Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Efficient pedestrian detection by directly optimizing the partial area under the ROC curve|
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|
|Series/Report no.:||IEEE International Conference on Computer Vision|
|Conference Name:||International Conference on Computer Vision (2013 : Sydney)|
|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|
|Appears in Collections:||Computer Science publications|
Files in This Item:
|hdl_83158.pdf||Accepted version||753.54 kB||Adobe PDF||View/Open|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.