Two major limitations of real-time visual SLAM algorithms are the restricted range of views over which they can operate and their lack of robustness when faced with erratic camera...
Denis Chekhlov, Mark Pupilli, Walterio W. Mayol-Cu...
Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...
Sudheendra Vijayanarasimhan (University of Texas a...
: Ambient Intelligent (AmI) vision is a new concept materialized by the Six Framework Program of the European Community. It involves three key technologies: Ubiquitous Computing, U...
Visual tracking, in essence, deals with non-stationary data streams that change over time. While most existing algorithms are able to track objects well in controlled environments,...
Simultaneous localisation and mapping using a single camera becomes difficult when erratic motions violate predictive motion models. This problem needs to be addressed when visual...