Magnitude- and Shape-Related Feature Integration in Hyperspectral Mixture Analysis to Monitor Weeds in Citrus Orchards

• Published in: IEEE transactions on geoscience and remote sensing Vol. 47; no. 11; pp. 3630 - 3642
• Main Authors: Somers, B., Delalieux, S., Verstraeten, W.W., Verbesselt, J., Lhermitte, S., Coppin, P.
• Format: Journal Article Conference Proceeding
• Language: English
• Published: New York, NY IEEE 01-11-2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytical models; Applied geophysics; Automatic control; Canopies; Condition monitoring; Crops; Derivatives; Earth sciences; Earth, ocean, space; endmember similarity; Exact sciences and technology; Failure analysis; hyperspectral; Internal geophysics; Monitors; Performance analysis; Protocols; Reflectance; Reflectivity; Shape; Shape memory alloys; Spectra; Spectral analysis; spectral mixture analysis (SMA); stable feature selection; Weeds; weighted least squares (LS); stable feature selection; spectra; reflectance; mixing; hyperspectral; weighted least squares (LS); remote sensing; least-squares; Derivatives; spectral mixture analysis (SMA); in situ; management; endmember similarity; signal-to-noise ratio; soils; errors; Pixel
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2009.2024207

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 in situ -measured weed canopy, Citrus canopy, and soil spectra. Compared to traditional linear SMA, InSU significantly improved weed cover fraction estimations. An average decrease in fraction abundance error (Delta f ) of 0.09 was demonstrated for a signal-to-noise ratio (SNR) of 500 : 1, while for a SNR of 50 : 1, the decrease was 0.06.