Automated parameterisation for multi-scale image segmentation on multiple layers

Drăguţ, Lucian; Csillik, Ovidiu; Eisank, Clemens; Tiede, Dirk

doi:10.1016/j.isprsjprs.2013.11.018

Cited by 551 publications

(376 citation statements)

References 39 publications

Supporting

Mentioning

347

Contrasting

Unclassified

Order By: Relevance

“…A method to determine the rate of change in the variance of the generated regions is the ESP tool (Drăgut, Csillik, Eisank, & Tiede, 2014), which is widely used to pre-define segmentation levels in GEOBIA. In addition, the multi-resolution segmentation uses form constraints based on the shape index (see Equation 4).…”

Section: Methodsmentioning

confidence: 99%

Urban green valuation integrating biophysical and qualitative aspects

Lang

2017

European Journal of Remote Sensing

View full text Add to dashboard Cite

Urban green mapping has become an operational task in city planning, urban land management, and quality of life assessments. As a multi-dimensional, integrative concept, urban green comprising several ecological, socio-economic, and policy-related aspects. In this paper, the author advances the representation of urban green by deriving scale-adapted, policy-relevant units. These so-called geons represent areas of uniform green valuation under certain size and homogeneity constraints in a spatially explicit representation. The study accompanies a regular monitoring scheme carried out by the urban municipality of the city of Salzburg, Austria, using optical satellite data. It was conducted in two stages, namely SBG_QB (10.2 km², QuickBird data from 2005) and SBG_WV (140 km², WorldView-2 data from 2010), within the functional urban area of Salzburg. The geon delineation was validated by several quantitative measures and spatial analysis techniques, as well as ground documentation, including panorama photographs and visual interpretation. The spatial association pattern was assessed by calculating Global Moran’s I with incremental search distances. The final geonscape, consisting of 1083 units with an average size of 13.5 ha, was analyzed by spatial metrics. Finally, categories were derived for different types of functional geons. Future research paths and improvements to the described strategy are outlined.

show abstract

Section: Methodsmentioning

confidence: 99%

Urban green valuation integrating biophysical and qualitative aspects

Lang

2017

European Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The superimposed image is divided into homogeneous objects with consistent spatial positions. Estimation of scale parameter (ESP) [42,43] and the modified average segmentation evaluation index (ASEI) are used to guide the selection of the optimal segmentation scales for different ground objects. ESP, produced by Lucian et al (2010), is a scale parameter estimation plug-in developed for eCognition software that calculates the local variance (LV) of homogeneous image objects using different scale parameters.…”

Section: Mtis and Estimation Of Scale Parametersmentioning

confidence: 99%

A Novel Change Detection Approach for Multi-Temporal High-Resolution Remote Sensing Images Based on Rotation Forest and Coarse-to-Fine Uncertainty Analyses

Feng

Sui

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:In the process of object-based change detection (OBCD), scale is a significant factor related to extraction and analyses of subsequent change data. To address this problem, this paper describes an object-based approach to urban area change detection (CD) using rotation forest (RoF) and coarse-to-fine uncertainty analyses of multi-temporal high-resolution remote sensing images. First, highly homogeneous objects with consistent spatial positions are identified through vector-raster integration and multi-scale fine segmentation. The multi-temporal images are stacked and segmented under the constraints of a historical land use vector map using a series of optimal segmentation scales, ranging from coarse to fine. Second, neighborhood correlation image analyses are performed to highlight pixels with high probabilities of being changed or unchanged, which can be used as a prerequisite for object-based analyses. Third, based on the coarse-to-fine segmentation and pixel-based pre-classification results, change possibilities are calculated for various objects. Furthermore, changed and unchanged objects identified at different scales are automatically selected to serve as training samples. The spectral and texture features of each object are extracted. Finally, uncertain objects are classified using the RoF classifier. Multi-scale classification results are combined using a majority voting rule to generate the final CD results. In experiments using two pairs of real high-resolution remote sensing datasets, our proposed approach outperformed existing methods in terms of CD accuracy, verifying its feasibility and effectiveness.

show abstract

“…An estimation of scale parameter (ESP) tool was used to inform the selection of the optimal scale parameter for multi-resolution segmentation. It was implemented as a customised rule set in eCognition that runs multiple segmentations with a defined fixed increment for the scale parameter, and calculates the local variance (LV, the mean standard deviation for all objects) and the rate of change (ROC) to assess the change of LV from one scale level to another [39,40].…”

Section: Forest Mappingmentioning

confidence: 99%

Mapping Net Stocked Plantation Area for Small-Scale Forests in New Zealand Using Integrated RapidEye and LiDAR Sensors

Xu¹,

Morgenroth²,

Manley³

2017

Forests

View full text Add to dashboard Cite

Abstract:In New Zealand, approximately 70% of plantation forests are large-scale (over 1000 ha) with accurate resource description. In contrast, the remaining 30% of plantation forests are small-scale (less than 1000 ha). It is forecasted that these small-scale forests will supply nearly 40% of the national wood production in the next decade. However, in-depth description of these forests, especially those under 100 ha, is very limited. This research evaluates the use of remote sensing datasets to map and estimate the net stocked plantation area for small-scale forests. We compared a factorial combination of two classification approaches (Nearest Neighbour (NN), Classification and Regression Tree (CART)) and two remote sensing datasets (RapidEye, RapidEye plus LiDAR) for their ability to accurately classify planted forest area. CART with a combination of RapidEye and LiDAR metrics outperformed the other three combinations producing the highest accuracy for mapping forest plantations (user's accuracy = 90% and producer's accuracy = 88%). This method was further examined by comparing the mapped plantations with manually digitised plantations based on aerial photography. The mapping approach overestimated the plantation area by 3%. It was also found that forest patches exceeding 10 ha achieved higher conformance with the digitised areas. Overall, the mapping approach in this research provided a proof of concept for deriving forest area and mapping boundaries using remote sensing data, and is especially relevant for small-scale forests where limited information is currently available.

show abstract

Automated parameterisation for multi-scale image segmentation on multiple layers

Cited by 551 publications

References 39 publications

Urban green valuation integrating biophysical and qualitative aspects

Urban green valuation integrating biophysical and qualitative aspects

A Novel Change Detection Approach for Multi-Temporal High-Resolution Remote Sensing Images Based on Rotation Forest and Coarse-to-Fine Uncertainty Analyses

Mapping Net Stocked Plantation Area for Small-Scale Forests in New Zealand Using Integrated RapidEye and LiDAR Sensors

Contact Info

Product

Resources

About