Design of Intelligent IP Camera Middleware

• Main Authors: Huan-Ming Hsu, 許桓銘
• Other Authors: Shu-Chun Ho
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/67778876005744804151

碩士 === 國立高雄師範大學 === 資訊教育研究所 === 101 === The issue of surveillance and secutiry has been emphasized through the development of Internet. The evolution of the surveillance system has been a migration from the analog CCTV (Closed Circuit TeleVision) system to the integration system of digital IP camera. In 2008, two international alliances, PSIA (Physical Security Interoperability Alliance) and ONVIF (Open Network Video Interface Forum) are formed, and they purposed the front-end/rear-end integrated protocols based on the network surveillance system. So far, many products for surveillance software system in the marketplace claim to be able to fully support those two international alliances, PSIA (Physical Security Interoperability Alliance) and ONVIF (Open Network Video Interface Forum), based on a market survey. However, in fact, the ONVIF core specification Ver. 1 was first proposed in 2008. The ONVIF core specification Ver. 2 was then updated in 2010. In 2012, the ONVIF core structure specification Ver. 2.1.1 was launched. For those users and venders of IP camera, the uncertain protocol of the ONVIF core specification will cause the difficulty and inconvenience of surveillance software system in setting, installation, and management. The possibility of the uncertain protocol and the unstable surveillance software system still exists in those high cost system. In this thesis, the design of intelligent IP camera middleware is proposed and implemented based on a reliable architecture of surveillance software system. The main contributions of the thesis as follows. First, we implemented the Universal Middleware Bridge System (UMBS) for IP Cam networking. The UMBS provides the related mechanisms for system manual setting, automatic configuration, and management to improve the whole procedures of setting and installation. The UMBS is composed of four main functional modules, Live Video (LV), Playback Video (PV), Intelligent Scheduler (iScheduler), and System Configuration (SC). The structure of the robust UMBS supports the adaptability and flexibility for design and development of IP cam application system. Secondly, the image searching algorithm for surveillance system is purposed. There are two subsystems including face recognition subsystem and face/object comparsion subsystem in the algorithm. In the algorithm, four major functions comprise skin color recognition, image noise removal, conneted component labeling, and face or object comparsion. The image searching algorithm for surveillance system can be applied to the design of surveillance software platform in the future.