Please use this identifier to cite or link to this item:
Title: Group cost-sensitive boosting with multi-scale decorrelated filters for pedestrian detection
Authors: Zhou, Chengju
Wu, Meiqing
Lam, Siew-Kei
Keywords: Engineering
Issue Date: 2017
Source: Zhou, C., Wu, M. & Lam, S. (2017). Group cost-sensitive boosting with multi-scale decorrelated filters for pedestrian detection. The British Machine Vision Conference 2017.
metadata.dc.contributor.conference: The British Machine Vision Conference 2017
Abstract: We propose a novel two-stage pedestrian detection framework that combines multiscale decorrelated filters to extract more discriminative features and a novel group costsensitive boosting algorithm. The proposed boosting algorithm is based on mixture loss to alleviate the influence of annotation errors in training data and explores varying cost for different types of misclassification. Experiments on Caltech and INRIA datasets show that the proposed framework achieves the best detection performance among all state-of-the-art non-deep learning methods. In addition, the proposed approach runs 88X faster than the best performing method from the widely-known Filtered Channel Feature framework.
DOI: 10.5244/C.31.48
Schools: School of Computer Science and Engineering 
Rights: © 2017 The Authors. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
paper048.pdf1.71 MBAdobe PDFThumbnail

Citations 50

Updated on Sep 27, 2023

Page view(s)

Updated on Sep 27, 2023

Download(s) 50

Updated on Sep 27, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.