Deep Learning techniques for visual counting

Ciampi L.

Counting objects in images  Visual counting  Domain adaptation  Deep Learning  Synthetic data  Deep Learning with scarce data  Image analysis  Medical image analysis 

In this thesis, I investigated and enhanced Deep Learning (DL)-based techniques for the visual counting task, which automatically estimates the number of objects, such as people or vehicles, present in images and videos. Specifically, I tackled the problem related to the lack of data needed for training current DL-based solutions by exploiting synthetic data gathered from video games, employing Domain Adaptation strategies between different data distributions, and taking advantage of the redundant information characterizing datasets labeled by multiple annotators. Furthermore, I addressed the engineering challenges coming out of the adoption of DL-based techniques in environments with limited power resources, mainly due to the high computational budget the AI-based algorithms require.