University of Birmingham > Talks@bham > Artificial Intelligence and Natural Computation seminars > Machine Learning and Computer Vision on Mars

Machine Learning and Computer Vision on Mars

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Hector Basevi.

Host: Prof Peter Tino

Speaker’s homepage:

The systematic exploration of Mars over the last decades has generated a large volume of data, which have significantly improved the understanding of the past and present processes taking place on the planet. However, the optimal exploitation of the acquired data is impeded by the obsolete paradigm followed in planetary data analysis, according to which the input data are “manually” examined one-at-a-time by expert scientists, while hardly using any of the recent advances in machine learning, data fusion/big-data, computer vision, etc. As a matter of fact, the rapid progress in computer science that coincided Mars exploration is the root cause of severe compatibility issues that further curtail the semantic analysis that can be achieved through multi-temporal data comparison/fusion. This seminar is based on my recent research to resolve the above major challenges following a two-branch approach; firstly, computer vision and data processing tools are developed to integrate multi-temporal data to consistent datasets and, secondly, machine learning techniques are transferred to Mars data science to automate the semantic data analysis in a big-data framework. Apart from presenting the work done in this direction, a detailed future research plan based on the lessons learned will be discussed, along with possible applications of the developed technology to other space science and remote sensing domains.

This talk is part of the Artificial Intelligence and Natural Computation seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


Talks@bham, University of Birmingham. Contact Us | Help and Documentation | Privacy and Publicity.
talks@bham is based on from the University of Cambridge.