基于多源遥感数据融合的农村闲置宅基地目标识别研究
Research on Target Recognition of Rural Idle Homestead Land Based on Multi Source Remote Sensing Data Fusion
DOI: 10.12677/gser.2025.142046, PDF,    国家自然科学基金支持
作者: 郑荣宝, 陈 晶, 唐晓莲：广东工业大学管理学院，广东 广州；陈美招：广东外语外贸大学社会与公共管理学院，广东 广州
关键词: 图像融合；闲置宅基地；目标识别；Image Fusion； Idle Homestead Land； Target Recognition
摘要: 闲置宅基地的目标识别是土地科学界难以解决的技术问题，我国到底有多少农村闲置宅基地一直缺乏准确数据。本文基于多源遥感数据融合的数据处理方法，通过高分夜光遥感数据与无人机航飞数据的耦合，实现农村闲置宅基地的目标精确识别。研究结果表明：① 结合高分辨率遥感影像和夜间灯光数据，基于支持向量机分类方法中，Kappa系数分别为82.09%和0.8045，基本达到目标识别精度要求。② 惠东县的农村闲置宅基地总体比例较高，超过宅基地总面积的三分之一，实验证明了基于高分夜光遥感影像与高分航飞影像的数据融合进行农村闲置宅基地识别的研究是可行的。③ 需要创新农村闲置宅基地管理制度与方法，实现农村宅基地的盘活利用，以提高农村建设用地利用效率。本文提供了一种高效快速的农村闲置宅基地的目标识别方法，可为农村低效闲置用地改造利用提供技术支撑。
Abstract: It is a very difficult technical problem which is to solve target recognition of idle homesteads in land science. Not everyone knows the accurate data on how many idle rural homestead lands exist in China. Based on a data processing method of multi-source remote sensing data fusion, this article gets the accurate identification of idle rural homestead lands through the coupling of high-resolution night light remote sensing data and unmanned aerial vehicle (UAV) flight data. The research results show that: ① Combining high-resolution remote sensing images and nighttime light data, the Kappa coefficients in the support vector machine classification method are 82.09% and 0.8045, respectively, which basically meet the requirements of target recognition accuracy. ② The overall proportion of idle rural homestead lands in Huidong County is relatively high, exceeding one-third of the total area of homestead lands, and it has been proven that the research on identifying idle rural homestead lands based on the fusion of high-resolution night light remote sensing images and high-resolution aerial images is feasible. ③ It is necessary to innovate the management system and methods of idle rural homestead lands, realize the revitalization and utilization of rural homestead lands, and improve the efficiency of rural construction land utilization. The research results of this article provide an efficient and fast target recognition method for idle rural homestead lands, which can provide technical support for the transformation of inefficient idle rural land.
文章引用：郑荣宝, 陈美招, 陈晶, 唐晓莲. 基于多源遥感数据融合的农村闲置宅基地目标识别研究[J]. 地理科学研究, 2025, 14(2): 464-472. https://doi.org/10.12677/gser.2025.142046

参考文献

[1] 卢向虎. 新农村建设背景下的农村宅基地问题研究[D]: [博士学位论文]. 北京: 中国农业科学院, 2008.
[2] 祁全明. 我国农村闲置宅基地的现状、原因及其治理措施[J]. 农村经济, 2015(8): 21-27.
[3] 徐忠国, 卓跃飞, 陈阳, 等. 农村闲置宅基地盘活利用的多主体行为逻辑——以杭州临安为案例[J]. 中国土地科学, 2024, 38(1): 105-113.
[4] 岳涛, 黄宇民, 刘品雄, 等. 未来中国卫星遥感器的发展分析[J]. 航天器工程, 2008, 17(4): 77-82.
[5] Alparone, L., Aiazzi, B., Baronti, S., et al. (2015) Remote Sensing Image Fusion. CRC Press.
[6] 李盛阳, 张万峰, 杨松. 多源高分辨率遥感影像智能融合[J]. 遥感学报, 2017, 21(3): 415-424.
[7] Hall, D.L. and Llinas, J. (1997) An Introduction to Multisensor Data Fusion. Proceedings of the IEEE, 85, 6-23. [Google Scholar] [CrossRef] 
[8] Schowengerdt, R.A. (1980) Reconstruction of Multispatial, Multispectral Image Data Using Spatial Frequency Content. Photo-Grammetric Engineering and Remote Sensing, 46, 1325-1334.
[9] Merino, M.T. and Nunez, J. (2007) Super-Resolution of Remotely Sensed Images with Variable-Pixel Linear Reconstruction. IEEE Transactions on Geoscience and Remote Sensing, 45, 1446-1457. [Google Scholar] [CrossRef] 
[10] Hardie, R.C., Eismann, M.T. and Wilson, G.L. (2004) MAP Estimation for Hyperspectral Image Resolution Enhancement Using an Auxiliary Sensor. IEEE Transactions on Image Processing, 13, 1174-1184. [Google Scholar] [CrossRef] [PubMed]
[11] Wei, Q., Bioucas-Dias, J., Dobigeon, N. and Tourneret, J. (2015) Hyperspectral and Multispectral Image Fusion Based on a Sparse Representation. IEEE Transactions on Geoscience and Remote Sensing, 53, 3658-3668. [Google Scholar] [CrossRef] 
[12] Wu, P., Shen, H., Zhang, L. and Göttsche, F. (2015) Integrated Fusion of Multi-Scale Polar-Orbiting and Geostationary Satellite Observations for the Mapping of High Spatial and Temporal Resolution Land Surface Temperature. Remote Sensing of Environment, 156, 169-181. [Google Scholar] [CrossRef] 
[13] Meng, X., Shen, H., Zhang, L., Yuan, Q. and Li, H. (2015) A Unified Framework for Spatio-Temporal-Spectral Fusion of Remote Sensing Images. 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, 26-31 July 2015, 2584-2587. [Google Scholar] [CrossRef] 
[14] Moser, G., Tuia, D. and Shimoni, M. (2014) 2014 IEEE GRSS Data Fusion Contest: Multiresolution Fusion of Thermal Hyperspectral and VIS Data [Technical Committees]. IEEE Geoscience and Remote Sensing Magazine, 2, 21-22. [Google Scholar] [CrossRef] 
[15] Gianinetto, M., Rusmini, M., Marchesi, A., Maianti, P., Frassy, F., Dalla Via, G., et al. (2015) Integration of COSMO-SkyMed and GeoEye-1 Data with Object-Based Image Analysis. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8, 2282-2293. [Google Scholar] [CrossRef] 
[16] Beyer, H.G., Czeplak, G., Terzenbach, U. and Wald, L. (1997) Assessment of the Method Used to Construct Clearness Index Maps for the New European Solar Radiation Atlas (ESRA). Solar Energy, 61, 389-397. [Google Scholar] [CrossRef] 
[17] Corona, P., Fattorini, L., Franceschi, S., Chirici, G., Maselli, F. and Secondi, L. (2014) Mapping by Spatial Predictors Exploiting Remotely Sensed and Ground Data: A Comparative Design-Based Perspective. Remote Sensing of Environment, 152, 29-37. [Google Scholar] [CrossRef] 
[18] Babst, F., Esper, J. and Parlow, E. (2010) Landsat TM/ETM+ and Tree-Ring Based Assessment of Spatiotemporal Patterns of the Autumnal Moth (Epirrita autumnata) in Northernmost Fennoscandia. Remote Sensing of Environment, 114, 637-646. [Google Scholar] [CrossRef] 

为你推荐