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 the Applicability of Deep Learning Algorithm for Detection and Resolving of Occlusion Area

영상 폐색영역 검출 및 해결을 위한 딥러닝 알고리즘 적용 가능성 연구

  • Bae, Kyoung-Ho (Research Institute, Shinhan Aerial Survey CO.,LTD) ;
  • Park, Hong-Gi (Department of Civil & Environmental Engineering, Gachon University)
  • 배경호 ((주)신한항업 연구소) ;
  • 박홍기 (가천대학교 토목환경공학과)
  • Received : 2019.10.04
  • Accepted : 2019.11.01
  • Published : 2019.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, spatial information is being constructed actively based on the images obtained by drones. Because occlusion areas occur due to buildings as well as many obstacles, such as trees, pedestrians, and banners in the urban areas, an efficient way to resolve the problem is necessary. Instead of the traditional way, which replaces the occlusion area with other images obtained at different positions, various models based on deep learning were examined and compared. A comparison of a type of feature descriptor, HOG, to the machine learning-based SVM, deep learning-based DNN, CNN, and RNN showed that the CNN is used broadly to detect and classify objects. Until now, many studies have focused on the development and application of models so that it is impossible to select an optimal model. On the other hand, the upgrade of a deep learning-based detection and classification technique is expected because many researchers have attempted to upgrade the accuracy of the model as well as reduce the computation time. In that case, the procedures for generating spatial information will be changed to detect the occlusion area and replace it with simulated images automatically, and the efficiency of time, cost, and workforce will also be improved.

최근 드론을 이용한 공간정보 구축이 활성화되면서 공간정보 산업발전에 많은 기여를 하고 있다. 하지만 드론 공간정보는 카메라의 중심투영에 의한 발생하는 폐색영역 뿐 아니라 가로수, 보행자, 현수막과 같은 적치물에 의한 폐색 영역이 필연적으로 발생한다. 이러한 폐색영역을 효율적으로 해결하기 위한 다양한 방안이 연구되고 있다. 본 연구에서는 폐색영역 해결을 위해 원초적인 재촬영이 아닌 딥러닝 알고리즘을 적용하기 위한 다양한 알고리즘별 조사 및 비교 연구를 수행하였다. 그 결과, 객체 검출 알고리즘인 HOG부터 기계학습 방법인 SVM, 딥러닝 방식인 DNN, CNN, RNN까지 다양한 모델들이 개발 및 적용되고 있으며, 이 중 영상의 분류, 검출에 가장 보편적이고 효율적인 알고리즘은 CNN 기법임을 확인하였다. 향후 AI 기반의 자동 객체 탐지와 분류는 공간정보 분야에서 각광받는 최신 과학기술이다. 이를 위해 다양한 알고리즘에 대한 검토와 적용은 중요하다. 따라서, 본 연구에서 제시하는 알고리즘별 적용 가능성은 자동으로 드론 영상의 폐색영역을 탐지하고 해결할 수 있어 공간정보 구축의 시간, 비용, 인력에 대한 효율성 향상에 기여할 것으로 판단된다.

Keywords

References

  1. O. Kwon, Detection and Restoring the Occlusion Area for Generating Digital Orthoimage, Master's thesis, Seoul National University, Seoul, Korea, pp.13-16, 2000.
  2. J. Yom,, D. Lee, D. Kim, "Automatic 3D building reconstruction by integration of digital map and stereo imagery for urban area", KSCE Journal of Civil Engineering, Vol.8, No.4, pp.443-449, July. 2004 DOI: https://doi.org/10.1007/bf02829168
  3. M. Seo, D. Y. Han, B. K. Lee, Y. I. Kim, "Detecting and restoring the occlusion area for generating the true orthoimage using IKONOS image". Korean Journal of Remote Sensing, Vol.22, No.2, pp131-139, Apr. 2006. https://doi.org/10.7780/kjrs.2006.22.2.131
  4. J. Youn, G. H. Kim, 2008, "Visible height based occlusion area detection in true orthophoto generation", Journal of the Korean Society of Civil Engineers D, Vol.28, No.3D, pp.417-422, May. 2008.
  5. E. J. Yoo, D. Lee, "Detection and recovery of occlusion areas caused by building sidewalls and aerial photos", Proceedings of Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography 2016, KSGPC, Suwon, Korea, pp.156-158, Apr. 2016.
  6. S. Shim, C. Chun, S. Choi, S. Ruy, "Road Surface Damage Detection based on Object Recognition using Fast R-CNN", The Korean Institute of communications and Information Sciences, Vol.18. No.2, pp.104-113, Apr. 2019. DOI: https://doi.org/10.12815/kits.2019.18.2.104
  7. H. C. Song, M. Kang, T. Kim, "Object Detection based on Mask R-CNN from Infrared Camera", Journal of Digital Contents Society, Vol.19, No.6, pp.1213-1218, June 2018. DOI: https://doi.org/10.9728/dcs.2018.19.6.1213
  8. I. Choi, J. Seo, H. Park, "Object Recognition of Low Resolution Images based on Deep Learning", Proceeding of Korea Computer Congress 2017, KIISE, Jeju, Korea, pp.782-784, June 2017. DOI: https://doi.org/10.1109/access.2019.2941005
  9. D. S. Jeong, H. Kim, J. Shin, J. Paik, "Deep Learning-Based Person Re-identification Using Semantic Segmentation", Proceeding of the Institute of Electronics and Information Engineers, IEIE, Incheon, Korea, pp.392-394, Nov. 2018,
  10. A. Tang, K. Lu, Y. Wang, J. Huang, H. Li, "A real-time hand posture recognition system using deep neural networks". ACM Transactions on Intelligent Systems and Technology, Vol.6, No.2, p21, 2015. DOI: https://doi.org/10.1145/2735952
  11. W. Ouyang, X., Wang, "Joint deep learning for pedestrian detection", Proceedings of the IEEE International Conference on Computer Vision. IEEE, NSW, Australia, pp.2056-2063, Dec. 2013. DOI: https://doi.org/10.1109/iccv.2013.257
  12. N. Dalal, B. Triggs, "Histograms of oriented gradients for human detection", Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, CA, USA, pp.1-9, June 2005. DOI: https://doi.org/10.1109/cvpr.2005.177
  13. B. Kim, S. Oh, J. Kim, "Design of RBFNNs Pattern Classifier-based Two-dimensional Face Recognition System Using HOG and Adaboost Algorithm", Proceeding of the Korean Institute of Electrical Engineers, KIEE, Kosung, Korea, pp.77-78, Apr. 2015, DOI: https://doi.org/10.5370/kiee.2014.63.6.797
  14. Y. Freund, R. E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting", Journal of Computer and System Sciences, Vol.55, No.1, pp.119-139, 1997. DOI: https://doi.org/10.1006/jcss.1997.1504
  15. S. Kim, J. Park, J. Lee, "Monocular Image and AdaBoost Learning Based Nighttime Preceding Vehicle Detection for ADAS and Intelligent Headlamp System", Journal of Institute of Control, Robotics and Systems, Vol.23, No.10, pp.886-893, Oct. 2017. DOI: https://doi.org/10.5302/j.icros.2017.17.0134
  16. C. Cortes V, Vapnik, "Support-vector networks". Machine Learning, Vol.20, No.3, pp.273-297, July 1995. https://doi.org/10.1007/BF00994018
  17. V. Vapnik, The nature of statistical learning theory, p.313, New York: Springer-Verlag New York, 2000, pp.123-167. DOI: https://doi.org/10.1007/978-1-4757-2440-0
  18. X. Zhang, L. Li, D. Pi, "Toward Optimization of SVM Learning with RBF Kernel", Proceedings of International Technical Conference on Circuits Systems, Computers and Communications, ITC-CSCC, pp.437-440, July 2006.
  19. M. Im, D. K. Yoon, B. Kim, "A study on Object Recognition Algorithm based on SVM Machine Learning Algorithm", Proceeding of Institute of Control, Robotics and Systems, ICROS, Kyeong-ju, Korea, pp.272-273, May 2019.
  20. B. C. Kuo, H. H. Ho, C. Li, C. Jung, J. S. Taur, "A kernel-based feature selection method for SVM with RBF kernel for hyperspectral image classification", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.7, No.1, pp.317-326, 2013. DOI: https://doi.org/10.1109/jstars.2013.2262926
  21. P. P. Plehiers, S. H. Symoens, I. Amghizar, G. B. Marin, C. V. Stevens, K. M. Van, "Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent Prediction", Preprint version, July 2019. DOI: https://doi.org/10.1016/j.eng.2019.02.013
  22. Neural Networks and Deep Learning, Available From: http://neuralnetworksanddeeplearning.com/chap5.html (accessed Sep. 27, 2019)
  23. G. E. Hinton, R. R. Salakhutdinov. "Reducing the Dimensionality of Data with Neural Networks", Science, Vol.313, No.5786, PP.504-507, July 2006 DOI: https://doi.org/10.1126/science.1127647
  24. M. Oh, H. Choi, S. Kim, J. Jang, J. Jin, M. Cheon (2017). Analysis of social welfare and estimation model based on machine learning, Technical Report, Korea Institute for Health and Social Affairs, Korea, pp.54-84.
  25. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel, "Backpropagation Applied to Handwritten Zip Code Recognition", Neural Computation, Vol.1, No.4, pp.541-551, Mar. 1989. DOI: https://doi.org/10.1162/neco.1989.1.4.541
  26. A. Krizhevsky, I. Sutskever, G. E. Hinton. "Imagenet classification with deep convolutional neural networks". Proceedings of Advances in neural information processing systems, NIPS, NV, USA, pp.1097-1105, Dec. 2012. DOI: https://doi.org/10.1145/3065386
  27. 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, IEEE, OH, USA, pp. 580-587. June 2014. DOI: https://doi.org/10.1109/cvpr.2014.81
  28. J. R. Uijlings, K. E. Van De Sande, T. Gevers, A. W. Smeulders. "Selective search for object recognition". International journal of computer vision, Vol.104, No.2, pp.154-171, Apr. 2013. DOI: https://doi.org/10.1007/s11263-013-0620-5
  29. R. Girshick, "Fast r-cnn", Proceedings of the IEEE international conference on computer vision, IEEE, Santiago, Chile, pp. 1440-1448, Dec. 2015. DOI: https://doi.org/10.1109/iccv.2015.169
  30. S. Ren, K. He, R. Girshick, J. Sun, "Faster r-cnn: Towards real-time object detection with region proposal networks". Proceedings of Advances in neural information processing systems, NeurIPS, Montreal, Canada, pp.91-99, Dec. 2015. DOI: https://doi.org/10.1109/tpami.2016.2577031
  31. Kakao, Available From: https://brunch.co.kr/@kakao-it/66 (accessed Sep. 27, 2019)
  32. K. He, G. Gkioxari, P. Dollár, R. Girshick, "Mask r-cnn", Proceedings of the IEEE international conference on computer vision, IEEE, Venice, Italy, pp.2980-2988, Oct. 2017. DOI: https://doi.org/10.1109/iccv.2017.322
  33. K. Zhao, J. Kang, J. Jung, G. Sohn. "Building Extraction from Satellite Images Using Mask R-CNN with Building Boundary Regularization", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, IEEE, CA, USA, pp.247-251, June 2018. DOI: https://doi.org/10.1109/cvprw.2018.00045
  34. 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, Dec. 2016. DOI: https://doi.org/10.22640/LXSIRI.2018.48.2.213
  35. A. Sperduti, A. Starita, "Supervised neural networks for the classification of structures", IEEE Transactions on Neural Networks, Vol.8, No.3, pp.714-735, May 1997. DOI: https://doi.org/10.1109/72.572108
  36. P. Frasconi, M. Gori, A. Sperduti, "A general framework for adaptive processing of data structures", IEEE Transactions on Neural Networks. Vol.9, No.5, pp.768-786, Sep. 1998. DOI: https://doi.org/10.1109/72.712151