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

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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/hal-01557611
Contributor : Hal Ifip <>
Submitted on : Thursday, July 6, 2017 - 1:55:13 PM
Last modification on : Friday, December 1, 2017 - 1:16:27 AM
Long-term archiving on: Wednesday, January 24, 2018 - 1:38:02 AM

File

430537_1_En_10_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

S. Georgakopoulos, K. Kottari, K. Delibasis, V. 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⟩

Share

Metrics

Record views

135

Files downloads

103