Schematic Visualization of Object Trajectories across Multiple Cameras for Indoor Surveillances

This paper presents a video summarization method to visualize the video object trajectories across multiple cameras in a static image for monitoring the movements of suspicious people in a building. First, we have designed an object association algorithm across multiple stationary cameras, which can be used to build the object trajectories in the building with the assistants of the predefined locations of the cameras. The object associations are based on the features of human body, such as the clothing colour, stature, shoulder breadth and so on. These features are calculated from the anthropometric dimensions of the human body from calibrated monocular video sequences. Finally, the object trajectories are illustrated in a perspective picture that overviews all floors of the building, wihich is called storyboard. Some diagrammatic elements such as arrows and texts are used to annotate the object movements. Thicker arrows represent the more rapid movements and narrower arrows represent the slower movements. The visualization results can assist the monitors to real-time observe the people's movements and easily understand the people's activities in a building.