Catégorie : Talks

Talk by Mihai Datcu
CNAM, room 21.1.05, 10:30 – 12:00, January 23, 2020
The implicit data models and the expected parameters on which they are dependent may introduce biases in the Earth Observation (EO) data analysis methodologies. The estimated parameters can describe only particular, limited observations behavior. The broad diversity of the EO data, as sensing modalities, spatial, spectral, and radiometric resolution, and also the huge variety of the observed scenes make problematic the definition of a general model.
The lecture presents a communication channel approach for image information extraction. The information retrieval is elaborated based on data compression methods independent of the type, form, content or purpose of the data. This paradigm is common to any data type without the weakening effect of specializing it for specific, particular applications fields. This is realized by approaching these challenges from an Information Theoretic perspective and using also the latest progress in Algorithmic Information Theory. The objective is re-formulating the definition of the “relevant information” in relation to the notions of “image content” and “context”, for a broader class of data, including scientific and engineering instruments records.

Talk by Mihai Datcu
CNAM, room 31.3.10 (accès 31, 3rd floor), 10:00 – 12:00, November 20, 2019
Since the very beginning of satellite remote sensing the methods and applications the Satellite Image Time Series (SITS) are the main nature of Earth Observation. Presently, with the regular observations and free and open access of the Copernicus data the impact of SITS is largely amplified. The challenges of the EO Big Data are critically accentuated due to joint volume explosion, high acquisition velocity and sensor variety.
The presentation emphasizes novel Artificial Intelligence (AI) paradigms to convert the SITS into valuable EO products with impact in new applications for understanding of the Earth cover spatio-temporal processes over long periods of time. AI for EO is largely an interdisciplinary field and involves the convergence of very different methods. The lecture overviews and discuss specific topics for SITS regarding the orbit, mission, sensor constellations, intelligent agents, machine learning, deep learning, data indexing, data bases, and DNN.

Talk by Mihai Datcu
(Campus Pierre et Marie Curie de Sorbonne Université, salle 105 du LIP6 couloir 25-26 au 1er étage, 14:30 – 16:00, April 5th, 2019)
The Earth is facing unprecedented climatic, geomorphologic, environmental and anthropogenic changes, which require global scale observation and monitoring. Thus a multitude of new orbital and suborbital Earth Observation (EO) sensors and mission are in operation or will be soon launched. The interest is in a global understanding involving observation of large extended areas, and long periods of time, with a broad variety of EO sensors. The collected EO data volumes are thus increasing immensely with a rate of many Terabytes of data a day. With the current EO technologies these figure will be soon amplified, the horizons are beyond Zettabytes of data. The challenge is the exploration of these data and the timely delivery of focused information and knowledge in a simple understandable format.
Therefore, search engines, and Data Mining are new fields of study that have arisen to seek solutions to automating the extraction of information from EO observations and other related sources that can lead to Knowledge Discovery and the creation of an actionable intelligence. Knowledge Discovery is among the most interesting research trends, however, the real challenge is to combine Artificial Intelligence with the power and potential of human intelligence, this being a primary objective in the field of Human Machine Communication (HMC). The goal is to go beyond the today methods of information retrieval and develop new concepts and methods to support end users of EO data to interactively analyze the information content, extract relevant parameters, associate various sources of information, learn and/or apply knowledge and to visualize the pertinent information without getting overwhelmed. In this context, the synergy of HMC and information retrieval becomes an interdiscipl!
inary approach in automating EO data analysis.

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.

Talk by Mihai Datcu
(Centrale-Supélec, 3 rue Joliot-Curie, 91190 Gif-sur-Yvette: Salle du Conseil, Laboratoire des Signaux et Systèmes (L2S), Bâtiment Breguet, 11:00-12:30, May 4th, 2018; Café/croissants from 10:30)
The challenges of the Synthetic Aperture Radar (SAR) image formation principles, the high data volume and the very high acquisition rate stimulated from the very beginning the elaborations of sophisticated techniques. Meanwhile the SAR technologies have immensely evolved. The state of the art sensors deliver widely different imaging modes, and have made considerable progress in spatial and radiometric resolution, target acquisition strategies, or geographical coverage and data rates. Generally imaging sensors generate an isomorphic representation of the observed scene. This is not the case for SAR, the observations are a doppelganger of the scattered field, an indirect signature of the imaged object. This spots the load of SAR image understanding, and the outmost challenge of Big SAR Data Science, as a new and particular challenge of Machine Learning (ML) and Artificial Intelligence (AI). The presentation reviews and analyses the new approaches of SAR imaging leveraging the recent advances in physical process based ML and AI methods and signal processing. These is leading to Computational Imaging paradigms where intelligence is the analytical component of the end-to-end sensor and Data Science chain design. A particular focus is on the scientific methods of Deep Learning and an information theoretical model of the SAR information extraction process.

Talk by Mihai Datcu
(CNAM, Amphitheatre George Friedmann, 10:30 – 12:00, March 9, 2018)
The volume and variety of valuable Earth Observation (EO) images as well as non-EO related data is rapidly growing. The open free data access becomes widespread and has an enormous scientific and socio-economic relevance. EO images are acquired by sensors on satellite, suborbital or airborne platforms. They extend the observation beyond the visual information, gathering physical parameters of the observed scenes in a broad electromagnetic spectrum. The sensed information depends largely on the imaging geometry, orbit, illumination and other specific parameters of the space instruments. Typical EO systems can be classified into optical or radar instruments. During the last years, both types of sensors deliver widely different images, and both have made considerable progress in spatial and radiometric resolution, image acquisition strategies, and data rates.
Therefore, the domain of EO Data Science spans from mathematical models for the satellite orbit, the physics of electromagnetic propagation and scattering, signal processing, machine learning, AI and knowledge representation. The new specific EO methods to Data Analytics and Data Mining are designed to leverage advances in physical parameters extraction and leads to AI paradigms where learning is a critical non-traditional element joining the overall EO system parameters to achieve the optimal information extraction. This involves the inclusion of machine or deep learning and reasoning tools in the EO data processing chains together with supplementary external information to analyze target characteristics, to perform classification, to search for similarities or extract semantic entities. Information-theoretic approaches are the fundament for modeling the end-2-end system behavior and analyze its performance and bounds.