Abstract
The latest breed of very high resolution (VHR) commercial satellites opens new possibilities for cartographic and remote sensing applications. In this way, object based image analysis (OBIA) approach has been proved as the best option when working with VHR satellite imagery. OBIA considers spectral, geometric, textural and topological attributes associated with meaningful image objects. Thus, the first step of OBIA, referred to as segmentation, is to delineate objects of interest. Determination of an optimal segmentation is crucial for a good performance of the second stage in OBIA, the classification process. The main goal of this work is to assess the multiresolution segmentation algorithm provided by eCognition software for delineating greenhouses from WorldView- 2 multispectral orthoimages. Specifically, the focus is on finding the optimal parameters of the multiresolution segmentation approach (i.e., Scale, Shape and Compactness) for plastic greenhouses. The optimum Scale parameter estimation was based on the idea of local variance of object heterogeneity within a scene (ESP2 tool). Moreover, different segmentation results were attained by using different combinations of Shape and Compactness values. Assessment of segmentation quality based on the discrepancy between reference polygons and corresponding image segments was carried out to identify the optimal setting of multiresolution segmentation parameters. Three discrepancy indices were used: Potential Segmentation Error (PSE), Number-of-Segments Ratio (NSR) and Euclidean Distance 2 (ED2).
Highlights
The latest very high resolution (VHR) commercial satellites successfully launched over the past years (e.g., GeoEye-1, WorldView-2 and WorldView-3) are being the focus of intensive research in the remote sensing field
Regarding the scale parameter (SP) value computed by Estimation of Scale Parameter 2” (ESP2) tool (Dragut et al, 2014), the application of local variance (LV) to find the optimal SP in the multiresolution segmentation algorithm applied to segment greenhouses (WV2 MS orthoimage) achieved acceptable results
As far as we know, this work is the first attempt to identify the optimal values of the well-known multiresolution segmentation algorithm (i.e., SP, Shape and Compactness parameters) working on a plastic greenhouse area through an 8-band multispectral WV2 orthoimage
Summary
The latest very high resolution (VHR) commercial satellites successfully launched over the past years (e.g., GeoEye-1, WorldView-2 and WorldView-3) are being the focus of intensive research in the remote sensing field. Most of these research works were conducted using object based image analysis (OBIA) techniques (Carleer and Wolff, 2006; Stumpf and Kerle, 2011; Pu et al, 2011; Pu and Landry, 2012; Aguilar et al, 2013; Fernández et al, 2014; Heenkenda et al, 2015). OBIA techniques are based on aggregating similar pixels to obtain homogenous objects, which are assigned to a target class. A comprehensive review of the advantages and disadvantages of using OBIA techniques for image classification, as well as the state of the art of these methods, can be found in Blaschke (2010) and Blaschke et al (2014)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
