Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지
DOI QR코드

DOI QR Code

An Instance Segmentation using Object Center Masks

오브젝트 중심점-마스크를 사용한 instance segmentation

  • 이종혁 (전북대학교 전자.정보공학부) ;
  • 김형석 (전북대학교 지능형로봇연구소)
  • Received : 2020.01.28
  • Accepted : 2020.06.04
  • Published : 2020.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a network model composed of Multi path Encoder-Decoder branches that can recognize each instance from the image. The network has two branches, Dot branch and Segmentation branch for finding the center point of each instance and for recognizing area of the instance, respectively. In the experiment, the CVPPP dataset was studied to distinguish leaves from each other, and the center point detection branch(Dot branch) found the center points of each leaf, and the object segmentation branch(Segmentation branch) finally predicted the pixel area of each leaf corresponding to each center point. In the existing segmentation methods, there were problems of finding various sizes and positions of anchor boxes (N > 1k) for checking objects. Also, there were difficulties of estimating the number of undefined instances per image. In the proposed network, an effective method finding instances based on their center points is proposed.

본 논문에서는 새롭게 제안하는 Multi-Path Encoder-Decoder 의 구조를 바탕으로 두개의 가지로 구성된 심층신경망을 통해서 영상 이미지에서 물체를 하나의 객체 단위로 분할 검출하는 방법을 제안하였다. 각 가지는 중심점 검출 가지(Dot branch), 객체 분할 가지(Segmentation branch)라 하고 중심점 검출 가지는 이미지로부터 각 객체의 중심점을 찾는 역할을 수행하고, 객체 분할 가지는 각 객체의 영역을 이미지로부터 분할하는 역할을 수행한다. 실험에서는 CVPPP 식물 이미지의 나뭇잎을 각각 구분하도록 학습 하였으며 중심점 검출 가지는 각 나뭇잎의 중심점들을 찾아내고, 객체 분할 가지는 원본 이미지와 찾아낸 중심점 이미지를 통하여 각 중심점에 해당하는 나뭇잎의 픽셀 분할 영역을 최종적으로 예측하게 된다. 기존의 객체 분할에서는 다양한 크기, 위치의 앵커박스를 만들어서 많은 영역(N > 1k)의 물체를 확인해야하는 연산량 문제점 혹은 이미지에서 고정되지 않는 총 객체의 개수를 예측하기 어려웠던 문제가 있었다. 제안한 심층신경망에서는 중심점을 기반으로 객체를 찾아내는 효과적인 방법을 제안하였다.

Keywords

References

  1. CVPPP 2017 LSC TRAINING DATASET, https://www.plant-phenotyping.org/CVPPP2019 (accessed Dec., 2019).
  2. Hei Law, Jia Deng, "CornerNet: Detecting Objects as Paired Keypoints," ECCV, 2018.
  3. T. Lin, P. Goyal, R. Girshick, K. He and P. Dollar, "Focal Loss for Dense Object Detection," 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999-3007, Venice, 2017.
  4. K. He, G. Gkioxari, P. Dollr, and R. Girshick. "Mask r-cnn," 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980-2988, Oct 2017.
  5. Joseph Redmon and Ali Farhadi. "Yolov3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.
  6. X. Zhou, J. Zhuo, and P. Krahenb uhl. "Bottom-up object detection by grouping extreme and center points," CoRR, abs/1901.08043, 2019.
  7. Xingyi Zhou, Dequan Wang, and Philipp Krahenbuhl. "Objects as points," arXiv preprint arXiv:1904.07850, 2019.
  8. Long, J., Shelhamer, E., and Darrell, T. "Fully convolutional networks for semantic segmentation," CoRR, abs/1411.4038, 2014.
  9. Badrinarayanan. V, Kendall. A, and Cipolla. R. "SegNet: A deep convolutional encoder-decoder architecture for image segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 39, pp. 2481-2495, 2017. https://doi.org/10.1109/TPAMI.2016.2644615
  10. O. Ronneberger, P. Fischer and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234-241, 2015.
  11. B. D. Brabandere, D. Neven and L. V. Gool, "Semantic Instance Segmentation with a Discriminative Loss Function," CoRR, abs/1708.02551, 2017.
  12. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. "Faster R-CNN: Towards real-time object detection with region proposal networks," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2017.
  13. Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll'ar, P, "Focal loss for dense object detection," arXiv preprint arXiv:1708.02002, 2017.
  14. D. P. Kingma and J. Ba, "Adam: A Method for Stochastic Optimization," CoRR, abs/1412.6980, 2014.
  15. Bernardino Romera-Paredes and Philip Hilaire Sean Torr, "Recurrent instance segmentation," European Conference on Computer Vision (ECCV), pp. 312-329, 2016.
  16. Jean-Michel Pape and Christian Klukas, "3-d histogram-based segmentation and leaf detection for rosette plants," European Conference on Computer Vision (ECCV), pp. 61-74, 2014.
  17. Bert De Brabandere, Davy Neven, and Luc Van Gool, "Semantic instance segmentation with a discriminative loss function," arXiv preprint arXiv:1708.02551, 2017.
  18. Mengye Ren and Richard S Zemel, "End-to-end instance segmentation with recurrent attention," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21-26, Honolulu, HI, USA, 2017.
  19. Daniel Ward, Peyman Moghadam, and Nicolas Hudson. "Deep leaf segmentation using synthetic data," CVPPP 2018, Newcastle, UK, Sept. 2018.
  20. 김서정, 이재수, 김형석, "딥러닝을 이용한 양파밭의 잡초 검출 연구," 스마트미디어저널, 제7권, 제3호, 16-21쪽, 2018년 9월 https://doi.org/10.30693/SMJ.2018.7.3.16
  21. 김서정, 김형석, "Multi-Tasking U-net 기반 파프리카 병해충 진단," 스마트미디어저널, 제9권 제1호, 16-22쪽, 2020년 03월 https://doi.org/10.30693/SMJ.2020.9.1.16
  22. 이한솔, 김영관, 홍지만, "사물인식을 위한 딥러닝 모델 선정 플랫폼," 스마트미디어저널, 제8권, 제2호, 66-73쪽, 2019년 06월 https://doi.org/10.30693/smj.2019.8.2.66