Urban Objects Segmentation Using Edge Detection

Abstract

This manuscript describes urban objects segmentation using edge detection methods. The goal of this research was to compare an efficiency of edge detection methods for orthophoto and LiDAR data segmentation. The following edge detection methods were used: Sobel, Prewitt and Laplacian, with and without Gaussian kernel. The results have shown, that LiDAR data is better, because it does not contain shadows, which produce a noise.

An Improved Method of Land Masking for Synthetic Aperture Radar-based Ship Detection

“…An edge of an object is an image in a region where changes in image intensity are significant (Kodors and Zarembo, 2013; Singh and Kaur, 2013). Thus, an edge can be defined as a set of connected pixels that lie on a particular boundary between two regions (Singh and Kaur, 2013).…”

“…The image approach exploits image analysis techniques (for example, segmentation and edge detection) in order to isolate the coastline for building a mask by discriminating land pixels from sea pixels (Margarit et al, 2009; Romeiser et al, 2005). Image segmentation is the process of partitioning a digital image into several regions of similar features (Al-amri et al, 2010; Ramadevi et al, 2010; Senthilkumaran and Rajesh, 2009), and edge detection is one of the segmentation processes commonly used for digital images (Kodors and Zarembo, 2013). Many techniques for segmentation are in use: interferometry on SAR image pairs (Dellepiane et al, 2004), wavelet-based active contour model (Della Rocca et al, 2004), morphological filtering (Shu et al, 2010), non-local fuzzy C-means algorithm (Feng et al, 2013), mathematical morphology (Mashaly et al, 2014), etc.…”

Land Cover Recognition using Min-Cut/Max-Flow Segmentation and Orthoimages

“… the edge detection [6][7][8];  the watershed algorithm [9];  the expectation-maximization method [7];  the genetic algorithms [7], [10];  Kohenen's self-organizing maps [10];  min-cut/max-flow segmentation [11]- [14].…”