TY  - CONF
AU  - Jiaolong Xu
AU  - David Vazquez
AU  - Antonio Lopez
AU  - Javier Marin
AU  - Daniel Ponsa
A2  - IV
PY  - 2013//
TI  - Learning a Multiview Part-based Model in Virtual World for Pedestrian Detection
BT  - IEEE Intelligent Vehicles Symposium
SP  - 467
EP  - 472
PB  - IEEE
KW  - Pedestrian Detection
KW  - Virtual World
KW  - Part based
N2  - State-of-the-art deformable part-based models based on latent SVM have shown excellent results on human detection. In this paper, we propose to train a multiview deformable part-based model with automatically generated part examples from virtual-world data. The method is efficient as: (i) the part detectors are trained with precisely extracted virtual examples, thus no latent learning is needed, (ii) the multiview pedestrian detector enhances the performance of the pedestrian root model, (iii) a top-down approach is used for part detection which reduces the searching space. We evaluate our model on Daimler and Karlsruhe Pedestrian Benchmarks with publicly available Caltech pedestrian detection evaluation framework and the result outperforms the state-of-the-art latent SVM V4.0, on both average miss rate and speed (our detector is ten times faster).
SN  - 1931-0587
SN  - 978-1-4673-2754-1
L1  - http://158.109.8.37/files/xvl2013a.pdf
UR  - http://dx.doi.org/10.1109/IVS.2013.6629512
N1  - ADAS; 600.054; 600.057
ID  - Jiaolong Xu2013
ER  -