Hierarchical Cascade of Classifiers for Efficient Poselet Evaluation
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.31
Abstract
Poselets have been used in a variety of computer vision tasks, such as detection, segmentation, action classification, pose estimation and action recognition, often achieving state-of-the-art performance. Poselet evaluation, however, is computationally intensive as it involves running thousands of scanning window classifiers. We present an algorithm for training a hierarchical cascade of part-based detectors and apply it to speed up poselet evaluation. Our cascade hierarchy leverages common components shared across poselets. We generate a family of cascade hierarchies, including trees that grow logarithmically on the number of poselet classifiers. Our algorithm, under some reasonable assumptions, finds the optimal tree structure that maximizes speed for a given target detection rate. We test our system on the PASCAL dataset and show an order of magnitude speedup at less than 1% loss in AP.
Session
Image Classification
Files
Extended Abstract (PDF, 1 page, 1.4M)Paper (PDF, 12 pages, 1.8M)
Bibtex File
Presentation
Citation
Bo Chen, Pietro Perona and Lubomir Bourdev. Hierarchical Cascade of Classifiers for Efficient Poselet Evaluation. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.31
title = {Hierarchical Cascade of Classifiers for Efficient Poselet Evaluation},
author = {Chen, Bo and Perona, Pietro and Bourdev, Lubomir},
year = {2014},
booktitle = {Proceedings of the British Machine Vision Conference},
publisher = {BMVA Press},
editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
doi = { http://dx.doi.org/10.5244/C.28.31 }
}