• 
• 
• 
• 
• 
• 

Surveillance Architecture

Surveillance products are increasingly being differentiated by software. Future generations of surveillance systems will need to be flexible, scalable, robust, and will need to incorporate new software technologies easily, quickly, and effectively in order to compete. We are currently developing a modular software architecture that uses computer vision routines for surveillance. Our first components will use face detection, and stereo vision.

Background & Objective:  Mitsubishi Electric has a presence in the surveillance components market, and the custom surveillance system design market. The computer vision technology and MPEG technology at MERL could help Mitsubishi Electric increase its competitiveness in these areas.  The object of the surveillance architecture project is to provide a robust, scalable, flexible, and modular architecture that adds value to Mitsubishi Electric's next generation surveillance components, systems, and services.

Technical Discussion:  MERL technologies relevant to surveillance include computer vision technologies such as face detection, face analysis, and stereo techniques, and MPEG technologies for video streaming, indexing, browsing, and searching. A software architecture for surveillance can provide a framework for integrating these technologies into Mitsubishi Electric equipment and systems.

Technology Areas:
Computer Vision
Audio Video Processing

Modification Date:  October 3, 2007