Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Object Detection of AGV in Manufacturing Plants using Deep Learning

딥러닝 기반 제조 공장 내 AGV 객체 인식에 대한 연구

  • Received : 2020.10.04
  • Accepted : 2020.11.02
  • Published : 2021.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this research, the accuracy of YOLO v3 algorithm in object detection during AGV (Automated Guided Vehicle) operation was investigated. First of all, AGV with 2D LiDAR and stereo camera was prepared. AGV was driven along the route scanned with SLAM (Simultaneous Localization and Mapping) using 2D LiDAR while front objects were detected through stereo camera. In order to evaluate the accuracy of YOLO v3 algorithm, recall, AP (Average Precision), and mAP (mean Average Precision) of the algorithm were measured with a degree of machine learning. Experimental results show that mAP, precision, and recall are improved by 10%, 6.8%, and 16.4%, respectively, when YOLO v3 is fitted with 4000 training dataset and 500 testing dataset which were collected through online search and is trained additionally with 1200 dataset collected from the stereo camera on AGV.

본 논문에서는 제조 공장 내 AGV (Automated Guided Vehicle) 주행 중 객체 인식을 위한 YOLO v3 알고리즘의 정확도에 대해 살펴보았다. 실험을 위해 2D LiDAR 및 스테레오 카메라가 장착된 AGV를 준비하였다. AGV 주행 중 2D LiDAR를 활용한 SLAM 기법으로 지도 정보를 획득하였고 스테레오 카메라를 활용한 객체 인식이 이루어졌다. 그리고 YOLO v3 알고리즘 기반의 학습 정도에 따른 재현율, AP, mAP 등을 측정하였다. 실험 결과, 4000장의 train data 와 500장의 test data 로 훈련된 YOLO v3 알고리즘에 AGV에 장착된 스테레오 카메라의 시점과 높이에서 획득한 1200장의 이미지를 추가로 학습할 경우 mAP가 약 10% 향상되었다. 정밀도(precision) 와 재현율 역시 각각 6.8%와 16.4% 향상되었다.

Keywords

References

  1. S. Kaliappan, J. Lokesh, P. Mahaneesh, and M. Siva, "Mechanical Design and Analysis of AGV for Cost Reduction of Material Handling in Automobile Industries," International Research Journal of Automotive Technology, vol. 1, no. 1, pp. 1-7, Jan. 2018.
  2. E. S. Maarif and T. Moyo, "Driving control module for low cost industrial automated guided vehicle," IOP Conference Series: Materials Science and Engineering, vol. 535, no. 1, pp. 1-13, Jun. 2019.
  3. S. Simoncic and P. Podrzaj, "Vision‐based control of a line tracing mobile robot," Computer Applications in Engineering Education, vol. 22, no. 3, pp. 474-480, Aug. 2011. https://doi.org/10.1002/cae.20573
  4. J. Li, W. Chen, B. Li, and T. Wang, "Road recognition and tracking control of an vision guided AGV," Transactions of the Chinese Society for Agricultural Machinery, Feb. 2008.
  5. G. Zhou, J. Yuan, I. Yen, and F. Bastani, "Robust real-time UAV based power line detection and tracking," in Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, pp. 744-748, 2016.
  6. M. Lv, T. Gao, and N. Zhang, "Research of AGV scheduling and path planning of automatic transport system," International Journal of Control and Automation, vol. 9, no. 4, pp. 1-10, Apr. 2016. https://doi.org/10.14257/ijca.2016.9.8.01
  7. C. Liu, J. Tan, H. Zhao, Y. Li, and X. Bai, "Path planning and intelligent scheduling of multi-AGV systems in workshop," in Proceedings of the 2017 36th Chinese Control Conference (CCC), Dalian, pp. 2735-2739, 2017.
  8. Y. Yang, M. Zhong, Y. Dessouky, and O. Postolache, "An integrated scheduling method for AGV routing in automated container terminals," Computers & Industrial Engineering, vol. 126, pp. 482-493, Dec. 2018. https://doi.org/10.1016/j.cie.2018.10.007
  9. M. V. Gomes, L. A. Bassora, O. Morandin, and K. C. T. Vivaldini, "PID control applied on a line-follower AGV using a RGB camera," in Proceedings of 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, pp. 194-198, 2016.
  10. S. Buck, R. Hanten, K. Bohlmann, and A. Zell, "Generic 3d obstacle detection for AGVs using time-of-flight cameras," in Proceedings of 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, pp. 4119-4124, 2016.
  11. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, pp. 580-587, 2014.
  12. R. Girshick, "Fast R-CNN," in Proceedings of 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, pp. 1440-1448, 2015.
  13. S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," in Proceedings of Advances in Neural Information Processing Systems 28 (NIPS 2015), pp. 1-9, 2015.
  14. K. He, G. Gkioxari, P. Dollar, and R. Girshick, "Mask R-CNN," in Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV), Venice, pp. 2980-2988, 2017.
  15. J. R. R. Uijlings, K. E. A. van de Sande, T. Gevers, and A. W. M. Smeulders, "Selective search for object recognition," International journal of computer vision, vol. 104, no. 2, pp. 154-171, Sep. 2013. https://doi.org/10.1007/s11263-013-0620-5
  16. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in Proceedings of 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp. 779-788, 2016.
  17. J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," in Proceedings of 2017 IEEE conference on computer vision and pattern recognition (CVPR), Hawaii, pp. 7263-7271, 2017.