Band Selection and Its Construction for the Normalized Shadow
Vegetation Index (NSVI) of ZY1-02D AHSI Image
XU Zhang-hua1, 2, 3, 4, CHEN Ling-yan1, 4, 5, XIANG Song-yang1, 4, 5, DENG Xi-peng6, LI Yi-fan1, 2, YU Hui1, 4, 5, HE An-qi1, 2, LI Zeng-lu3, 7, GUO Xiao-yu3
1. Academy of Geography and Ecological Environment, Fuzhou University, Fuzhou 350108, China
2. College of Environmental and Safety Engineering, Fuzhou University, Fuzhou 350108, China
3. Fujian Provincial Key Laboratory of Resources and Environment Monitoring & Sustainable Management and Utilization, Sanming 365004, China
4. Key Laboratory of Spatial Data Mining & Information Sharing, Ministry of Education, Fuzhou 350108, China
5. The Academy of Digital China, Fuzhou University, Fuzhou 350108, China
6. Fujian Geologic Surveying and Mapping Institute, Fuzhou 350108, China
7. SEGi University, Kota Damansara 47810, Malaysia
Abstract：Hyperspectral images have continuous spectral information of features and have great potential for shadow detection, but high band redundancy requires band preference. Normalized Shaded Vegetation Index (NSVI) can expand the spectral difference, and the application of NSVI in hyperspectral images will identify shadows more effectively. ZY1-02D satellite is the first hyperspectral operational satellite independently developed and successfully operated in China, with a large data signal-to-noise ratio and strong coverage capability, and it is important to perform accurate shadow detection on this hyperspectral image. In this paper, ZY1-02D AHSI images were used as experimental data to extract and analyze the spectral reflectance of vegetation in bright areas, vegetation in shaded areas and water bodies, and Combining Competitive Adaptive Reweighted Sampling (CARS) and Successive Projection Algorithm (SPA) to filter the main wavebands that can effectively distinguish typical features, the characteristics of the algorithms are considered to select the characteristic wavebands further to construct NSVI. The optimal threshold value is determined by the step method to classify the images, and the best band for constructing NSVI is compared in terms of image element value distribution, classification accuracy and spectral enhancement effect. A comprehensive evaluation is made by combining different shadow indices, bands and images to verify the significance and universality of the method in this paper. The results show that band 32 and band 73 are the best bands for NSVI construction, corresponding to the Red band and NIR band, respectively; the classification accuracy of NSVI constructed by different bands is generally higher than 90%, and the classification accuracy of NSVI constructed by the best band is 94.33% with a Kappa coefficient of 0.832 8, which is the best classification effect; NSVI can enhance the spectral difference between typical features and alleviate the “easy saturation” phenomenon of Normalized Difference Vegetation Index, and the small peaks generated by the accumulation of water bodies in this image is helpful to extract water bodies; The classification of NSVI in ZY1-02D AHSI image is better than Normalized Different Umbra Index and Shadow Index, and the classification accuracy in another scene image also reaches 93.55% with a kappa coefficient of 0.816 7; Therefore, the wavebands filtered by the algorithm are representative, and the NSVI constructed by the best waveband has better shadow detection ability in ZY1-02D AHSI images, which has a certain reference and significance for hyperspectral image shadow detection and construction of vegetation index.
许章华，陈玲燕，项颂阳，邓西鹏，李一帆，俞 辉，贺安琪，李增禄，郭孝玉. ZY1-02D AHSI影像归一化阴影植被指数NSVI的波段选择及其构建[J]. 光谱学与光谱分析, 2024, 44(09): 2626-2637.
XU Zhang-hua, CHEN Ling-yan, XIANG Song-yang, DENG Xi-peng, LI Yi-fan, YU Hui, HE An-qi, LI Zeng-lu, GUO Xiao-yu. Band Selection and Its Construction for the Normalized Shadow
Vegetation Index (NSVI) of ZY1-02D AHSI Image. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(09): 2626-2637.
[1] Lu S H, Xuan J J, Zhang T, et al. Remote Sensing, 2022, 14(9): 2259.
[2] Zhou T T, Fu H Y, Sun C L, et al. Remote Sensing, 2021, 13(4): 699.
[3] Mostafa Y G, Yousef M A, Mostafa F A. International Journal of Remote Sensing, 2020, 41(2): 420.
[4] Ye S P, Nedzved A, Chen C X, et al. Pattern Recognition and Image Analysis, 2022, 32(2): 332.
[5] Shi L, Fang J, Zhao Y F. Computers and Electrical Engineering, 2023, 105: 108557.
[6] XU Zhang-hua, LIN Lu, WANG Qian-feng, et al(许章华，林 璐，王前锋，等). Journal of Infrared and Millimeter Waves(红外与毫米波学报), 2018, 37(2): 154.
[7] Badgley G, Field C B, Berry J A. Science Advances, 2017, 3(3): e1602244.
[8] LI Mei-xuan, ZHU Xi-cun, BAI Xue-yuan, et al(李美炫，朱西存，白雪源，等). Scientia Agricultura Sinica(中国农业科学), 2021, 54(10): 2084.
[9] Zhang G C, Cerra D, Müller R. Remote Sensing, 2020, 12(23): 3985.
[10] XIAO Bin, XU Yong, HE Hong-chang(肖 斌，徐 勇，何宏昌). Radio Engineering(无线电工程), 2021, 51(12): 1442.
[11] KONG Yu-ru, WANG Li-juan, FENG Hai-kuan, et al(孔钰如，王李娟，冯海宽，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(3): 933.
[12] HU Xin-yu, XU Zhang-hua, CHEN Wen-hui, et al(胡新宇，许章华，陈文慧，等). Remote Sensing for Natural Resources(国土资源遥感), 2021, 33(2): 55.
[13] Sun W W, Liu K, Ren G B, et al. International Journal of Applied Earth Observation and Geoinformation, 2021, 104: 102572.
[14] Yang Z, Gong C L, Ji T M, et al. Remote Sensing, 2022, 14(19): 5029.
[15] Liu Y, Li J S, Xiao C C, et al. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1.
[16] Xu D D, Liu Y Q, Xu W X, et al. Remote Sensing, 2022, 14(13): 3031.
[17] Yang G, Huang K, Sun W W, et al. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 189: 236.
[18] Kundu R, Dutta D, Nanda M K, et al. Smart Agricultural Technology, 2021, 1: 100019.
