Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 595796

Accelerometer Based Gesture Recognition System Using Distance Metric Learning for Nearest Neighbour Classification


Marasović, Tea; Papić, Vladan
Accelerometer Based Gesture Recognition System Using Distance Metric Learning for Nearest Neighbour Classification // Proc. 2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2012) / Santamaría, Ignacio ; Arenas-García, Jerónimo ; Camps-Valls, Gustavo ; Erdogmus, Deniz ; Pérez-Cruz, Fernando ; Larsen, Jan (ur.).
Santander, Spain, 2012. (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 595796 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Accelerometer Based Gesture Recognition System Using Distance Metric Learning for Nearest Neighbour Classification

Autori
Marasović, Tea ; Papić, Vladan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proc. 2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2012) / Santamaría, Ignacio ; Arenas-García, Jerónimo ; Camps-Valls, Gustavo ; Erdogmus, Deniz ; Pérez-Cruz, Fernando ; Larsen, Jan - , 2012

ISBN
978-1-4673-1025-3

Skup
2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2012)

Mjesto i datum
Santander, Spain, 23-26.09.2012

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
accelerometer- based gesture recognition; distance metric learning; NN classification; convex optimization
(accelerometer-based gesture recognition; distance metric learning; NN classification; convex optimization)

Sažetak
The need to improve communication between humans and computers has been motivation for defining new communication models, and accordingly, new ways of interacting with machines. In many applications today, user interaction is moving away from traditional keyboards and mouses and is becoming much more physical, pervasive and intuitive. This paper examines hand gestures as an alternative or supplementary input modality for mobile devices. A new gesture recognition system based on the use of acceleration sensor, that is nowadays being featured in a growing number of consumer electronic devices, is presented. Accelerometer sensor readings can be used for detection of hand movements and their classification into previously trained gestures. The proposed system utilizes Mahalanobis distance metric learning to improve the accuracy of nearest neighbour classification. In the approach we adopted, the objective function for metric learning is convex and, therefore, the required optimization can be cast as an instance of semidefinite programming. The experiments, carried out to evaluate system performance, demonstrate its efficacy.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo



POVEZANOST RADA


Projekti:
177-0232006-1662 - Računalni vid u identifikaciji kinematike sportskih aktivnosti
023-0232006-1655 - Biomehanika ljudskih pokreta, upravljanje i rehabilitacija (Zanchi, Vlasta, MZOS ) ( POIROT)
023-0232006-1662 - Računalni vid u identifikaciji kinematike sportskih aktivnosti (Papić, Vladan, MZOS ) ( POIROT)

Ustanove:
Fakultet elektrotehnike, strojarstva i brodogradnje, Split,
Prirodoslovno-matematički fakultet, Split

Profili:

Avatar Url Vladan Papić (autor)

Avatar Url Tea Marasović (autor)


Citiraj ovu publikaciju

Marasović, Tea; Papić, Vladan
Accelerometer Based Gesture Recognition System Using Distance Metric Learning for Nearest Neighbour Classification // Proc. 2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2012) / Santamaría, Ignacio ; Arenas-García, Jerónimo ; Camps-Valls, Gustavo ; Erdogmus, Deniz ; Pérez-Cruz, Fernando ; Larsen, Jan (ur.).
Santander, Spain, 2012. (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Marasović, T. & Papić, V. (2012) Accelerometer Based Gesture Recognition System Using Distance Metric Learning for Nearest Neighbour Classification. U: Santamaría, I., Arenas-García, J., Camps-Valls, G., Erdogmus, D., Pérez-Cruz, F. & Larsen, J. (ur.)Proc. 2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2012).
@article{article, year = {2012}, keywords = {accelerometer- based gesture recognition, distance metric learning, NN classification, convex optimization}, isbn = {978-1-4673-1025-3}, title = {Accelerometer Based Gesture Recognition System Using Distance Metric Learning for Nearest Neighbour Classification}, keyword = {accelerometer- based gesture recognition, distance metric learning, NN classification, convex optimization}, publisherplace = {Santander, Spain} }
@article{article, year = {2012}, keywords = {accelerometer-based gesture recognition, distance metric learning, NN classification, convex optimization}, isbn = {978-1-4673-1025-3}, title = {Accelerometer Based Gesture Recognition System Using Distance Metric Learning for Nearest Neighbour Classification}, keyword = {accelerometer-based gesture recognition, distance metric learning, NN classification, convex optimization}, publisherplace = {Santander, Spain} }




Contrast
Increase Font
Decrease Font
Dyslexic Font