18 September 2013 Shoreline extraction from light detection and ranging digital elevation model data and aerial images
Author Affiliations +
Optical Engineering, 53(1), 011006 (2013). doi:10.1117/1.OE.53.1.011006
Abstract
There is an increased demand for understanding the accurate position of the shorelines. The automatic extraction of shorelines utilizing the digital elevation models (DEMs) obtained from light detection and ranging (LiDAR), aerial images, and multispectral images has become very promising. In this article, we develop two innovative algorithms that can effectively extract shorelines depending on the available data sources. The first is a multistep morphological technique that works on LiDAR DEM with respect to a tidal datum, whereas the second depends on the availability of training data to extract shorelines from LiDAR DEM fused with aerial images. Unlike similar techniques, the morphological approach detects and eliminates the outliers that result from waves, etc., by means of an anomaly test with neighborhood constraints. Additionally, it eliminates docks, bridges, and fishing piers along the extracted shorelines by means of Hough transform. The second approach extracts the shoreline by means of color space conversion of the aerial images and the support vector machines classifier to segment the fused data into water and land. We perform Monte-Carlo simulations to estimate the confidence interval for the error in shoreline position. Compared with other relevant techniques in literature, the proposed methods offer better accuracy in shoreline extraction.
© 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)
Amr H. Yousef, Khan M. Iftekharuddin, Mohammad A. Karim, "Shoreline extraction from light detection and ranging digital elevation model data and aerial images," Optical Engineering 53(1), 011006 (18 September 2013). http://dx.doi.org/10.1117/1.OE.53.1.011006
JOURNAL ARTICLE
16 PAGES


SHARE
KEYWORDS
LIDAR

Image segmentation

Data modeling

Coastal modeling

Hough transforms

Optical engineering

RGB color model

Back to Top