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).
Learning a multiview part-based model in virtual world for pedestrian detection
2013-06-01
1027781 byte
Conference paper
Electronic Resource
English
LEARNING A MULTIVIEW PART-BASED MODEL IN VIRTUAL WORLD FOR PEDESTRIAN DETECTION
British Library Conference Proceedings | 2013
|Multiview Pedestrian Detection Based on Vector Boosting
Springer Verlag | 2007
|Two-stage part-based pedestrian detection
IEEE | 2012
|