No abstract

Human Activity Recognition (HAR) is an interdisciplinary research area that has been attracting interest from several research communities specialized in machine learning, computer vision, medical and gaming research. The potential applications range from surveillance systems, human computer interfaces, sports video analysis, digital shopping assistants, video retrieval, games and health-care. Several and diverse approaches exist to recognize a human action. From computer vision techniques, modeling relations between human motion and objects, marker-based tracking systems and RGB-D cameras. Using a Kinect sensor that provides the position of the main skeleton joints we extract features based solely on the motion of those joints. This paper aims to compare the performance of several supervised classifiers trained with manually labeled data versus the same classifiers trained with data automatically labeled. We propose a framework capable of recognizing human actions using supervised classifiers trained with automatically labeled data.

In our daily activities we perform prediction or anticipation when interacting with other humans or with objects. Prediction of human activity made by computers has several potential applications: surveillance systems, human computer interfaces, sports video analysis, human-robot-collaboration, games and health-care. We propose a system capable of recognizing and predicting human actions using supervised classifiers trained with automatically labeled data evaluated in our human activity RGB-D dataset (recorded with a Kinect sensor) and using only the position of the main skeleton joints to extract features. Using conditional random fields (CRFs) to model the sequential nature of actions in a sequence has been used before, but where other approaches try to predict an outcome or anticipate ahead in time (seconds), we try to predict what will be the next action of a subject. Our results show an activity prediction accuracy of 89.9% using an automatically labeled dataset.

In this paper, we describe a novel approach to teaching early mathematical concepts to young children. This approach aims to merge storytelling and Maths. Evidence show that through dramatic games and role-playing activities young children (aging from 5-7 years old) learn to master new knowledge, to fit in a new school setting and to socially relate with their peers. So taking this evidence into account, it is possible to devise an innovative collaborative learning scenario that teaches early mathematical concepts by telling and creating stories. More than doing it in the traditional formats (oral or theatrical form), we are investigating the possibility to take this scenario to an innovative computerised platform -Microsoft Surface TM .