High-Level Feature Extraction for Classification and Person Re-Identification

Abstract

The need to understand behaviors and identify individuals across surveillance cameras has led to a growing interest in research on feature extraction. High-level feature extraction aims at discriminating behaviors and individuals with high accuracy. In this paper, instead of using low-level image features, a novel method for extracting high-level features, which can be used for classification and person re-identification, is proposed. For this purpose, a set of low-level features is first extracted for each local of image. Then, a set of prototypes is sampled in each low-level feature space. These prototypes represent a different category of features which have the maximum inter-distance. Using canonical correlation analysis, new distance criteria are set to measure the mutual distance between each pair of sampled prototypes. This allows the proposed method to evaluate the similarity of the prototypes more accurately. As a result, the sample prototypes have the maximum inter-distance and their discriminative capacity is high. Once the set of the prototypes is achieved in each low-level feature space, the set is used to project the low-level feature space onto a new feature space. To serve this purpose, the correlation between the feature extracted for each local of image in the low-level feature space and each prototype in the set is computed and the resulting correlation is considered as one element of the new feature vector for that local. Now, there are two feature vectors for each local of image which are then combined to obtain a single feature vector. The deep belief network (DBN) is employed as a final stage whereby the single feature vector is fed into the DBN to train it in order to output a discriminant feature with a reduced dimension. This new high-level feature can be efficiently used for such applications as data classification and person re-identification.