# Camera-based vehicle velocity estimation from monocular video

arXiv: https://arxiv.org/abs/1802.07094 · HTML: https://mlsanity.com/paper/1802.07094/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2018.

## Built on by (most cited first, 5 of 5)

- [Lidar with Velocity: Correcting Moving Objects Point Cloud Distortion from Oscillating Scanning Lidars by Fusion with Camera](https://mlsanity.com/paper/2111.09497/) (2021)
- [PAVAS: Physics-Aware Video-to-Audio Synthesis](https://mlsanity.com/paper/2512.08282/) (2025)
- [Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation](https://mlsanity.com/paper/2110.11608/) (2021)
- [Real Time Monocular Vehicle Velocity Estimation using Synthetic Data](https://mlsanity.com/paper/2109.07957/) (2021)
- [STAR-VLM: Spatiotemporal Grounding Vision-Language Models for Motion and Velocity Estimation via Automotive Radar Supervision](https://mlsanity.com/paper/2608.01535/) (2026)

## Abstract (arXiv)

This paper documents the winning entry at the CVPR2017 vehicle velocity estimation challenge. Velocity estimation is an emerging task in autonomous driving which has not yet been thoroughly explored. The goal is to estimate the relative velocity of a specific vehicle from a sequence of images. In this paper, we present a light-weight approach for directly regressing vehicle velocities from their trajectories using a multilayer perceptron. Another contribution is an explorative study of features for monocular vehicle velocity estimation. We find that light-weight trajectory based features outperform depth and motion cues extracted from deep ConvNets, especially for far-distance predictions where current disparity and optical flow estimators are challenged significantly. Our light-weight approach is real-time capable on a single CPU and outperforms all competing entries in the velocity estimation challenge. On the test set, we report an average error of 1.12 m/s which is comparable to a (ground-truth) system that combines LiDAR and radar techniques to achieve an error of around 0.71 m/s.