Toshiba America Electronic Components, Inc., (TAEC)*, a committed leader that collaborates with technology companies to create breakthrough designs, today announced the second-generation of its Visconti series of image recognition processors for automotive applications, Visconti™2 (TMPV7500). The processors recognize lanes, vehicles and pedestrians using a camera-based vision system. The Visconti2 devices support up to four 1.3 megapixel color cameras, making them suitable for applications requiring color identification, such as the detection of traffic lights and signs. They incorporate four separate media processing engines (MPEs) and up to six image processing accelerators to enhance image recognition performance.
The Visconti2 devices' image processing accelerators use Toshiba's own histogram of oriented gradients (HOG) technology to enable real-time pedestrian detection at both day and night, thanks to its ability to sense lighting changes and small deformations. When connected to four cameras, the Visconti2, TMPV7506XBG, device can simulate a bird's-eye view based on image data captured by the cameras for use in parking assistance applications.
Comments