From Berkeley, Calif., Eutecus has released InstantVisionTM ISE 3.0., an integrated image processing software environment with tools and libraries especially optimized to run at extremely high speeds on embedded vision systems.  InstantVision 3.0 features a new Video Analytics Library especially designed to help application developers and systems integrators working in the rapidly expanding security/surveillance video content analysis sector to build powerful embedded applications with reduced time-to-market.

Eutecus President and CEO Stephen D. Hester told Zalud’s Blog, ”The bandwidth and processing demands of today’s video content analysis systems requires that image processing move from central servers to embedded systems at the edges of the network. Eutecus created InstantVision ISE 3.0 in order to provide developers with both extremely fast embedded processing capability and a flexible, easy-to-use, development environment.”

InstantVision 3.0 also includes updated versions of the earlier software libraries (Signal and Image Processing, Signal and Image Flow Processing, Feature Classification, and Multitarget Tracking Libraries). These platform-independent libraries can be used together or separately to put together applications for video content analysis, traffic monitoring, multitarget tracking, or any machine vision task.

The InstantVision libraries can be ported to any platform and also come ready for use on a PC in order to facilitate rapid prototyping.  They are especially optimized for the powerful TMS320C64xx series of DSPs from Texas Instruments used by Eutecus’ own award-winning Bi-i series of camera.

Developers writing applications specifically for Eutecus’ Bi-i V301F, the newest model of the Bi-i series of Intelligent Cameras that won the Vision 2003 Product of the Year Award, can take advantage of Eutecus’ C-MVATM (Cellular Multicore Video Analytics) processor technology, in which the most computationally demanding image pre-processing tasks are executed by the C-MVA processor (currently embedded in FPGA) leaving the DSP to focus on higher-level tasks such as event detection and image encoding, thereby significantly increasing overall performance.