Thesis supervisor: Tamás Szirányi
Location of studies (in Hungarian): Department of Material Handling and Logistics Systems Abbreviation of location of studies: ALRT
Description of the research topic:
a) Preliminaries: Pedestrian detection in 2D, 3D point cloud analysis and recognition
b) Research goals: Using the on-board camera system for detecting objects and events from video streams and/or separated 2D image series. Calibration of cameras and Lidar scanning systems for fused imagery data. Detection of the environment to establish the a posteriori model of the possible structures and objects.
c) Tasks:
• Managing data stream for the sensor system;
• Feature descriptors for objects, motion and events;
• Feature selection for the optimal classification methods;
• Automatic annotation systems;
• Deep Neural Network based clustering methods: training and test.
d) Equipment: cameras, Lidars and computer systems of the laboratory.
e) Planned scientific results: Publications in the leading image processing and autonomous driving journals and conferences. Key-words: 3D recognition, Hidden Markov models, Deep learning, 3D geometry, laser scanning, vision based safety systems, graph theory.
Required language skills: English Further requirements: Expected background: good math, programming in MATLAB and/or C/C++.
Number of students who can be accepted: 2
Deadline for application: 2019-05-15
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).