Journal of Cadastre & Land InformatiX (지적과 국토정보)

LX Spatial Information Research Institute (한국국토정보공사 공간정보연구원)
권호 표지
DOI QR코드

DOI QR Code

Application Research on Obstruction Area Detection of Building Wall using R-CNN Technique

R-CNN 기법을 이용한 건물 벽 폐색영역 추출 적용 연구

  • Kim, Hye Jin (Department of Advanced Technology Fusion, Konkuk University) ;
  • Lee, Jeong Min (Shinhan Aerial Survey Research Institute) ;
  • Bae, Kyoung Ho (Shinhan Aerial Survey Research Institute) ;
  • Eo, Yang Dam (Department of Advanced Technology Fusion, Konkuk University)
  • 김혜진 (건국대학교 신기술융합학과) ;
  • 이정민 ((주)신한항업 연구소) ;
  • 배경호 ((주)신한항업 연구소) ;
  • 어양담 (건국대학교 신기술융합학과)
  • Received : 2018.10.04
  • Accepted : 2018.11.22
  • Published : 2018.12.10
Download PDF
⟨ Previous Next ⟩

Abstract

For constructing three-dimensional (3D) spatial information occlusion region problem arises in the process of taking the texture of the building. In order to solve this problem, it is necessary to investigate the automation method to automatically recognize the occlusion region, issue it, and automatically complement the texture. In fact there are occasions when it is possible to generate a very large number of structures and occlusion, so alternatives to overcome are being considered. In this study, we attempt to apply an approach to automatically create an occlusion region based on learning by patterning the blocked region using the recently emerging deep learning algorithm. Experiment to see the performance automatic detection of people, banners, vehicles, and traffic lights that cause occlusion in building walls using two advanced algorithms of Convolutional Neural Network (CNN) technique, Faster Region-based Convolutional Neural Network (R-CNN) and Mask R-CNN. And the results of the automatic detection by learning the banners in the pre-learned model of the Mask R-CNN method were found to be excellent.

3차원 공간정보 구축을 위해 건물 텍스처를 촬영하는 과정에서 폐색영역 문제가 발생한다. 이를 해결하기 위해선 폐색영역을 자동 인식하여 이를 검출하고 텍스처를 자동 보완하는 자동화 기법 연구가 필요하다. 현실적으로 매우 다양한 구조물 형상과 폐색을 발생시키는 경우가 있으므로 이를 극복하는 대안들이 고려되고 있다. 본 연구는 최근 대두되고 있는 딥러닝 기반의 알고리즘을 이용하여 폐색지역 패턴화하고, 학습기반 폐색영역 자동 검출하는 접근을 시도한다. 영상 내 객체 추출에서 우수한 성과를 발표하는 Convolutional Neural Network (CNN) 기법의 향상된 알고리즘인 Faster Region-based Convolutional Network (R-CNN)과 Mask R-CNN 2가지를 이용하여, 건물 벽면 촬영 시 폐색을 유발하는 사람, 현수막, 차량, 신호등에 대한 자동 탐지하는 성능을 알아보기 위해 실험하고, Mask R-CNN의 미리 학습된 모델에 현수막을 학습시켜 자동탐지하는 실험을 통해 적용이 높은 결과를 확인할 수 있었다.

Keywords

References

  1. Kim SS, Kim BG. 2002. Adjustment of texture image for construction of a 3D virtual city. Journal of the Korean Society for Geospatial Information Science. 10(2):49-56.
  2. Kim HJ, Han YK, Choi JW, Kim YI. 2009. High resolution satellite image classification enhancement using restortation of buildin shadow and occlusion. The Korean Society of Remote Sensing. Proceedings of the KSRS Conference (Mar):13-17.
  3. Park JH, Suh YC. 2017. Calculation of the Duration of Sunshine Using a Three-Dimensional Spatial Information Open Platform. Journal of the Korean Association of Geographic Information Studies. 20(3):80-89. https://doi.org/10.11108/KAGIS.2017.20.3.080
  4. Shin DK, Park CW, Park JW, Kim YM, Park KT, Moon YS. 2011. Feature based Depth Map Generation for Compensation of Occlusion Region using Disparity Estimation. The Journal of Korean Institute of Information Technology. 9(5):217-230.
  5. Lee JS, Lee IG. 2018. The 3D Modeling Data Production Method Using Drones Photographic Scanning Technology. Journal of the Korea Institute of Information and Communication Engineering. 22(6):874-880. https://doi.org/10.6109/JKIICE.2018.22.6.874
  6. Jung SH, Lee JK. 2008. Application of Photorealitstic Modeling and Visualization Using Digital Image Data in 3D GIS. Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography. 26(1):73-83.
  7. Cho MH, Seo JT, Lee CY, Par YJ. 2011. The Realization of Disaster Information using Virtual Simulation based on 3D Spatial Information. Journal of the Korean Society of Hazard Mitigation. 11(5):175-184. https://doi.org/10.9798/KOSHAM.2011.11.5.175
  8. Girshick R, Donahue J, Darrell T, Malik J. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition. pp.580-587.
  9. Gruen A, Huang X, Qin R, Du T, Fang W, Boavida J, Oliveira A. 2013. Joint processing of UAV imagery and terrestrial mobile mapping system data for very high resolution city modeling. Remote Sens Spatial Inf Sci. pp.175-182.
  10. Hammoudi K, Dornaika F, Soheilian B, Vallet B, McDonald J, Paparoditis N. 2012. Recovering occlusion-free textured 3D maps of urban facades by a synergistic use of terrestrial images, 3D point clouds and area-based information. Procedia Engineering. 41(2012): 971-980. https://doi.org/10.1016/j.proeng.2012.07.271
  11. He K, Gkioxari G, Dollar P, Girshick R. 2017. Mask R-CNN. IEEE International Conference on Computer Vision (ICCV). pp.2980-2988.
  12. Ho WT, Lim HW, Tay YH. 2009. Two-stage license plate detection using gentle Adaboost and SIFT-SVM. Intelligent Information and Database Systems. pp.109-114.
  13. Kim HT, Kim SB, Go JS, Eo YD, Lee BK. 2010. Building 3D Geospatial Information using Airborne Multi-Looking Digital Camera System. Journal of Convergence Information Technology. 5(1):15-22. https://doi.org/10.4156/jcit.vol5.issue1.2
  14. Levi D, Garnett N, Fetaya E. 2015. StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation. British Machine Vision Conference 2015. pp.109.1-109.12.
  15. Papageorgiou CP, Oren M, Poggio T. 1998. A general framework for object detection. Sixth International Conference on Computer Vision. pp.555-562.
  16. Powers, David MW. 2011. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation. Journal of Machine Learning Technologies. 2(1):37-63.
  17. Remondino F, Barazzetti L, Nex F, Scaioni M, Sarazzi D. 2011. UAV photogrammetry for mapping and 3D modeling-Current status and future perspectives. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XXXVIII-1(C22):25-31.
  18. Ren S, He K, Girshick R, Sun J. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Neural Information Processing Systems (NIPS). pp.91-99.
  19. Simard PY, Steinkraus D, Platt JC. 2003. Best practices for convolutional neural networks applied to visual document analysis. Document Analysis and Recognition. p.958.
  20. Sivaraman S, Trivedi MM. 2013. A review of recent developments in vision-based vehicle detection. Intelligent Vehicles Symposium (IV). pp.310-315.
  21. Sivaraman S, Trivedi MM. 2014. Active learning for on-road vehicle detection: A comparative study. Machine vision and applications. 25(3): 599-611. https://doi.org/10.1007/s00138-011-0388-y
  22. Xiao J, Fang T, Zhao P, Lhuillier M, Quan L. 2009. Image-based street-side city modeling. In ACM transactions on Graphics (TOG). 28(5):114. https://doi.org/10.1145/1618452.1618460

Cited by

  1. 포인트 클라우드에서 딥러닝을 이용한 객체 분류 및 변화 탐지 vol.50, pp.2, 2018, https://doi.org/10.22640/lxsiri.2020.50.2.37
  2. 복층 건물 실내외 역설계를 위한 UAV 및 LiDAR SLAM 조합 효용성 검토 vol.50, pp.2, 2018, https://doi.org/10.22640/lxsiri.2020.50.2.69
  3. 적외선 영상, 라이다 데이터 및 특성정보 융합 기반의 합성곱 인공신경망을 이용한 건물탐지 vol.38, pp.6, 2020, https://doi.org/10.7848/ksgpc.2020.38.6.635