cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 

What does Zynq-based, real-time object recognition for autonomous driving look like? Got your 4-minute demo video right here

Xilinx Employee
Xilinx Employee
0 0 23.4K

 

Korea-based ATUS has just published a 4-minute video of its Zynq-based CNN (convolutional neural network) performing real-time object recognition on a 416x234-pixel dashcam video stream at 46.7fps. Reliable, real-time object recognition is essential to the development of autonomous driving and ADAS systems. ATUS’ design is based on a Xilinx Zynq Z-7020 SoC running a YOLO (you only look once) object-detection system. In the video below, the system recognizes cars, trucks, buses, and pedestrians.

 

Last year in the Xcell Daily blog pots titled “CNN-based automotive vision sensor running on Zynq Z7045 SoC recognizes objects at 17.53 frames/sec,” ATUS’ system ran only one third as fast on a larger Zynq SoC. It appears that a lot of development has occurred in the ensuing six months.

 

Here’s the video proof:

 

 

 

Tags (4)