Parameterized Synthetic Image Data Set for Fisheye Lens

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Based on different projection geometry, a fisheye image can be presented as a parameterized non-rectilinear image. Deep neural networks(DNN) is one of the solutions for extracting the parameters for fisheye image feature expression. However, a number of images are required for training a reasonable prediction model for DNN. In this paper, we propose to extend the scale of the dataset using parameterized synthetic images which effectively boost the diversity of samples and avoid the limitation on the scale. To simulate different viewing angles and distances, we adopt controllable parameterized projection processes on transformation. The reliability of the proposed method is tested with the image captured by a fisheye camera. The synthetic fisheye image dataset is the first dataset that is developed by existing labeled perspective images. It is accessible via: http://www2.leuphana.de/misl/fisheye-data-set/.

Original languageEnglish
Title of host publicationProceedings - 2018 5th International Conference on Information Science and Control Engineering, ICISCE 2018
EditorsY Cheng, S. Li, Y. Dai
Number of pages5
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date02.07.2018
Pages370-374
Article number8612582
ISBN (electronic)978-153865500-9
DOIs
Publication statusPublished - 02.07.2018
Event5th International Conference on Information Science and Control Engineering - ICISCE 2018 - Zhengzhou, Henan, China
Duration: 20.07.201822.07.2018
Conference number: 5
http://www.icisce.org/ICISCE2018/

    Research areas

  • Fisheye lens, Image processing, Neural network, Synthetic data set
  • Engineering