Softeq is developing an ADAS that analyzes data from 15 in-vehicle cameras. The Softeq Advanced Driver Assitance System (ADAS) is focused on monitoring weather, but most importantly also collision avoidance.
Softeq has designed the ADAS to be extensible to enhance any feature. That includes autonomous driving back to notify the driver about any situation on the road before them.
The system is set up for a Linux SMP architecture, developed to analyze data captured from 15 full HD cameras in real-time. There are also interfaces for 3 x FPD-Link III displays and five ARM-powered processors. The system handles exposure, autofocus, fish-eye effects, and white balance.
The company was asked to design an ADAS to enhance the design of a lightweight commercial vehicle.
The solution required a system-on-module (SoM) device, which was the basis for the system. The device had to collect data from cameras, but also collect data from internal vehicle systems that include HMI, ECU, and IVI, all through CAN, LIN connectivity, and more.
The solution had to be capable of processing data captured from 15 Full HD cameras in real-time. The challenges presented to using an SoM called for the use of Five Arm-based processors, four for processing digital images generated by onboard cameras and one for math calculations.
— ADVERTISMENT—
—Advertise Here—
The way to lighten the load of the primary processors, coprocessors are used for image analysis. The system also can use RADAR/LiDAR technology for precisely measuring the distance between objects.
The custom system that was designed to meet all these issues was based on the Linux symmetric multiprocessing (SMP) architecture. This architecture can take multiple processors and combine them in a single system. Therefore 15x cameras were able to be utilized in a Full HD environment to monitor and analyze data to avoid collisions and monitor weather conditions.
To find out more about the Softeq Advanced Driver Assistance System (ADAS) check out the product case study here.
Softeq | softeq.com
Sponsor this Article
For the past 8 years, I have been writing about embedded technologies, added to my technical, academic, and medical editorial experience, with companies like Elsevier and Cambridge University Press. I tell people to read what I write, not try to pronounce my last name. I am always available for comments and suggestions you can reach me at product-editor@circuitcellar.com and I promise I will take the time to reach back out to you. I live in the North East with my wonderful family.
