Speed Measurement from Traffic Camera Video Using Structure-from-Motion-Based Calibration

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0198170" target="_blank" >RIV/00216305:26220/26:0198170 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2025_sbornik_2.pdf" target="_blank" >https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2025_sbornik_2.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.13164/eeict.2025.231" target="_blank" >10.13164/eeict.2025.231</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Speed Measurement from Traffic Camera Video Using Structure-from-Motion-Based Calibration

Popis výsledku v původním jazyce

Speed measurement from traffic camera video is an active research problem, primarily due to the challenges associated with accurate camera calibration in an uncontrolled environment. Traditional calibration techniques often require prior knowledge of the scene or manual input from the user, limiting their applicability in real-world scenarios. In this work, we propose a novel approach for traffic speed measurements using a camera calibration based on automatic 3D scene reconstruction via structure-from-motion (SfM). Our approach leverages deep learning-based feature extraction and matching, specifically SuperPoint and SuperGlue, to achieve precise scene reconstruction. By placing the camera within the reconstructed environment, we obtain its intrinsic and extrinsic parameters without requiring predefined reference objects. This allows us to establish a reliable reference for measuring distances in the scene. With this setup, we can accurately measure point distances on the ground plane, enabling robust speed estimation of moving vehicles. We present the implementation of our speed measurement method as a real-time application based on YOLO11 object detector and BoT-SORT object tracker. Our approach achieves speed measurement accuracy with an error of 6.9 km/h compared to a GPS RTK-based reference benchmark, demonstrating its effectiveness for traffic monitoring applications.

Název v anglickém jazyce

Speed Measurement from Traffic Camera Video Using Structure-from-Motion-Based Calibration

Popis výsledku anglicky

Speed measurement from traffic camera video is an active research problem, primarily due to the challenges associated with accurate camera calibration in an uncontrolled environment. Traditional calibration techniques often require prior knowledge of the scene or manual input from the user, limiting their applicability in real-world scenarios. In this work, we propose a novel approach for traffic speed measurements using a camera calibration based on automatic 3D scene reconstruction via structure-from-motion (SfM). Our approach leverages deep learning-based feature extraction and matching, specifically SuperPoint and SuperGlue, to achieve precise scene reconstruction. By placing the camera within the reconstructed environment, we obtain its intrinsic and extrinsic parameters without requiring predefined reference objects. This allows us to establish a reliable reference for measuring distances in the scene. With this setup, we can accurately measure point distances on the ground plane, enabling robust speed estimation of moving vehicles. We present the implementation of our speed measurement method as a real-time application based on YOLO11 object detector and BoT-SORT object tracker. Our approach achieves speed measurement accuracy with an error of 6.9 km/h compared to a GPS RTK-based reference benchmark, demonstrating its effectiveness for traffic monitoring applications.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings II of the 31th Student EEICT 2025: Selected Papers

ISBN

978-80-214-6320-2

ISSN

—

e-ISSN

2788-1334

Počet stran výsledku

262

Strana od-do

246-250

Název nakladatele

Brno University of Technology, Faculty of Electronic Engineering and Communication

Místo vydání

Brno

Místo konání akce

Brno

Datum konání akce

29. 4. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—