Introspective classification for pedestrian detection

State-of-the-art pedestrian detectors are capable of finding humans in images with reasonable accuracy. However, accurate object detectors such as Integral Channel Features (ICF) do not provide good reliability; they are unable to identify detections which they are less confident (or more uncertain) about. We apply existing methods for generating probabilistic measures from classifier scores (such as Piatt exponential scaling and Isotonic Regression) and compare these to Gaussian Process classifiers (GPCs), which can provide more informative predictive variance. GPCs are less accurate than ICF classifiers, but GPCs and Adaboost with Piatt scaling both provide improved reliability over existing methods.

[1]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[2]  Martin D. Levine,et al.  Online Dominant and Anomalous Behavior Detection in Videos , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[4]  Luc Van Gool,et al.  Traffic sign recognition — How far are we from the solution? , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[5]  Rich Caruana,et al.  Predicting good probabilities with supervised learning , 2005, ICML.

[6]  VezzaniRoberto,et al.  People reidentification in surveillance and forensics , 2013 .

[7]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Rudolph Triebel,et al.  Knowing when we don't know: Introspective classification for mission-critical decision making , 2013, 2013 IEEE International Conference on Robotics and Automation.

[9]  David J. Hand,et al.  Construction and Assessment of Classification Rules , 1997 .

[10]  Pietro Perona,et al.  The Fastest Pedestrian Detector in the West , 2010, BMVC.

[11]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[12]  Regis Hoffman,et al.  Visual classification of coarse vehicle orientation using Histogram of Oriented Gradients features , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[13]  Robert E. Schapire,et al.  The Boosting Approach to Machine Learning An Overview , 2003 .

[14]  Pietro Perona,et al.  Pedestrian Detection: An Evaluation of the State of the Art , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[16]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.