Forward cameras are a critical element of advanced driver-assistance systems (ADAS) because they provide the advanced sensing capabilities required for safety-critical functions, including lane-keeping assistance (LKA), automatic emergency braking (AEB), and adaptive cruise control (ACC). To power these ADAS functions, automakers desire a solution that’s scalable, with varying levels of performance and price – that’s why Xilinx and Motovis have teamed up to provide a complete hardware and convolutional neural network (CNN) IP solution for forward camera systems’ vehicle perception and control. The solution pairs the Xilinx Automotive (XA) Zynq® system-on-chip (SoC) platform and Motovis’ CNN IP, and it scales across the 28nm and 16nm XA Zynq SoC families. It’s a unique combination of optimized hardware and software partitioning capabilities with customizable CNN-specific engines that host Motovis’ deep learning networks which can support image resolutions up to eight megapixels. For the first time, automakers and tier-1 suppliers can now layer their own feature algorithms on top of Motovis’ perception stack to differentiate and future-proof their forward camera designs.