The IEEE GRSS standardized remote sensing data website: A step towards "science 2.0" in remote sensing

The issue of homogeneity in performance assessment of proposed algorithms for information extraction is generally perceived also in the Earth Observation ( EO) domain. Different authors propose different dataset s to test their developed algorithms and to the reader i t is frequently difficult to assess which is better for his/her specific application, given the wide variability in test sets that makes pure comparison of e.g. accuracy va lues less meaningful than one would desire. With our wor k, we gave a modest contribution to ease the problem b y making it possible to automatically distribute a li mited set of possible “standard” open datasets, together with some ground truth info, and automatically assess processing results provided by the users. 1. CONTEXT AND RATIONALE The Geoscience and Remote Sensing Society (GRSS) [1] of the IEEE [2] has a mandate to foster researc h nd advance science in Remote Sensing. The fields of interest of the Society are the theor y, concepts, and techniques of science and engineering as they apply to the remote sensing of the Earth, ocea ns, atmosphere, and space, as well as the processing, interpretation and dissemination of such informatio n. The Image Analysis and Data Fusion Technical Committee (IADFTC) [3] of the GRSS serves as a global, multi-disciplinary network for geospatial d ata fusion, with the aim of connecting people and resou rces, educating students and professionals, and promoting the best practices in data fusion applications. Under the auspices of the GRSS Image Analysis and Data Fusion Technical Committee, an initiative call ed the Standardized Algorithm and Data Evaluation Working Group (SADE WG) has identified a set of community data sets and algorithm evaluation standa rds for use by the Earth remote sensing community. Encouraging young scientists and researchers to inv est in Remote Sensing and pursuing a scientific career in the field has always been a priority for the GRS So ciety in general, and the IADFTC in particular. This is accomplished at various levels, including organizin g a yearly Data Fusion Contest promoting progress on fusion and analysis methodologies for multisource remote sensing data; also, facilitating the dissemi nation and testing of new methods and algorithms for Remotely Sensed data processing, envisaging differe nt applications. In this context, an important initiative of the GRS S was to envisage the “Standardized Algorithm and Data Evaluation" (SADE) web site, intended to distribute a set of community data sets and algorithm evaluation standards for use by the Earth observation communit y to support research, development, and testing of algorithms for remote sensing data products. The SA DE website is conceived for remote sensing scientists, students, and professionals, who wish to evaluate t he performances of their image analysis methods on fre ely available data against undisclosed test samples. Th i is meant as an effort in favour of further steps towar ds “Science 2.0” in the Remote Sensing arena. A call for proposals for a web portal with the abov ementioned features was issued by IEEE GRSS in 2014. Our response to the call turned out to be the start ing point for the current GRSS Data and Algorithm Standardized website (DASE) [4], as it was renamed after a discussion on the final denomination of the real product. The web site is undergoing further development, which will make it even more userfriendly and flexible, and will hopefully encourage further curiosity and interest in the remote sensin g research community at large.