A Web-based surveillance system for traffic behavior and its application for practical recommendation of crosswalk installation

A Web-based surveillance system has been developed to observe some intrusion into dangerous and security area. It is designed based on a Linux PC with Web services, Open CV engine, remote monitoring camera, remote controlling sub-server and other facilities. It supports users of mobile phones. Its image understanding facility by Open CV engine gives us information about intruders' tracks at the monitored places. As the result, it is beneficial that we can exactly know moving direction of intruders. Traffic security is one of the most important problems to be improved for our daily environment. In order to monitor traffic behavior, the surveillance system has been customized and applied to monitor traffic behavior about a specific area. It can acquire data about intruders' tracks when they go across relatively narrow streets. Such data provide information about suitable place to realize a necessary crosswalk which will comply with silent but real intruder's requests. Its monitoring function and image processing one are not so excellent but there are significant results for surveillance by means of limited adoption and adjustment. And we can recommend installation of Crosswalk based on intruders' tracks with image processing function of the surveillance system. It is concluded that our surveillance system is efficient enough to observe a specific place, compute image understanding about it and mine some kind of useful information of intruder's periodical behaviors.