[논문]딥러닝에 의한 항공사진 구름 분류 및 탐지 비교 실험

송준영; 원태연; 조수민; 어양담; 박소영; 신상호; 박진수; 김창재

doi:10.7848/ksgpc.2021.39.6.409

딥러닝에 의한 항공사진 구름 분류 및 탐지 비교 실험
Comparative Experiment of Cloud Classification and Detection of Aerial Image by Deep Learning 원문보기

한국측량학회지 = Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, v.39 no.6, 2021년, pp.409 - 418

송준영 (Dept. of Advanced Technology Fusion, Konkuk University) , 원태연 (Dept. of Advanced Technology Fusion, Konkuk University) , 조수민 (Dept. of Advanced Technology Fusion, Konkuk University) , 어양담 (Dept. of Civil and Environmental Engineering, Konkuk University) , 박소영 (Geographic Information Division, National Geographic Information Institute, Ministry of Land, Infrastructure and Transport) , 신상호 (Geographic Information Division, National Geographic Information Institute, Ministry of Land, Infrastructure and Transport) , 박진수 (Project Development Division, ALLforLAND.Co.Ltd) , 김창재 (Dept. of Civil and Environmental Engineering, Myongji University,)

초록
AI-Helper

항공사진 촬영량이 증가함에 따라 품질검사 자동화의 필요성이 대두되고 있다. 본 연구에서는 딥러닝 기법으로 항공사진 내 구름을 분류 또는 탐지하는 실험을 수행하였고, 또한 위성영상을 학습자료에 포함시켜 분류 및 탐지를 수행하였다. 실험에 사용한 알고리즘으로는 GoogLeNet, VGG16, Faster R-CNN과 YOLOv3을 적용하여 결과를 비교하였다. 또한 구름이 포함된 오류영상 확보의 현실적 제한을 고려하여 항공영상만 존재하는 학습 데이터세트에서 위성영상을 활용한 추가학습이 분류 및 탐지정확도에 영향을 미치는지도 분석하였다. 실험결과, 항공사진의 구름 분류와 탐지에서 각각 GoogLeNet과 YOLOv3 알고리즘이 상대적으로 우월한 정확도를 나타냈고, GoogLeNet은 구름에 대한 생산자정확도 83.8% 그리고 YOLOv3는 구름에 대한 생산자정확도 84.0%를 보여주었다. 또한, 위성영상 학습자료 추가가 항공사진 자료의 부족 시 대안으로 적용가능 함을 보여주었다.

Abstract ▼ AI-Helper

As the amount of construction for aerial photography increases, the need for automation of quality inspection is emerging. In this study, an experiment was performed to classify or detect clouds in aerial photos using deep learning techniques. Also, classification and detection were performed by including satellite images in the learning data. As algorithms used in the experiment, GoogLeNet, VGG16, Faster R-CNN and YOLOv3 were applied and the results were compared. In addition, considering the practical limitations of securing erroneous images including clouds in aerial images, we also analyzed whether additional learning of satellite images affects classification and detection accuracy in comparison a training dataset that only contains aerial images. As results, the GoogLeNet and YOLOv3 algorithms showed relatively superior accuracy in cloud classification and detection of aerial images, respectively. GoogLeNet showed producer's accuracy of 83.8% for cloud and YOLOv3 showed producer's accuracy of 84.0% for cloud. And, the addition of satellite image learning data showed that it can be applied as an alternative when there is a lack of aerial image data.

주제어

표/그림 (8)

그림 Fig. 1. Object detection in experimental images (a) Object detection data labeling example, (b) Examples of detection results
그림 Fig. 2. Cloud object labeling in the image (a) Cloud object labeling example in aerial image, (b) Cloud object labeling example in Sentinel 2A MSIL1C image
표 Table 1. Number of images used for object detection and number of object labeling
그림 Fig. 3. Test data(examples of image by class) (a) An example of an image classified by cloud class, (b) An example of an image classified by non-cloud class
그림 Fig. 4. Classification results of case 2 in Table 2, (a) An image in which clouds exist is classified as a cloud image, (b) An image in which clouds exist but cannot be classified as a cloud image.
표 Table 2. Classification experiment result with satellite image learning data added
그림 Fig. 5. Object detection results of case 1 in Table 3, (a) Images in which clouds are detected in images with clouds, (b) Images in which clouds are detected in images without clouds
표 Table 3. Detection experiment result with satellite image learning data added

참고문헌 (26)

Cho, W., Lee, S.H., Choi, S.S., Hwang, H.D., and Lee, H.J. (2003), Quality Improvement on Aerial Photographs, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 21, No. 3, pp. 277-287. (in Korean with English abstract)
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014), Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 24-27 June, Columbus, Ohio, pp. 580-587.
He, K., Gkioxari, G., Dollar, P., and Girshick, R. (2017), Mask R-CNN, IEEE International Conference on Computer Vision (ICCV), 22-29 October, Venice, Italy, pp. 2961-2969.
He, K., Zhang, X., Ren, S., and Sun, J. (2015), Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, IEEE International Conference on Computer Vision (ICCV), 13-16 December, Santiago, Chile, pp. 1026-1034.
Kim, B.H., Kim, Y.H., Han, Y.K., Choi, W.S., and Kim, Y.I. (2014), Fully Automated Generation of Cloud-free Imagery Using Landsat-8, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 32, No. 2, pp. 133-142. (in Korean with English abstract)

원문보기 상세보기
Kim, B., Kim, G., Jin, S., and Cho, S. (2019), A Comparative Study on Performance of Deep Learning Models for Vision-based Concrete Crack Detection according to Model Types, Journal of the Korean Society of Safety, Vol. 34, No. 6, pp. 50-57. (in Korean with English abstract)

원문보기 상세보기
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012), ImageNet classification with deep convolutional neural networks, In Proceedings of NIPS, pp. 1106-1114.
Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998), Gradient-based learning applied to document recognition, IEEE, vol. 86, no. 11, pp. 2278-2324.

상세보기
Lee, M.H., Cheon, E.J., and Eo, Y.D. (2019), Cloud Detection and Restoration of Landsat-8 using STARFM, Korean Journal of Remote Sensing, Vol. 35, No. 5-2, pp. 861-871. (in Korean with English abstract)
Lee, J.O., and Sung, S.M. (2019), Quality Evaluation of UAV Images Using Resolution Target, Journal of the Korean Association of Geographic Information Studies, Vol. 22, No. 1, pp. 103-113. (in Korean with English abstract)

원문보기 상세보기
Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollar, P. 2017, Focal Loss for Dense Object Detection, IEEE International Conference on Computer Vision (ICCV), 2017, 22-29 October, Venice, Italy, pp. 2980-2988.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A. C. 2016, SSD: Single Shot MultiBox Detector, In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.), Computer Vision - ECCV 2016, Springer, Cham. pp. 21-37.
Liu, Z., Du, J., Tian, F., and Wen, J. (2019), MR-CNN: A Multi-Scale Region-Based Convolutional Neural Network for Small Traffic Sign Recognition, IEEE Access, vol. 7, pp. 57120-57128.

상세보기
Mittal, A., Moorthy, A.K., and Bovik, A.C. (2012), No-Reference Image Quality Assessment in the Spatial Domain, IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol. 21, No. 12, pp. 4695-4708.

상세보기
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016), You Only Look Once: Unified, Real-Time Object Detection, 29th IEEE Conference on Computer Vision and Pattern Recognition, 27-30 June, Las Vegas, Nevada, USA, pp. 779-788.
Redmon, J., and Farhadi, A. (2018), YOLOv3: An Incremental Improvement, arXiv, https://arxiv.org/abs/1804.02767 (last date accessed: 17 December 2021).
Ren, S., He, K., Girshick, R., and Sun, J. (2015), Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 6, pp. 1137-1149.

상세보기
Seong, S.K., Choi, S.K., and Choi, J.W., Cloud Detection of PlanetScope Imagery Based on Deeplab-V3+ by Using Transfer Learning, Journal of Korean Society for Geospatial Information Science, Vol. 28, No. 4, pp. 25-32. (in Korean with English abstract)

상세보기
Simonyan, K. and Zisserman, A. (2015), Very Deep Convolutional Networks For Large-Scale Image Recognition, Computer Vision and Pattern Recognition, Cornell University, Ithaca, NY, USA.
National Geographic Information Institute (2015), Data Quality for Aerial Photograph, NGII-STD.2015-7/2020, National Geographic Information Institute, Suwon, Korea.
Song, H.J., Lee, E.B., Jo, H.J., Park, S.Y., Kim, S.Y., Kim, H.J., and Hong, J.W. (2020), Evaluation of Classification and Accuracy in Chest X-ray Images using Deep Learning with Convolution Neural Network, Journal of the Korean Society of Radiology, Vol. 14, No. 1, pp. 39-44. (in Korean with English abstract)

원문보기 상세보기
Sun, L., Mi, X., Wei, J., Wang, J., Tian, X., Yu, H., and Gan, P. (2017), A cloud detection algorithm generating method for remote sensing data at visible to short-wave infrared wavelengths, ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 124, pp. 70-88.

상세보기
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015), Going Deeper with Convolutions, 2015 IEEE Conference on Computer Vision and Pattern Recognition, 7-12 June, Boston, MA, USA, pp. 1-9.
Zhang, H., Li, B., Zhang, J., and Xu, F. (2014), Aerial Image Series Quality Assessment, 35th International Symposium on Remote Sensing of Environment-2013, 22-26 April, Beijing, China, Vol. 17, pp. 012183.
Zhang, G.F., Wang, L., Zheng, Z.N., Chen, Y.F., Zhou, Z.B., and Zhao K. (2016), No-reference aerial image quality assessment based on natural scene statistics and color correlation blur metric, 13th International Conference on Transmission & Distribution Construction, Operation & Live-Line Maintenance, 21 August, Columbus, OH, USA, pp. 1-4.
Zeiler, M.D., and Fergus, R. (2014), Visualizing and understanding convolutional networks, In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.), ECCV 2014, Springer, Cham, vol. 8689, pp. 818-833.

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증