Previous Article in event Previous Article in session
Next Article in event
Design and Optimization of Mach-Zehnder Interferometer Sensor for Dye Sensing by Using Central Composite Design Coupled with Surface Response MethodNext Article in session
Object-Based Feature Extraction of Google Earth Imagery for Mapping Termite Mounds in Amazon's Savannas
Published: 02 June 2014 by MDPI in International Electronic Conference on Sensors and Applications session Applications
Abstract: This study investigates the potential of object-based feature extraction from Google Earth Imagery for mapping termite mounds in Amazon's savannas. Termite mounds are often hotspots of plant growth (i.e. primary productivity). Accurate and timely information about termite mounds is crucial for land management decision-making and ecosystem monitoring. To address this issue, the effectiveness of object-based feature extraction that use automated image segmentation to extract meaningful ground features from imagery was tested. The study used very high resolution multispectral Google Earth images to produce termite mounds maps in Bahia, Brazil. The results from the study indicated that an object-based approach provides a better means for ground feature extraction than a pixel based method because it provides an effective way to incorporate spatial information and expert knowledge into the feature extraction process. Also the results suggest that Google earth imagery has considerable potential in mapping termite mounds in Amazon's savannas.
Keywords: Object-based image analysis; Feature extraction; Remote sensing; Google Earth; Termite mounds; Amazon