[논문]항공영상을 이용한 딥러닝 기반 건물객체 추출 기법들의 비교평가

모준상; 성선경; 최재완

doi:10.7848/ksgpc.2021.39.3.157

항공영상을 이용한 딥러닝 기반 건물객체 추출 기법들의 비교평가
Comparative evaluation of deep learning-based building extraction techniques using aerial images 원문보기

한국측량학회지 = Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, v.39 no.3, 2021년, pp.157 - 165

모준상 (Dept. of Civil Engineering, Chungbuk National University) , 성선경 (Dept. of Civil Engineering, Chungbuk National University) , 최재완 (Dept. of Civil Engineering, Chungbuk National University)

초록
AI-Helper

최근 위성영상, 항공사진 등의 해상도가 향상됨에 따라 고해상도 원격탐사 자료를 이용한 다양한 연구가 진행되고 있다. 특히, 국토 전역의 건물객체 추출은 수치지도 레이어 및 주제도 작성에 필수적이기 때문에 높은 정확도가 요구된다. 본 연구에서는 딥러닝의 영상처리 기법 중 의미론적 분할에 사용되는 대표적인 모델인 SegNet, U-Net, FC-DenseNet, HRNetV2를 이용하여 건물객체 추출 모델을 생성하고, 이에 따른 모델의 평가를 수행하였다. 학습자료는 다양한 건물들로 이루어진 영상을 이용하여 생성하였고, 평가는 세 지역에 나누어서 진행하였다. 먼저 학습자료와 인접한 지역을 통해 모델의 성능을 평가하였고, 이후 학습자료와 상이한 지역을 통해 모델의 적용성을 평가하였다. 그 결과 HRNetV2 모델이 건물객체 추출의 성능과 적용성 면에서 가장 우수한 결과를 보였다. 본 연구를 통해 수치지도 내 건물레이어 생성 및 수정의 가능성을 확인하였다.

Abstract ▼ AI-Helper

Recently, as the spatial resolution of satellite and aerial images has improved, various studies using remotely sensed data with high spatial resolution have been conducted. In particular, since the building extraction is essential for creating digital thematic maps, high accuracy of building extraction result is required. In this manuscript, building extraction models were generated using SegNet, U-Net, FC-DenseNet, and HRNetV2, which are representative semantic segmentation models in deep learning techniques, and then the evaluation of building extraction results was performed. Training dataset for building extraction were generated by using aerial orthophotos including various buildings, and evaluation was conducted in three areas. First, the model performance was evaluated through the region adjacent to the training dataset. In addition, the applicability of the model was evaluated through the region different from the training dataset. As a result, the f1-score of HRNetV2 represented the best values in terms of model performance and applicability. Through this study, the possibility of creating and modifying the building layer in the digital map was confirmed.

주제어

표/그림 (17)

그림 Fig. 1. Architecture of SegNet(Badrinarayanan et al., 2017)
그림 Fig. 2. Architecture of U-Net(Ronneberger et al., 2015)
그림 Fig. 3. Architecture of FC-DenseNet(Jegou et al., 2017)
그림 Fig. 4. Architecture of HRNetV2(Wang et al., 2020)
그림 Fig. 5. Study area from aerial imagery (a) image, (b) reference data (yellow box: training dataset, blue box: test dataset)
표 Table 1. Experimental conditions
표 Table 2. Hyperparameter for model training
그림 Fig. 6. Test dataset (a) image of site 3, (b) reference data of site 3
표 Table 3. Confusion matrix for evaluation of deep learning model
그림 Fig. 7. Building extraction results of site 1 (a) image, (b) reference data, (c) result by SegNet, (d) result by U-Net, (e) result by FC-DenseNet, (f) result by HRNetV2
그림 Fig. 8. Building extraction results of site 2 (a) image, (b) reference data, (c) result by SegNet, (d) result by U-Net, (e) result by FC-DenseNet, (f) result by HRNetV2
표 Table 4. Quantitative evaluation of site 1
표 Table 5. Quantitative evaluation of site 2
그림 Fig. 9. Building extraction results of site 3 (a) image, (b) reference data, (c) result by SegNet, (d) result by U-Net, (e) result by FC-DenseNet, (f) result by HRNetV2
그림 Fig. 10. Cropped images on building extraction results of site 3 (a) image, (b) reference data, (c) result by SegNet, (d) result by U-Net, (e) result by FC-DenseNet, (f) result by HRNetV2
표 Table 6. Quantitative evaluation of site 3
그림 Fig. 11. Cropped images on building extraction results of site 3 (a) image, (b) reference data, (c) result by SegNet, (d) result by U-Net, (e) result by FC-DenseNet, (f) result by HRNetV2

참고문헌 (16)

Badrinarayanan, V., Kendall, A., and Cipolla, R. (2017), SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 39, No. 12, pp.2481-2495.

상세보기
Chen, D.Y., Peng, L., Li, W.C., and Wang, Y.D. (2021), Building extraction and number statistics in WUI areas based on UNet structure and ensemble learning, Remote Sensing, Vol. 13, No. 6, pp. 1172.

상세보기
Cheng, Z. and Fu, D. (2020), Remote sensing image segmentation method based on HRNet, IEEE International Geoscience and Remote Sensing Symposium, pp. 6750-6753.
Huang, G., Liu, S., Van der Maaten, L., and Weinberger, K.Q. (2017), Densely connected convolutional networks, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261-2269.
Jegou, S., Drozdzal, M., Vazquez, D., Romero, A., and Bengio, Y. (2017), The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation, In proceedings of the IEEE Conference on Computer Vision and Patter Recognition Workshops, pp. 1175-1183.
Joo, G.H., Park, C.H., and Im, H.S. (2020), Performance evaluation of machine learning optimizers, Journal of Korean Electrical and Electronics Engineers, Vol. 24, No. 3, pp. 766-776. (in Korean with English abstract)
Kim, H.J., Kim, J.Y., and Kim, Y.I. (2019), A study on the object-based building extraction using UAV imagery, Journal of Korean Society for Geospatial Information Science, Vol. 27, No. 4, pp. 21-28. (in Korean with English abstract)

상세보기
Lee, D.G., Cho, E.J., and Lee, D.C. (2018), Evaluation of building detection from aerial images using region-based convolutional neural network for deep learning, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 36, No. 6, pp. 469-481. (in Korean with English abstract)

원문보기 상세보기
Pashaei, M., Kamangir, H., Starek, M.J., and Tissot, P. (2020), Review and evaluation of deep learning architectures for efficient land cover mapping with UAS hyper-spatial imagery: a case study over a wetland, Remote Sensing, Vol. 12, No. 6, pp. 959.

상세보기
Ronneberger, O., Fischer, P., and Brox, T. (2015), U-net: Convolutional networksfor biomedical image segmentation, International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, pp.234-241.
Seo, H.D. and Kim, E.M. (2020), Object classification and change detection in point clouds using deep learning, Journal of Cadastre & Land InformatiX, Vol. 50, No. 2, pp. 37-51. (in Korean with English abstract)

원문보기 상세보기
Seo, K.H., Oh, C.W., Kim, D., Lee, M.Y., and Yang, Y.J. (2019), An empirical study on automatic building extraction from aerial images using a deep learning algorithm, Proceedings of Korean Society for Geospatial Information Science, Vol. 2019, No. 5, pp. 243-252. (in Korean with English abstract)
Sun, K., Xiao, B., Liu, D., and Wang, J. (2019), Deep high-resolution representation learning for human pose estimation, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5686-5696.
Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., Liu, W., and Xiao, B. (2020), Deep high-resolution representation learning for visual recognition, In IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1.
Xu, Y., Wu, L., Xie, Z., and Chen, Z. (2018), Building extraction in very high resolution remote sensing imagery using deep learning and guided filters, Remote Sensing, Vol. 10, No. 1, pp. 144.

상세보기
Zhang, L., Wu, J., Fan, Y., Gao, H., and Chao, Y. (2020), An efficient building extraction method from high spatial resolution remote sensing images based on improved Mask R-CNN, Sensors, Vol. 20, No. 5, pp.1465.

상세보기

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