DOI QR코드

DOI QR Code

등록오차 분포특성을 이용한 고해상도 위성영상 간 정밀 등록

Fine Registration between Very High Resolution Satellite Images Using Registration Noise Distribution

  • Han, Youkyung (School of Convergence & Fusion System Engineering, Kyungpook National University)
  • 투고 : 2017.02.23
  • 심사 : 2017.06.08
  • 발행 : 2017.06.30

초록

IKONOS, QuickBird, Kompsat-2 등 서로 다른 고해상도 광학 센서로 취득된 다중시기 영상은, 취득 당시의 센서 자세나 환경의 차이에 의해 영상 등록(image registration)을 수행한 이후에도 여전히 지역적인 지형 불일치가 존재한다. 등록오차(registration noise)라고도 불리는 이러한 지형 불일치는 고해상도 다중시기 영상을 이용하여 공간정보를 추출하는 다양한 활용분야의 정확도를 떨어뜨리는 방해 요인으로 작용한다. 반대로, 등록오차를 추출하여 이를 효과적으로 제거한다면 결과적으로는 다중시기 고해상도 영상을 이용하여 추출되는 공간정보의 정확도를 높일 수 있다. 이에 본 연구에서는 지배적인 등록오차는 주로 영상 내 객체의 경계를 따라서 존재한다는 가정 하에, 경계강도 영상을 이용하여 등록오차를 추출한다. 추출된 등록오차의 지역적 분포특성을 고려하여 고해상도 영상 간 지형 불일치를 최소화하는 정밀 등록 기법을 제안한다. 제안 기법을 평가하기 위해, 고해상도 다중시기 광학위성 영상을 이용하여 실험지역을 구성한다. 등록오차 기반의 정밀 등록 기법 적용 결과와 수동으로 수행한 등록 결과와의 정량적/정성적 비교평가를 통해 제안 기법의 우수성을 판단하고자 한다.

Even after applying an image registration, Very High Resolution (VHR) multi-temporal images acquired from different optical satellite sensors such as IKONOS, QuickBird, and Kompsat-2 show a local misalignment due to dissimilarities in sensor properties and acquisition conditions. As the local misalignment, also referred to as Registration Noise (RN), is likely to have a negative impact on multi-temporal information extraction, detecting and reducing the RN can improve the multi-temporal image processing performance. In this paper, an approach to fine registration between VHR multi-temporal images by considering local distribution of RN is proposed. Since the dominant RN mainly exists along boundaries of objects, we use edge information in high frequency regions to identify it. In order to validate the proposed approach, datasets are built from VHR multi-temporal images acquired by optical satellite sensors. Both qualitative and quantitative assessments confirm the effectiveness of the proposed RN-based fine registration approach compared to the manual registration.

키워드

참고문헌

  1. Arevalo, V. and Gonzalez, J. (2008), Improving piecewise linear registration of high-resolution satellite images through mesh optimization, IEEE Transactions on Geoscience and Remote Sensing, Vol. 46, No. 11, pp. 3792-3803. https://doi.org/10.1109/TGRS.2008.924003
  2. Carson, C., Belongie, S. Greenspan H., and Malik, J. (2002), Blobworld: Image segmentation using expectationmaximization and its application to image querying, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 8, pp. 1026-1038. https://doi.org/10.1109/TPAMI.2002.1023800
  3. Goshtasby, A. (1986), Piecewise linear mapping functions for image registration, Pattern Recognition, Vol. 19, No. 6, pp. 459-466. https://doi.org/10.1016/0031-3203(86)90044-0
  4. Han, Y., Bovolo, F., and Bruzzone, L. (2015), An approach to fine coregistration between very-high-resolution multispectral images based on registration noise distribution, IEEE Transactions on Geoscience and Remote Sensing, Vol. 53, No. 12, pp. 6650-6662. https://doi.org/10.1109/TGRS.2015.2445632
  5. Han, Y., Bovolo, F., and Bruzzone, L. (2016), Edge-based registration-noise estimation in VHR multitemporal and multisensor images, IEEE Geoscience and Remote Sensing Letters, Vol. 13, No. 9, pp. 1231-1235. https://doi.org/10.1109/LGRS.2016.2577719
  6. Hu, H., Zhu, Q., Du, Z., Zhang, Y., and Ding, Y. (2015), Reliable spatial relationship constrained feature point matching of oblique aerial images, Photogrammetric Engineering and Remote Sensing, Vol. 81, No. 1, pp. 49-58. https://doi.org/10.14358/PERS.81.1.49
  7. Kim, Y. and Kim, Y. (2015), Evaluation on tie point extraction methods of WorldView-2 stereo images to analyze height information of buildings, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 33, No. 5, pp. 407-414. (in Korean with English abstract) https://doi.org/10.7848/ksgpc.2015.33.5.407
  8. Sedaghat, A. and Ebadi, H. (2015), Very high resolution image matching based on local features and k-means clustering, The Photogrammetric Record, Vol. 30, pp. 166-186. doi:10.1111/phor.12101.
  9. Wang, Z. and Bovik, A. C. (2009), Mean squared error: Love it or leave it? A new look at signal fidelity measures, IEEE Signal Processing Magazine, Vol. 26, No. 1, pp. 98-117. https://doi.org/10.1109/MSP.2008.930649
  10. Zitova, B. and Flusser, J. (2003), Image registration methods: a survey, Image and Vision Computing, Vol. 21, No. 11, pp. 977-1000. https://doi.org/10.1016/S0262-8856(03)00137-9