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

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

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.

OriginalspracheEnglisch
Titel2019 4th International Conference on Robotics and Automation Engineering (ICRAE 2019) : November 22-24, 2019, Singapore
Anzahl der Seiten5
ErscheinungsortPiscataway
VerlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Erscheinungsdatum11.2019
Seiten125-129
Aufsatznummer9043800
ISBN (Print)978-1-7281-4741-3
ISBN (elektronisch)978-1-7281-4740-6, 978-1-7281-4739-0
DOIs
PublikationsstatusErschienen - 11.2019
Veranstaltung4th International Conference on Robotics and Automation Engineering, ICRAE 2019 - Nanyang Technological University, Singapore, Singapore, Singapur
Dauer: 22.11.201924.11.2019
Konferenznummer: 4
https://www.ieee-ras.org/component/rseventspro/event/1695-icrae-2019-international-conference-on-robotics-and-automation-engineering

DOI

Zuletzt angesehen

Publikationen

  1. Design and Control of an Inductive Power Transmission System with AC-AC Converter for a Constant Output Current
  2. Changes of Perception
  3. Explicit and Implicit Framing Effects on Product Attitudes When Using Country-of- Origin Cues
  4. Species composition and forest structure explain the temperature sensitivity patterns of productivity in temperate forests
  5. Design optimization of spiral coils for textile applications by genetic algorithm
  6. Errors, error taxonomies, error prevention, and error management
  7. Playing in the Spaces: Anarchism in the Classroom
  8. Exploring priority effects in a central European grassland field experiment in order to inform restoration
  9. Development and comparison of processing maps of Mg-3Sn-1Ca alloy from data obtained in tension versus compression
  10. Direct parameter specification of an attention shift: Evidence from perceptual latency priming
  11. Performance of an IMU-Based Sensor Concept for Solving the Direct Kinematics Problem of the Stewart-Gough Platform
  12. Learning to change universities from within
  13. Local lens for SDG implementation: lessons from bottom-up approaches in Africa
  14. Linked Accomplishment Of Order Management And Production Planning And Control. An Integrated Model-based Approach
  15. Errors in Organizations
  16. Secondary task as a measure of cognitive load
  17. Scripting a distance-learning university course
  18. Self-Regulated Learning with Expository Texts as a Competence
  19. Development of environmental fate models for engineered nanoparticles--a case study of TiO2 nanoparticles in the Rhine River
  20. How much can we learn about voluntary climate action from behavior in public goods games?
  21. Change and Continuity in Western Welfare Practices
  22. Introduction
  23. University mathematics students’ use of resources: strategies, purposes, and consequences
  24. Gewalt
  25. Embodiment of Science in Science Slams.
  26. Manufacturing, control, and performance evaluation of a Gecko-inspired soft robot