An hierarchical object based image analysis approach to extract impervious surfaces within the domestic garden

Abstract

Creating detailed and easy to produce land cover maps of urban residential areas continue to be a challenge. In this research, we discuss and illustrate a methodology for VHR multispectral image segmentation and classification of impervious surfaces. On two levels we have firstly detected impervious and pervious land surfaces and secondly rooftops, pathways and gardens. By using a second image, we have tackled the problem of large shaded areas in the most recent multispectral Quickbird image, used as the main input. Our final map had an overall accuracy of 63,8% and a kappa value of 0,457. These accuracy values can be considered as good, yet may be improved by further fine-tuning the approach and postprocessing.

Classification of Multi-temporal Images using Machine Learning

“…Image quality) any medium quality (Mitkari et al, 2017;Yu et al, 2016) to high-quality image will work with this approach. And if one cannot get hands-on high-resolution (Hay et al, 2005;Verbeeck et al, 2011) data, then go with sentinel-2 (Whyte et al, 2018) data rather than going for landsat-2 (Wieland et al, 2016). This study was done keeping mainly India in mind as India is a developing nation so the Chandigarh area was selected for this research.…”

“…For image pre-processing Gis-Software (Verbeeck et al, 2011) is used to perform all the necessary tasks. Apart from this Ecognition Developer 9.0 software is used, which is specifically developed for OBIA and for the ROI (region of interest) creation that will be used as a training data set for machine learning algorithms and for thematic change Envi 5.1 software is utilized.…”

“…Secondly, in the segmentation settings the hyperparameter and image layer weights of the algorithm should be Blue:Green:Nir: Red to 1:1:2:1. Nonetheless the last hyper-parameter is composition of homogenous (Castillejo-gonzález et al, 2014;Whiteside et al, 2011) criterion where the shape is set to 0.2 and compactness (Verbeeck et al, 2011) to 0.8. In the end, export the image with all the 4-bands with a file extension of .tif file.…”

“…So, after the creation of 2nd ROI one can simply reconcile it with ROI map on both the classified image. Now go to Classification and select post-classification in envi (Hay et al, 2005;Jingping et al, 2016) from that further select Confusion Matrix and, in that select, using ground truth ROI, as a result, the overall accuracy plus the kappa-coefficient (Verbeeck et al, 2011) will be calculated by the software.…”

External geo-information in the segmentation of VHR imagery improves the detection of imperviousness in urban neighborhoods

“…While other areas are segmented with the same scale parameter into small homogenous segments, the shadowed areas remain relatively large and heterogeneous in terms of land cover. To overcome this problem, 'shadow' was first considered as a class of interest to ensure that these large heterogeneous objects could be selected for a second segmentation, resulting in smaller, more homogenous objects within the shadowed areas (Zhou et al, 2009;Verbeeck et al, 2011).…”