{"date_published":"2009-10-07T00:00:00Z","intvolume":"      5748","extern":1,"acknowledgement":"This work was funded in part by the EU project CLASS, IST 027978.\nConference Information URL: http://www.optecnet.de/veranstaltungen/2009/09/dagm-2009/","year":"2009","volume":5748,"quality_controlled":0,"type":"conference","_id":"3715","citation":{"mla":"Lampert, Christoph, and Jan Peters. <i>Active Structured Learning for High-Speed Object Detection</i>. Vol. 5748, Springer, 2009, pp. 221–31, doi:<a href=\"https://doi.org/10.1007/978-3-642-03798-6_23\">10.1007/978-3-642-03798-6_23</a>.","short":"C. Lampert, J. Peters, in:, Springer, 2009, pp. 221–231.","ama":"Lampert C, Peters J. Active structured learning for high-speed object detection. In: Vol 5748. Springer; 2009:221-231. doi:<a href=\"https://doi.org/10.1007/978-3-642-03798-6_23\">10.1007/978-3-642-03798-6_23</a>","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.","chicago":"Lampert, Christoph, and Jan Peters. “Active Structured Learning for High-Speed Object Detection,” 5748:221–31. Springer, 2009. <a href=\"https://doi.org/10.1007/978-3-642-03798-6_23\">https://doi.org/10.1007/978-3-642-03798-6_23</a>.","apa":"Lampert, C., &#38; 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. <a href=\"https://doi.org/10.1007/978-3-642-03798-6_23\">https://doi.org/10.1007/978-3-642-03798-6_23</a>"},"publist_id":"2642","abstract":[{"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.","lang":"eng"}],"author":[{"orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Christoph Lampert","last_name":"Lampert","first_name":"Christoph"},{"first_name":"Jan","full_name":"Peters, Jan","last_name":"Peters"}],"date_created":"2018-12-11T12:04:46Z","conference":{"name":"DAGM: German Association For Pattern Recognition"},"status":"public","doi":"10.1007/978-3-642-03798-6_23","page":"221 - 231","alternative_title":["LNCS"],"day":"07","publication_status":"published","date_updated":"2021-01-12T07:51:41Z","month":"10","publisher":"Springer","title":"Active structured learning for high-speed object detection"}