Effective October 1, 2012, QUALCOMM Incorporated completed a corporate reorganization in which the assets of certain of its businesses and groups, as well as the stock of certain of its direct and indirect subsidiaries, were contributed to Qualcomm Technologies, Inc. (QTI), a wholly-owned subsidiary of QUALCOMM Incorporated. Learn more about these changes

You are here

Real time visual methods for shape-based object detection and RGB-D camera relocalisation

Feb 12, 2013

Detecting objects and computing pose are two central requirements for a range of agile systems in robotics, wearables and mobiles. Developing methods that are fast to operate and train is of critical importance in particular if new information needs to be incorporated immediately into the system.

This talk will cover two methods we have recently developed for real-time (framerate) training and operation. The first is aimed at scalable, textureless, and multi-object detection based around the idea of scanning paths. We build a tractable approach to extract edge configurations described with invariance to scale and rotation and that importantly allows for in-situ training and detection. This method works on conventional RGB cameras and is amenable to work on low processing platforms such as mobiles.

The second method aims to rapidly compute the pose of an RGBD camera visiting a space previously mapped. This problem known as relocalisation is key to develop agile perceptual systems that can go in and out of 3D environments where precise 6D estimation of pose is important such as for Augmented Reality, assembly guidance or manipulation. The method uses a regression approach and is fast enough to replace tracking altogether

Dr. Walterio Mayol-Cuevas, University of Bristol
Date: 12-2-13
Time: 14:15 -15:45
Location: TU Vienna
Zemanek Lecture Room (Room Number: HHEG01)
HS 13 Ernst Melan
1040 Wien, Karlsplatz 13 (Main building, Stiege VII, 2nd floor)

Download the presentation slides

Event Location

TU Vienna - Zemanek Lecture Room (Room Number: HHEG01)
1040 Vienna Favoritenstraße 9-11, Stiege III, ground floor, light green area