Header logo is ei

Active Structured Learning for High-Speed Object Detection

2009

Conference Paper

ei


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.

Author(s): Lampert, CH. and Peters, J.
Book Title: DAGM 2009
Journal: Pattern Recognition: 31st DAGM Symposium
Pages: 221-231
Year: 2009
Month: September
Day: 0
Editors: Denzler, J. , G. Notni, H. S{\"u}sse
Publisher: Springer

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1007/978-3-642-03798-6_23
Event Name: 31st Annual Symposium of the German Association for Pattern Recognition
Event Place: Jena, Germany

Address: Berlin, Germany
Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{6073,
  title = {Active Structured Learning for High-Speed Object Detection},
  author = {Lampert, CH. and Peters, J.},
  journal = {Pattern Recognition: 31st DAGM Symposium},
  booktitle = {DAGM 2009},
  pages = {221-231},
  editors = {Denzler, J. , G. Notni, H. S{\"u}sse},
  publisher = {Springer},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Berlin, Germany},
  month = sep,
  year = {2009},
  month_numeric = {9}
}