Abstract
Superpixels, as a state-of-the-art segmentation paradigm, have recently been widely used in computer vision and pattern recognition. Despite the effectiveness of these algorithms, there are still many limitations and challenges dealing with Very High-Resolution (VHR) satellite images especially in complex urban scenes. In this paper, we develop a superpixel algorithm as a modified edge-based version of Simple Linear Iterative Clustering (SLIC), which is here called ESLIC, compatible with VHR satellite images. Then, based on the modified properties of generated superpixels, a heuristic multi-scale approach for building extraction is proposed, based on the stereo satellite imagery along with the corresponding Digital Surface Model (DSM). First, to generate the modified superpixels, an edge-preserving term is applied to retain the main building boundaries and edges. The resulting superpixels are then used to initially refine the stereo-extracted DSM. After shadow and vegetation removal, a rough building mask is obtained from the normalized DSM, which highlights the appropriate regions in the image, to be used as the input of a multi-scale superpixel segmentation of the proper areas to determine the superpixels inside the building. Finally, these building superpixels with different scales are integrated and the output is a unified building mask. We have tested our methods on building samples from a WorldView-2 dataset. The results are promising, and the experiments show that superpixels generated with the proposed ESLIC algorithm are more adherent to the building boundaries, and the resulting building mask retains urban object shape better than those generated with the original SLIC algorithm.
Highlights
Segmentation, as an integral and basic part of computer vision and image processing, literally means to segment the image into meaningful pieces or into the “ingredients” that a human mind unconsciously does
Later some studies have been proposed superpixel algorithms based on the multi-scale formation of Normalized Cuts (Ncuts) in [20,21], and more recently [22] in which a Linear Spectral Clustering (LSC) superpixel algorithm as a normalized formation of Ncuts is proposed that measures the color similarity and space proximity between image pixels
It demonstrates that in comparison to Simple Linear Iterative Clustering (SLIC) and level set algorithms, ESLIC superpixels have lower Under-Segmentation Error (UE), meaning lower percentage of pixel leakage from the ground truth boundaries. This advantage is due to using textural as well as spectral features in the ESLIC superpixel generation
Summary
Segmentation, as an integral and basic part of computer vision and image processing, literally means to segment the image into meaningful pieces or into the “ingredients” that a human mind unconsciously does. Since early in 2000s, Blaschke et al discussed the question: ‘what is wrong with pixels?’ [5] They introduced a new paradigm in image segmentation known as Object Based Image Analysis (OBIA) which led to the development of object-oriented GIS and remote sensing software. The seeds are updated in each iteration to form the final superpixels [6] They are generally known as over-segmentation methods; segmenting an image into small regions which are smaller than objects. Deep learning techniques are basically machine learning methods with multi-layer (deep) convolutional neural networks, that can deal with huge amount of input data to predict the output They are increasingly being used in segmentation and classification problems in the field of remote sensing applications as well and have been reported to get promising results [15].
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
