Control method and device for unmanned aerial vehicle

Abstract

The invention discloses a control method and device for an unmanned aerial vehicle. The control method comprises the steps that a dynamic image is acquired, and multiple variation regions in all image frames contained in the dynamic image are extracted; the variation regions are sequentially matched with a gesture template and a human body silhouette template which are prestored in a prestored template library, the variation regions are recognized according to matching results, and corresponding operating instructions are acquired; when any one variation region is successfully matched with the gesture template, the variation region is recognized as a gesture, and a gesture control operating instruction matched with the gesture is generated; when any one variation region is unsuccessfully matched with the gesture template and successfully matched with the human body silhouette template, the variation region is recognized as a human body silhouette, and a human body control operating instruction is generated; when the variation region is unsuccessfully matched with the gesture template and the human body silhouette template, a returning operating instruction is generated; the operating instructions corresponding to the variation regions are executed.

Description

technical field [0001] The present invention relates to the field of aviation science and technology, and more specifically, to a control method and device for an unmanned aerial vehicle. Background technique [0002] Unmanned UAV, referred to as UAV, is an unmanned UAV controlled by remote control method and self-contained program control device. In order to maintain the balance of the body and complete work tasks, more and more sensors are installed on the drone body. With the development of microelectronics technology, it has become a reality to integrate multiple high-precision sensors on small drones. At present, UAVs can achieve more and more functions, and have been widely used in aerial reconnaissance, surveillance, communication, anti-submarine, electronic jamming, etc. Image recognition refers to the technology of using computers to process, analyze and understand images to identify targets and objects in various patterns. [0003] Generally, in the prior art, th...

AI Technical Summary

Problems solved by technology

[0004] The above scheme uses gestures to control the UAV, and obtains the trajectory of the UAV to fly by matching the recognized gestures with the template library corresponding to the pre-stored gestures. The control method is novel, but it is limited to short-distance control. When flying farther and higher, the control effect of gesture recognition will be reduced or even the drone will lose control.

Images