Multi-class multi-instance boosting for part-based human detection

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.