DNN hardware IP developed for image recognition AI processor in ADAS
08-01-2019 |
Toshiba
|
Automotive & Transport
Toshiba Electronic Devices and Storage Corporation has launched the development of Deep Neural Network (DNN) hardware IP that will help to achieve ADAS and autonomous driving functions. The company will combine the DNN hardware IP with conventional image processing technology and start sample shipments of Visconti5, the next generation of the company's image-recognition processor.
The DNN hardware IP draws on deep learning to produce more accurate detection and identification of a broader range of objects than image recognition based on conventional pattern recognition and machine learning. It allows Visconti5 to identify road traffic signs and road situations at high speed with low power consumption.
The company will promote Visconti5 equipped with DNN hardware IP as a key component of next-generation ADAS.
By Electropages
Electropages is a trusted source of news and insights from the global electronics industry. With a dedicated team of experts and editors, Electropages delivers in-depth articles, product updates, and market trends across sectors such as embedded systems, IoT, connectors, and power solutions. Our mission is to empower engineers and professionals with the knowledge they need to innovate and succeed in a rapidly evolving technological landscape.