A Construction Method for Automatic Human Tracking System with Mobile Agent Technology

Abstract

Human tracking systems that can track a specific person is being researched and developed aggressively, since the system is available for security and a flexible service like investigation of human behaviour. For example, Terashita, Kawaguchi and others propose the method for tracking an object captured by simple active video camera (Terashita et al. 2009; Kawaguchi et al. 2008), and Yin and others propose the solution of the problem of the blurring of the active video camera (Yin et al. 2008). Tanizawa and others propose a mobile agent framework that can become the base of a human tracking system (Tanizawa et al. 2002). These are component technology, and they are available in construction of the human tracking system. On the other hand, Tanaka and others propose a human tracking system using the information from video camera and sensor (Tanaka et al. 2004), and Nakazawa and others propose a human tracking system using recognition technique which recognizes same person using multiple video cameras at the same time (Nakazawa et al. 2001). However, although these proposed systems are available as human tracking system, the systems are constructed under fixed camera position and unchanged photography range of camera. On the other hand, there are several researches to track people with active cameras. Wren and others propose a class of hybrid perceptual systems that builds a comprehensive model of activity in a large space, such as a building, by merging contextual information from a dense network of ultra-lightweight sensor nodes with video from a sparse network of high-capability sensors. They explore the task of automatically recovering the relative geometry between an active camera and a network of one-bit motion detectors. Takemura and others propose a view planning of multiple cameras for tracking multiple persons for surveillance purposes (Takemura et al. 2007). They develop a multi-start local search (MLS)based planning method which iteratively selects fixation points of the cameras by which the expected number of tracked persons is maximized. Sankaranarayanan and others discuss the basic challenges in detection, tracking, and classification using multiview inputs (Sankaranarayanan et al. 2008). In particular, they discuss the role of the geometry induced by imaging with a camera in estimating target characteristics. Sommerlade and others propose a consistent probabilistic approach to control multiple, but diverse active cameras concertedly observing a scene (Sommerlade et al. 2010). The cameras react to objects moving about, arbitrating conflicting interests of target resolution and trajectory accuracy, and the cameras anticipate the appearance of new targets. Porikli and others propose an automatic