Miniature Vision Sensor System Geared for Real Time Analysis

October 10th, 2006

The ViSe camera enables broad-based monitoring and interpretation of visual data in real time, in any light conditions. The low-cost system, called ViSe, allows original equipment manufacturers (OEMs) to develop application-specific image analysis and response systems aimed at automotive, security, building and home automation, and industrial markets.

The ability to rapidly process data in real time and at low cost — regardless of changing light conditions — gives the system broad applicability for markets where vision sensing was previously not an option. Additionally the system addresses privacy issues through an option that identifies human forms but not facial or body detail. Application-specific algorithms have already been developed by CSEM to enable human versus animal differentiation, automobile seat occupancy, lane departure warning systems, intruder alert systems, motion sensing and movement tracking.

The ViSe camera is composed of a vision sensor and a digital signal processing chip (DSP) that can run identification algorithms. The system speeds throughput of visual data by enabling the vision sensor chip itself to extract key image features needed for interpretation — prior to sending it for software processing on the DSP.

Unlike other platforms, the ViSe sensor chip captures a detailed image but extracts from the image contrast strength and orientations, permitting it to pass on to the DSP only the key features of the scene needed for analysis. This allows a drastic reduction in the amount of data transmitted off the sensor chip, enabling rapid and low-cost post-processing of imagery in real time.

A ViSe evaluation kit is available now and the technology is available for licensing and transfer. CSEM will develop customized software and algorithms for specific applications upon request. Technology licensing fees depend on application-specific criteria. For more information and for sales inquiries, visit the Swiss Center for Electronics and Microtechnology website.

Entry Filed under: Vision Systems