Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/107587
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Pedestrian detection with spatially pooled features and structured ensemble learning
Author: Paisitkriangkrai, S.
Shen, C.
Van Den Hengel, A.
Citation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016; 38(6):1243-1257
Publisher: IEEE
Issue Date: 2016
ISSN: 0162-8828
1939-3539
Statement of
Responsibility: 
Sakrapee Paisitkriangkrai, Chunhua Shen, and 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 prescribed range is irrelevant. This measure is labelled as the partial area under the ROC curve (pAUC). 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. In addition, in order to achieve high object detection performance, we propose a new approach to extracting low-level visual features based on spatial pooling. Incorporating spatial pooling improves the translational invariance and thus the robustness of the detection process. 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 with spatially pooled features. The result is the current best reported performance on the Caltech-USA pedestrian detection dataset.
Keywords: Pedestrian detection; boosting; ensemble learning; spatial pooling; structured learning
Rights: © 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
RMID: 0030049930
DOI: 10.1109/TPAMI.2015.2474388
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107587.pdfRestricted Access746.45 kBAdobe PDFView/Open


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