Abstract
Abstract. In this paper, we propose distributed feature extraction tool from high spatial resolution remote sensing images. Tool is based on Apache Hadoop framework and Hadoop Image Processing Interface. Two corner detection (Harris and Shi-Tomasi) algorithms and five feature descriptors (SIFT, SURF, FAST, BRIEF, and ORB) are considered. Robustness of the tool in the task of feature extraction from LandSat-8 imageries are evaluated in terms of horizontal scalability.
Highlights
Acquiring remote sensing data has been improved to an anomalous line
We focus on local image features (LIFs) and implementation of distributed feature extraction tool (DIFET) for high spatial resolution remote sensing images
To extract LIFs features from high spatial resolution remote sensing images, we use Hadoop Image Processing Interface (HIPI)1, which is based on MapReduce approach
Summary
Acquiring remote sensing data has been improved to an anomalous line. The volume of global data archive could even be on the Exabyte level because of both of improvements in spatial, spectral, radiometric, and temporal resolutions and increasing number of satellites by year by. We have big remote sensing data with characteristics of multi-source, multi-scale, high-dimensional, and etc. LIFs are computed at multiple points in the image and are more robust to occlusion, clutter and illumination change. They are invariant to translation, rotation, scale, affine transformation, and presence of noise, blur etc. We focus on LIFs and implementation of distributed feature extraction tool (DIFET) for high spatial resolution remote sensing images. To extract LIFs features from high spatial resolution remote sensing images, we use Hadoop Image Processing Interface (HIPI), which is based on MapReduce approach.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
