Indoor localisation through object detection within multiple environments utilising a single wearable camera

Abstract

The recent growth in the wearable sensor market has stimulated new opportunities within the domain of Ambient Assisted Living, providing unique methods of collecting occupant information. This approach leverages contemporary wearable technology, Google Glass, to facilitate a unique first-person view of the occupants immediate environment. Machine vision techniques are employed to determine an occupant’s location via environmental object detection. This method provides additional secondary benefits such as first person tracking within the environment and lack of required sensor interaction to determine occupant location. Object recognition is performed using the Oriented Features from Accelerated Segment Test and Rotated Binary Robust Independent Elementary Features algorithm with a K-Nearest Neighbour matcher to match the saved key-points of the objects to the scene. To validate the approach, an experimental set-up consisting of three ADL routines, each containing at least ten activities, ranging from drinking water to making a meal were considered. Ground truth was obtained from manually annotated video data and the approach was previously benchmarked against a common method of indoor localisation that employs dense sensor placement in order to validate the approach resulting in a recall, precision, and F-measure of 0.82, 0.96, and 0.88 respectively. This paper will go on to assess to the viability of applying the solution to differing environments, both in terms of performance and along with a qualitative analysis on the practical aspects of installing such a system within differing environments.

Hardware for Recognition of Human Activities: A Review of Smart Home and AAL Related Technologies

“…For the rest, it seems to be sufficient to use wearable technology alone to assess activity recognition for smart home and AAL, maybe to try simplicity in technological solutions. Commercial devices from big companies, such as Samsung Galaxy Gear Live [ 42 ], Microsoft Band 2 [ 43 ], and Intel Basis Peak [ 44 ], are mentioned in several studies, as well as other commercial alternatives like Empatica E3 [ 33 ], Fitbit [ 44 ], HiCling [ 34 ], Pebble [ 45 ], and Google Glass [ 33 , 46 ] (see Table 2 ).…”

Ambient assisted living for frail people through human activity recognition: state-of-the-art, challenges and future directions

“…Even combining multiple sensors into a single framework can provide valuable data for meaningful and complex predictions, thus achieving a more versatile, robust and trustworthy wearable system for HAR purposes. Moreover, commercial tools are widely used, such as Samsung Galaxy Gear Live ( Faye et al, 2017 ), Microsoft Band 2 ( Garcia-Ceja et al, 2018 ) and Intel Basis Peak ( Kang and Larkin, 2017 ), as well as other alternatives like Empatica E3 ( Clapés et al, 2018 ), Fitbit ( Kang and Larkin, 2017 ), and Google Glass ( Shewell et al, 2017 ; Clapés et al, 2018 ).…”