Pose Estimation and Its Impact on Quadcopter Control: An Experimental Study

Autonomous quadcopter control based on computer vision has become one of the popular research methods. However, challenges persist due to constraints in processing speed and memory associated with embedded edge computing, thereby limiting accuracy and real-time performance. In this study, we introduce a novel gesture controlled autonomous quadcopter system capable of achieving high accuracy in real-time scenarios. Firstly, the Lightweight OpenPose method is employed to extract gesture sequences. Secondly, we propose a gesture classifier based on the SimVP architecture. In order to validate our approach, we conduct an evaluation using a generated dataset, followed by testing in a real-world environment. Results of our evaluation and experiments demonstrate the effectiveness of the proposed method.