Anotation
- Human body segmentation into particular body parts (regions) is a crucial task in many human body-oriented computer vision applications.
- In general, body segmentation as a preprocessing step can be helpful in understanding the skeletal and body structure of a human subject.
- Applying the segmentation methods on 3D human data is an important task, since 3D data has potential to provide additional information over RGB images, and tends to yield more accurate results.
Goal
- research current state-of-the-art segmentation methods (which can be used on 3D data)
- apply various (analytical/machine learning) segmentation techniques on human body data
- use programming language of your choice (for machine learning methods, python is recommended)
- load and process 3D human data in form of point clouds/depth images (use available datasets)
- summarize results, evaluate accuracy of the methods
Milestones
- 29.10.2020 Webpage for bachelor thesis
- 10.11.2020 Add milestones
- 01.12.2020 Research papers & initial data + presentation
- 31.01.2021 Initial chapter(10 pages) + Prototype(tensorflow, cuDNN, dataset)
- 15.02.2021 ML study sessions, neural networks basics
- 31.02.2021 Find suitable methods
- 15.03.2021 Implementation - implement selected method/s
- 31.03.2021 Add more datasets - evaluate method
- 30.04.2021 Complementation of Bachelor thesis
- 15.05.2021 Submit a bachelor's thesis