Result Details
Methods of Video and Sensor Information Processing in Traffic
Created: 2025
Type
software
Language
English
Authors
Zemčík Pavel, prof. Dr. Ing., dr. h. c., DCGM (FIT)
Juránek Roman, Ing., Ph.D., DCGM (FIT)
Dobeš Petr, Ing., DCGM (FIT)
Juhas Miroslav, Ing.
Maršík Lukáš, Ing., DCGM (FIT)
Juránek Roman, Ing., Ph.D., DCGM (FIT)
Dobeš Petr, Ing., DCGM (FIT)
Juhas Miroslav, Ing.
Maršík Lukáš, Ing., DCGM (FIT)
Description
The software includes the developed package for processing sensor information in traffic scenes. The first group of integrated methods includes several approaches for vehicle detection in video frames. These are mainly based on the MMDetection framework and the YOLO v11 family of models. Moreover, the package also provides tracking algorithms for building detection tracks across the time domain. The second part of the package offers a method for radar sensor processing.
Keywords
Traffic analysis, Visual-based vehicle detection, Radar-based vehicle detection
URL
License
Use of the result by another entity is possible without acquiring a license in some cases
License Fee
The licensor does not require a license fee for the result in some cases
Projects
Detection of Traffic Threats and 3D Semantic Analysis of Traffic Scenes, TAČR, 5. veřejná soutěž programu Delta 2, TM05000040, start: 2024-01-01, end: 2025-12-31, completed
Research groups
Computer Graphics Research Group (RG GRAPH)
Departments