In an effort to help customers meet SAE Level 5 Autonomous Driving standards, FEV in Auburn Hills is bringing new technology to the table.
The latest example to make smart vehicle development easier is FEV’s Advanced Driver Assistance Systems (ADAS) Annotation Tool, which will be unveiled at next month’s Consumer Electronics Show in Las Vegas.
The tool will be able to process data and that information will be continually fed into a vehicle’s Deep Neural Network, which allows the car to “learn” about its surroundings. This means the car will be able to assign a label to certain objects, vehicles, pedestrians, and signs via an auto-classifier. The tool will effectively build a database of objects (or labels), decreasing the man-hours spent manually building one.
Labeling is critical to smart vehicle development, as it is the process, much like filming a movie and identifying certain objects, by which an autonomous car “learns” about its surroundings.
The Annotation Tool supports deep learning of neural networks by integrating the database. Like many FEV-developed tools, the Annotation Tool is user-friendly, using neural a network tool chain.
