Karel Košnar — accepted AI-conference papers

2023

Towards Visual Classification Under Class Ambiguity

Viktor Kozák, Jan Mikula, Lukáš Bertl, Karel Košnar, Libor Přeučil

ICRA 2023poster

Visual classification under uncertainty is a complex computer vision problem. We present a thorough comparison of several variants of convolutional neural network (CNN) classification techniques in the context of ambiguous image data interpretation. We explore possible improvements in classification…

Cited by 2 Source ↗Scholar ↗

2020

Accurate and Robust Teach and Repeat Navigation by Visual Place Recognition: A CNN Approach

Luis G. Camara, Tomáš Pivoňka, Martin Jílek, Carl Gäbert, Karel Košnar, Libor Přeučil

IROS 2020poster

We propose a novel teach-and-repeat navigation system, SSM-Nav, which is based on the output of the recently introduced SSM visual place recognition methodology. During the teach phase, a teleoperated wheeled robot stores in a database features of images taken along an arbitrary route. During the re…

Cited by 20 Source ↗Scholar ↗