Choosing the best embedded processing platform for on-board UAV image processing

Abstract

Nowadays, complex image processing algorithms are a necessity to make UAVs more autonomous. Currently, the processing of images of the on-board camera is often performed on a ground station, thus severely limiting the operating range. On-board processing has numerous advantages, however determining a good trade-off between speed, power consumption and weight of a specific hardware platform for onboard processing is hard. Many hardware platforms exist, and finding the most suited one for a specific vision algorithm is difficult. We present a framework that automatically determines the most-suited hardware platform given an arbitrary complex vision algorithm. Our framework estimates the speed, power consumption and flight time of this algorithm for multiple hardware platforms on a specific UAV. We demonstrate this methodology on two real-life cases and give an overview of the present top performing CPU-based platforms for on-board UAV image processing.