Hierarchical land cover and vegetation classification using multispectral data acquired from an unmanned aerial vehicle

Ahmed, Oumer S.; Shemrock, Adam; Chabot, Dominique; Dillon, Chris; Williams, Griffin; Wasson, Rachel J.; Franklin, Steven E.

doi:10.1080/01431161.2017.1294781

Cited by 117 publications

(98 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…UAS therefore offer the potential to overcome these limitations and have been applied to monitor a disparate range of habitats and locations, including tropical forests, riparian forests, dryland ecosystems, boreal forests, and peatlands. Pioneering researchers have been using UAS to monitor attributes such as plant population [107,108]; biodiversity and species richness [109,110]; plant species invasion [111]; restoration ecology [112]; disturbances [113]; phenology [114]; pest infestation in forests [115,116]; and land cover change [117].…”

Section: Monitoring Of Natural Ecosystemsmentioning

confidence: 99%

On the Use of Unmanned Aerial Systems for Environmental Monitoring

et al. 2018

View full text Add to dashboard Cite

Environmental monitoring plays a central role in diagnosing climate and management impacts on natural and agricultural systems; enhancing the understanding of hydrological processes; optimizing the allocation and distribution of water resources; and assessing, forecasting, and even preventing natural disasters. Nowadays, most monitoring and data collection systems are based upon a combination of ground-based measurements, manned airborne sensors, and satellite observations. These data are utilized in describing both small-and large-scale processes, but have spatiotemporal constraints inherent to each respective collection system. Bridging the unique spatial and temporal divides that limit current monitoring platforms is key to improving our understanding of environmental systems. In this context, Unmanned Aerial Systems (UAS) have considerable potential to radically improve environmental monitoring. UAS-mounted sensors offer an extraordinary opportunity to bridge the existing gap between field observations and traditional air-and space-borne remote sensing, by providing high spatial detail over relatively large areas in a cost-effective way and an entirely new capacity for enhanced temporal retrieval. As well as showcasing recent advances in the field, there is also a need to identify and understand the potential limitations of UAS technology. For these platforms to reach their monitoring potential, a wide spectrum of unresolved issues and application-specific challenges require focused community attention. Indeed, to leverage the full potential of UAS-based approaches, sensing technologies, measurement protocols, postprocessing techniques, retrieval algorithms, and evaluation techniques need to be harmonized. The aim of this paper is to provide an overview of the existing research and applications of UAS in natural and agricultural ecosystem monitoring in order to identify future directions, applications, developments, and challenges.

show abstract

Section: Monitoring Of Natural Ecosystemsmentioning

confidence: 99%

On the Use of Unmanned Aerial Systems for Environmental Monitoring

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The camera included five narrow-band separate sensors: blue (center ~490 nm, width 20 nm), green (center ~510 nm, width 20 nm), red (center ~670 nm, width 10 nm), red-edge (center ~720 nm, width 10 nm) and near infra-red (center ~840 nm, width 40 nm). Similar narrow-band sensors were found more suitable for vegetation sensing compared to regular consumer-grade cameras [95,96]. The camera produced 1.2 mega-pixel images in a 12-bit raw format.…”

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

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

“…Such VIs can be highly useful for estimating biological parameters such as vegetation productivity and the leaf-area index (LAI; e.g. see Aasen et al 2015, Wehrhan et al 2016), and for the purpose of vegetation classification (Juszak et al 2017, Ahmed et al 2017, Müllerová et al 2017, Samiappan et al 2017, Dash et al 2017). Particularly in remote high-latitude ecosystems, where satellite records suggest a ‘greening’ based on NDVI time series (Fraser et al 2011, Guay et al 2014, Ju and Masek 2016), multispectral drone monitoring could play an important role in validating satellite remotely-sensed productivity trends (see Laliberte et al 2011, Matese et al 2015).…”

Section: Introductionmentioning

confidence: 99%

“…A variety of multispectral camera and sensor options are available and have been deployed with drones. These range from modified off-the-shelf digital cameras (Lebourgeois et al 2008, for examples see Berra et al 2017, Müllerová et al 2017), to compact purpose-build multi-band drone sensors such as the Parrot Sequoia (Ahmed et al 2017, Fernández-Guisuraga et al 2018) and the MicaSense Red-Edge (Samiappan et al 2017, Dash et al 2017). The Parrot Sequoia and MicaSense Red-Edge sensors are compact bundles (rigs) of 4-5 cameras with Complementary Metal-Oxide-Semiconductor (CMOS) (Weste 2011) sensors, a type of imaging sensor commonly found in the consumer cameras of phones and DSLRs.…”

Section: Introductionmentioning

confidence: 99%

“…There are several ways to convert image DNs into absolute surface reflectance, but the most common is the so-called empirical line approach: Images of surfaces with known reflectance are used to establish an assumed linear relationship (empirical line) between image DNs and surface reflectance under the specific light conditions of the survey (Laliberte et al 2011, Turner et al 2014, Wang and Myint 2015, Aasen et al 2015, Wehrhan et al 2016, Ahmed et al 2017, Crusiol et al 2017, Dash et al 2017). Additionally, information from incident light sensors, such as the Parrot Sequoia sunshine sensor may be incorporated to account for changes in irradiation during the flight.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vegetation monitoring using multispectral sensors – best practices and lessons learned from high latitudes

Assmann

Kerby

Cunliffe

et al. 2018

Preprint

View full text Add to dashboard Cite

17Emerging drone technologies have the potential to revolutionise ecological monitoring. The 18 rapid technological advances in recent years have dramatically increased affordability and 19 ease of use of Unmanned Aerial Vehicles (UAVs) and associated sensors. Compact 20 multispectral sensors, such as the Parrot Sequoia (Paris, France) and MicaSense RedEdge 21 (Seattle WA, USA) capture spectrally accurate high-resolution (fine grain) imagery in visible 22 and near-infrared parts of the electromagnetic spectrum, providing supplement to satellite 23 and aircraft-based imagery. Observations of surface reflectance can be used to calculate 24 vegetation indices such as the Normalised Difference Vegetation Index (NDVI) for 25 productivity estimates and vegetation classification. Despite the advances in technology, 26 challenges remain in capturing consistently high-quality data, particularly when operating in 27 extreme environments such as the high latitudes. Here, we summarize three years of 28 ecological monitoring with drone-based multispectral sensors in the remote Canadian Arctic. 2We discuss challenges, technical aspects and practical considerations, and highlight best 30 practices that emerged from our experience, including: flight planning, factoring in weather 31 conditions, and geolocation and radiometric calibration. We propose a standardised 32 methodology based on established principles from remote sensing and our collective field 33 experiences, using the Parrot Sequoia sensor as an example. With these good practises, 34 multispectral sensors can provide meaningful spatial data that is reproducible and 35 comparable across space and time. 36 37

show abstract

Hierarchical land cover and vegetation classification using multispectral data acquired from an unmanned aerial vehicle

Cited by 117 publications

References 33 publications

On the Use of Unmanned Aerial Systems for Environmental Monitoring

On the Use of Unmanned Aerial Systems for Environmental Monitoring

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

Vegetation monitoring using multispectral sensors – best practices and lessons learned from high latitudes

Contact Info

Product

Resources

About