Komplexpraktikum Computergraphik und Visualisierung (WS 2019/20)
SWS 0/0/4
Modules
INF-B-510 (Vertiefung) INF
INF-B-520 (Vertiefung zur Bachelor-Arbeit) INF
INF-B-530 (Vertiefung) MI
INF-B-540 (Vertiefung zur Bachelor-Arbeit)t MI
INF-VMI-8 (Angewandte Graphische Datenverarbeitung) MI
INF-MA-PR (Master-Praktikum) INF
INF-E-4 (Master-Praktikum) MI
INF-04-KP (Komplexpraktikum)
MINF-04-KP-FG1 (Komplexpraktikum Fachgebiet 1)
IST-05-KP (Komplexpraktikum)
You can use the Komplexpraktikum also in INF-VERT7 with a corresponding notice to Prof. Gumhold.
Advisor
Organisation
To register, please contact Josua Zscheile via mail:
The first appointment will take place in the week of October, 21st to 25th. The
concrete date will be agreed with all participants.
Topic "Flying Garbage"
In cooperation with the Leipzig public transport services, DEKRA, Continental and other companies TU Dresden is developing an autonomous electrified bus shuttle in the project ABSOLUT. Among the tasks of TU scientists and engineers is the processing of sensory data from multiple cameras, radars and lidars integrated in the vehicle and the detection of all objects substantial for high level automation.
The complex lab "Flying Garbage" is concerned with providing a training data base for highly deformable, dynamic objects by 3D modelling and physically correct movement simulation. This can include plastic bags, paper waste and leaves. This is important for the project, because objects like these that are generally able to drive over, and such objects are not well presented in the scientific discourse. That has practical implications, because many autonomous vehicles stop in front of waste objects and require intervention by a driver.
Problem
Classification whether an object can be driven over
Task
- generate training data for trash that can safely be driven over
- modelling of traffic scene including trash like highly deformable plastic bags
- randomized generation of wind
- physically plausible simulation of trash, rendering to simulate camera sensor and to generate ground truth segmentation
Requirements
- knowledge in Computer Graphics
- preferably experience in some game engine