University of Cambridge > Talks.cam > Computer Laboratory Wednesday Seminars > Remote sensing and computer vision – just analysis of images from different sensors?

Remote sensing and computer vision – just analysis of images from different sensors?

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

  • UserClement Atzberger - BOKU University, Austria & Mantle Labs Ltd., UK
  • ClockWednesday 27 October 2021, 15:05-15:55
  • HouseOnline.

If you have a question about this talk, please contact Ben Karniely.

Both, computer vision (CV) and satellite-based remote sensing (Earth Observation – EO), devote much efforts to the analysis of imagery for deriving useful information. As a result of the enormous progress in CV over the past 2 decades, one sees nowadays a huge influx of CV-based research into the EO community. A large fraction of more traditional remote sensing experts, however, is still rather sceptical if CV developed methods are really game-changers for Earth Observation. This is partly due to the sheer amount of published CV-based papers in remote sensing journals with little guidance and unclear quality, but also due to differences in terminology. Together this hinders uptake and complicates mutual understanding.

In my personal opinion, there are also more fundamental differences between the two fields which deserve attention. This concerns especially the importance of radiometric, respectively, structural information. The former is of utmost importance in EO for prominent applications such as crop/tree species identification, biomass/yield estimates, nitrogen/irrigation management, crop health/status assessments, etc., in particular in combination with its temporal evolution. The structural information provided by the imagery, although present, offers on the other hand in the EO domain only very limited information.

Indeed, I believe that a correct identification of similarities and differences could potentially lead to a joint – and boosted – progress. In this talk I will try to highlight main differences, areas of overlap and what each field could potentially learn from the other.

Link to join: https://cl-cam-ac-uk.zoom.us/j/97767639783?pwd=T09GcVJxZUNEUFEvRnZnbWwxeEwzQT09

This talk is part of the Computer Laboratory Wednesday Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity