Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images

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

Authors

Object detection plays a significant role in an intelligent system equipped with a fisheye camera. The fisheye image captures a wide field-of-view but deforms in the radial direction. The deformation changes the relative angle between the edge of objects and the image. Therefore, a horizontal bounding box cannot perform an accurate description of an object's location and dimension in advanced neural network training. In this paper, we build a rotation sensitive neural network targeting to realize one-stage regression on the fisheye image detection. The oriented bounding box is applied in the object's description and detection. To evaluate our proposed method, we develop a new labelled fisheye image dataset that contains two categories. The network model training takes around 3 hours and achieves 100% precious by the test set.

Original languageEnglish
Title of host publication2019 4th International Conference on Robotics and Automation Engineering (ICRAE 2019) : November 22-24, 2019, Singapore
Number of pages5
Place of PublicationPiscataway
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date11.2019
Pages125-129
Article number9043800
ISBN (print)978-1-7281-4741-3
ISBN (electronic)978-1-7281-4740-6, 978-1-7281-4739-0
DOIs
Publication statusPublished - 11.2019
Event4th International Conference on Robotics and Automation Engineering, ICRAE 2019 - Nanyang Technological University, Singapore, Singapore, Singapore
Duration: 22.11.201924.11.2019
Conference number: 4
https://www.ieee-ras.org/component/rseventspro/event/1695-icrae-2019-international-conference-on-robotics-and-automation-engineering

    Research areas

  • Fisheye image, Image distortion, Orientated Box, YOLO detector
  • Engineering