Procedural Generation of Datasets for Training Hand Pose Estimation Systems

Computer Science, Theses and dissertations | September 10, 2023

The rise of computer vision systems has reshaped many industries, driven by the powerful capabilities of deep neural networks. However, as the complexity of these systems grows, so does the demand for larger datasets. However, the manual annotation of large-scale datasets comprising the diversity required by these systems is labour-intensive and time-consuming. This dissertation delves […]

View project

Video tracking and trajectory abstraction for automatic annotation applied to tennis

Computer Science, Featured, Theses and dissertations | March 30, 2020

There are several automatic annotation systems for tennis matches currently on the market in addition to several algorithms reported in the literature without widespread real-world use. These solutions are based on diverse technologies and require different resources to be deployed during their installation and exploitation. In this bachelor’s thesis, we propose a solution to perform […]

View project