Abstract-This paper reviews recent works in the literature on the use of systems based on Radar and RGB-Depth sensors for fall detection, and discusses outstanding research challenges and trends related to this research field. Systems to detect reliably fall events and promptly alert carers and first responders have gained significant interest in the past few years in order to address the societal issue of an increasing number of elderly people living alone, with the associated risk of them falling and the consequences in terms of health treatments, reduced well-being, and costs. The interest in radar and RGB-D sensors is related to their capability to enable contactless and non-intrusive monitoring, which is an advantage for practical deployment and users' acceptance and compliance, compared with other sensor technologies such as video-cameras, or wearables. Furthermore, the possibility of combining and fusing information from heterogeneous types of sensors is expected to improve the overall performance of practical fall detection systems. Researchers from different fields can benefit from multidisciplinary knowledge and awareness of the latest developments in radar and RGB-D sensors that this paper is discussing.

The aim of Active and Assisted Living is to develop tools to promote the ageing in place of elderly people, and human activity recognition algorithms can help to monitor aged people in home environments. Different types of sensors can be used to address this task and the RGBD sensors, especially the ones used for gaming, are cost-effective and provide much information about the environment. This work aims to propose an activity recognition algorithm exploiting skeleton data extracted by RGBD sensors. The system is based on the extraction of key poses to compose a feature vector, and a multiclass Support Vector Machine to perform classification. Computation and association of key poses are carried out using a clustering algorithm, without the need of a learning algorithm. The proposed approach is evaluated on five publicly available datasets for activity recognition, showing promising results especially when applied for the recognition of AAL related actions. Finally, the current applicability of this solution in AAL scenarios and the future improvements needed are discussed.

We propose an automatic, privacy-preserving, fall detection method for indoor environments, based on the usage of the Microsoft Kinect® depth sensor, in an “on-ceiling” configuration, and on the analysis of depth frames. All the elements captured in the depth scene are recognized by means of an Ad-Hoc segmentation algorithm, which analyzes the raw depth data directly provided by the sensor. The system extracts the elements, and implements a solution to classify all the blobs in the scene. Anthropometric relationships and features are exploited to recognize one or more human subjects among the blobs. Once a person is detected, he is followed by a tracking algorithm between different frames. The use of a reference depth frame, containing the set-up of the scene, allows one to extract a human subject, even when he/she is interacting with other objects, such as chairs or desks. In addition, the problem of blob fusion is taken into account and efficiently solved through an inter-frame processing algorithm. A fall is detected if the depth blob associated to a person is near to the floor. Experimental tests show the effectiveness of the proposed solution, even in complex scenarios.

No abstract

Abstract-Significant research exists on the use of wearable sensors in the context of assisted living for activities recognition and fall detection, whereas radar sensors have been studied only recently in this domain. This paper approaches the performance limitation of using individual sensors, especially for classification of similar activities, by implementing information fusion of features extracted from experimental data collected by different sensors, namely a tri-axial accelerometer, a micro-Doppler radar, and a depth camera. Preliminary results confirm that combining information from heterogeneous sensors improves the overall performance of the system. The classification accuracy attained by means of this fusion approach improves by 11.2% compared to radar-only use, and by 16.9% compared to the accelerometer. Furthermore, adding features extracted from a RGB-D Kinect sensor, the overall classification accuracy increases up to 91.3%.