Application of spectral features’ ratios for improving classification in partially calibrated hyperspectral imagery: a case study of separating Mediterranean vegetation species

Rud, Ronit; Shoshany, Maxim; Alchanatis, V.; Cohen, Yafit

doi:10.1007/s11554-006-0015-8

Cited by 18 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, previous studies indicate that the East Mediterranean woody species are not necessarily an easy target for classification by remote sensing. Most local vegetation formations are characterized by densely-growing evergreen species, often with similar spectral properties [58][59][60], small intra-annual differences [61] and morphological similarities [62][63][64][65]. To the best of our knowledge, there are currently no studies that use high spatial resolution imagery with a limited number of bands for the classification of East Mediterranean common species.…”

Section: Classification Of East Mediterranean Vegetation By Remote Sementioning

confidence: 99%

“…We did not choose to focus on ideal target species (e.g., large homogeneous canopies with visually distinct phenophases), rather, we examined the local species assembly as-is, including species with challenging spectral and morphological properties with regard to classification by remote sensing [59,60,62,65]; furthermore, after examining the preliminary classification results, we did not see fit to merge or omit species in order to increase overall accuracy.…”

Section: Overhead Data Acquisition and Species Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing the Timing of Unmanned Aerial Vehicle Image Acquisition for Applied Mapping of Woody Vegetation Species Using Feature Selection

et al. 2017

View full text Add to dashboard Cite

Abstract:Most recent studies relating to the classification of vegetation species on the individual level use cutting-edge sensors and follow a data-driven approach, aimed at maximizing classification accuracy within a relatively small allocated area of optimal conditions. However, this approach does not incorporate cost-benefit considerations or the ability of applying the chosen methodology for applied mapping over larger areas with higher natural heterogeneity. In this study, we present a phenology-based cost-effective approach for optimizing the number and timing of unmanned aerial vehicle (UAV) imagery acquisition, based on a priori near-surface observations. A ground-placed camera was used in order to generate annual time series of nine spectral indices and three color conversions (red, green and blue to hue, saturation and value) in four different East Mediterranean sites that represent different environmental conditions. After outliers' removal, the time series dataset represented 1852 individuals of 12 common vegetation species and annual herbaceous patches. A feature selection process was used for identifying the optimal dates for species classification in every site. The feature selection can be designed for various objectives, e.g., optimization of overall classification, discrimination between two species, or discrimination of one species from all others. In order to evaluate the a priori findings, a UAV was flown for acquiring five overhead multiband orthomosaics (five bands in the visible-near infrared range based on the five optimal dates identified in the feature selection of the near-surface time series of the previous year. An object-based classification methodology was used for the discrimination of 976 individuals of nine species and annual herbaceous patches in the UAV imagery, and resulted in an average overall accuracy of 85% and an average Kappa coefficient of 0.82. This cost-effective approach has high potential for detailed vegetation mapping, regarding the accessibility of UAV-produced time series, compared to hyper-spectral imagery with high spatial resolution which is more expensive and involves great difficulties in implementation over large areas.

show abstract

Section: Classification Of East Mediterranean Vegetation By Remote Sementioning

confidence: 99%

Section: Overhead Data Acquisition and Species Classificationmentioning

confidence: 99%

Optimizing the Timing of Unmanned Aerial Vehicle Image Acquisition for Applied Mapping of Woody Vegetation Species Using Feature Selection

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Similar spectral features have been used to discriminate among species [17,[21][22][23][24][25]. If such features are able to be detected at the satellite level, discriminability may also be possible using satellite imagery.…”

Section: Context Of Key Findingsmentioning

confidence: 99%

Distinguishing Early Successional Plant Communities Using Ground-Level Hyperspectral Data

Aneece

Epstein

2015

Remote Sensing

View full text Add to dashboard Cite

Abandoned agricultural fields have recently become more abundant in the U.S. and remain susceptible to species invasions after cultivation disturbance. As invasive species become more widespread with increases in anthropogenic activities, we need more effective ways to use limited resources for conservation of native ecosystems. Remote sensing can help us monitor the spread and effects of invasive species, and thus determine the species and locations to target for conservation. To examine this potential, we studied plant communities dominated by exotic invasive plant species in secondary successional fields in northern Virginia using ground-level hyperspectral data. Within these communities, ordination analyses of vegetation surveys revealed differences in species compositions among plots and fields. These differences among communities were also observed in the spectral data. Stepwise multiple linear regression analyses to determine which species influenced the ordination axes revealed that many of the influential species are considered invasive, again underscoring the influence of invasive species on community properties. Stepwise regression analyses also revealed that the most influential wavelengths for discrimination were distributed along the spectral profile from the visible to the near-infrared regions. A discriminant analysis using wavelengths selected with a principal components analysis demonstrated that different plant communities were separable using spectral data. These spectrally observable differences suggest that we can use hyperspectral data to distinguish among invasive-dominated successional plant communities in this region.

show abstract

“…When extracting ecological information from spectral data, there are many sources of spectral variability, due to variability in ecological characteristics, including leaf properties such as surface characteristics, internal structure, water content, nutrient content, stress, disease, and phenology/ senescence (Cochrane, 2000;Mahlein, 2011;Merzlyak et al, 2003) as well as crown properties such as foliar reflectance, foliar transmittance, crown architecture, Species biochemical and structural similarities in some traits, and differences in illumination within canopies, make species discrimination challenging (Ribeiro da Luz and Crowley, 2010;Rud et al, 2006). However, Asner (1998) suggests that vegetation types should be distinguishable remotely due to differences in biochemical and structural properties.…”

Section: 1 Variability In Ecological Characteristicsmentioning

confidence: 99%

“…Despite high intraspecific variability due to environmental factors and sometimes low interspecific variability across species for some traits (Ribeiro da Luz and Crowley, 2010;Rud et al, 2006), Asner (1998) suggests that plant species should be distinguishable remotely due to differences in biochemical and structural properties. Species differences have been detected remotely (Burkholder, 2010;Narumalani et al, 2009;Pinard and Bannari, 2003;Rud et al, 2006;Schmidt and Skidmore, 2001;Yingying et al, 2011) by examining such 58 vegetation characteristics as total chlorophyll (chl), chl a, and chl b, carotenoids, soluble carbon (C), lignin, foliar N and phosphorus (P), leaf water content, compactness of the mesophyll layer, specific leaf area (SLA), and leaf mass per area (LMA) (Asner and Martin, 2011, 2009;Carlson et al, 2007;Castro-Esau et al, 2004).…”

Section: If Interspecific Differences In Vegetation Characteristics Amentioning

confidence: 99%

Assessing the Role of Invasive Species in Successional Plant Communities Using Hyperspectral Remote Sensing

Aneece¹

View full text Add to dashboard Cite

I AbstractBiodiversity has been correlated with ecosystem stability and function. Invasive species can decrease biodiversity and cause ecological and economical damage. These species are especially prevalent in abandoned agricultural fields, and can disrupt secondary successional dynamics. Although field surveys are used to assess the impacts of these species, remote sensing can be more efficient, especially at large spatial extents. I examined the ability to use ground-level hyperspectral remote sensing to study invasive species and their effects on community properties at the Blandy Experimental Farm (BEF) in north-central Virginia. Their effects on ecosystem properties could not be assessed using ground-level remote sensing in this system; thus, I used leaf and soil measurements to assess their effects on secondary succession.I found that remote sensing can be used to differentiate among plant communities.The most influential species to community discriminability are considered invasive, suggesting that these species can strongly influence species compositions and other community properties. The most influential wavelengths for discrimination were distributed throughout the spectral profile and corresponded with plant physiological and structural elements.Thus, spectral differences across species were large enough to be used in aggregate to differentiate plant communities. Additionally, these differences were large enough to differentiate individual species, but discriminability varied by species. The two thistle species that are similar phylogenetically and structurally were readily distinguished amongst each other. However, the shrubby buckthorn was difficult to distinguish from the oriental bittersweet vine despite phylogenetic distance and differences in structure. This was likely due to physical overlap in the field and thus the difficulty in obtaining pure signatures for discrimination. Discriminability also differed by the spectral region examined. Buckthorn and oriental bittersweet were least discriminable in the 550-599 nm and 650-699 nm regions, due 2 to greater intraspecific variability of spectral data in these regions.Additionally, remote sensing can be used to estimate higher order community properties like species diversity, and thus assess the effects of invasive species on plant diversity.However, correlations between species diversity and spectral diversity varied by the spectral transformation technique used and the spectral region examined. There was a strong positive correlation between the two in the visible region when band depth was used and in the near-infrared region when first derivatives were used. There were no strong correlations in the red edge, due to high intraspecific variability in chlorophyll content.Lastly, I assessed the effects of these exotic invasive species on ecosystem properties, specifically secondary succession, using leaf and soil data. Differences in soil characteristics were larger across fields and stages than across species. However, there were species-level ...

show abstract

Application of spectral features’ ratios for improving classification in partially calibrated hyperspectral imagery: a case study of separating Mediterranean vegetation species

Cited by 18 publications

References 16 publications

Optimizing the Timing of Unmanned Aerial Vehicle Image Acquisition for Applied Mapping of Woody Vegetation Species Using Feature Selection

Optimizing the Timing of Unmanned Aerial Vehicle Image Acquisition for Applied Mapping of Woody Vegetation Species Using Feature Selection

Distinguishing Early Successional Plant Communities Using Ground-Level Hyperspectral Data

Assessing the Role of Invasive Species in Successional Plant Communities Using Hyperspectral Remote Sensing

Contact Info

Product

Resources

About