A Multilevel Mixture-of-Experts Framework for Pedestrian Classification
- 11 April 2011
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 20 (10), 2967-2979
- https://doi.org/10.1109/tip.2011.2142006
Abstract
Notwithstanding many years of progress, pedestrian recognition is still a difficult but important problem. We present a novel multilevel Mixture-of-Experts approach to combine information from multiple features and cues with the objective of improved pedestrian classification. On pose-level, shape cues based on Chamfer shape matching provide sample-dependent priors for a certain pedestrian view. On modality-level, we represent each data sample in terms of image intensity, (dense) depth, and (dense) flow. On feature-level, we consider histograms of oriented gradients (HOG) and local binary patterns (LBP). Multilayer perceptrons (MLP) and linear support vector machines (linSVM) are used as expert classifiers. Experiments are performed on a unique real-world multi-modality dataset captured from a moving vehicle in urban traffic. This dataset has been made public for research purposes. Our results show a significant performance boost of up to a factor of 42 in reduction of false positives at constant detection rates of our approach compared to a baseline intensity-only HOG/linSVM approach.Keywords
This publication has 47 references indexed in Scilit:
- A Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving VehicleThe International Journal of Robotics Research, 2009
- A survey of advances in vision-based human motion capture and analysisComputer Vision and Image Understanding, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Learning to detect objects in images via a sparse, part-based representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Example-based object detection in images by componentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Statistical pattern recognition: a reviewIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- A time delay neural network algorithm for estimating image-pattern shape and motionImage and Vision Computing, 1999
- The Visual Analysis of Human Movement: A SurveyComputer Vision and Image Understanding, 1999
- On combining classifiersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991