Unmanned aerial vehicle autonomous landing method based on visual identification

Abstract

The invention relates to the field of unmanned aerial vehicles, and discloses an unmanned aerial vehicle autonomous landing method based on visual identification. The method comprises the steps of binocular camera correction and calibration, landing landmark selection, close-range landing landmark positioning and long-distance landing landmark positioning. According to the unmanned aerial vehicleautonomous landing method based on visual identification, the calibration process is simplified, the calibration precision is improved, and the positioning precision is guaranteed; and threshold segmentation is performed on an image by adopting a maximum between-cluster variance method, the threshold can be adaptively determined, calculation is facilitated, and two algorithms of short-distance landing landmark positioning and long-distance landing landmark positioning are respectively designed according to the distance between the unmanned aerial vehicle and the landing landmark, so the positioning precision of the unmanned aerial vehicle during autonomous landing is higher, and the risk of air crash caused by inaccurate positioning is reduced.

Description

technical field [0001] The invention relates to the field of unmanned aerial vehicles, in particular to a method for autonomously landing an unmanned aerial vehicle based on visual recognition. Background technique [0002] Unmanned aircraft is referred to as "unmanned aerial vehicle", and the English abbreviation is "UAV". Compared with manned aircraft, drones are often more suitable for tasks that are too "dull, dirty or dangerous". For military use, drones are divided into reconnaissance aircraft and target drones. For civilian use, drones + industry applications, It is the real rigid demand of drones. Currently, it is used in aerial photography, agriculture, plant protection, miniature selfies, express delivery, disaster relief, observation of wild animals, monitoring of infectious diseases, surveying and mapping, news reports, power inspections, disaster relief, film and television shooting, making romance, etc. Applications in fields such as drones have greatly expand...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a method for autonomous landing of UAVs based on visual recognition, which sets fewer calibration parameters, can simplify the calibration process, can ensure positioning accuracy, and can adaptively determine the threshold value. Designing two positioning algorithms for long and short distances, the positioning accuracy is higher, and it solves the problem of the existing human-machine autonomous landing without visual recognition, which cannot simplify the calibration process, cannot adaptively determine the threshold value, and cannot specifically design two long and short distances Positioning algorithm, the problem that the positioning accuracy cannot be guaranteed

Images