Browse Publications Technical Papers 2019-26-0020
2019-01-19

High Speed Raw Radar Data Acquisition Using MIPI CSI2 Interface for Deep Learning in Autonomous Driving Applications 2019-26-0020

Technological Advances in ADAS, AI, AD [Advanced driver assistance systems, Artificial Intelligence, and Autonomous Driving] there has been a demand of raw data transfer from Sensors like Radar, Camera, LiDAR, etc. because existing methods are unable to meet sensor fusion requirements of Level 5 AD. Advanced deep learning algorithms need raw data to extract complex features and fusion of data from sensors further helps to build algorithms that simulate human-like intelligence. Traditionally, the output of Radar is point cloud data [i.e. Range, Velocity, Angle] of the detected target which is the outcome of the computation done by the local radar. Transfer of raw data allows the central computer to decide whether to process the radar data at the edge or at the central computer where sensor fusion can be performed. This leads to high data rate transfer requirements from Radar sensor. MIPI being an established standard for high data rate transfer from camera, car OEMs extended its usage for high data rate transfer from Radar. This paper will help to understand the mapping of Radar Frame data into image frame data as required by MIPI CSI2 format.

SAE MOBILUS

Subscribers can view annotate, and download all of SAE's content. Learn More »

Access SAE MOBILUS »

Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Members save up to 43% off list price.
Login to see discount.
Special Offer: With TechSelect, you decide what SAE Technical Papers you need, when you need them, and how much you want to pay.
X