The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Improved Object Detection and Pose Using Part-Based Models

På svenska

Author

Editor

  • Joni-Kristian Kämäräinen
  • Markus Koskela

Summary, in English

Automated object detection is perhaps the most central task of computer vision and arguably the most difficult one. This paper extends previous work on part-based models by using accurate geometric models both in the learning phase and at detection. In the learning phase manual annotations are used to reduce perspective distortion before learning the part-based models. That training is performed on rectified images, leads to models which are more specific, reducing the risk of false positives. At the same time a set of representative object poses are learnt. These are used at detection to remove perspective distortion. The method is evaluated on the bus category of the Pascal dataset with promising results.

Publishing year

2013

Language

English

Pages

396-407

Publication/Series

Lecture Notes in Computer Science (Image Analysis : 18th Scandinavian Conference, SCIA 2013, Espoo, Finland, June 17-20, 2013. Proceedings)

Volume

7944

Document type

Conference paper

Publisher

Springer

Topic

  • Mathematics

Conference name

18th Scandinavian Conference on Image Analysis (SCIA 2013)

Conference date

2013-06-17 - 2013-06-20

Conference place

Espoo, Finland

Status

Published

Research group

  • Mathematical Imaging Group

ISBN/ISSN/Other

  • ISSN: 0302-9743
  • ISSN: 1611-3349
  • ISBN: 978-3-642-38885-9 (print)
  • ISBN: 978-3-642-38886-6 (online)