Real-time human pose estimation with convolutional neural networks

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu

Tutkijat

Organisaatiot

  • University of Oulu
  • Tampere University of Technology

Kuvaus

In this paper, we present a method for real-time multi-person human pose estimation from video by utilizing convolutional neural networks. Our method is aimed for use case specific applications, where good accuracy is essential and variation of the background and poses is limited. This enables us to use a generic network architecture, which is both accurate and fast. We divide the problem into two phases: (1) pre-training and (2) finetuning. In pre-training, the network is learned with highly diverse input data from publicly available datasets, while in finetuning we train with application specific data, which we record with Kinect. Our method differs from most of the state-of-the-art methods in that we consider the whole system, including person detector, pose estimator and an automatic way to record application specific training material for finetuning. Our method is considerably faster than many of the state-of-the-art methods. Our method can be thought of as a replacement for Kinect in restricted environments. It can be used for tasks, such as gesture control, games, person tracking, action recognition and action tracking. We achieved accuracy of 96.8% (PCK@0.2) with application specific data.

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoVISAPP
AlaotsikkoProceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
ToimittajatJose Braz, Francisco Imai, Alain Tremeau
TilaJulkaistu - 1 tammikuuta 2018
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Funchal, Portugali
Kesto: 27 tammikuuta 201829 tammikuuta 2018
Konferenssinumero: 13
http://www.visapp.visigrapp.org/?y=2018

Conference

ConferenceInternational Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
LyhennettäVISIGRAPP
MaaPortugali
KaupunkiFunchal
Ajanjakso27/01/201829/01/2018
www-osoite

ID: 30110933