Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회지)

Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회)
권호 표지
DOI QR코드

DOI QR Code

Integrated Automatic Pre-Processing for Change Detection Based on SURF Algorithm and Mask Filter

변화탐지를 위한 SURF 알고리즘과 마스크필터 기반 통합 자동 전처리

  • Kim, Taeheon (Dept. of Geospatial Information, Kyungpook National University) ;
  • Lee, Won Hee (School of Convergence & Fusion System Engineering, Kyungpook National University) ;
  • Yeom, Junho (Research Institute for Automotive Diagnosis Technology of Multi-scale Organic and Inorganic Structure, Kyungpook National University) ;
  • Han, Youkyung (School of Convergence & Fusion System Engineering, Kyungpook National University)
  • Received : 2019.05.19
  • Accepted : 2019.06.28
  • Published : 2019.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Satellite imagery occurs geometric and radiometric errors due to external environmental factors at the acquired time, which in turn causes false-alarm in change detection. These errors should be eliminated by geometric and radiometric corrections. In this study, we propose a methodology that automatically and simultaneously performs geometric and radiometric corrections by using the SURF (Speeded-Up Robust Feature) algorithm and the mask filter. The MPs (Matching Points), which show invariant properties between multi-temporal imagery, extracted through the SURF algorithm are used for automatic geometric correction. Using the properties of the extracted MPs, PIFs (Pseudo Invariant Features) used for relative radiometric correction are selected. Subsequently, secondary PIFs are extracted by generated mask filters around the selected PIFs. After performing automatic using the extracted MPs, we could confirm that geometric and radiometric errors are eliminated as the result of performing the relative radiometric correction using PIFs in geo-rectified images.

위성영상은 취득 당시의 외부 환경적 요소에 의해 기하 및 방사오차가 발생하며, 이는 변화탐지에 있어 오탐지를 유발하는 원인이 된다. 이러한 기하 및 방사오차는 전처리과정인 기하보정 및 방사보정을 통해 제거해야 한다. 본 연구에서는 SURF (Speeded-Up Robust Feature)기법과 마스크필터를 활용하여 동시에 기하 및 방사보정을 자동으로 수행하는 방법론을 제안하고자 한다. SURF 기법을 통해 추출되는 정합쌍(MPs: Matching Points)은 자동 기하보정에 활용되며, 다시기 영상 간 불변특성을 보이는 지역에서 추출된다. 이러한 정합쌍의 특성을 바탕으로 상대방사보정에 활용되는 PIFs (Pseudo Invariant Features)를 선정하고, 선정된 PIFs를 중심으로 마스크필터를 생성하여 2차 PIFs를 추출했다. 추출된 정합쌍들을 활용하여 자동 기하보정을 수행한 후 기하보정된 영상에 PIFs를 활용하여 상대방사보정을 수행한 결과 기하 및 방사오차가 함께 제거된 것을 확인하였다.

Keywords

GCRHBD_2019_v37n3_209_f0001.png 이미지

Fig. 1. Flowchart of the proposed method

GCRHBD_2019_v37n3_209_f0002.png 이미지

Fig. 2. An example of number of extracted data samples (band 1): (a) MPs, (b) PIFs

GCRHBD_2019_v37n3_209_f0003.png 이미지

Fig. 3. Mask filter generation for secondary PIFs extraction (M×M size): (a) Mask filter generation, (b) Evaluation of similarity between PIFs and its neighboring pixels within mask filter, (C) Secondary PIFs extraction

GCRHBD_2019_v37n3_209_f0004.png 이미지

Fig. 4. Experimental images of study area: (a) Reference image, (b) Subject image

GCRHBD_2019_v37n3_209_f0005.png 이미지

Fig. 5. Extracted MPs: (a) Reference image, (b) Subject image

GCRHBD_2019_v37n3_209_f0006.png 이미지

Fig. 8. Secondary PIFs extracted by mask filter (a) Reference image, (b) Geo-rectified subject image

GCRHBD_2019_v37n3_209_f0007.png 이미지

Fig. 9. Comparison of band-by-band linear regression analysis according to relative radiometric correction: (a) MPs (SURF): 3,042, (b) PIFs: 290, (C) Proposed method (7×7 size): 972

GCRHBD_2019_v37n3_209_f0008.png 이미지

Fig. 10. Experimental results of relative radiometric correction: (a) Reference image, (b) Geo-rectified subject image, (c) MPs, (d) PIFs, (e) Proposed method (7×7 size)

GCRHBD_2019_v37n3_209_f0009.png 이미지

Fig. 11. Accuracy analysis of radiometric correction (converting NRMSE as a percentage): (a) Band 1, (b) Band 2, (c) Band 3, (d) Band 4, (e) Average

GCRHBD_2019_v37n3_209_f0010.png 이미지

Fig. 6. Mosaic images of automatic geometric correction result: (a) Raw image, (b) Geo-rectified image

GCRHBD_2019_v37n3_209_f0011.png 이미지

Fig. 7. Extracted PIFs: (a) Reference image, (b) Georectified subject image

Table 1. Specification of the study data

GCRHBD_2019_v37n3_209_t0001.png 이미지

Table 2. NRMSE values of automatic geometric correction results

GCRHBD_2019_v37n3_209_t0002.png 이미지

Table 3. NRMSE values of relative radiometric correction results

GCRHBD_2019_v37n3_209_t0003.png 이미지

References

  1. Bay, H., Ess, A., Tuytelaars, T., and Van Gool, L. (2008), Speeded-up robust features (SURF), Computer vision and image understanding, Vol. 110, No. 3, pp. 346-359. https://doi.org/10.1016/j.cviu.2007.09.014
  2. Du, Y., Teillet, P.M., and Cihlar, J. (2002), Radiometric normalization of multitemporal high-resolution satellite images with quality control for land cover change detection, Remote sensing of Environment, Vol. 82, No. 1, pp. 123-134. https://doi.org/10.1016/S0034-4257(02)00029-9
  3. Han, Y.K. (2013), Automatic Image-to-image Registration between High-resolution Multisensor Satellite Data in Urban Areas. Ph.D. dissertation, Seoul National University, Seoul, Korea, 146p.
  4. Han, Y.K., Byun., Y.G., Choi, J.W., Han, D.Y., and Kim, Y.I. (2010), Automatic registration of high resolution satellite images using local properties of tie points, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 28, No. 3, pp. 353-359. (in Korean with English abstract)
  5. Han, Y.K. and Choi, J.W. (2015), Matching points extraction between optical and TIR images by using SURF and local phase correlation, Journal of the Korean Society for Geospatial Information Science, Vol. 23, No. 1, pp. 81-88. (in Korean with English abstract) https://doi.org/10.7319/kogsis.2015.23.1.081
  6. Hong, G. and Zhang, Y. (2008), A comparative study on radiometric normalization using high resolution satellite images, International Journal of Remote Sensing, Vol. 29, No. 2, pp. 425-438. https://doi.org/10.1080/01431160601086019
  7. Huo, C., Pan, C., Huo, L., and Zhou, Z. (2012), Multilevel SIFT matching for large-size VHR image registration, IEEE Geoscience and Remote Sensing Letters, Vol. 9, No, 2, pp. 171-175. https://doi.org/10.1109/LGRS.2011.2163491
  8. Janzen, D.T., Fredeen, A.L., and Wheate, R.D. (2006), Radiometric correction techniques and accuracy assessment for Landsat TM data in remote forested regions, Canadian Journal of Remote Sensing, Vol. 32, No. 5, pp. 330-340. https://doi.org/10.5589/m06-028
  9. Kim, D.S. and Kim, Y.I. (2008), Relative radiometric normalization of hyperion hyperspectral images through automatic extraction of pseudo-invariant features for change detection, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 26, No. 2, pp. 129-137. (in Korean with English abstract)
  10. Klaric, M.N., Claywell, B.C., Scott, G.J., Hudson, N.J., Sjahputera, O., Li, Y., and Davis, C.H. (2013), GeoCDX: An automated change detection and exploitation system for high-resolution satellite imagery, IEEE Transactions on Geoscience and Remote Sensing, Vol. 51, No. 4, pp. 2067-2086. https://doi.org/10.1109/TGRS.2013.2243840
  11. Li, C. and Xiong, H. (2017), A Geometric and Radiometric Simultaneous Correction Model (GRSCM) framework for high-accuracy remotely sensed image preprocessing, Photogrammetric Engineering & Remote Sensing, Vol. 83, No. 9, pp. 621-632. https://doi.org/10.14358/PERS.83.9.621
  12. Li, Y. and Davis, C.H. (2011), Pixel-based invariant feature extraction and its application to radiometric co-registration for multi-temporal high-resolution satellite imagery, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 4, No. 2, pp. 348-360. https://doi.org/10.1109/JSTARS.2010.2062490
  13. Lowe, D.G. (2004), Distinctive image features from scale-invariant keypoints, International journal of computer vision, Vol. 60, No. 2, pp. 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  14. Seo, D.K. and Eo, Y.K. (2018), Relative radiometric normalization for high-spatial resolution satellite imagery based on multilayer perceptron, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 36, No. 6, pp. 515-523. (in Korean with English abstract) https://doi.org/10.7848/KSGPC.2018.36.6.515
  15. Seo, D., Kim, Y., Eo, Y., Park, W., and Park, H. (2017), Generation of radiometric, phenological normalized image based on random forest regression for change detection, Remote Sensing, Vol. 9, No. 11, pp. 1163. https://doi.org/10.3390/rs9111163
  16. Zhang, L., Wu, C., and Du, B. (2014), Automatic radiometric normalization for multitemporal remote sensing imagery with iterative slow feature analysis, IEEE Transactions on Geoscience and Remote Sensing, Vol. 52, No. 10, pp. 6141-6155. https://doi.org/10.1109/TGRS.2013.2295263