A trend analysis method and system based on UAV autonomous flight situation awareness trend

Abstract

The present invention provides an analysis method based on the autonomous flight situation awareness trend of the UAV, including: according to the image information, the attitude angle of the UAV and the three-dimensional acceleration information, the improved visual real-time positioning and map construction algorithm is used to obtain the three-dimensional information of the UAV. Position and attitude information; obtain multi-target situation data in the environment, use the MobileNetSSD algorithm to identify the target and determine the target frame; then use the ORB algorithm to extract the features of the target in the target frame, and perform feature matching with the features of a specific target to estimate the movement of the target Trajectory, according to the three-dimensional position and attitude information of the UAV, and the estimated moving trajectory of the target, obtain the obstacle avoidance path; adjust the global path in real time according to the obstacle avoidance path, and obtain the adjusted navigation path. The method proposed by the present invention, the UAV It can obtain its own information in real time, and be able to perceive the environment information, realize target recognition and trajectory estimation, and then generate obstacle avoidance paths and adjust paths in real time, so as to realize reliable autonomous flight of UAVs.

Description

technical field [0001] In the field of unmanned aerial vehicle of the present invention, in particular, it refers to an analysis method and system based on the trend of autonomous flight situation awareness of unmanned aerial vehicles. Background technique [0002] With the continuous development of UAV technology, UAVs are not only widely used in the military, but also widely used in agriculture and people's daily life. In order to achieve better performance of UAVs, the flight trajectory of UAVs Planning becomes an important factor in realizing the functions of drones. [0003] When the existing drones plan the flight path autonomously, they simply connect the target point and the starting point based on the map to form a straight line as the flight path. However, during the actual flight of the UAV, it is very likely to encounter unexpected obstacles. [0004] When avoiding obstacles, it only adopts fixed methods such as hovering when encountering obstacles or bypassing...

AI Technical Summary

Problems solved by technology

However, during the actual flight of the UAV, it is very likely to encounter unexpected obstacles

[0004] When avoiding obstacles, it only adopts fixed methods such as hovering when encountering obstacles or bypassing obstacles. The flight process will obviously be affected by obstacles and deviate from the originally set flight path, making it difficult to accurately reach the destination. The reliability of autonomous flight Poor sex

Images