Skip to main content Skip to main navigation

Publication

Active Structured Learning for High-Speed Object Detection

Christoph H. Lampert; Jan Peters
In: Joachim Denzler; Gunther Notni; Herbert Süße (Hrsg.). Pattern Recognition, 31st DAGM Symposium, Proceedings. Annual Symposium of the German Association for Pattern Recognition (DAGM-2009), September 9-11, Jena, Germany, Pages 221-231, Lecture Notes in Computer Science, Vol. 5748, Springer, 2009.

Abstract

High-speed smooth and accurate visual tracking of objects in arbitrary, unstructured environments is essential for robotics and human motion analysis. However, building a system that can adapt to arbitrary objects and a wide range of lighting conditions is a challenging problem, especially if hard real-time constraints apply like in robotics scenarios. In this work, we introduce a method for learning a discriminative object tracking system based on the recent structured regression framework for object localization. Using a kernel function that allows fast evaluation on the GPU, the resulting system can process video streams at speed of 100 frames per second or more.

More links