%0 Journal Article %1 MixtureAnalysis2009 %A Somers, B. %A Delalieux, S. %A Verstraeten, W. W. %A Verbesselt, J. %A Lhermitte, S. %A Coppin, P. %D 2009 %J Geoscience and Remote Sensing, IEEE Transactions on %K agriculture crops imageprocessing imported inference inversions linearmixing optical remotesensing satellite vegetation %N 11 %P 3630-3642 %R 10.1109/TGRS.2009.2024207 %T Magnitude- and Shape-Related Feature Integration in Hyperspectral Mixture Analysis to Monitor Weeds in Citrus Orchards %U http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=5291960&arnumber=5208311 %V 47 %X <para> Traditionally, spectral mixture analysis (SMA) fails to fully account for highly similar ground components or endmembers. The high similarity between weed and crop spectra hampers the implementation of SMA for steering weed control management practices. To address this problem, this paper presents an alternative SMA technique, referred to as Integrated Spectral Unmixing (InSU). InSU combines both magnitude (i.e., reflectance) and shape (i.e., derivative reflectance) related features in an automated waveband selection protocol. Analysis was performed on different simulated mixed pixel spectra sets compiled from <emphasis emphasistype="boldital">in situ</emphasis>-measured weed canopy, <emphasis emphasistype="boldital">Citrus</emphasis> canopy, and soil spectra. Compared to traditional linear SMA, InSU significantly improved weed cover fraction estimations. An average decrease in fraction abundance error <formula formulatype="inline"><tex Notation="TeX">$(Delta f)$</tex></formula> of 0.09 was demonstrated for a signal-to-noise ratio (SNR) of 500&#x2009;:&#x2009;1, while for a SNR of 50&#x2009;:&#x2009;1, the decrease was 0.06. </para>

@article{MixtureAnalysis2009, abstract = {<para> Traditionally, spectral mixture analysis (SMA) fails to fully account for highly similar ground components or endmembers. The high similarity between weed and crop spectra hampers the implementation of SMA for steering weed control management practices. To address this problem, this paper presents an alternative SMA technique, referred to as Integrated Spectral Unmixing (InSU). InSU combines both magnitude (i.e., reflectance) and shape (i.e., derivative reflectance) related features in an automated waveband selection protocol. Analysis was performed on different simulated mixed pixel spectra sets compiled from <emphasis emphasistype="boldital">in situ</emphasis>-measured weed canopy, <emphasis emphasistype="boldital">Citrus</emphasis> canopy, and soil spectra. Compared to traditional linear SMA, InSU significantly improved weed cover fraction estimations. An average decrease in fraction abundance error <formula formulatype="inline"><tex Notation="TeX">$(Delta f)$</tex></formula> of 0.09 was demonstrated for a signal-to-noise ratio (SNR) of 500&#x2009;:&#x2009;1, while for a SNR of 50&#x2009;:&#x2009;1, the decrease was 0.06. </para>}, added-at = {2009-10-28T15:21:41.000+0100}, author = {Somers, B. and Delalieux, S. and Verstraeten, W. W. and Verbesselt, J. and Lhermitte, S. and Coppin, P.}, biburl = {https://www.bibsonomy.org/bibtex/2a824c7176c857bbde09cad1208f397ee/jgomezdans}, description = {Welcome to IEEE Xplore 2.0: Magnitude- and Shape-Related Feature Integration in Hyperspectral Mixture Analysis to Monitor Weeds in Citrus Orchards}, doi = {10.1109/TGRS.2009.2024207}, interhash = {907a0344283a605bc3b6a614c610d8e4}, intrahash = {a824c7176c857bbde09cad1208f397ee}, issn = {0196-2892}, journal = {Geoscience and Remote Sensing, IEEE Transactions on}, keywords = {agriculture crops imageprocessing imported inference inversions linearmixing optical remotesensing satellite vegetation}, month = {Nov. }, number = 11, pages = {3630-3642}, timestamp = {2009-10-28T15:21:41.000+0100}, title = {Magnitude- and Shape-Related Feature Integration in Hyperspectral Mixture Analysis to Monitor Weeds in Citrus Orchards}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=5291960&arnumber=5208311}, volume = 47, year = 2009 }