Sea-air collaborative visual tracking and autonomous recovery method for unmanned ship-mounted unmanned aerial vehicle

Abstract

The invention discloses a sea-air collaborative visual tracking and autonomous recovery method for an unmanned ship-mounted unmanned aerial vehicle. The method comprises the following steps: the unmanned aerial vehicle searches an unmanned ship by adopting a camera and utilizing a deep learning target detection algorithm; the identification code arranged on the unmanned ship is identified by adopting an airborne camera; when the height between the unmanned aerial vehicle and the boat is smaller than a set value h1, the boat-mounted camera is started to recognize an identification code arranged at the bottom end of the unmanned aerial vehicle and obtain relative position information delta X, delta Y and height H of the unmanned aerial vehicle relative to the boat-mounted camera, and data fusion is performed on the relative position information obtained by the boat-mounted camera and the airborne camera, and control information for adjusting the flight pose of the unmanned aerial vehicle is outputted. The attitude of the unmanned aerial vehicle is adjusted based on the relative position information of the unmanned aerial vehicle relative to the unmanned ship to enable the unmanned aerial vehicle to move along with the unmanned ship, the error of the unmanned aerial vehicle relative to the two-dimensional plane of the landing platform is reduced, and a corresponding descending speed is given to control the unmanned aerial vehicle to land to the center of the identification code according to the vertical distance of the unmanned aerial vehicle relative to the identification code.

Description

technical field [0001] The invention relates to the field of unmanned control technology and application technology, in particular to a target tracking and autonomous recovery method based on visual navigation of an unmanned ship-borne UAV. Background technique [0002] Unmanned boats have the advantages of small size, low cost, and no casualties. They are widely used in ocean detection, ocean sovereignty maintenance, and search and rescue. However, its relatively slow moving speed and the inaccessibility of special sea areas limit the mission range of unmanned vehicles. UAVs also have the characteristics of low cost, no casualties, and diverse functions, and UAVs are also flexible and maneuverable, which can effectively make up for the shortcomings of unmanned boats. By carrying drones on unmanned boats, the flight distance of drones and the range of missions can be expanded. Equipped with cameras on drones to move the perspective to the air, it can provide aerial perspect...

AI Technical Summary

Problems solved by technology

However, in mobile navigation, the positioning accuracy of mobile GPS receivers can only reach the meter level due to the influence of satellite signal conditions and the external environment; the error of inertial navigation will accumulate more and more with time, and even diverge

Neither of them can meet the accuracy requirements for drones to land on unmanned boats

Visual navigation can reduce the positioning accuracy to the centimeter level by identifying the designed identification code. However, during the landing process of the drone, due to the reflection and occlusion of the sea surface, the positioning of the identification code may fail; The problems of loss of logos in the field of view and inaccurate pose calculation eventually lead to the failure of the drone to land

Images