基于馬爾科夫分割的單極化SAR數(shù)據(jù)洪澇水體檢測方法
doi: 10.11999/JEIT180420
-
1.
中國科學(xué)院大學(xué) ??北京 ??100049
-
2.
中國科學(xué)院電子學(xué)研究所 ??北京 ??100190
-
3.
中國科學(xué)院空間信息處理與應(yīng)用系統(tǒng)技術(shù)重點實驗室 ??北京 ??100190
Single-polarization SAR Data Flood Water Detection Method Based on Markov Segmentation
-
1.
University of Chinese Academy of Sciences, Beijing 100049, China
-
2.
Insititute of Electronics, Chinese Academy of Sciences, Beijing 100190, China
-
3.
Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing 100190, China
-
摘要:
我國是個洪澇災(zāi)害多發(fā)的國家,每年7月、8月份洪澇災(zāi)害時常發(fā)生。因此,實現(xiàn)洪澇受災(zāi)區(qū)域的水體快速檢測對災(zāi)害救援和評估具有重要的意義。高分3號SAR衛(wèi)星數(shù)據(jù)采用主動式對地觀測技術(shù),全天時、全天候成像的特點在洪澇減災(zāi)應(yīng)用中具有明顯的優(yōu)勢。以湖南省洪澇災(zāi)害區(qū)域快速檢測為目的,該文提出基于高分3號單極化SAR數(shù)據(jù)的洪澇區(qū)域水體快速檢測方法,包括SAR預(yù)處理,顧及SAR分布特性且保邊緣的馬爾科夫模型洪澇水體提取,基于SAR幾何構(gòu)象模型的陰影虛警干擾去除等步驟,并利用人工檢測結(jié)果進(jìn)行相對精度評價。測試結(jié)果表明,所提方法可以實現(xiàn)洪澇受災(zāi)區(qū)域的快速、精確提取。
-
關(guān)鍵詞:
- SAR /
- 高分3號衛(wèi)星 /
- 馬爾科夫隨機場 /
- 洪澇 /
- 減災(zāi)
Abstract:China is a flood disaster-prone country, where floods occur frequently every year, from July to August. Therefore, rapid disaster detection and assessment of floods affected areas is of great significance. GF-3 SAR satellite data has obvious advantages of all-day, all-weather imaging characteristics in flood disaster reduction applications because of its active observation technology. For the purpose of rapid water detection in flooding area, a rapid detection method of flood area based on GF-3 single-polarized SAR data is proposed, including SAR preprocessing, flood extraction based on Markov random fields, shadow false alarm removal. Its detecting accuracy is evaluated with manual detection result. The test results show that this method can realize the rapid and accurate extraction of waters in flood disaster area.
-
Key words:
- SAR /
- GF-3 /
- Markov Random Field (MRF) /
- Flood disaster /
- Disaster reduction
-
表 1 災(zāi)區(qū)水體自動提取結(jié)果質(zhì)量分析(%)
數(shù)據(jù)區(qū)域 正確率 精確率 召回率 湖南岳陽 99 88 75 湖南懷化 99 81 78 下載: 導(dǎo)出CSV
表 2 災(zāi)區(qū)水體自動提取效率分析(s)
計算
硬件生成
1B轉(zhuǎn)換
8位一致性
濾波受災(zāi)區(qū)域
提取去除
陰影地理
編碼總時間 4核CPU 1 1 713 2 43 2 762 8核CPU 1 1 218 1 15 1 237 36核CPU 1 1 55 1 8 1 67 64核CPU 1 1 27 1 5 1 36 下載: 導(dǎo)出CSV
-
張慶君. 高分3號衛(wèi)星總體設(shè)計與關(guān)鍵技術(shù)[J]. 測繪學(xué)報, 2017, 46(3): 269–277. doi: 10.11947/j.AGCS.2017.20170049ZHANG Qingjun. System design and key technologies of the GF-3 satellite[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(3): 269–277. doi: 10.11947/j.AGCS.2017.20170049 張薇, 楊思全, 王磊, 等. 合成孔徑雷達(dá)數(shù)據(jù)減災(zāi)應(yīng)用潛力研究綜述[J]. 遙感技術(shù)與應(yīng)用, 2012, 27(6): 904–911.ZHANG Wei, YANG Siquan, WANG Lei, et al. Review on disaster reduction application potentiality of synthetic aperture radar[J]. Remote Sensing Technology and Application, 2012, 27(6): 904–911. 胡德勇. 遙感技術(shù)在防災(zāi)減災(zāi)中的應(yīng)用[J]. 高科技與產(chǎn)業(yè)化, 2013, 3(11): 44–47.HU Deyong. Application of remote sensing technology in disaster prevention and mitigation[J]. High-Technology and Industrialization, 2013, 3(11): 44–47. 鄧瀅, 張紅, 王超, 等. 結(jié)合紋理與極化分解的面向?qū)ο髽O化SAR水體提取方法[J]. 遙感技術(shù)與應(yīng)用, 2016, 31(4): 714–723.DENG Ying, ZHANG Hong, WANG Chao, et al. An Object-oriented water extraction method based on texture and polarimetric decomposition feature[J]. Remote Sensing Technology and Application, 2016, 31(4): 714–723. 周廣益, 鐘華, 楊健. 基于負(fù)指數(shù)變換和 Mean-shift 算法的 SAR 圖像可視化方法[J]. 清華大學(xué)學(xué)報: 自然科學(xué)版, 2011, 51(7): 983–987. doi: 10.12000/JR17024ZUOU Guangyi, ZHONG Hua, and YANG Jian. Visualization method for SAR images based on a negative exponential transformation and mean-shift algorithm[J]. Journal of Tsinghua University(Science and Technology) , 2011, 51(7): 983–987. doi: 10.12000/JR17024 YU Y and ACTION S T. Spcckle reducing anisotropic diffusion[J]. IEEE Transactions on image processing, 2002, 11(11): 1260–1270. doi: 10.1109/TIP.2002.804276 王峰, 尤紅建. 基于級聯(lián)變換的光學(xué)和SAR圖像配準(zhǔn)算法[J]. 紅外與毫米波學(xué)報, 2015, 34(4): 486–492. doi: 10.11972/j.issn.1001-9014.2015.04.18WANG Feng and YOU Hongjian. Robust registration method of SAR and optical remote sensing Images based on cascade transforms[J]. Journal of Infrared and Millimeter Waves, 2015, 34(4): 486–492. doi: 10.11972/j.issn.1001-9014.2015.04.18 BLASCHKE T, HAY G J, KELLY M, et al. Geographic object-based image analysis-towards a new paradigm[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2014, 87(1): 180–191. doi: 10.11972/j.issn.1001-9014.2015.04.18 BENZ U C, HOFMANN P, WILLHAUCK G, et al. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2011, 58(3): 239–258. YU Q and CLAUSI D A. IRGS: Image segmentation using edge penalties and region growing[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2008, 30(12): 2126–2139. 丁赤飚, 劉佳音, 雷斌, 等. 高分3號SAR衛(wèi)星系統(tǒng)級幾何定位精度初探[J]. 雷達(dá)學(xué)報, 2017, 6(1): 11–16. doi: 10.12000/JR17024DING Chibiao, LIU Jiayin, LEI Bin, et al. Preliminary exploration of systematic geolocation accuracy of GF-3 SAR satellite system[J]. Journal of Radars, 2017, 6(1): 11–16. doi: 10.12000/JR17024 -