Feature Co-occurrence Representation Based on Boosting for Object Detection
- Yuji Yamauchi, Masanari Takaki, Takayoshi Yamashita, Hironobu Fujiyoshi
- International Workshop on Socially Intelligent Surveillance and Monitoring (in conjunction with CVPR), 2010
Download: PDF (English)
This paper proposes a method of feature co-occurrence representation based on boosting for object detection. A previously proposed method that combines multiple binaryclassified codes by AdaBoost to represent the co-occurrence of features has been shown to be effective in face detection. However, if an input feature is difficult to be assigned to a correct binary code due to occlusion or other factors, a problem arises here since the process of binary classification and co-occurrence representation may combine features that include an erroneous code. In response to this problem, this paper proposes a Co-occurrence Probability Feature (CPF) that combines multiple weak classifiers by addition and multiplication arithmetic operators using Real AdaBoost in which the outputs of weak classifiers are real values. Since CPF combines classifiers using two types of operators, diverse types of co-occurrence can be represented and improved detection performance can be expected. To represent even more diversified co-occurrence, this paper also proposes co-occurrence representation that applies a subtraction arithmetic operator. Although cooccurrence representation using addition and multiplication operators can represent co-occurrence between features, use of the subtraction operator enables the representation of co-occurrence between local features and features having other properties. This should have the effect of revising the probability of the detection-target class obtained from local features. Evaluation experiments have shown cooccurrence representation by the proposed methods to be effective.