Convolutional Neural Networks for Pose Recognition in Binary Omni-directional Images - Artificial Intelligence Applications and Innovations Access content directly
Conference Papers Year : 2016

Convolutional Neural Networks for Pose Recognition in Binary Omni-directional Images

S. V. Georgakopoulos
  • Function : Author
  • PersonId : 991058
K. Kottari
  • Function : Author
  • PersonId : 991051
K. Delibasis
  • Function : Author
  • PersonId : 991052
V. P. Plagianakos
  • Function : Author
  • PersonId : 991060
I. Maglogiannis
  • Function : Author
  • PersonId : 991053

Abstract

In this work, we present a methodology for pose classification of silhouettes using convolutional neural networks. The training set consists exclusively from the synthetic images that are generated from three-dimensional (3D) human models, using the calibration of an omni-directional camera (fish-eye). Thus, we are able to generate a large volume of training set that is usually required for Convolutional Neural Networks (CNNs). Testing is performed using synthetically generated silhouettes, as well as real silhouettes. This work is in the same realm with previous work utilizing Zernike image descriptors designed specifically for a calibrated fish-eye camera. Results show that the proposed method improves pose classification accuracy for synthetic images, but it is outperformed by our previously proposed Zernike descriptors in real silhouettes. The computational complexity of the proposed methodology is also examined and the corresponding results are provided.
Fichier principal
Vignette du fichier
430537_1_En_10_Chapter.pdf (1.93 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01557611 , version 1 (06-07-2017)

Licence

Attribution

Identifiers

Cite

S. V. Georgakopoulos, K. Kottari, K. Delibasis, V. P. Plagianakos, I. Maglogiannis. Convolutional Neural Networks for Pose Recognition in Binary Omni-directional Images. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. pp.106-116, ⟨10.1007/978-3-319-44944-9_10⟩. ⟨hal-01557611⟩
98 View
97 Download

Altmetric

Share

Gmail Facebook X LinkedIn More