Wireless Visual Sensing and Real Time Interpretation - ViSeLink - CSEM

CSEM introduced the ViSeLink a wireless version of its ViSe vision sensor system (see below). ViSeLink provides real-time recognition of still and moving visual objects in light or dark conditions. ViSeLink is designed to be able to operate in low data rates wireless infrastructure (current version uses Bluetooth). Moveable camera analyses the images and send the security alerts to computer or network gateway.

ViSeLink Wireless Camera

The ViSeLink system is composed of the ViSe camera vision sensor and DSP that runs 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. The Bluetooth transmitter in the system housing communicates with other Bluetooth-enabled devices.

—

Related news, October 9, 2006

Real Time Visual Sensing and Interpretation - ViSe Vision Sensor

CSEM (The Swiss Center for Electronics and Microtechnology) launched ViSe, a vision sensor monitoring system that able to make real time interpretation of visual data. ViSe vision sensor is targeted for image analysis and response system applications, aimed at security, industrial, building and home automation and automotive markets. Application-specific algorithms have already been developed to enable human versus animal differentiation, automobile seat occupancy, lane departure warning systems, intruder alert systems, motion sensing and tracking of movement.

Dr. Christian Enz, CSEM, said:

ViSe system offers customers a highly flexible vision sensing platform that can increase safety and productivity through computer-based identification and response, reducing the visual monitoring by human eyes that can cause fatigue…

The Low cost ViSe vision sensor is able to rapidly process visual data in real time, regardless of lighting conditions. The ViSe system addresses privacy issues through an option that identifies human forms but not facial or body detail.

The ViSe contain a DSP that run identification software. The system speeds throughput of visual data by enabling the vision sensor chip itself to extract key image features needed for interpretation, before send the data to DSP.

Nello Zuech, Vision Systems International, said:

Vision sensing technology will become more accessible with the advent of application-specific IC implementations, since today’s machine vision implementations generally still cannot meet the flexibility, low-cost and low power requirements needed for expansion to volume markets

The CSEM vision sensing implementation seems to make it possible to deploy cost-effective solutions for high-volume applications outside of traditional industrial markets, such as automotive, intelligent security/surveillance, and disease-specific diagnostic medical…

The conventional image processing involves acquiring an image with a CCD or CMOS camera, converting the intensity distribution to a digital representation, and processing it by means of a digital processing device. This approach poses considerable problems in certain applications such as automotive or surveillance markets where vision tasks must be executed in real-time

The ViSe sensor chip, in other way, 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.

The ViSe technology is available for licensing. CSEM offer ViSe evaluation kit will to speed up development stage.

Source: Visual Sensing and Interpretation - ViSe Vision Sensor -CSEM