Finite asymmetric generalized Gaussian mixture models learning for infrared object detection

The interest in automatic surveillance and monitoring systems has been growing over the last years due to increasing demands for security and law enforcement applications. Although, automatic surveillance systems have reached a significant level of maturity with some practical success, it still remains a challenging problem due to large variation in illumination conditions. Recognition based only on the visual spectrum remains limited in uncontrolled operating environments such as outdoor situations and low illumination conditions. In the last years, as a result of the development of low-cost infrared cameras, night vision systems have gained more and more interest, making infrared (IR) imagery as a viable alternative to visible imaging in the search for a robust and practical identification system. Recently, some researchers have proposed the fusion of data recorded by an IR sensor and a visible camera in order to produce information otherwise not obtainable by viewing the sensor outputs separately. In this article, we propose the application of finite mixtures of multidimensional asymmetric generalized Gaussian distributions for different challenging tasks involving IR images. The advantage of the considered model is that it has the required flexibility to fit different shapes of observed non-Gaussian and asymmetric data. In particular, we present a highly efficient expectation-maximization (EM) algorithm, based on minimum message length (MML) formulation, for the unsupervised learning of the proposed model's parameters. In addition, we study its performance in two interesting applications namely pedestrian detection and multiple target tracking. Furthermore, we examine whether fusion of visual and thermal images can increase the overall performance of surveillance systems. (C) 2013 Elsevier Inc. All rights reserved.