Vision-based human activities recognition in supervised or assisted environment

Human Activity Recognition HAR has been a hot research topic in the last decade due to its wide range of applications. Indeed, it has been the basis for implementa- tion of many computer vision applications, home security, video surveillance, and human-computer interaction. We intend by HAR, tools, and systems allowing to detect and recognize actions performed by individuals. With the considerable progress made in sensing technologies, HAR systems shifted from wearable and ambient-based to vision-based. This motivated the researchers to propose a large mass of vision-based solutions. From another perspective, HAR plays an impor- tant role in the health care sector and gets involved in the construction of fall detection systems and many smart home-related systems. Fall detection FD con- sists in identifying the occurrence of falls among other daily life activities. This is essential because falling is one of the most frequent serious health issues encoun- tered by seniors. FD systems are especially used in elderly homes and workplaces to enable elderly isolated populations to live alone for as long as possible, enhance their security and remote assistance. In this thesis, gaps in HAR field and current challenges are identified. This was performed by reviewing the most prominent state-of-the-art techniques, analyzing and evaluating them. Based on the literature review, new algorithms are intro- duced and embedded to explore the multi-modal HAR by combining different modalities that allowed us to highlight the spatial and temporal evolution of the actions. The proposed approach based on deep learning and video representation is quite simple and achieves state-of-the-art results. Afterwards, to address some issues related to FD, we combine human body ge- ometry available at different frames of the video sequence with pose estimation. The proposed approach relies on deep learning architectures and transfer learning to achieve high accuracy while identifying falls from daily life activities and is intended to be used for elderly assistance. Finally, the thesis identifies manda- tory extensions regarding our proposed frameworks for HAR and FD and future research directions.