Inh.: Dr. Renate Gorre
Fon: +49 (0)7533 97227
Fax: +49 (0)7533 97228
Selected Readings in
Vision and Graphics
edited by Luc Van Gool, Gábor Székely, Markus Gross, Bernt Schiele
Alain D. Lehmann,
Efficient Object Detection.
2011. XII, 142 pages. EUR 64,00.
A long-term goal of computer vision is to interpret visual sceneries, in other words, to let computer perceive like humans do. To this end, computers have to localise and categorise objects in images. This fundamental task is called object detection and is the subject of this work. The difficulty of this task lies in the vast number of possible object locations and the strong variations of an object's appearance.
This dissertation focuses on efficient localisation; we analyse and discuss several strategies. These investigations lead to a novel branch&rank algorithm that detects with often less than 100 ranking operations. This allows for rich appearance models (like non-linear SVMs) which eventually improves overall performance.
About the author
Alain D. Lehmann received his PhD degree (Dr. Sc. ETH) in 2011 and his MSc in Computer Science ETH in 2006, both from ETH Zurich. During his studies he visited various research laboratories across Europe, namely IRISA Rennes and INRIA Sophia-Antipolis in France, as well as the Southampton University in the United Kingdom. After finishing his master thesis in 2006, supervised by Prof. Dr. John Shawe-Taylor, he started as a research assistant at the Computer Vision Laboratory of ETH Zurich headed by Prof. Dr. Luc Van Gool. Dr. Lehmann won the "Best Impact Paper Award" at the British Machine Vision Conference in 2011 for his work on efficient branch&rank object detection.
Keywords: object detection.
Reihe " Selected Readings in Vision and Graphics " im Hartung-Gorre Verlag
Direkt bestellen bei / to order directly from:
Hartung-Gorre Verlag / D-78465 Konstanz / Germany
Telefon: +49 (0) 7533 97227 Telefax: +49 (0) 7533 97228