Publication Details

Real-Time Pose Estimation Piggybacked on Object Detection

JURÁNEK Roman, HEROUT Adam, DUBSKÁ Markéta and ZEMČÍK Pavel. Real-Time Pose Estimation Piggybacked on Object Detection. In: Proceedings of ICCV. Santiago: IEEE Computer Society, 2015, pp. 1-9. ISBN 978-1-4673-8391-2.
Czech title
Odhad pózy objektu přidružená k detekci objektů
Type
conference paper
Language
english
Authors
Keywords

Object detection, Pose estimation, Sliding window detector, Channel features

Abstract

We present an object detector coupled with pose estimation directly in a single compact and simple model, where the detector shares extracted image features with the pose estimator. The output of the classification of each candidate window consists of both object score and likelihood map of poses. This extension introduces negligible overhead during detection so that the detector is still capable of real time operation. We evaluated the proposed approach on the problem of vehicle detection. We used existing datasets with viewpoint/pose annotation (WCVP, 3D objects, KITTI).  Besides that, we collected a new traffic surveillance dataset COD20k which fills certain gaps of the existing datasets and we make it public. The experimental results show that the proposed approach is comparable with state-of-the-art approaches in terms of accuracy, but it is considerably faster -- easily operating in real time (Matlab with C++ code). The source codes and the collected COD20k dataset are made public along with the paper.

Published
2015
Pages
1-9
Proceedings
Proceedings of ICCV
Conference
International Conference on Computer Vision, Santiago, CL
ISBN
978-1-4673-8391-2
Publisher
IEEE Computer Society
Place
Santiago, CL
UT WoS
000380414100266
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB10963,
   author = "Roman Jur\'{a}nek and Adam Herout and Mark\'{e}ta Dubsk\'{a} and Pavel Zem\v{c}\'{i}k",
   title = "Real-Time Pose Estimation Piggybacked on Object Detection",
   pages = "1--9",
   booktitle = "Proceedings of ICCV",
   year = 2015,
   location = "Santiago, CL",
   publisher = "IEEE Computer Society",
   ISBN = "978-1-4673-8391-2",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10963"
}
Back to top