# Traffic Danger Recognition With Surveillance Cameras Without Training Data

arXiv: https://arxiv.org/abs/1811.11969 · HTML: https://mlsanity.com/paper/1811.11969/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2018.

## Built on by (most cited first, 3 of 3)

- [Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals](https://mlsanity.com/paper/2201.05290/) (2022)
- [Real-time Lane-wise Traffic Monitoring in Optimal ROIs](https://mlsanity.com/paper/2404.15212/) (2024)
- [A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance](https://mlsanity.com/paper/2510.20016/) (2025)

## Abstract (arXiv)

We propose a traffic danger recognition model that works with arbitrary traffic surveillance cameras to identify and predict car crashes. There are too many cameras to monitor manually. Therefore, we developed a model to predict and identify car crashes from surveillance cameras based on a 3D reconstruction of the road plane and prediction of trajectories. For normal traffic, it supports real-time proactive safety checks of speeds and distances between vehicles to provide insights about possible high-risk areas. We achieve good prediction and recognition of car crashes without using any labeled training data of crashes. Experiments on the BrnoCompSpeed dataset show that our model can accurately monitor the road, with mean errors of 1.80% for distance measurement, 2.77 km/h for speed measurement, 0.24 m for car position prediction, and 2.53 km/h for speed prediction.