Optimal Feature Space Construction for Multispectral Vegetation Recognition Considering Endmember Variability
Abstract
Due to differences in data acquisition and vegetation growth periods, vegetation recognition on low-and medium-resolution remote sensing imagery widely suffers from endmember variability. The endmember variability directly leads to large vegetation unmixing errors. To increase the vegetation recognition accuracy on the multispectral imagery, an intra-inter distance genetic algorithm (IIDGA) that accounts for the endmember variability was proposed. IIDGA can decrease the intra-distance and increase the inter-distance simultaneously, which enhanced the distinguishability of the endmembers through an automatic feature selection method. An optimal feature space for vegetation unmixing was constructed on the medium resolution imagery to improve the vegetation recognition accuracy based on the Landsat imagery. The importance of optimal feature selection was demonstrated by comparing the linear unmixing model accuracy based on the classical band combination features, the spectral and textural feature set and the proposed IIDGA. The results verified that feature selection was beneficial to improve the unmixing accuracy. The RMSE of IIDGA equalled 0.180 which was the lowest among the three methods. Meanwhile, the IID index-based Filter method, the standard GA-based Wrapper method and the proposed method were compared with their performances in automatic optimal feature selection. The results confirmed the superiority of the IIDGA in trading off accuracy and efficiency.
Keywords: multispectral remote sensing;vegetation recognition;spectral endmember variability;intra-inter distance genetic algorithm (IIDGA);automatic feature selection
Download Full Text:
PDFReferences
FU Yongshuo, ZHANG Jing, WU Zhaofei, et al. Vegetation phenology response to climate change in China [J]. Journal of Beijing Normal University ( Natural Science) , 2022, 58(3) : 424 -433. (in Chinese)
XIONG T, DU S, ZHANG H, et al. Satellite observed reversal in trends of spring phenology in the middle-high latitudes of the Northern Hemisphere during the global warming hiatus[J ]. Global Change Biology, 2023, 29(8) ; 2227 -2241.
XIE 'ii, WANG Jia'nan, LIU Yu. Research on winter wheat planting area identification method based on Sentinel — 1/2 data feature optimization [ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55 ( 2 ): 231 - 241. (in Chinese)
JIA Kai, CHEN Shuisen, JIANG Weiguo. Long time-series remote sensing monitoring of mangrove forests in the Guangdong — Hong Kong — Macao Greater Bay Area[J]. National Remote Sensing Bulletin, 2022, 26(6) ; 1096 - 1111. (in Chinese)
YANG Bin, W ANG Bin. Research advances of spectral unmixing technology and its applications[ J]. Laser and Optoelectronics Progress, 2021 , 58( 16) ; 76 — 103. (in Chinese)
YU J, CHEN D, LIN Y, et al. Comparison of linear and nonlinear spectral unmixing approaches; a case study with multispectral TM imagerv [j ]. International Journal of Remote Sensing, 2017, 38(3) ; 773 -795.
CHEN Jin, MA Lei, CHEN Xuehong, et al. Research progress of spectral mixture analysis [J ]. National Remote Sensing Bulletin, 2016, 20(5): 1102 -1109. (in Chinese)
SOMERS B, ASNER G P, TITS L, et al. Endmember variability in spectral mixture analysis; a review[ J]. Remote Sensing of Environment, 2011, 115(7); 1603 -1616.
LI J, CHENG K, WANG S, et al. Feature selection; a data perspective [ J ] . ACM Computing Surveys, 2017, 50(6) ; 1 -45.
CHANDRASHEKAR G, SAHIN F. A survey on feature selection methods [J] . Computers and Electrical Engineering, 2014, 40(1) ; 16 -28.
KHAIRE U M, DHANALAKSHMI R. Stability of feature selection algorithm; a review[J]. Journal of King Saud University— Computer and Information Sciences, 2022, 34(4) ; 1060 - 1073.
LI Ruili, YANG Fang, WANG Hui, et al. Current development status and countermeasures of mangrove protection and restoration standards[J ]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(5); 916 -928. (in Chinese)
WANG Y, JIANG B, LIANG S, et al. Surface shortwave net radiation estimation from Landsat TM/ETM + data using four
YU Jie, YE Qin, LIN Yi. Novel weighted coefficient of variation analysis approach for endmember variability issue in unmixing process of multi-spectral imagery [J ]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(9) ; 154 - 159. (in Chinese)
ZHU Z, WOODCOCK С E, ROGAN J, et al. Assessment of spectral, polarimetric, temporal, and spatial dimensions for urban and peri-urban land cover classification using Landsat and SAR data [ J ]. Remote Sensing of Environment, 2012, 117: 72 -82.
LI S, XU L, JING Y, et al. High-quality vegetation index product generation; a review of NDVI time series reconstruction techniques[J] . International Journal of Applied Earth Observation and Geoinformation, 2021 , 105; 102640.
CHAI L, JIANG H, CROW W T, et al. Estimating corn canopy water content from normalized difference water index ( NDWI) : an optimized NDWI-based scheme and its feasibility for retrieving corn VWC [ J ]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(10); 8168-8181.
YARBROUGH L D, EASSON G, KUSZMAUL J S. Proposed workflow for improved Kauth—Thomas transform derivations [J]. Remote Sensing of Environment, 2012, 124; 810-818.
DU Xiaodong, TENG Guanghui, TOMAS N, et al. Classification and recognition of laying hens’ vocalization based on texture features of spectrogram [ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(9) : 215 -220. (in Chinese)
YAO X, W ANG X D, ZHANG Y X, et al. Summary of feature selection algorithms[ J ]. Control and Decision, 2012, 27(2) ; 161 - 166.
QIU Yunfei, GAO Huacong. Hybrid Filter and improved adaptive GA for feature selection [ J]. Computer Engineering and Application, 2021 , 57( 11); 95 — 102. (in Chinese)
Refbacks
- There are currently no refbacks.
