Toshiba Develops DNN Hardware IP for Image Recognition AI Processor Visconti™5 for Automotive Driver Assistance Systems
January 7, 2019
Toshiba Electronic Devices & Storage Corporation
TOKYO—Toshiba Electronic Devices & Storage Corporation (“Toshiba”) today announced the development of Deep Neural Network (DNN [1]) hardware IP[2] that will help to realize advanced driver assistance systems (ADAS) and autonomous driving functions. The company will integrate the DNN hardware IP with conventional image processing technology and start sample shipments of Visconti™5, the next generation of Toshiba’s image-recognition processor, in September 2019.
The DNN hardware IP draws on deep learning to deliver more accurate detection and identification of a wider range of objects than image recognition based on conventional pattern recognition and machine learning. It enables Visconti™5 to recognize road traffic signs and road situations at high speed with low power consumption.
Toshiba will promote Visconti™5 equipped with DNN hardware IP as a key component of next-generation advanced driver assistance systems.
Advanced driver assistance systems such as autonomous emergency braking are now being widely adopted, from luxury cars to subcompacts. They are also expected to offer increasingly advanced capabilities - for instance, the 2020 version of the influential European New Car Assessment Programme (Euro NCAP), the EU-backed safety standard, adds testing to avoid collisions at intersections. This trend will increase the demand for more advanced and capable systems.
Toshiba Electronic Devices & Storage Corporation will continue to develop the Visconti™ family and contribute to traffic safety.
Outline of Visconti™5
Product Series Name |
TMPV770 series |
|---|---|
CPU core |
Arm® Cortex®-A53 |
Arm® Cortex®-R4 processor with Floating Point Unit |
|
Image processing DSP |
General DSP |
Image Processing Accelerator |
Affine conversion |
Pyramid Image Generator |
|
Enhanced CoHOG Feature-based Support Vector Machine |
|
| Dense Optical Flow | |
Template Matching |
|
Dense Stereo Matching |
|
Deep Neural Network |
|
Image Signal Processor |
|
| Video input interface | MIPI CSI-2 RX |
Video output interface |
MIPI CSI-2 TX |
Notes
[1] DNN is a machine model using artificial deep neural networks inspired by human brain function.
[2] IP (Intellectual Property) is a function block for SoC development.
* Visconti™ is a trademark of Toshiba Electronic Device & Storage Corporation
* Arm and Cortex are registered trademarks of Arm Limited (or one of its subsidiaries) in the United States or other countries.
* MIPI is a registered trademark of MIPI Alliance.
* All other company names, product names and service names may be trademarks of their respective companies.
Customer Inquiries:
System LSI Marketing Dept.III
Tel: +81-44-548-2422
Information in this document, including product prices and specifications, content of services and contact information, is current on the date of the announcement but is subject to change without prior notice.