In the context of elderly people health-care in a domestic environment, being able for a robot to understand the pose of a person in a scene is essential. Having the position and orientation of every member of a human being can lead to extract higher level information such as the type of action being performed or the identification of unsafe positions. The proposed algorithm is based on a widely used method called Iterative Closest Point and uses three-dimensional data. The algorithm developed in the project, called Constrained Articulated-ICP, is a variant of this method. It is adapted to the articulated properties of a human body. Several techniques have hence been developed in order to improve the pose recognition, as well as to ensure its validity. A human model is created and the orientation of every member is found by iterative matchings. The pose information is then directly extracted thanks to this model. Developing the algorithm for a real-time application, the pose tracking proved to be accurate and stable. The performed evaluation highlights its ability to recognise the human pose in motion and while performing everyday life movements such as sitting or walking.
Leon is nine, and has a perfect baby brother called Jake. They have gone to live with Maureen, who has fuzzy red hair like a halo, and a belly like Father Christmas. But the adults are speaking in low voices, and wearing Pretend faces. They are threatening to give Jake to strangers. As Leon struggles to cope with his anger, certain things can still make him smile - like chocolate bars, riding his bike fast downhill, burying his hands deep in the soil, hanging out with Tufty (who reminds him of his dad), and stealing enough coins so that one day he can rescue Jake and his mum.
Head pose and eye gaze estimation is a hot research topic in computer vision as it is deeply related to someone’s intentions and attention. Despite many years of research, it remains a very difficult and largely unsolved problem in unconstrained environments. There have been several books on face recognition in which the head pose and eye gaze are only discussed independently. This book is the first to provide a comprehensive introduction to the head pose, eye gaze and their integration from a computational and implementation perspective. Face detection, a related topic, is also discussed. This book has been written with an emphasis on face domain knowledge that can provide fast and robust solutions to estimate the head pose and eye gaze. Domain knowledge is not about features but more anatomical properties. This book will serve as a reference for students, researchers in the field of face recognition and also practitioners in the field of face-based commercial applications including engagement, disability assistance and HCI. The content in this book does not require particular knowledge. Nevertheless, some basic knowledge of geometric computation would be useful for the reader.