PARIS - Toshiba America Electronic Components, Inc. said it has added Visconti 3 to its series of image recognition processors aimed specifically at automotive applications.
The Visconti series is used in camera-based vision systems for advanced driver assistance systems. Toshiba claimed it detects and recognizes lanes, vehicles, traffic lights, signs and pedestrians in real time, both day and night, and processes image data from multiple camera inputs frame-by-frame and then outputs results to an LCD panel.
Toshiba said the Visconti 3, part number TMPV7528XBG, integrates an ARM Cortex-A9 MPCore to facilitate the connection to other automotive systems, including navigation, smartphone, driver assistance and the Cloud.
The A9 CPU core includes a single/double-precision floating point unit that is claimed to improve performance of image processing by handling the mathematical computations required to analyze large volumes of image data from the video source, frame-by-frame in real time, in some of the algorithms.
Visconti processor applications Click on image to enlarge
Visconti system organization
Toshiba said it expects that samples of the Visconti 3, TMPV7528XBG, will be available in April 2013.
The drivers' assist is a good way to build consumers' confidence to self driving cars. I hope there are more cars using Visconti 3 or similar product. BTW, does Toshiba have patent protection to Visconti?
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.