Human Behaviour Understanding using Top-View RGB-D Data

The capability of automatically detecting people and understanding their behaviours is an important functionality of intelligent video systems. The interest in behaviour understanding has effectively increased in recent years, motivated by a societal needs. This thesis is focused on the development of algorithms and solutions for different environments exploiting top-view RGB-D data. In particular, the addressed topics refer to HBU in different research areas. The first goal is to implement people detection algorithms in order to monitor the people activities. To this aim, a thorough study of the state of the art has been conducted to identify the advantages and weakness. An initial approach, proposed in this thesis, is based on CV techniques, it regards the extraction the head of each person using depth data. Another approach is based on deep learning and is proposed to simplify the heads detection implementation in chaotic environments and in the presence of people with different heights. These solutions are validated with a specific dataset. The second goal is to extract several feature from subject and to identify possible interactions that they have with the surrounding environment. Finally, in order to demonstrate the actual contribution of algorithms for understanding the human behaviour in different environments, several use cases have been realized and tested.

I moderni sistemi di visione sono in grado di individuare in maniera automatica gli spostamenti delle persone in modo da poterne comprendere i comportamenti. Questa tesi si focalizza sullo sviluppo di algoritmi di visione e di modelli matematici basati su dati provenienti da sensori RGB-D posti in modalità top-view. Dopo uno studio approfondito sullo stato dell'arte, verranno presentate due tipologie di approcci per l'individuazione delle persone all'interno delle immagini di profondità. Esse sfruttano algoritmi che si basano su tecniche di image processing e su recenti metodi di deep learning. Ulteriori informazioni presenti nell'immagine a colori verranno usate per identificare i soggetti anche in un secondo momento e per individuare eventuali interazioni che questi hanno con l'ambiente circostante. Infine, gli algoritmi verranno testati in diversi casi d'uso reali al fine di valutarne le prestazioni.