C_AssesSeg Concurrent Computing Version of AssesSeg: A Benchmark Between the New and Previous Version

摘要

This paper presents the capabilities of a command line tool (.exe) created to assess the quality of segmented digital images. The executable source code, called AssesSeg (Assess Segmentation), was written in Python 2.7 using only open source libraries. AssesSeg implements a modified version of the supervised discrepancy measure named Euclidean Distance 2 (ED2) and was tested on different satellite images (Sentinel-2, Landsat 8, World View-2 and WorldView-3). The segmentation was applied to plastic covered greenhouse detection in the south of Spain (Almeria). AssesSeg 2.0 was compared with the previous version computing time. The comparisons showed how the new version can benefit from modern multi-core CPU.