--- _id: '3715' abstract: - lang: eng text: 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. Consecutive frames in high speed video sequences are typically very redundant, and for training an object detection system, it is sufficient to have training labels from only a subset of all images. We propose an active learning method that select training examples in a data-driven way, thereby minimizing the required number of training labeling. Experiments on realistic data show that the active learning is superior to previously used methods for dataset subsampling for this task. acknowledgement: |- This work was funded in part by the EU project CLASS, IST 027978. Conference Information URL: http://www.optecnet.de/veranstaltungen/2009/09/dagm-2009/ alternative_title: - LNCS author: - first_name: Christoph full_name: Christoph Lampert id: 40C20FD2-F248-11E8-B48F-1D18A9856A87 last_name: Lampert orcid: 0000-0001-8622-7887 - first_name: Jan full_name: Peters, Jan last_name: Peters citation: ama: 'Lampert C, Peters J. Active structured learning for high-speed object detection. In: Vol 5748. Springer; 2009:221-231. doi:10.1007/978-3-642-03798-6_23' apa: 'Lampert, C., & Peters, J. (2009). Active structured learning for high-speed object detection (Vol. 5748, pp. 221–231). Presented at the DAGM: German Association For Pattern Recognition, Springer. https://doi.org/10.1007/978-3-642-03798-6_23' chicago: Lampert, Christoph, and Jan Peters. “Active Structured Learning for High-Speed Object Detection,” 5748:221–31. Springer, 2009. https://doi.org/10.1007/978-3-642-03798-6_23. ieee: 'C. Lampert and J. Peters, “Active structured learning for high-speed object detection,” presented at the DAGM: German Association For Pattern Recognition, 2009, vol. 5748, pp. 221–231.' ista: 'Lampert C, Peters J. 2009. Active structured learning for high-speed object detection. DAGM: German Association For Pattern Recognition, LNCS, vol. 5748, 221–231.' mla: Lampert, Christoph, and Jan Peters. Active Structured Learning for High-Speed Object Detection. Vol. 5748, Springer, 2009, pp. 221–31, doi:10.1007/978-3-642-03798-6_23. short: C. Lampert, J. Peters, in:, Springer, 2009, pp. 221–231. conference: name: 'DAGM: German Association For Pattern Recognition' date_created: 2018-12-11T12:04:46Z date_published: 2009-10-07T00:00:00Z date_updated: 2021-01-12T07:51:41Z day: '07' doi: 10.1007/978-3-642-03798-6_23 extern: 1 intvolume: ' 5748' month: '10' page: 221 - 231 publication_status: published publisher: Springer publist_id: '2642' quality_controlled: 0 status: public title: Active structured learning for high-speed object detection type: conference volume: 5748 year: '2009' ...