A Vision-Based System for Intelligent Monitoring: Human Behaviour Analysis and Privacy by Context

Abstract

Due to progress and demographic change, society is facing a crucial challenge related to increased life expectancy and a higher number of people in situations of dependency. As a consequence, there exists a significant demand for support systems for personal autonomy. This article outlines the vision@home project, whose goal is to extend independent living at home for elderly and impaired people, providing care and safety services by means of vision-based monitoring. Different kinds of ambient-assisted living services are supported, from the detection of home accidents, to telecare services. In this contribution, the specification of the system is presented, and novel contributions are made regarding human behaviour analysis and privacy protection. By means of a multi-view setup of cameras, people's behaviour is recognised based on human action recognition. For this purpose, a weighted feature fusion scheme is proposed to learn from multiple views. In order to protect the right to privacy of the inhabitants when a remote connection occurs, a privacy-by-context method is proposed. The experimental results of the behaviour recognition method show an outstanding performance, as well as support for multi-view scenarios and real-time execution, which are required in order to provide the proposed services.

Continuous Human Action Recognition in Ambient Assisted Living Scenarios

“…These, in turn, are employed for action recognition, where temporal alignment of sequences is performed for matching using dynamic time warping (DTW). Also multi-view recognition is taken into account [5]. Concretely, intelligent feature fusion of single-view feature representations is performed with a feature concatenation operator in addition to a weighted feature fusion scheme that is based on a priori knowledge about the usefulness of each camera.…”

“…Great advances have been made in order to improve the recognition rate, support multiple views and view-invariant recognition [2,3] as well as real-time performance [4,5]. However, it can be observed that HAR has been addressed by classifying short video sequences that contain single actions.…”

Designing a Video Monitoring System for AAL applications: the SPHERE Case Study

“…Furthermore, video data analysis allows one to identify specific actions, long term activities, and behavioural patterns [9], with some exploiting contextual information [11]. While video based platforms offer the opportunity to extract unique, continuous, and rich information from the home environment, they also present a number of disadvantages, such as privacy issues [9], user acceptance and system cost and scalability. Finally, the accepted challenges of computer vision, such as arbitrary body poses, changing illumination, occlusion, and low cost/low resolution are still unsolved problems [23] even if depth data is combined with colour [6].…”

“…Video based systems are efficient for implementing alert systems to detect dangerous events like falls, as in [20]. Furthermore, video data analysis allows one to identify specific actions, long term activities, and behavioural patterns [9], with some exploiting contextual information [11]. While video based platforms offer the opportunity to extract unique, continuous, and rich information from the home environment, they also present a number of disadvantages, such as privacy issues [9], user acceptance and system cost and scalability.…”

“…Research interest in smart homes for eHealth and Active and Assisted Living (AAL) has continuously grown in the recent years. This research has examined different diseases and target groups [19,4] and technologies ranging from wearable devices gathering movement information [27] and vital signals [4], to environmental sensors [1] and video based platforms [9].…”