Abstract. The field of human-robot interaction (HRI) is a broad community encompassing robotics, artificial intelligence (AI), human-computer interaction (HCI), psychology and social science. HRI in social robotics explores important issues in designing a robot system that works with people in daily life environments, capable of interacting with, modeling, and learning from humans. Robotic systems should improve their capabilities to not only understand humans but also to convey their intention within their actions. The present work demonstrates this behaviour is achievable through a field study conducted at a science museum. This article introduces a computer vision algorithm which is able to detect and track a leader within a group of peoplethe science communicator, for this particular case -and distinguish between group members and non-group members as well, all by means of a cognitive and logical behaviour analysis of their interactions on scene. The leader's direction is also computed as an attention reference for this approach. The computer vision system is supervising people within a group following a guide to prevent accidents and missing persons. This work represents one of a wide range of possible applications and future scenarios where group interactions are a key aspect for robots to understand and effectively participate in social environments.

Abstract.Active Appearance Model (AAM) is a computer vision procedure for statistical matching of object shape and appearance between images. A main drawback in this technique comes from the construction of the shape mesh. Since landmarks must be manually placed when training shapes, AAM is a very time consuming procedure and it cannot be automatically applied on new objects observed in the images. An approach for automatic landmarking of body shapes on still images for AAM training is introduced in this paper. Several works exist applying automatic landmarking on faces or body joints. Here, we explore the possibility to extend one of these methods to full body contours and demonstrate it is a plausible approach in terms of accuracy and speed measures in experimentation. Our proposal represents a new research line in human body pose tracking with a single-view camera. Hence, implementation in real-time would lead to people being recognized by robots endowed with minimal vision resources, like a webcam, in human-robot interaction tasks.