Distributed framework for visual event detection in parking lot area

Abstract

The paper presents the framework for automatic detection of various events occurring in a parking lot basing on multiple camera video analysis. The framework is massively distributed, both in the logical and physical sense. It consists of several entities called node stations that use XMPP protocol for internal communication and SRTP protocol with Jingle extension for video streaming. Recognized events include detecting parking vehicles supplemented with parking place and vehicle identification. Event detection is based on low level image processing consisting of moving object detection, tracking and classification. Front-end of the framework is formed by the operator console that presents results of the framework accompanied with video streams from selected cameras in the real-time. Additionally, the operator console may be used to automatically aim any PTZ camera in the framework at the selected spot in video frames from fixed cameras and track moving objects as long as they move within the monitored area. The paper is concluded with the framework performance evaluation during real condition experiments. © 2011 Springer-Verlag.