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

Recently viewed

Publications

  1. Using trait-based filtering as a predictive framework for conservation
  2. A two-step approach for the prediction of mood levels based on diary data
  3. Machine Learning and Knowledge Discovery in Databases
  4. XOperator - An extensible semantic agent for instant messaging networks
  5. PLM ‑supported automated process planning and partitioning for collaborative assembly processes based on a capability analysis
  6. Guided discovery learning with computer-based simulation games
  7. Enabling Road Condition Monitoring with an on-board Vehicle Sensor Setup
  8. Control of the inverse pendulum based on sliding mode and model predictive control
  9. Evolutionary cost-tolerance optimization for complex assembly mechanisms via simulation and surrogate modeling approaches
  10. Switching Dispatching Rules with Gaussian Processes
  11. On the Appropriate Methodologies for Data Science Projects
  12. Soil conditions modify species diversity effects on tree functional trait expression
  13. Robust Estimation of Linear Fixed Effects Panel Data Models with an Application to the Exporter Productivity Premium
  14. Soft Optimal Computing Methods to Identify Surface Roughness in Manufacturing Using a Monotonic Regressor
  15. Duration of Organizational Decision Processes in Organizations in View of Simulation Calculations
  16. The role of task complexity, modality and aptitude in narrative task performance
  17. Development and comparison of processing maps of Mg-3Sn-1Ca alloy from data obtained in tension versus compression
  18. Optimal dynamic scale and structure of a multi-pollution economy
  19. A Hybrid Actuator and its Control Using a Cascade Sliding Mode Technique
  20. Enacting migration through data practices
  21. Dynamic efficiency and path dependencies in venture capital markets
  22. Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration
  23. Crises at Work: Potentials for Change?
  24. Methane yield of biomass from extensive grassland is affected by compositional changes induced by order of arrival
  25. An Optimal and Stabilising PI Controller with an Anti-windup Scheme for a Purification Process of Potable Water
  26. Legitimizing Digital Transformation: From System Integration to Platformization
  27. Geometric series with randomly increasing exponents
  28. Hypertexts in context
  29. Serendipity as a Mechanism of Change and its Potential for Explaining Change Processes
  30. Injection of CO2 for the inhibition of scaling in ATES systems
  31. Training in Components of Problem-Solving Competence
  32. Nonlinear analyses of self-paced reading
  33. Perception of Space and Time in a Created Environment
  34. Usage pattern-based exposure screening as a simple tool for the regional priority-setting in environmental risk assessment of veterinary antibiotics
  35. Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence
  36. Managing technology as a virtual enterprise
  37. Review of transit data sources