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

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images. / Chen, Zhen; Georgiadis, Anthimos.
2019 4th International Conference on Robotics and Automation Engineering (ICRAE 2019): November 22-24, 2019, Singapore . Piscataway: IEEE - Institute of Electrical and Electronics Engineers Inc., 2019. S. 125-129 9043800 (International Conference on Robotics and Automation Engineering, ICRAE ; Band 4).

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Chen, Z & Georgiadis, A 2019, Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images. in 2019 4th International Conference on Robotics and Automation Engineering (ICRAE 2019): November 22-24, 2019, Singapore ., 9043800, International Conference on Robotics and Automation Engineering, ICRAE , Bd. 4, IEEE - Institute of Electrical and Electronics Engineers Inc., Piscataway, S. 125-129, 4th International Conference on Robotics and Automation Engineering, ICRAE 2019, Singapore, Singapur, 22.11.19. https://doi.org/10.1109/ICRAE48301.2019.9043800

APA

Chen, Z., & Georgiadis, A. (2019). Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images. In 2019 4th International Conference on Robotics and Automation Engineering (ICRAE 2019): November 22-24, 2019, Singapore (S. 125-129). Artikel 9043800 (International Conference on Robotics and Automation Engineering, ICRAE ; Band 4). IEEE - Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRAE48301.2019.9043800

Vancouver

Chen Z, Georgiadis A. Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images. in 2019 4th International Conference on Robotics and Automation Engineering (ICRAE 2019): November 22-24, 2019, Singapore . Piscataway: IEEE - Institute of Electrical and Electronics Engineers Inc. 2019. S. 125-129. 9043800. (International Conference on Robotics and Automation Engineering, ICRAE ). doi: 10.1109/ICRAE48301.2019.9043800

Bibtex

@inbook{2b05183077a3424685998d0eab3b31a6,
title = "Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images",
abstract = "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.",
keywords = "Fisheye image, Image distortion, Orientated Box, YOLO detector, Engineering",
author = "Zhen Chen and Anthimos Georgiadis",
year = "2019",
month = nov,
doi = "10.1109/ICRAE48301.2019.9043800",
language = "English",
isbn = "978-1-7281-4741-3",
series = "International Conference on Robotics and Automation Engineering, ICRAE ",
publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",
pages = "125--129",
booktitle = "2019 4th International Conference on Robotics and Automation Engineering (ICRAE 2019)",
address = "United States",
note = "4th International Conference on Robotics and Automation Engineering, ICRAE 2019, ICRAE2019 ; Conference date: 22-11-2019 Through 24-11-2019",
url = "https://www.ieee-ras.org/component/rseventspro/event/1695-icrae-2019-international-conference-on-robotics-and-automation-engineering",

}

RIS

TY - CHAP

T1 - Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images

AU - Chen, Zhen

AU - Georgiadis, Anthimos

N1 - Conference code: 4

PY - 2019/11

Y1 - 2019/11

N2 - 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.

AB - 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.

KW - Fisheye image

KW - Image distortion

KW - Orientated Box

KW - YOLO detector

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=85083237395&partnerID=8YFLogxK

U2 - 10.1109/ICRAE48301.2019.9043800

DO - 10.1109/ICRAE48301.2019.9043800

M3 - Article in conference proceedings

AN - SCOPUS:85083237395

SN - 978-1-7281-4741-3

T3 - International Conference on Robotics and Automation Engineering, ICRAE

SP - 125

EP - 129

BT - 2019 4th International Conference on Robotics and Automation Engineering (ICRAE 2019)

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway

T2 - 4th International Conference on Robotics and Automation Engineering, ICRAE 2019

Y2 - 22 November 2019 through 24 November 2019

ER -

DOI

Zuletzt angesehen

Publikationen

  1. Explicit and Implicit Framing Effects on Product Attitudes When Using Country-of- Origin Cues
  2. Design optimization of spiral coils for textile applications by genetic algorithm
  3. Simple saturated PID control for fast transient of motion systems
  4. The signal location task as a method quantifying the distribution of attention
  5. Methods for Ensuring the Accuracy of Radiometric and Optoelectronic Navigation Systems of Flying Robots in a Developed Infrastructure
  6. Performance of an IMU-Based Sensor Concept for Solving the Direct Kinematics Problem of the Stewart-Gough Platform
  7. Critical look at dynamic sketches when learning mathematics
  8. Linked Accomplishment Of Order Management And Production Planning And Control. An Integrated Model-based Approach
  9. Secondary task as a measure of cognitive load
  10. Digital twin support for laser-based assembly assistance
  11. Knowledge Generation and Sustainable Development
  12. Influence of data clouds fusion from 3D real-time vision system on robotic group dead reckoning in unknown terrain
  13. Self-Regulated Learning with Expository Texts as a Competence
  14. Competence models for assessing individual learning outcomes and evaluating educational processes - a priority program of the German research foundation (DFG)
  15. Towards Computer Simulations of Virtue Ethics
  16. Introduction
  17. Toward a gecko-inspired, climbing soft robot
  18. How much can we learn about voluntary climate action from behavior in public goods games?
  19. Energy-aware system design for autonomous wireless sensor nodes
  20. Foundation of digital badges and micro-credentials
  21. Structure and Organization of Product Development Projects
  22. Development of environmental fate models for engineered nanoparticles--a case study of TiO2 nanoparticles in the Rhine River
  23. Manufacturing, control, and performance evaluation of a Gecko-inspired soft robot
  24. Shared mobility business models
  25. Embodiment of Science in Science Slams.
  26. EU decision-making in asylum policy
  27. From 'one right way' to 'one ruinous way'? Discursive shifts in 'There is no alternative'
  28. Gas-Kampf oder Gas-Krampf
  29. Next generation wireless energy aware sensors for internet of things
  30. Integrated curvature sensing of soft bending actuators using inertial measurement units
  31. Connected Text Reading and Differences in Text Reading Fluency in Adult Readers
  32. Patterns of International Organization
  33. Powers of Abstraction
  34. Influence of clouds on the photochemical degradation in aqueous phase - II
  35. Forecasting Government Bond Yields with Neural Networks Considering Cointegration
  36. No need for new natural gas pipelines and LNG terminalsin Europe
  37. Implementing inquiry-based science education to foster emotional engagement of special-needs students
  38. Learning with summaries
  39. Diffusion of tax policies in the European Union
  40. Income inequality, status decline and support for the radical right
  41. Klimapaket
  42. Temporary organizing and acceleration
  43. IGH
  44. Das fossile Imperium schlägt zurück
  45. Discovering cooperation
  46. Ice clamping system in manufacturing systems as a cyber-physical system towards Industry 4.0
  47. Using the learner-generated drawing strategy
  48. Utilising learning analytics for study success
  49. “Happy, happy, happy …”
  50. Gewalt oder Macht