Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Detection and Resolving of Occlusion Area by Street Tree Object using ResNet Algorithm

ResNet 알고리즘을 이용한 가로수 객체의 폐색영역 검출 및 해결

  • Park, Hong-Gi (Department of Civil and Environmental Engineering, Gachon University) ;
  • Bae, Kyoung-Ho (Research Institute, Shinhan Aerial Survey CO.,LTD)
  • 박홍기 (가천대학교 토목환경공학과) ;
  • 배경호 ((주)신한항업 연구소)
  • Received : 2020.09.04
  • Accepted : 2020.10.05
  • Published : 2020.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

The technologies of 3D spatial information, such as Smart City and Digital Twins, are developing rapidly for managing land and solving urban problems scientifically. In this construction of 3D spatial information, an object using aerial photo images is built as a digital DB. Realistically, the task of extracting a texturing image, which is an actual image of the object wall, and attaching an image to the object wall are important. On the other hand, occluded areas occur in the texturing image. In this study, the ResNet algorithm in deep learning technologies was tested to solve these problems. A dataset was constructed, and the street tree was detected using the ResNet algorithm. The ability of the ResNet algorithm to detect the street tree was dependent on the brightness of the image. The ResNet algorithm can detect the street tree in an image with side and inclination angles.

국토를 효율적으로 관리하고 도시문제를 과학적으로 해결하기 위해 최근 스마트시티, 디지털트윈 등 3차원 공간정보 관련 기술이 급격하게 발전하고 있다. 이러한 3차원 공간정보 구축은 주로 영상정보를 이용하여 객체를 3차원 입체화하고 실감형 영상인 텍스처링 영상을 추출하여 객체벽면에 영상을 부여하는 방식으로 수행된다. 하지만 객체 주변의 다양한 요인으로 인해 텍스처링 영상에서는 필연적으로 폐색영역이 발생한다. 이에 본 연구에서는 최근 기술인 딥러닝 기술 중에서 ResNet 알고리즘을 이용하여 건물 폐색을 유발하는 가로수에 대한 데이터셋을 만들고 이에 대한 해결방안을 제시하고자 한다. 연구결과 ResNet 알고리즘의 공간정보 적용 가능성을 판단하고 이를 적용한 레이블링 생성 SW 개발하여 실제 가로수를 대상으로 데이터셋을 구축하였다. 구축된 데이터셋을 텍스처링 영상에 적용하여 정확도와 재현율로 검출능력을 분석하였다. 분석결과를 위해 딥러닝 분야에서 많이 사용되고 있는 정밀도와 재현율을 이용한 F값을 적용하였으며 가로수 단일 객체가 포함된 건물의 측면부 영상과 경사 영상에 대해서는 높은 F값을 도출하여 우수한 성과를 확인하였으나, 같은 해상도를 가진 건물 전면부 영상에서는 그림자 등의 요인으로 F값이 낮음을 확인하였다.

Keywords

References

  1. S. Y. Lim, M. J. Kim, "Digital Twin Application Plan for Smart City Success", Brief, Korea Research Institute for Human Settlements, Korea, pp.1-6, 2018.
  2. K. H. Bae, G. W. Ham, J. M. Lee, "A Study on Estimating the Vegetable Cultivation Complex Area using Aerial Photogrammetry", Journal of the Korean Association of Geographic Information Studies, Vol.21, No.4, pp.108-118, 2018. DOI: https://doi.org/10.11108/kagis.2018.21.4.108
  3. H. Y. LIm, K. H. Ro, "A Study on a CMS Platform for AR-based Remote Collaboration in a Smart Factory", Journal of Digital Convergence, Vol.16, No.12, pp.327-334, 2018. DOI: https://doi.org/10.14400/JDC.2018.16.12.327
  4. Y. J. Cha, W. Choi, O. Buyukozturk, "Deep learningbased crack damage detection using convolutional neural networks", Computer‐Aided Civil and Infrastructure Engineering, Vol.32, No.5, pp.361-378, 2017. DOI: https://doi.org/10.1111/mice.1226
  5. N. Kussul, M. Lavreniuk, S. Skakun, A. Shelestov, "Deep learning classification of land cover and crop types using remote sensing data", IEEE Geoscience and Remote Sensing Letters, Vol.14, No.5, pp.778-782, 2017. DOI: https://doi.org/10.1109/LGRS.2017.2681128
  6. N. Lv, C. Chen, T. Qiu, A. K. Sangaiah, "Deep learning and superpixel feature extraction based on contractive autoencoder for change detection in SAR images", IEEE transactions on industrial informatics, Vol.14, No.12, pp.5530-5538, 2018. DOI: https://doi.org/10.1109/TII.2018.2873492
  7. Y. Cao, F. Yang, Q. Tang, X. Lu, "An attention enhanced bidirectional LSTM for early forest fire smoke recognition", IEEE Access, Vol.7, pp.154732-154742, 2019. DOI: https://doi.org/10.1109/TII.2018.2873492
  8. M. Saqib, S. D. Khan, N. Sharma, P. Scully-Power, P. Butcher, A. Colefax, M. Blumenstein, "Real-time drone surveillance and population estimation of marine animals from aerial imagery", In 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ), pp.1-6, 2018. DOI: https://doi.org/10.1109/IVCNZ.2018.8634661
  9. S. P. Mohanty, D. P. Hughes, M. Salathe, "Using deep learning for image-based plant disease detection", Frontiers in plant science, Vol.7, 1419, 2016. DOI: https://doi.org/10.3389/fpls.2016.01419
  10. H. L. Wang, M. Zhu, C. B. Lin, D. B. Chen, "Ship detection in optical remote sensing image based on visual saliency and AdaBoost classifier", Optoelectronics Letters, Vol.13, No.2, pp.151-155, 2017. DOI: https://doi.org/10.1007/s11801-017-7014-9
  11. Y. Li, J. Li, J. S. Pan, "Hyperspectral image recognition using SVM combined deep learning", Journal of Internet Technology, Vol.20, No.3, pp.851-859. 2019.
  12. H. J. Kim, J. M. Lee, K. H. Bae, Y. D. Eo, "Application research on obstruction area detection of building wall using R-CNN technique", Journal of Cadastre & Land InformatiX, Vol.48, No.2, pp.213-225, 2016. DOI: https://doi.org/10.22640/lxsiri.2018.48.2.213
  13. L. M. Dang, S. I. Hassan, I. Suhyeon, A. kumar Sangaiah, I. Mehmood, S. Rho, H. Moon, "UAV based wilt detection system via convolutional neural networks", Sustainable Computing: Informatics and Systems, 2018. DOI: https://doi.org/10.1016/j.suscom.2018.05.01
  14. M. J. Kang, "Comparison of gradient descent for deep learning", Journal of the The Korea Academia-Industrial Cooperation Society, Vol.21, No.2, pp.189-194, 2020. DOI: https://doi.org/10.5762/KAIS.2020.21.2.189
  15. K. He, X. Zhang, S. Ren, J. Sun, "Deep residual learning for image recognition", In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770-778, 2016.
  16. J. Davis, M. Goadrich, "The relationship between Precision-Recall and ROC curves", In Proceedings of the 23rd international conference on Machine learning, pp.233-240, 2016. DOI: https://doi.org/10.1145/1143844.1143874