HomeMobility HazardsDetected via Object Recognition in Augmented Reality

HomeMobility HazardsDetected via Object Recognition in Augmented Reality

Eloy, Sara; Dias, Luís; Ourique, Lázaro; Dias, Miguel Sales

:

We present an Environmental Analysis and Safety Advisor system capable ofidentify the environmental barriers and hazards found in the homes of elderlypeople. This augmented reality tool runs on a portable computing device and canbe used by informal and formal caregivers without specific knowledge ofAccessible Design, to evaluate the safeness of an elderly home environment,ensuring that potential fall hazards are detected and corrected. The systemrecognizes specific indoor elements of the house (e.g. arm-chair, bed, chair), andthen computes and analyses their mutual distances in the environment so that awarning of hazard is emitted in case of need (e.g. loose cable, not enough spaceto pass a wheelchair). In this context, we implemented object recognition at thecategory level of miniature versions of real sized furniture and the determinationof the distance between neighboring objects, signaling if it is below a certainthreshold value. Environmental Analysis tool can then recognize furniture andmeasure the distance between two furniture elements enabling the system to popup an alert sign if the space left does not guarantee good accessibility.

We present an Environmental Analysis and Safety Advisor system capable ofidentify the environmental barriers and hazards found in the homes of elderlypeople. This augmented reality tool runs on a portable computing device and canbe used by informal and formal caregivers without specific knowledge ofAccessible Design, to evaluate the safeness of an elderly home environment,ensuring that potential fall hazards are detected and corrected. The systemrecognizes specific indoor elements of the house (e.g. arm-chair, bed, chair), andthen computes and analyses their mutual distances in the environment so that awarning of hazard is emitted in case of need (e.g. loose cable, not enough spaceto pass a wheelchair). In this context, we implemented object recognition at thecategory level of miniature versions of real sized furniture and the determinationof the distance between neighboring objects, signaling if it is below a certainthreshold value. Environmental Analysis tool can then recognize furniture andmeasure the distance between two furniture elements enabling the system to popup an alert sign if the space left does not guarantee good accessibility.

Palavras-chave:

DOI: 10.5151/proceedings-ecaadesigradi2019_016

Referências bibliográficas

• [1]

Como citar:

Eloy, Sara; Dias, Luís; Ourique, Lázaro; Dias, Miguel Sales; "HomeMobility HazardsDetected via Object Recognition in Augmented Reality", p-415-422. In: Proceedings of 37 eCAADe and XXIII SIGraDi Joint Conference, “Architecture in the Age of the 4Th Industrial Revolution”, Porto 2019, Sousa, José Pedro; Henriques, Gonçalo Castro; Xavier, João Pedro (eds.). São Paulo: Blucher, 2019.
ISSN 23186968, DOI 10.5151/proceedings-ecaadesigradi2019_016