such AI-based systems. Here we explore the utility of a certified control architecture for a runtime monitor that prevents false positive detection of traffic signs in an AI-based perception system. The monitor uses classical computer vision algorithms to check if the signs -- detected by an AI object detection model -- fit predefined specifications. We provide such specifications for some critical signs and integrate a Python prototype of the monitor with a popular object detection model to measure relevant performance metrics on generated data. Our initial results are promising, achieving considerable precision gains with only minor recall reduction; however, further investigation into generalization possibilities will be necessary.