Detail publikace

Real-Time Pose Estimation Piggybacked on Object Detection

JURÁNEK, R. HEROUT, A. JURÁNKOVÁ, M. ZEMČÍK, P.

Originální název

Real-Time Pose Estimation Piggybacked on Object Detection

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

JURÁNEK, R.; HEROUT, A.; JURÁNKOVÁ, M.; ZEMČÍK, P.

Rok RIV

2015

Vydáno

18. 12. 2015

Nakladatel

IEEE Computer Society

Místo

Santiago

ISBN

978-1-4673-8391-2

Kniha

Proceedings of ICCV

Strany od

1

Strany do

9

Strany počet

9

BibTex

@inproceedings{BUT123622,
  author="Roman {Juránek} and Adam {Herout} and Markéta {Juránková} and Pavel {Zemčík}",
  title="Real-Time Pose Estimation Piggybacked on Object Detection",
  booktitle="Proceedings of ICCV",
  year="2015",
  pages="1--9",
  publisher="IEEE Computer Society",
  address="Santiago",
  isbn="978-1-4673-8391-2"
}