Abstract
Video-based recognition of activities of daily living (ADLs) is being used in ambient assisted living systems in order to support the independent living of older people. However, current systems based on cameras located in the environment present a number of problems, such as occlusions and a limited field of view. Recently, wearable cameras have begun to be exploited. This paper presents a review of the state of the art of egocentric vision systems for the recognition of ADLs following a hierarchical structure: motion, action and activity levels, where each level provides higher semantic information and involves a longer time frame. The current egocentric vision literature suggests that ADLs recognition is mainly driven by the objects present in the scene, especially those associated with specific tasks. However, although object-based approaches have proven popular, object recognition remains a challenge due to the intra-class variations found in unconstrained scenarios. As a consequence, the performance of current systems is far from satisfactory.
Highlights
The number of people aged 65 years or over in Europe and the U.S will almost double between2015 and 2060 [1,2]
Ambient assisted living (AAL) systems aim at improving the quality of life and supporting independent and healthy living of older or/and impaired people by using information and communication technologies at home, at the workplace and in public spaces
Betancourt et al [53] proposed a two-level sequential classifier for hand segmentation. They proposed different combinations of features and classifiers as hand detectors, namely colour histograms, Histogram of Oriented Gradients (HOG) and GIST [61], a global descriptor based on colour, intensity, and orientation, and as machine learning methods, they tested Support vector machines (SVM), decision tree and random forest
Summary
The number of people aged 65 years or over in Europe and the U.S will almost double between. Most of the methods follow this pyramidal scheme, some methods analyse activities based on information acquired from the motion level, bypassing the recognition at the action level. These methods usually applied similar techniques to those for action recognition, but considering a longer time lapse. In [15,16], eye-motion and ego-motion (motion of the camera wearer) were combined to classify indoor office tasks, such as reading or typing, and in [17], the motion of the shoulder-mounted camera was used in order to infer the whole body motion These approaches are only beneficial for activities that require big movements.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
