DOI QR코드

DOI QR Code

Urban Building Change Detection Using nDSM and Road Extraction

nDSM 및 도로망 추출 기법을 적용한 도심지 건물 변화탐지

  • Jang, Yeong Jae (Dept. of Civil Engineering, Korea Maritime and Ocean University) ;
  • Oh, Jae Hong (Dept. of Civil Engineering, Korea Maritime and Ocean University) ;
  • Lee, Chang No (Dept. of Civil Engineering, Seoul National University of Science and Technology)
  • Received : 2020.05.25
  • Accepted : 2020.06.11
  • Published : 2020.06.30

Abstract

Recently, as high resolution satellites data have been serviced, frequent DSM (Digital Surface Model) generation over urban areas has been possible. In addition, it is possible to detect changes using a high-resolution DSM at building level such that various methods of building change detection using DSM have been studied. In order to detect building changes using DSM, we need to generate a DSM using a stereo satellite image. The change detection method using D-DSM (Differential DSM) uses the elevation difference between two DSMs of different dates. The D-DSM method has difficulty in applying a precise vertical threshold, because between the two DSMs may have elevation errors. In this study, we focus on the urban structure change detection using D-nDSM (Differential nDSM) based on nDSM (Normalized DSM) that expresses only the height of the structures or buildings without terrain elevation. In addition, we attempted to reduce noise using a morphological filtering. Also, in order to improve the roadside buildings extraction precision, we exploited the urban road network extraction from nDSM. Experiments were conducted for high-resolution stereo satellite images of two periods. The experimental results were compared for D-DSM, D-nDSM, and D-nDSM with road extraction methods. The D-DSM method showed the accuracy of about 30% to 55% depending on the vertical threshold and the D-nDSM approaches achieved 59% and 77.9% without and with the morphological filtering, respectively. Finally, the D-nDSM with the road extraction method showed 87.2% of change detection accuracy.

최근 고해상도 영상을 지원하는 위성들이 다양화되면서 도심지에 대한 DSM (Digital Surface Model) 생성 및 업데이트가 가능해지고 있다. 그에 따라 고해상도 DSM을 이용해 건물 단위의 변화탐지가 가능해지면서 DSM을 활용한 건물 변화탐지 기법들이 다양하게 연구되고 있다. 기본적으로 DSM을 활용한 건물 변화탐지를 위해서는 스테레오 위성영상을 이용한 두 시기에 대한 DSM의 생성이 필요하며, 생성된 DSM의 표고값 차이를 이용해 변화를 탐지하는 D-DSM (Differential DSM) 방법이 일반적으로 사용된다. 그러나 D-DSM을 이용하는 기법은 두 DSM 간의 수직오차가 클 경우 건물의 변화를 탐지하기 위한 최소 수직좌표의 임계치를 정밀하게 적용하기에 어려움이 있다. 따라서 본 연구에서는 DTM (Digital Terrain Model)의 높이를 기준표고로 지정하고 구조물의 높이만을 표현하는 nDSM (Normalized DSM)을 기반으로 D-nDSM (Differential nDSM)을 생성하고 모폴로지 필터링을 거쳐 변화탐지를 진행하여 표고 오차에 따른 변화탐지의 오류를 줄이고자 하였다. 또한 도로변 건물의 추출 정밀도 향상을 위해 nDSM에서 도심지의 도로망을 추출하는 방안을 제시해 D-nDSM기법에 적용하였다. 도시 변화지역을 대상으로 두 시기의 스테레오 영상을 이용하여 실험을 진행하였고, D-DSM을 이용한 변화탐지기법과 D-nDSM기법, 도로선형을 추출해 D-nDSM에 적용한 탐지방법 등을 비교하여 결과를 얻었다. 단순 D-DSM을 이용한 기법에서 수직 임계치에 따라 약 30~55%의 정확도를 얻어낼 수 있었다. 또한 D-nDSM 기법의 적용시 59%의 정확도를 얻었으며, 노이즈 필터링의 과정을 거쳐 77.9%의 정확도를 얻었다, 최종적으로 대상지의 도로 선형을 추출해 적용하여 87.2%의 전체 정확도를 얻을 수 있었다.

Keywords

References

  1. Boonpook, W., Tan, Y., Liu, H., Zhao, B., and He, L. (2018), UAV-based 3d urban environment monitoring, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., Vol. 4, No. 3, pp. 37-43. https://doi.org/10.5194/isprs-annals-IV-3-37-2018
  2. Choi, J.W. (2015), Unsupervised change detection for very high-spatial resolution satellite imagery by using objectbased IR-MAD algorithm, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 33, No. 4, pp. 297-304. https://doi.org/10.7848/ksgpc.2015.33.4.297
  3. Choi, K.A. and Lee, I.P. (2008), Automatic change detection of urban areas using LiDAR data, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 26, No. 4, pp. 341-350. (in Korean with English abstract)
  4. Dini, G.R., Jacobsen, K., Rottensteiner, F., Rajhi, M., and Heipke, C. (2012), 3D Building change detection using high resolution stereo images and a gis database, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 25 Aug-01 Sep, Melbourne, Australia, Vol. 19, No. 7.
  5. Du, S., Zhang, Y., Qin, R., Yang, Z., Zou, Z., Tang, Y., and Fan, C. (2016), Building change detection using old aerial images and new LiDAR data, Remote Sensing, Vol. 8, No. 1030, pp. 1-20.
  6. Han, Y.K., Kim, T.H., Han, S.H., and Song, J.H. (2017). Change detection of urban development over large area using KOMPSAT optical imagery. Korean Journal Of Remote Sensing, Vol. 33 No. 6-3, pp. 1223-1232.(in Korean with English abstract) https://doi.org/10.7780/KJRS.2017.33.6.3.6
  7. Jang, Y.J., Oh, K.Y., Lee, K.J., and Oh, J.H. (2019). A study on urban change detection using D-DSM from stereo satellite data, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 37, No. 5, pp. 389-395. https://doi.org/10.7848/ksgpc.2019.37.5.389
  8. Kang, G.S., Shin, S.C., and Cho, K.J. (2003), Change detection using the IKONOS satellite images, Journal of the Korean society for Geospatial Information System, Vol. 11, No. 2, pp. 61-66. (in Korean with English abstract)
  9. Lei, L., Perissin, D., and Qin, Y. (2013), Change detection with spaceborne InSAR technique in Hong Kong, 2013 IEEE International Geoscience and Remote Sensing Symposium, 54-26 July, Melbourne, VIC, Australia, pp. 338-341.
  10. Tian, J., Cui, S., and Reinartz, P. (2014), Building change detection based on satellite stereo imagery and digital surface models, IEEE Transactions On Geoscience And Remote Sensing, Vol. 52, No. 1, pp. 406-417. https://doi.org/10.1109/TGRS.2013.2240692
  11. Zhang, J., Zhang, Z. X., Fan, H., Fang, Z., and Liu, Z. (2000), Change detection in urban area based on stereo image pairs From different duration. International Archives Of Photogrammetry And Remote Sensing, 33(B4/3; PART 4), pp. 1203-1208.

Cited by

  1. 기계학습 기법에 따른 KOMPSAT-3A 시가화 영상 분류 - 서울시 양재 지역을 중심으로 - vol.36, pp.6, 2020, https://doi.org/10.7780/kjrs.2020.36.6.2.7