Multi-scale GEOBIA with very high spatial resolution digital aerial imagery: scale, texture and image objects

Kim, Minho; Warner, Timothy A.; Madden, Marguerite; Atkinson, D

doi:10.1080/01431161003745608

Cited by 158 publications

(124 citation statements)

References 35 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…The broadest extent of literature has emphasized defining individual plant reflectance spectra and optimizing spectral discrimination of vegetation classes [54][55][56][57][58][59][60][61][62][63][64]. Other studies have tested innovative approaches to classifying vegetation, including comparing use of different remote sensing data sources [65][66][67][68][69], testing object-based image analysis techniques [69][70][71][72][73][74][75], and other methods [76][77][78]. In addition to automated analysis methods, vegetation classes have long been digitized by hand [79][80][81].…”

Section: Invoking Multiple Stable State Theorymentioning

confidence: 99%

Multiple Stable States and Catastrophic Shifts in Coastal Wetlands: Progress, Challenges, and Opportunities in Validating Theory Using Remote Sensing and Other Methods

et al. 2015

View full text Add to dashboard Cite

Multiple stable states are established in coastal tidal wetlands (marshes, mangroves, deltas, seagrasses) by ecological, hydrological, and geomorphological feedbacks. Catastrophic shifts between states can be induced by gradual environmental change or by disturbance events. These feedbacks and outcomes are key to the sustainability and resilience of vegetated coastlines, especially as modulated by human activity, sea level rise, and climate change. Whereas multiple stable state theory has been invoked to model salt marsh responses to sediment supply and sea level change, there has been comparatively little empirical verification of the theory for salt marshes or other coastal wetlands. Especially lacking is long-term evidence documenting if or how stable states are established and maintained at ecosystem scales. Laboratory and field-plot studies are informative, but of necessarily limited spatial and temporal scope. For the purposes of long-term, coastal-scale monitoring, remote sensing is the best viable option. This review summarizes the above topics and highlights the emerging promise and challenges of using remote sensing-based analyses to validate coastal OPEN ACCESS Remote Sens. 2015, 7 10185 wetland dynamic state theories. This significant opportunity is further framed by a proposed list of scientific advances needed to more thoroughly develop the field.

show abstract

Section: Invoking Multiple Stable State Theorymentioning

confidence: 99%

Multiple Stable States and Catastrophic Shifts in Coastal Wetlands: Progress, Challenges, and Opportunities in Validating Theory Using Remote Sensing and Other Methods

et al. 2015

View full text Add to dashboard Cite

show abstract

“…The window size should be selected according to the physical size of the target plants; it should be large enough to include the entire plant, but not too large to introduce noise from the neighbouring plants. Interestingly, the scale dependency of the classification performance has also been observed in OBIA studies [39], where different performances were achieved with different segmentation sizes.…”

Section: Discussionmentioning

confidence: 84%

Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a UAV

2014

View full text Add to dashboard Cite

The development of low-cost unmanned aerial vehicles (UAVs) and light weight imaging sensors has resulted in significant interest in their use for remote sensing applications. While significant attention has been paid to the collection, calibration, registration and mosaicking of data collected from small UAVs, the interpretation of these data into semantically meaningful information can still be a laborious task. A standard data collection and classification work-flow requires significant manual effort for segment size tuning, feature selection and rule-based classifier design. In this paper, we propose an alternative learning-based approach using feature learning to minimise the manual effort required. We apply this system to the classification of invasive weed species. Small UAVs are suited to this application, as they can collect data at high spatial resolutions, which is essential for the classification of small or localised weed outbreaks. In this paper, we apply feature learning to generate a bank of image filters that allows for the extraction of features that discriminate between the weeds of interest and background objects. These features are pooled to summarise the image statistics and form the input to a texton-based linear classifier that classifies an image patch as weed or background. We evaluated our approach to weed classification on three weeds of significance in Australia: water hyacinth, tropical soda apple and serrated tussock. Our results showed that collecting images at 5-10 m resulted in the highest classifier accuracy, indicated by F1 scores of up to 94%.Remote Sens. 2014, 6 12038

show abstract

“…Previous studies emphasized intensive data requirements [25,26,[28][29][30] and repetitive testing on the applications of vegetation mapping, but those approaches may not form robust procedures toward long-term image processing with uncertain data sources (i.e., validation points) and the lack of multiple attributes. Moreover, segmentation studies (reviewed by [32][33][34][35][36][37]) have not been extensively applied to natural vegetation using a robust approach.…”

Section: Motivationmentioning

confidence: 99%

Hierarchical Segmentation Framework for Identifying Natural Vegetation: A Case Study of the Tehachapi Mountains, California

Liau

2014

Remote Sensing

View full text Add to dashboard Cite

Two critical limitations of very high resolution imagery interpretations for time-series analysis are higher imagery variances and large data sizes. Although object-based analyses with a multi-scale framework for diverse object sizes are one potential solution, more data requirements and large amounts of testing at high costs are required. In this study, I applied a three-level hierarchical vegetation framework for reducing those costs, and a three-step procedure was used to evaluate its effects on a digital orthophoto quadrangles with 1 m spatial resolution.Step one and step two were for image segmentation optimized for delineation of tree density, which involved global Otsu's method followed by the random walker algorithm.Step three was for detailed species delineations, which were derived from multiresolution segmentation, in two test areas.Step one and step two were able to delineating tree density segments and label species association robustly, compared to previous hierarchical frameworks. However, step three was limited by less image information to produce detailed, reasonable image objects with optimal scale parameters for species labeling. This hierarchical vegetation framework has potential to develop baseline data for evaluating climate change impacts on vegetation at lower cost using widely available data and a personal laptop.Keywords: object-based image analysis; image segmentation optimized for delineation of tree density; very high resolution imagery; species association labeling; the Z values of Moran's I

show abstract

Multi-scale GEOBIA with very high spatial resolution digital aerial imagery: scale, texture and image objects

Cited by 158 publications

References 35 publications

Multiple Stable States and Catastrophic Shifts in Coastal Wetlands: Progress, Challenges, and Opportunities in Validating Theory Using Remote Sensing and Other Methods

Multiple Stable States and Catastrophic Shifts in Coastal Wetlands: Progress, Challenges, and Opportunities in Validating Theory Using Remote Sensing and Other Methods

Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a UAV

Hierarchical Segmentation Framework for Identifying Natural Vegetation: A Case Study of the Tehachapi Mountains, California

Contact Info

Product

Resources

About