In order to join virtual sessions, you must be registered and logged-in(Were you registered for the in-person meeting in Denver? if yes, just log in.) 
Note: All session times are in Mountain Daylight Time.

A cloud-based framework for arctic high spatial resolution aerial image processing through Apache Spark

Authors: Dexuan Sha*, George Mason University, Chaowei Yang, George Mason University, Xin Miao, Missouri State University
Topics: Cyberinfrastructure, Polar Regions, Remote Sensing
Keywords: cryosphere, cyberinfrastructures, big data, Spark, OBIA, aerial imagery
Session Type: Paper
Presentation File: No File Uploaded


Sea ice observation and simulation are requiring high spatial resolution (HSR) imagery as ground truth in validation and modeling process. However, the large data volume in size and number pose grand challenges for domain scientists and data engineers to efficiently integrate standalone algorithms for high-speed computing. This paper proposes a cloud-based framework with Spark and HBase database to improve the large-number-small-size photos processing and analysis in parallel mode, and deconstruct object-based image analysis (OBIA) workflow for HSR aerial image classification. The experiment results show that the proposed system could not only provide a scalable and efficient fashion to handle large-size HSR images, but also speed up the OBIA classification process.

To access contact information login