Informatické kolokvium 31. 10. Advances in Learning for Robots Perception
Informatické kolokvium 31. 10. 2017, 14:00 posluchárna D2
prof. ing. Jana Košecká, Ph.D., George Mason University, Google Brain, Mountain
View, CA, USA
Advances in Learning for Robots Perception
Abstrakt: Advancements in robotic navigation, mapping, object search and
recognition rest to a large extent on robust, efficient and scalable semantic
understanding of the surrounding environment. In recent years we have developed
several approaches for capturing geometry and semantics of environment from
video, RGB-D data, or just simply a single RGB image, focusing on indoors and
outdoors environments elevant for robotics applications.
I will demonstrate our work on predicting locations of generic objects in videos
acquired by a moving vehicle, for detailed semantic parsing using deep
convolutional neural networks (CNNs), object detection and object pose recovery
from single RGB image. The applicability of the presented techniques for
autonomous driving, service robotics, mapping and augmented reality applications
will be discussed.