University of Birmingham > Talks@bham > IRLab Seminars: Robotics, Computer Vision & AI > From Classical to the Post Modern: What has Changed in SLAM in Dynamic Scenes?

From Classical to the Post Modern: What has Changed in SLAM in Dynamic Scenes?

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

If you have a question about this talk, please contact Martin Rudorfer.

This talk will present a temporal view (temporal as limited to the work done in our lab, over the last 12 years on tackling the intractable problem of reconstructing moving objects with a moving monocular camera. What have been the classical formulations prior to the Deep Learning era and what has changed since the last 5 years and what are indeed the problems that remain. The talk will also conclude time permitting with a ring side view of other problems worked upon in our lab in the context of vision, learning and navigation.

K Madhava Krishna suffers from the illusion of heading the Robotics Research Center @ IIIT Hyderabad for the last 16 years, while the more realistic assessment is that he has merely held fort and either as a culmination of several chance events in a sequence or through good fortune (whichever way you want to see the puzzle) ended up working with top notch students who went on to become top notch researchers worldwide. During the hey days of 2017 the lab was ranked 22nd in the world in Robotics Research as per sandwiched between Stanford and Cornell (yes!!) and 2nd in Asia that made him wonder if he should now withdraw and look at other pressing problems such as indeed if it is possible that the brain can create the mind? But a safety-first option saw him shelf such extravagant ideas and he continued to work towards maintaining fort while always hoping such plethora of chance events continue to happen.

This talk is part of the IRLab Seminars: Robotics, Computer Vision & AI 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.