Performance benchmark of deep learning human pose estimation for UAVs

Abstract

Abstract Human pose estimation (HPE) is a computer vision application that estimates human body joints from images. It gives machines the capability to better understand the interaction between humans and the environment. For this accomplishment, many HPE methods have been deployed in robots, vehicles, and unmanned aerial vehicles (UAVs). This effort raised the challenge of balance between algorithm performance and efficiency, especially in UAVs, where computational resources are limited for saving battery power. Despite the considerable progress in the HPE problem, there are very few methods that are proposed to face this challenge. To highlight the severity of this fact, the proposed paper presents a brief review and an HPE benchmark from the aspect of algorithms performance and efficiency under UAV operation. More specifically, the contribution of HPE methods in the last 22 years is covered, along with the variety of methods that exist. The benchmark consists of 36 pose estimation models in 3 known datasets with metrics that fulfill the paper aspect. From the results, MobileNet-based models achieved competitive performance and the lowest computational cost, in comparison with ResNet-based models. Finally, benchmark results are projected in edge devices hardware specifications to analyze the appropriateness of these algorithms for UAV deployment.