Machine learning for automatic generation of ground-truth boundary boxes
- Bachelor-/Masterarbeit -
Beschreibung:
Object detection is a task of computer vision and aims to recognize and locate the position of objects in an image. It has a wide range of applications such as autonomous driving, surveillance, medical diagnostics, traffic analysis and production lines.
Learning-based object detection uses machine learning technology for this task and relies on the ground-truth boundary boxes of objects. Ground-truth boundary boxes are identified either by complicated analysis methods or by human beings, a time-consuming and tedious process. This work aims to developing an approach based on machine learning technology to automatically generate the ground-truth boundary boxes for image object detection.
Anforderungen/Kenntnisse:
Machine Learning - Basic
Betreuung:
Prof. Dr. rer.nat. habil. Sven Groppe
Institut für Informationssysteme
Ratzeburger Allee 160 ( Gebäude 64 - 2. OG)
23562 Lübeck
Telefon: 0451 / 3101 5706
Institut für Informationssysteme
Ratzeburger Allee 160 ( Gebäude 64 - 2. OG)
23562 Lübeck
Telefon: 0451 / 3101 5711