MMS로부터 취득된 LiDAR 점군데이터의 반사강도 영상과 UAV 영상의 정합을 위한 특징점 기반 매칭 기법 연구 = Feature-based Matching Algorithms for Registration between LiDAR Point Cloud Intensity Data Acquired from MMS and Image Data from UAV

다국어 초록 (Multilingual Abstract)

Recently, as the demand for 3D geospatial information increases, the importance of rapid and accurate data construction has increased. Although many studies have been conducted to register UAV (Unmanned Aerial Vehicle) imagery based on LiDAR (Light Detection and Ranging) data, which is capable of precise 3D data construction, studies using LiDAR data embedded in MMS (Mobile Mapping System) are insufficient. Therefore, this study compared and analyzed 9 matching algorithms based on feature points for registering reflectance image converted from LiDAR point cloud intensity data acquired from MMS with image data from UAV. Our results indicated that when the SIFT (Scale Invariant Feature Transform) algorithm was applied, it was able to stable secure a high matching accuracy, and it was confirmed that sufficient conjugate points were extracted even in various road environments. For the registration accuracy analysis, the SIFT algorithm was able to secure the accuracy at about 10 pixels except the case when the overlapping area is low and the same pattern is repeated. This is a reasonable result considering that the distortion of the UAV altitude is included at the time of UAV image capturing. Therefore, the results of this study are expected to be used as a basic research for 3D registration of LiDAR point cloud intensity data and UAV imagery.

국문 초록 (Abstract)

최근 3차원 공간정보에 대한 수요가 증가함에 따라 신속하고 정확한 데이터 구축의 중요성이 증대되어 왔다. 정밀한 3차원 데이터 구축이 가능한 LiDAR (Light Detection and Ranging) 데이터를 기준으로 UAV (Unmanned Aerial Vehicle) 영상을 정합하기 위한 연구가 다수 수행되어 왔으나, MMS (Mobile Mapping System)로부터 취득된 LiDAR 점군데이터의 반사강도 영상을 활용한 연구는 미흡한 실정이다. 따라서 본 연구에서는 MMS로부터 취득된 LiDAR 점군데이터를 반사영상으로 변환한 데이터와 UAV 영상 데이터의 정합을 위해 9가지의 특징점 기반 매칭 기법을 비교·분석하였다. 분석 결과 SIFT (Scale Invariant Feature Transform) 기법을 적용하였을 때 안정적으로 높은 매칭 정확도를 확보할 수 있었으며, 다양한 도로 환경에서도 충분한 정합점을 추출할 수 있었다. 정합 정확도 분석 결과 SIFT 알고리즘을 적용한 경우 중복도가 낮으며 동일한 패턴이 반복되는 경우를 제외하고는 약 10픽셀 수준으로 정확도를 확보할 수 있었으며, UAV 영상 촬영 당시 UAV 자세에 따른 왜곡이 포함되어 있음을 감안할 때 합리적인 결과라고 할 수 있다. 따라서 본 연구의 분석 결과는 향후 LiDAR 점군데이터와 UAV 영상의 3차원 정합을 위한 기초연구로 활용될 수 있을 것으로 기대된다.

참고문헌 (Reference)

1 박시영, "특징점 추적을 통한 다수 영상의 고속 스티칭 기법" 한국방송∙미디어공학회 20 (20): 728-737, 2015

2 Vedaldi, A., "VLfeat: An open and portable library of computer vision algorithms" 25-29, 2010

3 Hong, S., "Utilization of a terrestrial laser scanner for the calibration of mobile mapping systems" 17 (17): 24-, 2017

4 Guan, H., "Using mobile laser scanning data for automated extraction of road markings" 87 : 93-107, 2014

5 Kim, M., "The Study on Road Extraction Using LiDAR Data" Inha University 2005

6 Matas, J., "Robust wide-baseline stereo from maximally stable extremal regions" 22 : 761-767, 2004

7 Li, Q., "Robust scaleinvariant feature matching for remote sensing image registration" 6 (6): 287-291, 2009

8 Fischler, M. A., "Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography" 24 (24): 381-395, 1981

9 Peng, W. H., "Performance comparison of image keypoint detection, description, and matching methods" 1-2, 2016

10 Moravec, H., "Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover" Stanford University 1980

11 Rosten, E., "Machine learning for high speed corner detection" 1 : 430-443, 2006

12 Commercializations Promotion Agency for R&D Outcomes(COMPA), "LiDAR Technology and Market Trends, S&T Market Report, Vol. 54" 16-, 2017

13 Alcantarilla, P. F., "KAZE features" Springer 214-227, 2012

14 Lindeberg, T., "Image matching using generalized scalespace interest points" 52 (52): 3-36, 2015

15 Shi, J., "Good Features to Track" CVPR 1994

16 Park, J., "Framework for automated registration of UAV and UGV point clouds using local features in images" 98 : 175-182, 2019

17 Nho, H., "Fast Geocoding Processing for Low-cost Unmanned Aerial Vehicle Imagery" Yonsei University 2018

18 Kim, S., "FAST and BRIEF based real-time feature matching algorithms" 1-4, 2012

19 Miksik, O., "Evaluation of local detectors and descriptors for fast feature matching" 2681-2684, 2012

20 Schmind, C., "Evaluation of interest point detectors" 37 (37): 151-172, 2000

21 Lowe, D., "Distinctive image features from scaleinvariant keypoints" 60 (60): 91-110, 2004

22 Verma, S. B., "Comparative Study of FAST MSER and Harris for Palmprint Verification System" 7 (7): 855-858, 2016

23 Persad, R. A., "Co-registration of DSMs generated by UAV and terrestrial laser scanning systems, The International Archives of Photogrammetry" XLI-B1 : 985-990, 2016

24 Kim, T., "Automatic satellite image registration by combination of matching and random sample consensus" 41 (41): 1111-1117, 2003

25 Abayowa, B. O., "Automatic registration of optical aerial imagery to a LiDAR point cloud for generation of city models" 106 : 68-81, 2015

26 Yang, B., "Automatic registration of UAVborne sequent images and LiDAR data" 101 : 262-274, 2015

27 Böhm, J., "Automatic marker-free registration of terrestrial laser scans using reflectance" 9-12, 2007

28 Palenichka, R. M., "Automatic extraction of control points for the registration of optical satellite and LiDAR images" 48 (48): 2864-2879, 2010

29 Abedini, A., "An investigation into the registration of LiDAR intensity data and aerial images using the SIFT approach" XXXVII : 169-176, 2008

30 Conte, G., "An integrated UAV navigation system based on aerial image matching" IEEE 1-10, 2008

31 Tsai, C. H., "An accelerated image matching technique for UAV orthoimage registration" 128 : 130-145, 2017

32 Fernandez, J. C., "An Overview of Lidar Point Cloud Processing Software" University of Florida 27-, 2007

33 Mikolajczyk, K., "A performance evaluation of local descriptors" 27 : 1615-1630, 2005

34 Liu, S., "A linear feature-based approach for the registration of unmanned aerial vehicle remotely-sensed images and airborne LiDAR data" 8 (8): 15-, 2016

35 Tareen, S. A. K., "A comparative analysis of sift, surf, kaze, akaze, orb, and brisk" 1-10, 2018

36 Harris, C. G., "A combined corner and edge detector" 15 (15): 10-5244, 1988

37 Mikolajczyk, K., "A Comparison of Affine Region Detectors" 65 : 43-72, 2005