An autonomous vehicle for video surveillance of indoor environments

In this paper, the problem of the surveillance and the security of indoor environments is addressed through the development of an autonomous surveillance vehicle (ASV). The ASV has been designed to perform, in addition to the classical robotic tasks (e.g., navigation and obstacle avoiding), the tracking of objects (e.g., persons) moving in indoor environments. The selection of the target object to be tracked can be decided by a remote operator or autonomously by the ASV itself in the case that a suspicious behavior has been detected (e.g., a person entering a forbidden area, etc.). The tracking procedure allows the ASV to maintain the interesting objects in the center of the image and in specific cases to localize particular parts of the object (e.g., face of a person, etc.) in order to recognize it. Experimental results have been performed on different real scenarios where no objects move inside the monitored scene and where a group of people move in a hallway.