TOKYO, JAPAN. Renesas’ new Perception Quick Start Software is built on its R-Car V3H system-on-chip (SoC) that will provide reference software for camera obstacle detection (COD), LiDAR obstacle detection (LOD), and road feature detection (RFD).
Renesas Perception Quick Start Software features:
- The COD reference software employs convolutional neural network (CNN) IP, a computer vision engine (CV-E), and image rendering (IMR) technology to detect 2D objects such as cars, trucks, buses, and pedestrians. The COD achieves approximately 30 frames per second (FPS).
- The LOD software employs CNN-IP and CV-E to detect 3D objects, including cars and trucks. The LOD achieves approximately 15 FPS with 3D bounding boxes at 50 meters.
- The RFD reference software employs CNN-IP, CV-E, IMR, and a versatile pipeline engine (IMP) to identify drivable free space, lanes (crossable and uncrossable), road boundaries, and distances to lanes and nearest objects to support NCAP 2020. The RFD achieves approximately 30 FPS.
“Specialized hardware accelerators play an essential role in achieving the computer vision performance and accuracy required in embedded ADAS and autonomy applications while still meeting stringent in-vehicle power consumption limits; however, the complexity of these accelerators can present a steep learning curve,” said Renesas’ Director of Automotive Advanced Systems Innovation Department, Tim Grai. “With the new Perception Quick Start Software, we are able to offer a set of application software along with the underlying primitives to simplify the use of these complex accelerators needed to achieve embedded ADAS.”
Renesas will appear at TU-Automotive Detroit 2019 to showcase the new Perception Software solution June 5-6, in Novi, MI, Renesas’ booth C190.
For more information, visit renesas.com.