Subpixel abundance estimates in mixture-tuned matched filtering classifications of leafy spurge (<i>Euphorbia esula</i> L.)

Mitchell, Jessica J.; Glenn, Nancy F.

doi:10.1080/01431160902810620

Cited by 51 publications

(44 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some of the non-native invasive species frequently distinguished and mapped in the USA include saltcedar (Tamarix spp.) [33,52,58,59], leafy spurge (Euphorbia esula L.) [51,56,57], spotted knapweed (Centaurea maculosa Sam.) [32,48,53] and yellow starthistle (Centaurea solstitialis) [50,54,55].…”

Section: Introductionmentioning

confidence: 99%

“…The literature indicates that there is a growing body of work on the hyperspectral mapping of non-native invasive species [50][51][52][53][54][55][56][57]. Most of the previous hyperspectral remote sensing studies dealing with mapping invasive plants have commonly utilized Airborne Visible Infrared Imaging Spectrometer, HyMap and Compact Airborne Spectrographic Imager images with spectral resolution ≥ 10 nm and spatial resolution ≥ 1.5 m. In addition to this, spectral angle mapper and mixture tuned matched filtering were commonly employed as the classification algorithms after dimension reduction or transformation of hyperspectral data, such as principal component analysis, minimum noise fraction or vegetation indices.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Remote Distinction of A Noxious Weed (Musk Thistle: CarduusNutans) Using Airborne Hyperspectral Imagery and the Support Vector Machine Classifier

Mırık¹,

Ansley²,

Steddom³

et al. 2013

Remote Sensing

View full text Add to dashboard Cite

Remote detection of non-native invasive plant species using geospatial imagery may significantly improve monitoring, planning and management practices by eliminating shortfalls, such as observer bias and accessibility involved in ground-based surveys. The use of remote sensing for accurate mapping invasion extent and pattern offers several advantages, including repeatability, large area coverage, complete instead of sub-sampled assessments and greater cost-effectiveness over ground-based methods. It is critical for locating, early mapping and controlling small infestations before they reach economically prohibitive or ecologically significant levels over larger land areas. This study was designed to explore the ability of hyperspectral imagery for mapping infestation of musk thistle (Carduus nutans) on a native grassland during the preflowering stage in mid-April and during the peak flowering stage in mid-June using the support vector machine classifier and to assess and compare the resulting mapping accuracy for these two OPEN ACCESSRemote Sens. 2013, 5 613 distinctive phenological stages. Accuracy assessment revealed that the overall accuracies were 79% and 91% for the classified images at preflowering and peak flowering stages, respectively. These results indicate that repeated detection of the infestation extent, as well as infestation severity or intensity, of this noxious weed in a spatial and temporal context is possible using hyperspectral remote sensing imagery.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Remote Distinction of A Noxious Weed (Musk Thistle: CarduusNutans) Using Airborne Hyperspectral Imagery and the Support Vector Machine Classifier

Mırık¹,

Ansley²,

Steddom³

et al. 2013

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Some researchers found that leafy spurge (Euphorbia esula L.) is spectrally distinguishable from the surrounding vegetation due to its yellow-green flower during the flowering stage [70,71] and possibly musk thistle (Carduus nutans L.) due to its large, red-purple flower heads [72]. Some cool-season grass and broad-leaf forb species germinated or greened up in March and areas covered by cool-season species may be confused with wheat.…”

Section: Discussionmentioning

confidence: 99%

Remote Monitoring of Wheat Streak Mosaic Progression Using Sub-Pixel Classification of Landsat 5 TM Imagery for Site Specific Disease Management in Winter Wheat

Mırık¹,

Ansley²,

Price³

et al. 2013

ARS

View full text Add to dashboard Cite

Wheat streak mosaic (WSM), caused by Wheat streak mosaic virus is a viral disease that affects wheat (Triticum aestivum L.), other grains, and numerous grasses over large geographical areas around the world. To improve disease management and crop production, it is essential to have adequate methods for monitoring disease epidemics at various scales and multiple times. Remote sensing has become an essential tool for monitoring and quantifying crop stress due to biotic and abiotic factors. The objective of our study was to explore the utility of Landsat 5 TM imagery for detecting, quantifying, and mapping the occurrence of WSM in irrigated commercial wheat fields. The infection and progression of WSM was biweekly assessed in the Texas Panhandle during the 2007-2008 crop years. Diseased-wheat was separated from uninfected wheat on the images using a sub-pixel classifier. The overall classification accuracies were >91% with kappa coefficient between 0.80 and 0.94 for disease detection were achieved. Omission errors varied between 2% and 14%, while commission errors ranged from 1% to 21%. These results indicate that the TM image can be used to accurately detect and quantify disease for site-specific WSM management. Remote detection of WSM using geospatial imagery may substantially improve monitoring, planning, and management practices by overcoming some of the shortcomings of the ground-based surveys such as observer bias and inaccessibility. Remote sensing techniques for accurate disease mapping offer a unique set of advantages including repeatability, large area coverage, and cost-effectiveness over the ground-based methods. Hence, remote detection is particularly and practically critical for repeated disease monitoring and mapping over time and space during the course of a growing season.

show abstract

“…We were also interested in the MTMF threshold approach because previous studies found that spectral unmixing analyses, including MTMF, have a tendency to underestimate fractional cover of a target class within pixels. As a result, it has been suggested that classifier outputs should be interpreted as the likelihood that a target material is contained within a given pixel instead of fractional cover [25,46]. Therefore, our SGuava MF was assumed to scale with the likelihood of P. cattleianum presence with low values indicating lower likelihood and high values indicating higher likelihood.…”

Section: Mixture Tuned Matched Filteringmentioning

confidence: 99%

“…MTMF is a partial unmixing method that estimates subpixel abundance of a single target material [24]. MTMF estimates the similarity between spectra from given image pixels and the spectra of a target endmember (pure spectral signature from the focal species), estimating subpixel abundance of the target material or the likelihood for the target material is present in a given pixel [25]. Although some prior studies have used MTMF to detect invasive species [26][27][28][29], this technique has been poorly evaluated in ecosystems exhibiting complex canopy structure, such as tropical forests.…”

Section: Introductionmentioning

confidence: 99%

Determining Subcanopy Psidium cattleianum Invasion in Hawaiian Forests Using Imaging Spectroscopy

et al. 2016

View full text Add to dashboard Cite

High-resolution airborne imaging spectroscopy represents a promising avenue for mapping the spread of invasive tree species through native forests, but for this technology to be useful to forest managers there are two main technical challenges that must be addressed: (1) mapping a single focal species amongst a diverse array of other tree species; and (2) detecting early outbreaks of invasive plant species that are often hidden beneath the forest canopy. To address these challenges, we investigated the performance of two single-class classification frameworks-Biased Support Vector Machine (BSVM) and Mixture Tuned Matched Filtering (MTMF)-to estimate the degree of Psidium cattleianum incidence over a range of forest vertical strata (relative canopy density). We demonstrate that both BSVM and MTMF have the ability to detect relative canopy density of a single focal plant species in a vertically stratified forest, but they differ in the degree of user input required. Our results suggest BSVM as a promising method to disentangle spectrally-mixed classifications, as this approach generates decision values from a similarity function (kernel), which optimizes complex comparisons between classes using a dynamic machine learning process.

show abstract

Subpixel abundance estimates in mixture-tuned matched filtering classifications of leafy spurge (Euphorbia esula L.)

Cited by 51 publications

References 26 publications

Remote Distinction of A Noxious Weed (Musk Thistle: CarduusNutans) Using Airborne Hyperspectral Imagery and the Support Vector Machine Classifier

Remote Distinction of A Noxious Weed (Musk Thistle: CarduusNutans) Using Airborne Hyperspectral Imagery and the Support Vector Machine Classifier

Remote Monitoring of Wheat Streak Mosaic Progression Using Sub-Pixel Classification of Landsat 5 TM Imagery for Site Specific Disease Management in Winter Wheat

Determining Subcanopy Psidium cattleianum Invasion in Hawaiian Forests Using Imaging Spectroscopy

Contact Info

Product

Resources

About