A system and method for onboard vision intelligent processing of unmanned aerial vehicles

Abstract

The invention discloses an unmanned aerial vehicle airborne vision intelligent processing system and method. The system includes an unmanned aerial vehicle, an optoelectronic pod mounted on the unmanned aerial vehicle, and an information processing module. The information processing module includes an image recognition and tracking submodule, The gimbal PID controller sub-module and the parameter correction sub-module, the parameter correction sub-module obtains the detection data of the gyroscope, accelerometer and geomagnetometer, and corrects the lens rotation angular rate parameter output by the image recognition and tracking sub-module through the detection data. The method includes the following steps: collecting an image, identifying a target in the image, outputting a lens rotation angular rate parameter, correcting the lens rotation angular rate parameter, and controlling the rotation of the photoelectric pod lens through a PID controller. The intelligent processing system and method for on-board vision of the unmanned aerial vehicle of the present invention can solve or reduce the over-rotation phenomenon, the rotation of the photoelectric pod lens is stable, the shake of the lens is greatly reduced, and the captured image is clearer.

Description

technical field [0001] The invention relates to a system and method for onboard vision intelligent processing of an unmanned aerial vehicle, belonging to the field of unmanned aerial vehicles. Background technique [0002] In recent years, UAVs have been vigorously developed. After going through the transition from military to civilian use, they have successfully become a practical tool that is recognized by the majority of industries and can replace manpower to complete complex tasks. Among them, the use of unmanned aerial vehicles Machine-to-target continuous tracking is a common task. [0003] In the target tracking task, the traditional way is for the UAV to carry an airborne camera, such as a monocular camera or a binocular camera. However, the relative position information of the target obtained in this way needs to compensate for the current movement of the UAV. In order to make the relative position information accurate, and the camera lens is fixed with the drone, ...

AI Technical Summary

Problems solved by technology

[0003] In the target tracking task, the traditional way is for the drone to be equipped with an airborne camera, such as a monocular camera or a binocular camera. However, the relative position information of the target obtained in this way needs to compensate for the current movement of the drone. State, in order to make the relative position information accurate, and the camera lens is fixed with the UAV, the flight attitude of the UAV will affect the continuous tracking effect of the camera on the target, and the phenomenon of target loss often occurs

[0004] In the prior art, there is still a tracking method in which the UAV is equipped with the gimbal to capture the target image, and then obtain the relative position of the target. However, the existing gimbal PID control algorithm will cause over-rotation when controlling the rotation of the gimbal lens. For example, when the pan / tilt is actually required to rotate from 20° to 40°, under traditional PID control, the pan / tilt will over-rotate from 20° to 45°, then rotate to 35°, and then rotate to 40°, even multiple times. Rotation phenomenon, if the target moves too fast at this time, it is easy to lose the target, and when the UAV moves violently, the conventional PID control algorithm is less stable, and it is easy to cause the target to be lost

[0005] In addition, most of the current UAV tracking methods are that after the UAV captures the image, it transmits the image to the ground station, and the ground station controls the UAV to track. However, this process not only affects the timeliness of the system, but also affects the transmission of information. The integrity of the

Images