Multiscale Object Feature Library for Habitat Quality Monitoring in Riparian Forests

Strasser, Thomas; Lang, Stefan; Riedler, Barbara; Pernkopf, Lena; Paccagnel, K

doi:10.1109/lgrs.2013.2278335

Cited by 13 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Operator-and scene-dependency of rulesets can impair the repeatability and transferability of KBC workflows across scenes and sensors for the same land cover of interest. We propose to organize rulesets into target-and sensor-specific libraries [59,60] and systematically store a set of classified image objects as "bag-of-image-objects" (BIO) for refining and adapting KBC workflows. It is important to emphasize that our approach is not a fully-developed system architecture but instead represents a road map for an "image-to-assessment pipeline" that links integral components like class explanation, remote sensing expert knowledge, domain ontology [61,62], multiscale image content modeling, and ecological model integration.…”

Section: Conceptual Framewokmentioning

confidence: 99%

An Object-Based Image Analysis Approach for Detecting Penguin Guano in very High Spatial Resolution Satellite Images

Witharana

Lynch

2016

Remote Sensing

View full text Add to dashboard Cite

Abstract:The logistical challenges of Antarctic field work and the increasing availability of very high resolution commercial imagery have driven an interest in more efficient search and classification of remotely sensed imagery. This exploratory study employed geographic object-based analysis (GEOBIA) methods to classify guano stains, indicative of chinstrap and Adélie penguin breeding areas, from very high spatial resolution (VHSR) satellite imagery and closely examined the transferability of knowledge-based GEOBIA rules across different study sites focusing on the same semantic class. We systematically gauged the segmentation quality, classification accuracy, and the reproducibility of fuzzy rules. A master ruleset was developed based on one study site and it was re-tasked "without adaptation" and "with adaptation" on candidate image scenes comprising guano stains. Our results suggest that object-based methods incorporating the spectral, textural, spatial, and contextual characteristics of guano are capable of successfully detecting guano stains. Reapplication of the master ruleset on candidate scenes without modifications produced inferior classification results, while adapted rules produced comparable or superior results compared to the reference image. This work provides a road map to an operational "image-to-assessment pipeline" that will enable Antarctic wildlife researchers to seamlessly integrate VHSR imagery into on-demand penguin population census.

show abstract

Section: Conceptual Framewokmentioning

confidence: 99%

An Object-Based Image Analysis Approach for Detecting Penguin Guano in very High Spatial Resolution Satellite Images

Witharana

Lynch

2016

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…on the level of individual protected sites. VHR satellite data and object-based class modelling enable fine-scaled, yet area-wide forest habitat mapping and monitoring (STRASSER et al 2014). This was tested for riparian zones, which represent complex ecosystems that consist of biotic and abiotic functional elements.…”

Section: Fine-scale Monitoring Of Riparian Forest Habitatsmentioning

confidence: 99%

“…A semi-automated approach (STRASSER et al 2014, STRASSER et al 2012) was set up for mapping riparian forest habitats in Europe by applying class modelling of EUNIS-3 (European Nature Information System, Level 3) (DAVIES 2004) habitats, and incorporating strategies for the transferability to different nature protected habitat sites as well as additional information. WorldView-2 satellite data with 0.5 m GSD and 8 multispectral bands, covering the Natura 2000 site Salzach river floodplain (Austria), were used for a 3-level hierarchical representation of riparian forest habitats (Fig.…”

Section: Fine-scale Monitoring Of Riparian Forest Habitatsmentioning

confidence: 99%

“…The levels represent different scale domains in a continuous scale spectrum. Based on an initial tree species classification level (-1) and composed forest stands (level 0), final habitats (level +1) were delineated by using a semantic model derived from the EUNIS classification scheme (STRASSER et al, 2014). The classification of forest stands, resulting in phyto-sociological units, was based on the tree species dominance.…”

Section: Fine-scale Monitoring Of Riparian Forest Habitatsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-scale Forest Habitat Monitoring Using Remote Sensing Data

Osberger¹,

Strasser²,

Riedler³

et al. 2015

GI_Forum 2014 – Geospatial Innovation for Society

View full text Add to dashboard Cite

Remote sensing imagery and advanced image analysis methods show high potential for monitoring forest habitat issues. The objective of this paper is to provide ready-to-use information on forest habitats by conducting a multi-scale approach for the delineation of such, and the assessment of their conservation status on multi-spectral satellite imagery of high and very high spatial resolution, as well as LiDAR data. This information should help forest managers in the decision-making process and contribute to a sustainable management. The evaluation of the quality of forest habitats is performed on suitable indicators such as structure and composition on broad-scale for whole landscapes and on fine-scale for individual protected sites. In this context, information layers and direct habitat mapping can help to address the complex task of monitoring forest habitats and to harmonize information output.

show abstract

“…When aggregating the original pixel information in a stepwise manner, the higher-level objects' internal heterogeneity is increasing, leading to more functional homogeneity in the sense of Spence (1961). Using this strategy, some composite classes can be directly delineated by image segmentation, for example, forest stands with limited internal heterogeneity as composed by tree species with similar spectral behavior (Strasser et al 2014). However, most often composite classes are defined by internal heterogeneity that exceeds the capability of state-of-the-art segmentation algorithms .…”

Section: Geons Representing Functional Land-use Classes Rationalementioning

confidence: 99%

Geons – domain-specific regionalization of space

Lang

Kienberger

Tiede

et al. 2014

Cartography and Geographic Information Science

View full text Add to dashboard Cite

The design of methods and tools to build adequate representations of complex geographical phenomena in a way that spatial patterns are emphasized is one of the core objectives of GIScience. In this paper, we build on the concept of geons as a strategy to represent and analyze latent spatial phenomena across different geographical scales (local, national, regional) incorporating domain-specific expert knowledge. Focusing on two types, we illustrate and exemplify how geons are generated and explored. So-called composite geons represent functional land-use classes, required for regional planning purposes. They are created via class modeling to translate interpretation schemes from mapping keys. Integrated geons, on the other hand, address abstract, yet policy-relevant phenomena such as societal vulnerability to hazards. They are delineated by regionalizing continuous geospatial data sets representing relevant indicators in a multidimensional variable space. Using the geon approach, we create spatially exhaustive sets of units, scalable to the level of policy intervention, homogenous in their domain-specific response, and independent from any predefined boundaries. From a GIScience perspective, we discuss either type of geons in a semantic hierarchy of geographic information constructs. Despite its validity for decision-making and its transferability across scales and application fields, the delineation of geons requires further methodological research to assess their statistical and conceptual robustness.

show abstract

Multiscale Object Feature Library for Habitat Quality Monitoring in Riparian Forests

Cited by 13 publications

References 13 publications

An Object-Based Image Analysis Approach for Detecting Penguin Guano in very High Spatial Resolution Satellite Images

An Object-Based Image Analysis Approach for Detecting Penguin Guano in very High Spatial Resolution Satellite Images

Multi-scale Forest Habitat Monitoring Using Remote Sensing Data

Geons – domain-specific regionalization of space

Contact Info

Product

Resources

About