|
Descripción
|
|
|---|---|
| In this paper, a novel multi-modal method for person identification in indoor environments is presented. This ap- proach relies on matching the skeletons detected by a Kinect v2 device with wearable devices equipped with inertial sen- sors. Movement features such as yaw and pitch changes are employed to associate a particular Kinect skeleton to a person using the wearable. The entire process of sensor cal- ibration, feature extraction, synchronization and matching is detailed in this work. Six detection scenarios were de- fined to assess the proposed method. Experimental results have shown a high accuracy in the association process. | |
|
Internacional
|
Si |
|
Nombre congreso
|
2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) |
|
Tipo de participación
|
960 |
|
Lugar del congreso
|
Lecce (Italia) |
|
Revisores
|
Si |
|
ISBN o ISSN
|
978-1-5386-2939-0 |
|
DOI
|
10.1109/AVSS.2017.8078529 |
|
Fecha inicio congreso
|
29/08/2017 |
|
Fecha fin congreso
|
01/09/2017 |
|
Desde la página
|
416 |
|
Hasta la página
|
421 |
|
Título de las actas
|
2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) |