English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Active Structured Learning for High-Speed Object Detection

Lampert, C., & Peters, J. (2009). Active Structured Learning for High-Speed Object Detection. In J. Denzler, G. Notni, & H. Süsse (Eds.), Pattern Recognition: 31st DAGM Symposium, Jena, Germany, September 9-11, 2009 (pp. 221-231). Berlin, Germany: Springer.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C301-D Version Permalink: https://hdl.handle.net/21.11116/0000-0002-E585-5
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
https://link.springer.com/content/pdf/10.1007%2F978-3-642-03798-6_23.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Lampert, CH1, 2, Author           
Peters, J1, 2, Author           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 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.
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.

Details

show
hide
Language(s):
 Dates: 2009-09
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/978-3-642-03798-6_23
BibTex Citekey: 6073
 Degree: -

Event

show
hide
Title: 31st Annual Symposium of the German Association for Pattern Recognition (DAGM 2009)
Place of Event: Jena, Germany
Start-/End Date: 2009-09-09 - 2009-09-11

Legal Case

show

Project information

show

Source 1

show
hide
Title: Pattern Recognition: 31st DAGM Symposium, Jena, Germany, September 9-11, 2009
Source Genre: Proceedings
 Creator(s):
Denzler, J, Editor
Notni, G, Editor
Süsse, H, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 221 - 231 Identifier: ISBN: 978-3-642-03797-9

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 5748 Sequence Number: - Start / End Page: - Identifier: -