Abstract
Automatic building extraction from satellite images, an open research topic in remote sensing, continues to represent a challenge and has received substantial attention for decades. This paper presents an object-based and machine learning-based approach for automatic house detection from RGB high-resolution images. The images are first segmented by an algorithm combing a thresholding watershed transformation and hierarchical merging, and then shadows and vegetation are eliminated from the initial segmented regions to generate building candidates. Subsequently, the candidate regions are subjected to feature extraction to generate training data. In order to capture the characteristics of house regions well, we propose two kinds of new features, namely edge regularity indices (ERI) and shadow line indices (SLI). Finally, three classifiers, namely AdaBoost, random forests, and Support Vector Machine (SVM), are employed to identify houses from test images and quality assessments are conducted. The experiments show that our method is effective and applicable for house identification. The proposed ERI and SLI features can improve the precision and recall by 5.6% and 11.2%, respectively.
Highlights
Automatic object extraction has been a popular topic in the field of remote sensing for decades, but extracting buildings and other anthropogenic objects from monocular remotely sensed images is still a challenge
In order to measure how strongly these lines are perpendicular or parallel to each other, we developed a group of indices called edge regularity indices (ERI) that can describe the spatial relations between these lines
We propose an object-based image analysis (OBIA) and machine learning based approach for detecting houses from RGB high-resolution images
Summary
Automatic object extraction has been a popular topic in the field of remote sensing for decades, but extracting buildings and other anthropogenic objects from monocular remotely sensed images is still a challenge. With the rapid progress of sensors, remotely sensed images have become the most important data source for urban monitoring and map updating in geographic information systems (GIS) [1]. Buildings are the most salient objects on satellite images, and extracting buildings becomes an essential task. Buildings take various shapes, which makes them difficult to extract using a simple and uniform model. Aerial and satellite images often contain a number of other objects (e.g., trees, roads, and shadows), which make the task harder. The increasing amount of textural information does not warrant a proportional increase in accuracy but rather makes image segmentation extremely difficult
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.
