28 June 2017 Multifeature fusion for automatic building change detection in wide-area imagery
Author Affiliations +
Abstract
A strategy for detecting changes in known building regions in multitemporal visible and near-infrared imagery based on a linear combination of independent features is presented. Features identified for building and background detection include vegetation, texture, shadow intensity, and distance from known road areas. The resulting building candidates are classified by shape using a unique difference of Gaussian technique. Building regions reported in the reference dataset that indicate the initial observation time are revisited to check for changes in building candidates not identified in the feature fusion strategy. The performance of the proposed technique is tested on real-world aerial imagery and is evaluated visually and quantitatively. Compared with the gradient and normalized difference vegetation index-based building detection methods, the proposed fusion methodology yields better results. For building detection, it provided a completeness result of an average 82.08% and building change detection completeness result of an average 85.67% in our evaluations with five sample images, which included rural, suburban, and urban areas.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Daniel Prince, Paheding Sidike, Almabrok Essa, Vijayan Asari, "Multifeature fusion for automatic building change detection in wide-area imagery," Journal of Applied Remote Sensing 11(2), 026040 (28 June 2017). https://doi.org/10.1117/1.JRS.11.026040 . Submission: Received: 6 February 2017; Accepted: 8 June 2017
Received: 6 February 2017; Accepted: 8 June 2017; Published: 28 June 2017
JOURNAL ARTICLE
21 PAGES


SHARE
Back to Top