Search

Human activity recognition is an essential task for robots to effectively and efficiently interact with the end users. Many machine learning approaches for activity recognition systems have been proposed recently. Most of these methods are built upon a strong assumption that the labels in the training data are noise-free, which is often not realistic. In this paper, we incorporate the uncertainty of labels into a max-margin learning algorithm, and the algorithm allows the labels to deviate over iterations in order to find a better solution. This is incorporated with a hierarchical approach where we jointly estimate activities at two different levels of granularity. The model is tested on two datasets, i.e., the CAD-120 dataset and the Accompany dataset, and the proposed model shows outperforming results over the state-of-the-art methods.

The availability of cheap imaging sensors makes it possible to increase the robustness of vision-based alarm systems. This paper explores the benefit of data fusion in the application of fall detection. Falls are a common source of injury for elderly people and automatic fall detection is, therefore, an important development in automated home care. We first evaluate a skeleton-based classification method that uses the Microsoft Kinect as a sensor. Next, we evaluate an overhead camera-based method that looks at bounding ellipse features. Then, we fuse the data from these two methods by validating the skeleton tracked by the Kinect. Data fusion proves beneficial, since the data fusion approach outperforms the other methods.

We describe a system that recognizes human postures with heavy self-occlusion. In particular, we address posture recognition in a robot assisted-living scenario, where the environment is equipped with a top-view camera for monitoring human activities. This setup is very useful because top-view cameras lead to accurate localization and limited inter-occlusion between persons, but conversely they suffer from body parts being frequently self-occluded. The conventional way of posture recognition relies on good estimation of body part positions, which turns out to be unstable in the top-view due to occlusion and foreshortening. In our approach, we learn a posture descriptor for each specific posture category. The posture descriptor encodes how well the person in the image can be `explained' by the model. The postures are subsequently recognized from the matching scores returned by the posture descriptors. We select the state-of-the-art approach of pose estimation as our posture descriptor. The results show that our method is able to correctly classify 79.7% of the test sample, which outperforms the conventional approach by over 23%.

People counting is a challenging task with many applications. We propose a method with a fixed stereo camera that is based on projecting a template onto the depth image. The method was tested on a challenging outdoor dataset with good results and runs in real time.

This chapter focuses on activity monitoring in a home setting for health care purposes. First the most current sensing systems are described, which consist of wearable and ambient sensors. Then several approaches for the monitoring of simple actions are discussed, like falls or therapies. After that, the recognition of more complex activities is discussed. A number of applications for the care givers is presented. The chapter concludes with a section on acceptance and privacy.