Real-time bike-related traffic violation detection of cars

Information

• Publication Type: Bachelor Thesis
• Workgroup(s)/Project(s):
  • Modeling the World at Scale
• Date: September 2025
• Date (Start): 7. March 2024
• Date (End): 12. September 2025
• Matrikelnummer: 01417912
• First Supervisor: Stefan Ohrhallinger
• Keywords: sensors, bicycle, traffic rules

Abstract

Multi-modal object detection offers more significant results than 3D object de- tection within a single domain[Shi20]. In the case of autonomous driving, a

combination of modalities is used to complement other modalities weaknesses. While LIDAR sensors offer great depth and reflection information precision, the output is a sparsely populated point cloud. RGB images, on the other hand, offer great resolution and improve object detection and classification results. However, to be able to extract precise 3D bounding cuboids, it is often fusioned with point clouds or other depth information.

Additional Files and Images

Weblinks

No further information available.

BibTeX

@bachelorsthesis{mueller-2024-rbt,
  title =      "Real-time bike-related traffic violation detection of cars",
  author =     "Tobias M\"{u}ller",
  year =       "2025",
  abstract =   "Multi-modal object detection offers more significant results
               than 3D object de- tection within a single domain[Shi20]. In
               the case of autonomous driving, a  combination of modalities
               is used to complement other modalities weaknesses. While
               LIDAR sensors offer great depth and reflection information
               precision, the output is a sparsely populated point cloud.
               RGB images, on the other hand, offer great resolution and
               improve object detection and classification results.
               However, to be able to extract precise 3D bounding cuboids,
               it is often fusioned with point clouds or other depth
               information.",
  month =      sep,
  address =    "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria",
  school =     "Research Unit of Computer Graphics, Institute of Visual
               Computing and Human-Centered Technology, Faculty of
               Informatics, TU Wien ",
  keywords =   "sensors, bicycle, traffic rules",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2025/mueller-2024-rbt/",
}