Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Efficient pedestrian detection by directly optimizing the partial area under the ROC curve
Author: Paisitkriangkrai, S.
Shen, C.
Van Den Hengel, A.
Citation: Proceedings 2013 IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 1-8 December 2013: pp.1057-1064
Publisher: IEEE
Publisher Place: USA
Issue Date: 2013
Series/Report no.: IEEE International Conference on Computer Vision
ISBN: 9781479928392
ISSN: 1550-5499
Conference Name: International Conference on Computer Vision (2013 : Sydney)
Statement of
Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Hengel
Abstract: Many typical applications of object detection operate within a prescribed false-positive range. In this situation the performance of a detector should be assessed on the basis of the area under the ROC curve over that range, rather than over the full curve, as the performance outside the range is irrelevant. This measure is labelled as the partial area under the ROC curve (pAUC). Effective cascade-based classification, for example, depends on training node classifiers that achieve the maximal detection rate at a moderate false positive rate, e.g., around 40% to 50%. We propose a novel ensemble learning method which achieves a maximal detection rate at a user-defined range of false positive rates by directly optimizing the partial AUC using structured learning. By optimizing for different ranges of false positive rates, the proposed method can be used to train either a single strong classifier or a node classifier forming part of a cascade classifier. Experimental results on both synthetic and real-world data sets demonstrate the effectiveness of our approach, and we show that it is possible to train state-of-the-art pedestrian detectors using the proposed structured ensemble learning method.
Rights: © 2013 IEEE
RMID: 0020137293
DOI: 10.1109/ICCV.2013.135
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
hdl_83158.pdfAccepted version753.54 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.