IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Distortion Removal and False Positive Filtering for Camera-based Object Position Estimation

카메라 기반 객체의 위치인식을 위한 왜곡제거 및 오검출 필터링 기법

  • Received : 2023.10.20
  • Accepted : 2023.11.15
  • Published : 2024.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Robotic arms have been widely utilized in various labor-intensive industries such as manufacturing, agriculture, and food services, contributing to increasing productivity. In the development of industrial robotic arms, camera sensors have many advantages due to their cost-effectiveness and small sizes. However, estimating object positions is a challenging problem, and it critically affects to the robustness of object manipulation functions. This paper proposes a method for estimating the 3D positions of objects, and it is applied to a pick-and-place task. A deep learning model is utilized to detect 2D bounding boxes in the image plane, and the pinhole camera model is employed to compute the object positions. To improve the robustness of measuring the 3D positions of objects, we analyze the effect of lens distortion and introduce a false positive filtering process. Experiments were conducted on a real-world scenario for moving medicine bottles by using a camera-based manipulator. Experimental results demonstrated that the distortion removal and false positive filtering are effective to improve the position estimation precision and the manipulation success rate.

Keywords

Acknowledgement

This work was supported by Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean government [23ZD1130, Regional Industry ICT Convergence Technology Advancement and Support Project in Daegu-GyeongBuk (Robot)]. 본 과제 (결과물)는 교육부와 한국연구재단의 재원으로 지원을 받아 수행된 사회맞춤형 산학협력 선도대학 (LINC+) 육성사업의 연구결과입니다. 이 연구는 2023년도 산업통상자원부 및 산업기술평가관리원 (KEIT) 연구비 지원에 의한 연구임 (20023305).

References

  1. L. Friedrich, H. Gerd, "Calibration and Synchronization of a Robot-Mounted Camera for Fast Sensor-Based Robot Motion," IEEE International Conference On Robotics and Automation, Vol. 4, pp. 3900-3905, 2005.
  2. S. J. Park, S. B. Park, J. H. Kim, "A Study on the Motion Object Detection Method for Autonomous Driving," Journal of The Korean Society of Industry Convergence, Vol. 24, No. 5, pp. 547-553, 2021.
  3. S. H. Hwang, J. H. Choi, H. S. Park, J. H. Kim, "A Study on the Implementation of Camera Sensor for Object Detection Based on Deep Learning and Distance Estimation," Transactions of the Korean Society of Automotive Engineers, Vol. 30, No. 8, pp. 659-665, 2022. https://doi.org/10.7467/KSAE.2022.30.8.659
  4. S. H. Park, K. H. Lee, J. S. Park, Y. S. Shin, "Deep Learning-Based Defect Detection for Sustainable Smart Manufacturing," Sustainability, Vol. 14, No. 5, pp. 2697, 2022.
  5. N. Liu, L. Li, B. Hao, L. Yang, T. Hu, T. Xue, S. Wang, "Modeling and Simulation of Robot Inverse Dynamics Using LSTM-Based Deep Learning Algorithm for Smart Cities and Factories," IEEE ACCESS, Vol. 7, pp. 173989-173998, 2019. https://doi.org/10.1109/ACCESS.2019.2957019
  6. R. Girshick, J. Donahue, T. Darrell, J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, 2013.
  7. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, A. C. Berg, "SSD: Single Shot MultiBox Detector," ECCV, pp. 21-37, 2016.
  8. J. Redmon, S. Divvala, R. Girshick, A Farhadi, "You Only Look Once: Unified, Real-time Object Detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016.
  9. Y. B. Kim, H. Choi, J. H. Cho. "High-performance of Deep Learning Colorization With Wavelet Fusion," IEMEK J. Embed. Sys. Appl.,, Vol. 13, No. 6, pp. 313-319, 2018.
  10. J. S. Jung, H. J. Park, J. H. Hwang, G. T. Park, N. J. Kwak. "객체 사이의 관계를 고려한 객체검출 알고리즘," 30th Workshop on Image Processing and Image Understanding, Vol. 30, 2018.
  11. L. He, G. Wang, Z. Hu, "Learning Depth from Single Images with Deep Neural Network Embedding Focal Length," IEEE Transactions on Image Processing, Vol. 27, No. 9, pp. 4676-4689, 2018. https://doi.org/10.1109/TIP.2018.2832296
  12. M. Diaz-Cabrera, P. Cerri, P. Medici, "Robust Real-time Traffic Light Detection and Distance Estimation Using a Single Camera," Expert Systems with Applications, Vol. 42, No. 8, pp. 3911-3923, 2015. https://doi.org/10.1016/j.eswa.2014.12.037