Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning
- 28 August 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 38 (6), 1243-1257
- https://doi.org/10.1109/tpami.2015.2474388
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 realworld 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
Other Versions
Funding Information
- Data to Decisions CRC Centre
This publication has 54 references indexed in Scilit:
- Fast Feature Pyramids for Object DetectionIeee Transactions On Pattern Analysis and Machine Intelligence, 2014
- Seeking the Strongest Rigid DetectorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Pedestrian detection at 100 frames per secondPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Discriminative Models for Multi-Class Object LayoutInternational Journal of Computer Vision, 2011
- New features and insights for pedestrian detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Integral Channel FeaturesPublished by British Machine Vision Association and Society for Pattern Recognition ,2009
- Asymmetric support vector machinesPublished by Association for Computing Machinery (ACM) ,2008
- Robust Object Detection via Soft CascadePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIeee Transactions On Pattern Analysis and Machine Intelligence, 2002
- Combining diagnostic test results to increase accuracyBiostatistics, 2000