Editor’s Note: New approaches to FPGA architectures bring finer-grained control and greater flexibility to address the needs of machine learning (ML) and artificial intelligence (AI). Part 1 of this two-part series introduces one such architecture from Efinix and how to get started with it using a development board. Here, Part 2 discusses interfacing the development board to external devices and peripherals such as a camera, and how to leverage the FPGA to remove image processing bottlenecks.
FPGAs play a critical role in many applications, from industrial control and safety to robotics, aerospace, and automotive. Thanks to the flexible nature of the programmable logic core and their wide interfacing capabilities, one growing use case for FPGAs is in image processing, where machine learning (ML) can be deployed. FPGAs are ideal for implementing solutions that have several high-speed camera interfaces thanks to their parallel logic structure. In addition, FPGAs also enable the use of a dedicated processing pipeline in the logic, thereby removing shared-
resource bottlenecks that would be associated with CPU or GPU-based solutions. This second look at Efinix’s Titanium FPGAs will examine the reference image processing application that comes with the FPGA’s Ti180 M484 development board. The aim is to understand the constituent parts of the design, and to identify where FPGA technology enables the removal of bottlenecks or enables other benefits to developers.
Written by: Bill Schweber, Contributing Author at DigiKey
Figure 1. Conceptually, the Ti180 M484 reference design receives images from several MIPI cameras, performs frame buffering in the LPDDR4x, and then outputs the images to an HDMI display. Image source: Efinix
Why and how to use Efinix FPGAs for AI/ML imaging – Part 2: Image capture and processing Written by: Adam Taylor
we get technical
50
51
Powered by FlippingBook