Multi-class multi-instance boosting for part-based human detection
Authors:
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1177-1184
Abstract
With the purpose of designing a general learning framework for detecting human parts, we formulate this task as a classification problem over non-aligned training examples of multiple classes. We propose a new multi-class multi-instance boosting method, named MCMIBoost, for effective human parts detection in static images. MCMIBoost has two benefits. First, training examples are represented as a set of non-aligned instances, so that the alignment problem caused by human appearance variation can be handled. Second, instead of learning part detectors individually, MCMIBoost learns a unified detector for efficient detection, and uses the feature-sharing concept to design an efficient multi-class classifier. Experiment results on MIT and INRIA datasets demonstrate the superior performance of the proposed method.Keywords
This publication has 15 references indexed in Scilit:
- High-Performance Rotation Invariant Multiview Face DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part DetectorsInternational Journal of Computer Vision, 2007
- Hierarchical Part-Template Matching for Human Detection and Segmentation2007
- Histograms of Oriented Gradients for Human Detection2005
- Detection and Tracking of Humans by Probabilistic Body Part Assembly2005
- Learning object detection from a small number of examples: the importance of good features2004
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004
- Detecting pedestrians using patterns of motion and appearance2003
- Body plans2002
- Real-time object detection for "smart" vehicles1999