Successive Future Image Generation of a Walking Pedestrian Using Generative Adversarial Networks

Bate He and Eisuke Kita ()
Additional contact information
Bate He: Nagoya University
Eisuke Kita: Nagoya University

The Review of Socionetwork Strategies, 2021, vol. 15, issue 2, 309-325

Abstract: Abstract This research focuses on the generation algorithm of successive future images of a walking pedestrian from successive past images. The proposal algorithm is based on Generative adversarial networks (GANs) whose generative network and discriminative network are defined by Convolutional neural networks (CNN). The algorithm takes successive images as input data and generates their future images as the output images. The algorithm is compared with the other algorithms such as Optical Flow and Long Short-Term Memory (LSTM) for different numbers of input and output images. The results show that the accuracy of the proposed algorithm is better than LSTM in all cases and that the proposed algorithm shows better accuracy than Optical Flow in the case of large numbers of input and output images.

Keywords: Pedestrian; Future image generation; Generative adversarial networks (GANs); Peak signal-to-noise ratio (PSNR) (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s12626-021-00085-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:trosos:v:15:y:2021:i:2:d:10.1007_s12626-021-00085-6

Ordering information: This journal article can be ordered from
https://www.springer ... ystems/journal/12626

DOI: 10.1007/s12626-021-00085-6

Access Statistics for this article

The Review of Socionetwork Strategies is currently edited by Katsutoshi Yada, Yasuharu Ukai and Marshall Van Alstyne

More articles in The Review of Socionetwork Strategies from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().