Phương pháp phát hiện dị thường trên ảnh viễn thám quang học ứng dụng trong công tác tìm kiếm cứu nạn

Nguyễn Văn Phương * , Cao Thị Vinh , Tống Minh Đức và Đào Khánh Hoài

* Tác giả liên hệ (phuongnv.dl@gmail.com)

Article Sidebar

Full Text: PDF

Ngày nhận bài: 20-08-2019
Ngày nhận bài sửa: 29-11-2019
Ngày duyệt đăng: 28-02-2020
Ngày xuất bản: 28-02-2020
Title: Methods to detect anomalies in optical remote sensing images for search and rescue
DOI: 10.22144/ctu.jvn.2020.003
Lượt xem
159
Downloads
72
Crossref
Scopus
Google Scholar
Europe PMC
Trích dẫn
Phương, N. V., Vinh, C. T., Đức, T. M., & Hoài, Đ. K. (2020). Phương pháp phát hiện dị thường trên ảnh viễn thám quang học ứng dụng trong công tác tìm kiếm cứu nạn. Tạp chí Khoa học Đại học Cần Thơ, 56(1), 21-36. https://doi.org/10.22144/ctu.jvn.2020.003
Số báo
Tập. 56 Số. 1 (2020)
Chuyên mục
Công nghệ thông tin

Abstract

Research on human survival after a plane crash shows that victims are 10% less likely to survive if the rescue is delayed by more than 2 days, and the survival rate is up to 60% if the rescue is made timely within 8 hours (Xuân Đông, 2014). The same urgency also applies to maritime emergency situations or on land. Therefore, the time to find victims and rescue organizations is a decisive factor for the success of that campaign. To reduce the search time, an increasingly commonly used approach is to detect anomalies in high-resolution remote sensing images. In addition, the size of the missing person or object of interest is very small compared to the scene and is easily mixed with the terrain. Therefore, it is necessary to have methods to automatically locate objects that help improve the performance and speed of searching. In this paper, several methods of detecting anomalies in remote sensing images will be presented to solve the problem mentioned above.
Keywords: Anomaly detection, hyperspectral images, multispectral images, remote sensing images, search and rescue

Tóm tắt

Nghiên cứu về khả năng sống sót của con người sau tai nạn máy bay cho thấy rằng, người bị nạn có khả năng sống sót nhỏ hơn 10% nếu việc cứu hộ bị trễ quá 2 ngày, và tỷ lệ sống sót lên tới 60% nếu việc cứu hộ được thực hiện kịp thời trong vòng 8 tiếng (Xuân Đông, 2014). Sự khẩn cấp tương tự cũng được áp dụng trong các tình huống cấp cứu hàng hải hay trên đất liền. Vì vậy, thời gian tìm ra người bị nạn và tổ chức giải cứu là nhân tố quyết định đến sự thành công của chiến dịch đó. Để giảm thời gian tìm kiếm, một cách tiếp cận ngày càng được sử dụng phổ biến là ứng dụng phát hiện dị thường trên ảnh viễn thám độ phân giải cao. Ngoài ra, kích thước của người mất tích hoặc vật cần quan tâm rất nhỏ so với cảnh và dễ dàng bị trộn lẫn với địa hình. Vì vậy, cần có các phương pháp tự động để định vị các đối tượng hỗ trợ nâng cao hiệu suất và tốc độ tìm kiếm. Trong bài báo này, một số phương pháp phát hiện dị thường trên ảnh viễn thám sẽ được trình bày để giải quyết vấn đề đã đề cập ở trên.
Từ khóa: Ảnh đa phổ, ảnh siêu phổ, ảnh viễn thám, phát hiện dị thường, tìm kiếm cứu nạn

Article Details

Tài liệu tham khảo

Xuân Đông, 2014. Tổ chức và hoạt động của Trung tâm VNMCC trong Tổ chức Cospas-Sarsat. Đài thông tin vệ tinh mặt đất Cospas-Sarsat Việt Nam, ngày truy cập 28/02/2020, địa chỉ https://vnmcc.vishipel.vn/index.aspx?page=detail&id=7400.

Nguyễn Văn Phương, Đào Khánh Hoài, 2018. Một số kỹ thuật phát hiện dị thường trên ảnh UAV ứng dụng cho công tác tìm kiếm cứu nạn. Các công trình nghiên cứu phát triển Công nghệ Thông tin và Truyền thông, V-1(39): 1-8.

Ashton, E. A., 1998. Detection of subpixel anomalies in multispectral infrared imagery using an adaptive Bayesian classifier. IEEE Trans. Geosci. Remote Sens., 36(2): 506-517.

Banerjee, A., Burlina, P., and Diehl, C., 2006. A support vector method for anomaly detection in hyperspectral imagery. IEEE Trans. Geosci. Remote Sens., 44(8): 2282-2291.

Bolukbasi, T., and Tran P., 2012. Outline color identification for search and rescue. Technical Reportof Department of Electrical and Computer Engineering, Boston University, No. ECE-2012-07.

CAP, 2004. The United States air force auxiliary civil air patrol. in factsheet, accessed on 28 February 2020. Available from http://www.cap.gov

Carlotto, M. J., 2005. A Cluster-Based Approach for Detecting Man-Made Objects and Changes in Imagery. IEEE Trans. Geosci. Remote Sens., 43(2): 374-387.

Chang, C-I., and Chiang, S-S., 2002. Anomaly Detection and Classification for Hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 40(6): 1314-1325.

Chang, C-I., 2003. Hyperspectral Imaging: Techniques for Spectral Detection and Classification. Springer Science and Business Media, 370 pages.

Chang, Ch-I., Ren, H., and Chiang, Sh-Sh., 2001. Real-Time Processing Algorithms for Target Detection and Classification in Hyperspectral Imagery. IEEE Transactions on Geoscience and Remote Sensing, 39(4): 760-768.

Chang, S-S., Chang, C-I., and Ginsberg, I. W., 2001. Unsupervised Target Detection in Hyperspectral Images Using Projection Pursuit. IEEE Trans. Geosci. Remote Sens., 39(7): 1380-1391.

Chang, C.-I., Xiong, W., and Wen, C.-H., 2014. A Theory of High-Order Statistics-Based Virtual Dimensionality for Hyperspectral Imagery. IEEE Transactions on Geoscience and Remote Sensing, 52(1): 188-208.

Chen, J. Y., and Reed, I. S., 1987. A Detection Algorithm for Optical Targets in Clutter. IEEE Transactions on Aerospace and Electronic Systems, AES-23(1): 46-59.

Chen, Y., Nasrabadi, N. M., and Tran, T. D., 2011a. Simultaneous joint sparsity model for target detection in hyperspectral imagery. IEEE Geosci. Remote Sens. Lett., 8(4): 676–680.

Chen, Y., Nasrabadi, N. M., and Tran, T. D., 2011b. Hyperspectral image classification via kernel sparse representation. in Proc. IEEE Int. Conf. Image Process., Brussels, Belgium: 1233–1236.

Corbane, C., Najman, L., and Pecoul, E., 2010. A complete processing chain for ship detection usingoptical satellite imagery. International Journal of Remote Sensing, 31(22): 5837–5854.

Du, Q., and Kopriva, I., 2008. Automated Target Detection and Discrimination Using Constrained Kurtosis Maximization. IEEE Geosci. Remote Sens. Letters, 5(1):38-42.

Du, B., and Zhang, L., 2011. Random-Selection-Based Anomaly Detector for Hyperspectral Imagery. IEEE Transactions on Geoscience and Remote Sensing, 49(5): 1578-1589.

Duran, O., Petrou, M., Hathaway, D., and Nothard, J., 2006. Anomaly Detection Through Adaptive Background Class Extraction FromDynamic Hyperspectral Data. Proc. IEEE Nordic Sig. Proc. Conf.: 234-237.

Duran, O., and Petrou, M., 2007. A Time-Efficient Method for Anomaly Detection in Hyperspectral Images. IEEE Trans. Geosci. Remote Sens., 45(12): 3894-3904.

Duran, O., and Petrou, M., 2005. A time-efficient clustering method for pure class selection. Proc. IEEE Int. Geosci. Remote Sens. Symp., 1: 510-513.

Eismann, M. T., Meola, J., and Hardie, R. C., 2008. Hyperspectral change detection in the presence of diurnal and seasonal variations. IEEE Transactions on Geoscience and Remote Sensing, 46: 237–249.

Ettabaa K. S., and Salem M. B. 2019. Anomaly detection in hyperspectral imagery: an overview. In Environmental Information Systems: Concepts, Methodologies, Tools, and Applications, 1587-1606.

Gao, F., Li, B., Xu, Q., and Zhong, C., 2014. Moving Vehicle Information Extraction from Single-Pass WorldView-2 Imagery Based on ERGAS-SNS Analysis. Remote Sensing.

Grahn, H., and Geladi, P., 2007. Techniques and Applications of Hyperspectral Image Analysis. John Wiley & Sons.

Grossman, S. I., 2014. An automated directed spectral search methodology for small target detection. ProQuest Dissertations AndTheses; Thesis (Ph.D.), George Mason University, Virginia.

Gu, Y., Liu, Y., and Zhang, Y., 2008. A selective KPCA algorithm based on high-order statistics for anomaly detection in hyperspectral imagery. IEEE Geoscience and Remote Sensing Letters, 5(1): 43-47.

Guo, Q., Zhang, B., Ran, Q., Gao, L., Li, J., and Plaza, A., 2014. Weighted-RXD and linear filter-based RXD: improving background statistics estimation for anomaly detection in hyperspectral imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2351-2366.

Gurram, P., and Kwon, H., 2011. Support-vector-based hyperspectral anomaly detection using optimized kernel parameters. IEEE Geoscience and Remote Sensing Letters, 8(6): 1060–1064.

Harris, T., Streett, D., Belge, J., Ramirez, E., Jankot, J., Vogt, J., Hulslander, D., and Kamphaus, B., 2012. Spectral target detection for detecting and characterizing floating marine debris. American Geophysical Union Fall Meeting.

Harsanyi, J. C., 1993. Detection and classification of subpixel spectral signatures in hyperspectral image sequences. Rapport de doctorat, Universit de Maryland Baltimore County.

Hazel, G. H., 2000. Multivariate Gaussian MRF for multispectral scene segmentation and anomaly detection. IEEE Trans. Geosci. Remote Sens., 38(3): 1199-1211.

Healey, G., and Slater, D., 1999. Models and methods for automated material identification in hyperspectral imagery acquired under unknown illumination and atmospheric conditions. IEEE Transactions on Geoscience and Remote Sensing, 37(11): 2706-2717.

Hou Z., Chen Y., Tan K. and Du P., 2018. Novel hyperspectral anomaly detection methods base on unsupervised nearest regularized subspace. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-3: 539-546.

Hyvrinen, A., and Oja, E., 2000. Independent component analysis: algorithms and applications. Neural Networks, Elsevier Science Ltd. Oxford, UK, 13(4-5): 411-430.

Hytla, P., Hardie, R. C., Eismann, M. T., and Meola, J., 2007. Anomaly detection in hyperspectral imagery: A comparison of methods using seasonal data. Proceedings of SPIE - The International Society for Optical Engineering, 2(1): 656506-1-11.

Hyvärinen, A., and Oja, E., 2000. Independent component analysis: algorithms and applications. Neural Networks, 13: 411-430.

Huber, P. J., 1985. Projection Pursuit. Ann. Statist., 13(2): 435-475.

Imani M., 2018. 3D Gabor based hyperspectral anomaly detection. AUT Journal of Modeling and Simulation, 50(2): 189-194.

Ifarraguerri, A., and Chang, C-I., 2000. Unsupervised hyperspectral image analysis with projection pursuit. IEEE Trans. Geosci. Remote Sens., 38(6): 2529-2538.

Kwon, H., Der, S. Z., and Nasrabadi, N. M., 2003. Adaptive anomaly detection using subspace separation for hyperspectral imagery. Opt. Eng., 42(11): 3342-3351.

Kwon, H., and Nasrabadi, N.M., 2005. Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery. IEEE Trans. Geosci. Remote Sens., 43(2): 388-397.

Lehmann, E. L., 1993. The Fisher, Neyman-Pearson theories of testing hypotheses: One theory or two?.Journal of the American Statistical Association, 88(424): 1242-1249.

Li, W., Du, Q, 2014. Unsupervised nearest regularized subspace for anomaly detection in hyperspectral imagery. In Proceedings of the Geoscience and Remote Sensing Symposium, Melbourne, Australia, 21–26 July 2014: 1055–1058.

Li F., Zhang X., Zhang L., Jiang D., and Zhang Y. 2018. Exploiting structured sparsity for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 56(7): 4050-4064.

Liu, W., and Chang, C.-I, 2004. A nested spatial window-based approach to target detection for hyperspectral imagery. Proceedings. IEEE International Geoscience and Remote Sensing Symposium, IGARSS’04, 1.

Li, W., Prasad, S., and Fowler, J. E., 2013. Integration of spectral–spatial information for hyperspectral image reconstruction from compressive random projections. IEEE Geoscience and Remote Sensing Letters, 10(6): 1379-1383.

Li, W., and Du, Q., 2015. Collaborative representation for hyperspectral anomaly detection. IEEE Trans. Geosci. Remote Sens., 53(3):1463–1474.

Li, W., Wu, G., & Du, Q. 2017. Transferred deep learning for anomaly detection in hyperspectral imagery. IEEE Geoscience and Remote Sensing Letters, 14(5): 597-601.

Liu, W-M., and Chang, Ch-I., 2013. Multiple-window anomaly detection for hyperspectral imagery. Selected Topics in IEEE Journal of Applied Earth Observations and Remote Sensing, 6(2): 644-658.

Ma D., Yuan Y. and Wang Q., 2018. Hyperspectral anomaly detection via discriminative feature learning with multiple-dictionary sparse representation. Remote Sensing, 10(5): 745.

Ma, N., Peng, Y., Wang, S., and Leong P.H.W. 2018. An unsupervised deep hyperspectral anomaly detector. Sensors (Basel), 18(3): 693.

Manolakis, D., and Shaw, G., 2002a. Detection algorithms for hyperspectral imaging applications. IEEE Signal Process. Mag., 19: 29–43.

Marshall, T., and Perkins, L. N., 2015. Color outline detection for search and rescue. Technical Reportof Department of Electrical and Computer Engineering, Boston University, No. ECE-2015-01.

Manolakis, D., 2005. Taxonomy of detection algorithms for hyperspectral imaging applications. Optical Engineering, 44(6): 066403 1-11.

Manolakis, D., Marden, D., and Shaw, G. A., 2003. Hyperspectral image processing for automatic target detection applications. IEEE Signal Process. Mag., 14(1): 79-116.

Mas, J. F., 1999. Monitoring land-cover changes: A comparison of change detection techniques. Int. J. Remote Sens., 20(1):139–152.

Matteoli, S., Veracini, T., Diani, M., and Corsini, G., 2013. A locally adaptive background density estimator: an evolution for rx-based anomaly detectors. IEEE Geoscience and Remote Sensing Letters, 11(1): 323-327.

Matteoli, S., Veracini, T., Diani, M., and Corsini, G., 2014. Background density nonparametric estimation with data-adaptive bandwidths for the detection of anomalies in multi-hyperspectral imagery. IEEE Geoscience and Remote Sensing Letters, 11: 163 - 167.

Meng, L. and Kerekes, J. P., 2012. Object tracking using high resolution satellite imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5: 146 - 152.

Molero, J.M., Garzon, E.M., Garcia, I., and Plaza, A., 2013. Analysis and optimizations of global and local versions of the rx algorithm for anomaly detection in hyperspectral data. Selected Topics in IEEE Journal of Applied Earth Observations and Remote Sensing, 6(2): 801-814.

Nasrabadi, N. M., 2007. Penalized spectral matched filter for target detection in hyperspectral imagery. Proc.IEEE International Geosci. Remote Sens. Symp.: 4830-4833.

Penn, B., 2002. Using self-organizing maps for anomaly detection in hyperspectral imagery. Proc. IEEE Aerosp. Conf., 3: 1531-1535.

Parzen, E., 1962. On the estimation of a probability density function and mode. Ann. Math. Stat., 33.

Ramachandran, M., and Moik W., 2013. Outline color identification for search and rescue. Technical Reportof Department of Electrical and Computer Engineering, Boston University, No. ECE-2013-03.

Reed, I. S., and Yu, X., 1990. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution. IEEE Trans. Acoust. Speech Signal Process., 38(10): 1760-1770.

Ren, H., Du, Q., Wang, J., Chang, Ch-I., Jensen, J. O., and Jensen, J. L., 2006. Automatic target recognition for hyperspectral imagery using high-order statistics. IEEE Transactions on Aerospace and Electronic Systems, 42(4): 1372-1385.

Salem, M. B., Ettabaa, K. S., and Hamdi, M. A., 2014. Anomaly detection in hyperspectral imagery: an overview. International Image Processing, Applications and Systems Conference: 1-6.

School, N. P., 2012. Detection of subpixel submerged mine – like targets in worldview-2 multispectral imagery. Monterey, California.

Schowengerdt, R. A., 2007. Remote sensing: Models and methods for image processing. Academic Press, 3rd ed.

Schweizer, S. M., and Moura, J. M. F., 2000. Hyperspectral imagery: clutter adaptation in anomaly detection. IEEE Trans. Geosci. Remote Sens., 46(5): 1855-1871.

Schölkopf, B., and Smola, A. J., 2001a. Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press, accessed on 28 February 2020. Available from http://www.learning-with-kernels.org/.

Schölkopf, B., Platt, J. C., Shawe-Taylor, J., A. Smola, J., and Williamson, R. C., 2001b. Estimating the support of a high dimensional distribution. Neural Computation, 13: 1443-1471.

Schweizer, S. M., and Moura, J. M. F., 2000. Efficient detection in hyperspectral imagery, IEEE Trans. Geosci. Remote Sens., 10(4): 584-597.

Singh, A., 1989. Digital change detection techniques using remotely sensed data. Int. J. Remote Sens., 10(6): 989–1003.

Smetek, T. E., and Bauer, K. W., 2007. Finding hyperspectral anomalies using multivariate outlier detection. Aerospace Conference.

Stevenson, B., O’Connor, R., Kendall, W., Stocker, A., Schaff, W., Alexa, D., Salvador, J., Eismann, M., Barnard, K., and Kershenstein, J., 2005. Design and performance of the civil air patrol ARCHER hyperspectral processing system. in Proc. SPIE, 5806: 731–742.

Stellman, C. M., Hazel, G. G., Bucholtz, F., and Michalowicz, J. V., 2000. Real-time hyperspectral detection and cuing. Opt. Eng., 39(7): 1928-1935.

Stein, D. W. J., Beaven, S. G., Hoff, L. E., Winter, E. M., Schaum, A. P., and Stocker, A. D., 2002. Anomaly detection from hyperspectral imagery. IEEE Signal Process. Mag., 19(1): 58-69.

Suen, P-H., Healy, G., and Slater, D., 2001. The impact of viewing geometry on material discriminability in hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 39(7): 352-358.

Tan K., Hou Z., Wu F., Du Q. and Chen Y., 2019. Anomaly detection for hyperspectral imagery based on the regularized subspace method and collaborative representation. Remote Sensing, 11(11): 138.

Tax, D. M. J., and Duin, R. P. W., 1999. Support vector domain description. Pattern Recognition Letters, 20: 1191-1199.

Tax, D. M. J., and Duin, R. P. W., 2004. Support vector data description. Machine Learning, 54(1): 45-66.

Vafadar M. and Ghassemian H., 2018. Anomaly detection of hyperspectral imagery using modified collaborative representation. IEEE Geoscience and Remote Sensing Letters, 15(4): 577 – 581.

Veracini, T., Matteoli, S., Diani, M., and Corsini, G., 2011a. Nonparametric framework for detecting spectral anomalies in hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 8(4): 666-670.

Veracini, T., Matteoli, S., Diani, M., and Corsini, G., 2011b. An anomaly detection architecture based on a data-adaptive density estimation. In Proceedings of 2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). Lisbon: IEEE.

Xiong J., Ling Q., Lin Z. and Wu J., 2018. Kernel sparse representation for anomaly detectionin in hyperspectral imagery. International Conference on Advances in Image Processing (ICAIP'18), June 16–18, 2018, Chengdu, China: 106-110.

Xu, Y., Wu, Z., Li, J., Plaza, A., and Wei, Z., 2016. Anomaly detection in hyperspectral images based on low-rank and sparse representation. IEEE Transactions on Geoscience and Remote Sensing, 54(4): 1990-2000.

Yuan, Z., Sun, H., Ji, K., Li, Zh., and Zou, H., 2014. Local sparsity divergence for hyperspectral anomaly detection. IEEE Geoscience and Remote Sensing Letters, 11(10): 1697-1701.

Yan L., Yamaguchi M., Noro N., Takara Y., and Ando F. 2019. A novel two-stage deep learning-based small-object detection using hyperspectral images. Optical Review, 1-10.

Zitova, B., and Flusser, J., 2003. Image registration methods: A survey. Image Vision Comput., 21(11), 977–1000.

Zhang L. and Cheng B. 2019. A stacked autoencoders-based adaptive subspace model for hyperspectral anomaly detection. Infrared Physics & Technology, 96: 52–60.

Zhao, C., Wang, X., and Zhao, G., 2017. Detection of hyperspectral anomalies using density estimation and collaborative representation. Remote Sensing Letters, 8(11): 1025–1033.

Wallacea, R. G., Affensa, D. W., and McCandless, S. W., 1998. Search and rescue from space. Part of the SPIE Conference on Automatic Target Recognition VIII, 3371: 174-184.

Wu Y., López S., Zhang B., Qiao F., and Gao L. 2019. Approximate computing for onboard anomaly detection from hyperspectral images. Journal of Real-Time Image Processing, 16(1): 99-114.