Real-Time Pose Estimation Piggybacked on Object Detection
Juránek R., Herout A., Dubská M., Zemčík P.
Graph@FIT, Brno University of Technology
Corresponding author email: ijuranek[at]fit.vutbr.cz
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).
@INPROCEEDINGS{
author = {Juránek Roman and Herout Adam and Dubská Markéta and Zemčík Pavel},
title = {Real-Time Pose Estimation Piggybacked on Object Detection},
booktitle = {ICCV},
year = {2015}
}
Video
Acknowledgements
This research was supported by the CEZMSMT project IT4I -- CZ 1.05/1.1.00/02.0070, and by the project Visual Computing Competence Center -- V3C, TE01020415.