Talk by Mihai Datcu
(CNAM, Amphitheatre Jean Prouvé (accès 11), 10:30 – 12:00, November 29, 2018)
Artificial Intelligence (AI), i.e. machine and deep learning methods are mainly used for image classification or object segmentation. The data sets are an organic part of the learning process, and also of the performance evaluation of the algorithms. High and particularly very high-resolution (VHR) Earth Observation (EO) applications primarily aim at the semantic labeling of land cover structures or objects as well as of temporal evolution classes. Therefore, we need reliable labeled data sets and tools to train the developed algorithms and assess the performance of the AI paradigms.
The lecture introduces solutions for very specific EO cases as VHR multispectral, Synthetic Aperture Radar (SAR) and multi-temporal observations. Further are described and discussed procedures and machine learning based tools to generate large semantic training and benchmark data sets. The particularities of relative data set biases and cross-dataset generalization are reviewed and an algorithmic analysis frame is introduced. Finally, are reviewed and analyzed several examples of EO benchmark data sets.