基于光谱特征的拉萨市人造地表遥感提取研究

doi:10.3964/j.issn.1000-0593(2025)04-1061-10

摘要
参考文献
相关文章 (15)

全文: PDF (22400 KB)
输出: BibTeX | EndNote (RIS)

摘要：青藏高原在全球生态系统中占重要地位；拉萨市作为其核心城市，在研究平衡城市发展水平与生态系统服务能力方面具有代表意义。该研究在谷歌地球引擎(GEE)云平台，使用Sentinel-2、VIIRS、SRTM遥感影像数据，基于光谱结合地形、纹理等特征信息，分别通过基于像元(PB)与面向对象(OO)分类方法对拉萨市人造地表覆盖进行提取。使用基于像元/面向对象，是否加入纹理特征，随机森林(RF)/支持向量机(SVM)分类器三组对比方法各部分表现效果。结果表明：基于相同光谱特征，在OO方法中不使用纹理特征参与RF分类器分类(OO_RF)，可获得最佳的提取结果，其总体精度(OA)为98.03%，Kappa系数(KC)为0.9520，用户精度(UA)为94.44%，生产者精度(PA)为98.84%。纹理特征在人造地表提取中作用效果较弱，仅在基于像素方法中有微弱提升，使用RF分类器(PB_RF)时OA提升0.51%；使用SVM分类器(PB_SVM)时OA提升0.68%。RF分类器在本研究中表现最佳，能够避免高估，更准确地识别城市内部非人造地表覆盖。本研究提供了提取生态城市人造地表覆盖信息的方法及参数，为进一步进行动态监测及分析提供了数据，具有实际应用意义。

关键词：面向对象；基于像元；光谱特征；谷歌地球引擎；人造地表

Abstract：The Qinghai-Tibet Plateau holds a crucial position in the global ecosystem. As its core city, Lhasa City stands as a representative focal point for studying the delicate balance between urban development levels and ecosystem service capacities. This study was conducted on the Google Earth Engine (GEE) cloud platform, utilizing Sentinel-2, VIIRS, and SRTM remote sensing imagery data. Based on spectral data combined with terrain and texture features, the study extracted artificial surfaces in Lhasa City through Pixel-Based (PB) and Object-Oriented (OO)classification methods. To compare the performance of different parts of the method, this study conducted a comparative analysis of three groups: OO or PB classification, inclusion or exclusion of texture features, and using Random Forest (RF) or Support Vector Machine (SVM) classifiers. The results showed that Based on the same spectral features, the best extraction result can be obtained by not using texture features in the RF classifier in the OO method (OO_RF), with an Overall Accuracy (OA) of 98.03%, a Kappa Coefficient of 0.952 0, a User Accuracy (UA) of 0.944 4, and a Producer Accuracy (PA) of 0.988 4. The effect of texture features in extracting artificial surfaces is relatively weak, with only slight improvements observed in PB methods. Specifically, the OA increased by 0.51% when using the RF classifier (PB_RF) and 0.68% when using the SVM classifier (PB_SVM). The RF classifier performed the best in this study, avoiding over estimation and identifying non-artificial surfaces within cities more accurately. In conclusion, this study provides a reference for extracting artificial surface information regarding methods and parameter settings at the urban scale. Using result data allows for further analysis and dynamic monitoring, which has practical application significance.

Key words：Object-Oriented; Pixel-Based; Spectral features; Google Earth Engine; Artificial surface

收稿日期: 2024-05-13 修订日期: 2024-09-10

中图分类号:

P237

基金资助: 第二次青藏高原综合科学考察研究项目（2019QZKK0106）资助

通讯作者: 周广胜 E-mail: zhougs@cma.gov.cn

作者简介: 王金枝，女，2000年生，太原理工大学测绘科学与技术系硕士研究生 e-mail: wangjinzhi0761@link.tyut.edu.cn

引用本文:

王金枝，周广胜，吕晓敏，任鸿瑞. 基于光谱特征的拉萨市人造地表遥感提取研究[J]. 光谱学与光谱分析, 2025, 45(04): 1061-1070.
WANG Jin-zhi, ZHOU Guang-sheng, LÜ Xiao-min, REN Hong-rui. Research on Remote Sensing Extraction of Artificial Surface in Lhasa City Based on Spectral Features. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(04): 1061-1070.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2025)04-1061-10 或 https://www.gpxygpfx.com/CN/Y2025/V45/I04/1061

[1] Tassi A, Gigante D, Modica G, et al. Remote Sensing, 2021, 13(12): 2299.
[2] Zhuo L, Shi Q L, Tao H Y, et al. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 142: 64.
[3] Zhang B, Shi Y T, Wang S. Journal of Resources and Ecology, 2022, 13(1): 68.
[4] Foley J A, DeFries R, Asner G P, et al. Science, 2005, 309(5734): 570.
[5] Lautenbach S, Kugel C, Lausch A, et al. Ecological Indicators, 2011, 11(2): 676.
[6] Ban Y F, Jacob A. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(4): 1998.
[7] WANG Xiao-na, TIAN Jin-yan, LI Xiao-juan, et al(王小娜, 田金炎, 李小娟，等). National Remote Sensing Bulletin(遥感学报), 2022, 26(2): 299.
[8] Gorelick N, Hancher M, Dixon M, et al. Remote Sensing of Environment, 2017, 202: 18.
[9] European Commission GHSL Data Package 2023, Publications Office of the European Union, Luxembourg, 2023, doi: 10.2760/098587.
[10] Ren H Q, Liu Y, Chang X Y, et al. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 7288.
[11] Chen J, Chen J, Liao A P, et al. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 103: 7.
[12] Chen X H, Cao X, Liao A P, et al. Science China Earth Sciences, 2016, 59(12): 2295.
[13] Nery T, Sadler R, Solis-Aulestia M, et al. Proceedings of 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Beijing: IEEE, 2016: 5165.
[14] ZHANG Yi-li, LI Xiu-bin, FU Xiao-feng, et al(张镱锂, 李秀彬, 傅小锋，等). Acta Geographica Sinica(地理学报), 2000, 55(4): 395.
[15] NIE Yu, YANG Yan-min, WANG Yi-hang, et al(聂宇, 杨彦敏, 王一航，等). Acta Ecologica Sinica(生态学报), 2022, 42(6): 2202.
[16] WANG Hao, LU Shan-long, WU Bing-fang, et al(王浩, 卢善龙, 吴炳方，等). Advances in Earth Science(地球科学进展), 2013, 28(3): 327.
[17] Shao Z F, Cheng T, Fu H Y, et al. Remote Sensing, 2023, 15(10): 2562.
[18] LIU Tong, REN Hong-rui(刘通, 任鸿瑞). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2022, 38(12): 189.
[19] WANG Chao, KAN Ai-ke, ZENG Ye-long, et al(王超, 阚瑷珂, 曾业隆，等). Acta Geographica Sinica(地理学报), 2019, 74(4): 664.
[20] LI Feng, ZHANG Xiao-bo, LIAO Shun-bao, et al(李峰, 张晓博, 廖顺宝，等). Bulletin of Surveying and Mapping(测绘通报), 2020, (9): 89.
[21] Zhuo L, Zheng J, Zhang X F, et al. International Journal of Remote Sensing, 2015, 36(16): 4114.
[22] Zhang Q L, Seto K C. Remote Sensing of Environment, 2011, 115(9): 2320.
[23] Kalnay E, Cai M. Nature, 2003, 423: 528.
[24] de Leeuw J, Jia H, Yang L, et al. International Journal of Remote Sensing, 2006, 27(1): 223.
[25] Cortes C, Vapnik V. Machine Learning, 1995, 20: 273.
[26] Breiman L. Machine Learning, 2001, 45: 5.
[27] WANG Meng, ZHANG Xin-chang, WANG Jia-yao, et al(王猛, 张新长, 王家耀，等). Acta Geodaetica et Cartographica Sinica(测绘学报), 2020, 49(2): 235.
[28] DU Shang-hai, GU Cheng-ke, ZHANG Wen-jing(杜尚海, 古成科, 张文静). China Environmental Science(中国环境科学), 2022, 42(9): 4285.
[29] GU Hai-yan, YAN Li, LI Hai-tao, et al(顾海燕，闫利，李海涛，等). Geomatics and Information Science of Wuhan University(武汉大学学报·信息科学版), 2016, 41(2): 228.
[30] Achanta R, Shaji A, Smith K, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274.
[31] Tassi A, Vizzari M. Remote Sensing, 2020, 12(22): 3776.
[32] Duro D C, Franklin S E, Dubé M G. Remote Sensing of Environment, 2012, 118: 259.
[33] Gong P, Liu H, Zhang M N, et al. Science Bulletin, 2019, 64(6): 370.
[34] Zhang X, Liu L Y, Zhao T T, et al. Earth System Science Data, 2022, 14(4): 1831.