Unmanned aerial vehicle for intelligent identification of polar ice rink and intelligent identification method thereof

Abstract

The invention provides an unmanned aerial vehicle for intelligent identification of a polar ice rink. The unmanned aerial vehicle comprises an aerial vehicle main body, a solar battery pack, rudder wings, a spiral propeller and an observation cabin, the aircraft is powered by solar energy, so that long endurance time can be achieved; the rudder wings are symmetrically installed on the two sides of the aircraft body to achieve lifting and steering of the aircraft body. The spiral propeller provides propulsive force and cooperates with the rudder wings to complete lifting steering motion. A plurality of functional modules are arranged in the observation cabin, and the functions of ice rink recognition, aircraft and transport ship positioning, data transmission, state monitoring and the like can be achieved. Illumination warning lamps are arranged on the front edges of the two wings of the aircraft, so that ice rink identification and aircraft landing under the extremely night condition are facilitated. The invention also provides a polar ice rink intelligent identification method of the unmanned aerial vehicle. The sea ice morphology around the navigation channel can be observed in detail and accurately, accurate sea ice data can be obtained, the polar transport ship is helped to sail, a captain is assisted to make a decision, and the risk of distress is reduced.

Description

Technical Field

[0001] The present invention relates to an unmanned aerial vehicle in the technical field of polar equipment, and in particular to an unmanned aerial vehicle for intelligent identification of polar ice fields and an intelligent identification method thereof. Background Art

[0002] The Arctic region is rich in oil, natural gas and mineral resources. Countries around the world have attached unprecedented importance to the formulation of Arctic strategies, striving to seize the initiative in the development of Arctic routes and resources. Unlike conventional open waters, polar regions are covered with ice and snow all year round, and severe climates such as low temperatures, polar day and night, and blizzards emerge in an endless stream. In such an environment with poor visibility, polar transport ships are very likely to lose their way, deviate from the route, or even collide with multi-year thick ice, icebergs, and ice ridges and become trapped in the ice, resulting in huge economic losses. Ice field identification mainly relies on satellite and shipborne identification tools. Satellite identification has a large observation range, but is greatly affected by weather conditions, cannot identify small-scale sea ice information, and the resolution is difficult to meet the requirements of high-precision identification, so the accuracy and real-time performance of satellite identification are difficult to guarantee; shipborne identification has higher accuracy and real-time performance, but the distance of the transport ship above the horizontal plane is limited, and the flexibility is poor, so the observation range of shipborne identification is small.

[0003] In summary, the existing ice rink identification technology usually cannot guarantee the requirements of high accuracy, real-time performance and large observation range at the same time. Currently, no description or report of similar technology to the present invention has been found, and similar information at home and abroad has not been collected. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides an unmanned aerial vehicle for intelligent identification of polar ice fields and an intelligent identification method thereof.

[0005] According to one aspect of the present invention, there is provided an unmanned aerial vehicle for intelligent identification of polar ice fields, comprising: an aircraft body, a solar cell group, a rudder wing, a propeller and an observation cabin; wherein:

[0006] The aircraft body is used to achieve flight missions;

[0007] The solar cell group is installed above the flying body and is used to absorb solar energy and convert it into electrical energy;

[0008] The rudder wings are symmetrically mounted on both sides of the aircraft body, and are used to achieve the lifting and steering flight tasks of the aircraft body by controlling the rotation angle of the rudder wings;

[0009] The propeller is installed at the tail of the aircraft body, and provides propulsion force for the aircraft body by controlling the propeller to rotate around an axis, so as to realize the forward and backward flight tasks of the aircraft body;

[0010] The observation cabin is installed below the aircraft body and is used to achieve the identification task.

[0011] Preferably, the solar cell group is installed directly above the aircraft body.

[0012] Preferably, the aircraft body comprises: a delta-wing airship, a rudder wing and a lighting warning light; wherein:

[0013] The delta-wing airship uses carbon fiber as a skeleton structure, the exterior of the skeleton structure is covered with a skin, and the interior of the skeleton structure is filled with helium. By controlling the filling and discharge of the nitrogen, auxiliary control of the ascent and descent of the aircraft body is achieved;

[0014] The lighting warning lights are symmetrically mounted on the leading edges of the two wings of the delta-wing airship and are connected to the solar cell group for power supply, and are used to provide lighting assistance for the observation cabin detection;

[0015] The rudder wings are symmetrically mounted on the trailing edges of the two wings of the delta-wing airship.

[0016] Preferably, the observation cabin is in the shape of a pointed triangle which is narrow in the front and wide in the back.

[0017] Preferably, the observation cabin is installed at the center directly below the aircraft body.

[0018] Preferably, a wiper is provided at the rear of the observation cabin.

[0019] Preferably, the observation cabin is provided with a sea ice identification module, a positioning module, a data transmission module and a status monitoring module; wherein:

[0020] The sea ice identification module is used to obtain on-site sea ice data and flight parameter data of the aircraft body, and feed back to the positioning module;

[0021] The positioning module is used to obtain the navigation parameter data of the transport ship in real time, obtain the aircraft motion control parameters between the aircraft body and the transport ship according to the navigation parameter data and the data fed back by the sea ice identification module, obtain the motion mode of the aircraft and the transport ship and feed it back to the state monitoring module for flight control;

[0022] The data transmission module is used to realize data communication within the UAV and between the UAV and the transport ship;

[0023] The status monitoring module is used to monitor in real time the flight parameter data of the aircraft body during flight and the operating parameter data inside and outside the aircraft body, and: control the axial rotation direction of the propeller and / or the rotation angle of the rudder according to the movement mode of the aircraft and the transport ship fed back by the positioning module; and monitor the operating status of the aircraft body in real time based on the operating parameter data obtained through monitoring.

[0024] Preferably, the sea ice identification module acquires on-site sea ice data and flight parameter data of the aircraft body, including:

[0025] Collect on-site pictures in real time through the set high-definition camera;

[0026] Using a perspective transformation method, converting the scene image into a standard top view;

[0027] Gray-scaling and denoising the standard bird's-eye view to obtain a channel sea ice image;

[0028] The sea ice image of the channel is segmented by using a threshold method, wherein black is used to represent sea water and white is used to represent sea ice, and a binary result image for distinguishing sea water from sea ice is obtained;

[0029] Obtaining the internal and external parameters of the high-definition camera, matching the pixel points of the on-site picture, calculating the parallax, and calculating the flight altitude of the aircraft body, the distance between the aircraft body and the transport ship and / or the sea ice, and the size of the sea ice based on the binocular ranging principle, including:

[0030] The internal parameter K of the high-definition camera is obtained by camera calibration. In the geodetic coordinate system O-XYZ, the external parameters of the two high-definition cameras are C 10 and C 20 Indicates that C 10 and C 20 The rotation matrix R and the translation vector t are expressed as:

[0031]

[0032] Transformation matrix C from the first HD camera to the second HD camera 21 Then:

[0033]

[0034] Among them, C 01 C 10 The inverse of

[0035] P h is a point on the sea ice image collected by a high-definition camera that satisfies n h Ph The normal vector of the plane where the point is located under the high-definition camera, d is P h The distance between the plane where the point is located and the HD camera, is the projection of the point to the normal vector; for the first high-definition camera, there is a point P on the plane h1 satisfy:

[0036]

[0037] P h1 and P h2 P h Coordinates in the coordinate systems of the first and second high-definition cameras, n h1 P h1 The normal vector of the plane where the point is located under the high-definition camera; according to the projection relationship, Z C1 and Z C2 The external references of the first and second high-definition cameras are obtained respectively, K 1 and K 2 are the internal parameters of the first and second high-definition cameras, respectively, 1 P h1 The corresponding pixel points on the collected sea ice image; according to the coordinate transformation, there are:

[0038] P h2 =R 21 P h1 +t 21 (4)

[0039]

[0040] Among them, p 2 P h2 The corresponding pixel points on the collected sea ice image, is a homography matrix, from which the distance data between the aircraft body and the transport ship and / or the sea ice are calculated;

[0041] Using the flight altitude of the aircraft body and the distance between the aircraft body and the transport ship and / or the sea ice updated in real time as the flight parameter data of the aircraft body;

[0042] A sea ice database is constructed using the real-time updated binary result map and the sea ice size. The ice field is classified and the size is calculated based on the sea ice database. The category, size, distribution and density of the sea ice are statistically analyzed to obtain on-site sea ice data.

[0043] Preferably, the positioning module acquires the navigation parameter data of the aircraft and the transport ship in real time, acquires the aircraft motion control parameters between the aircraft body and the transport ship according to the navigation parameter data and the data obtained by the sea ice recognition module, and obtains the motion mode of the aircraft and the transport ship, including:

[0044] Obtain real-time navigation parameter data of aircraft and transport ships, including: the speed and trajectory of the transport ship;

[0045] The flight parameter data and sea ice data are obtained by the sea ice identification module, and the navigation hazard index k in the rectangular ice field with the transport ship as the center and extending outward by m times the ship length and n times the ship width is calculated:

[0046]

[0047] Among them, A total Represents the total area of ​​the rectangular ice rink, A ice berg A represents the area occupied by icebergs in this region. ice ridge A represents the area occupied by the ice ridge in the region. level ice A represents the area occupied by the ice layer in this region. rubble ice A represents the area occupied by floating ice in the region. open water A represents the area of ​​open water in the region. extra represents the area occupied by other regions; α, β, γ, λ, μ, τ are the risk coefficients corresponding to each ice condition and satisfy:

[0048]

[0049] According to the displacement and speed of the transport ship in the previous period a, the travel trajectory s a , predict the trajectory s of the transport ship in the next time period b in the geodetic coordinate system b :

[0050] s b =us a +s e (8)

[0051] Among them, s a =[s xa s ya v xa v ya ], where the first two terms are driving displacement and the last two terms are driving speed. is the transfer matrix, s b =[s xb s yb v xb v yb ],s e =[s xe sye v xe v ye ] is the additional movement of the transport ship caused by avoiding icebergs and ice ridges estimated based on the sea ice binary result map;

[0052] Actual moving position of the transport ship c and predicted trajectory s b The error E is:

[0053]

[0054]

[0055] RMSE(E i ) is the predicted trajectory s of the transport ship b The actual motion position s c The mean square error between ||E i || represents the error E i Take the determinant;

[0056] The error E represents the degree of coincidence between the actual navigation route and the predicted route;

[0057] The distance between the aircraft body and the transport ship, the transport ship navigation hazard index, and the overlap between the actual navigation route and the predicted route in the flight parameter data are used as the aircraft motion control parameters to obtain the aircraft and transport ship motion modes, and the aircraft is controlled as follows:

[0058] According to the ice resistance level of the transport ship, the maximum safe distance between the transport ship and the aircraft is set to s. safe and through Control the aircraft to achieve case 1 motion mode full speed to the transport ship to ensure safe navigation, case 2 motion mode to move away from the transport ship to shoot and identify distant sea ice data, or case 3 motion mode to move close to the transport ship to shoot and identify sea ice data near the channel, where ω, η, ξ are constants, and their sizes are determined by the ice resistance level of the transport ship, then:

[0059]

[0060] Preferably, the state monitoring module controls the rotation direction of the propeller around the axis and / or the rotation angle of the rudder wing according to the motion mode of the aircraft and the transport ship fed back by the positioning module, including:

[0061] Based on the control algorithm of the motion control equation and the motion mode of the aircraft and the transport ship, the rotation direction of the propeller around the axis and / or the rotation angle of the rudder wing are controlled as follows:

[0062] It is defined that when the aircraft is moving forward, the propeller is turned forward and recorded as 1, when the aircraft is moving backward, the propeller is turned backward and recorded as -1, and when it stops turning, it is 0; when the aircraft is climbing, the rotation direction of the two rudders is positive and recorded as 1, when the aircraft is diving, the rotation direction of the two rudders is negative and recorded as -1, and reset is 0; through the principle of binocular ranging of high-definition cameras, it is judged that the aircraft and the transport ship are sailing in the same direction as 1 or in the opposite direction as -1, and other states are recorded as 0; the state of the propeller and the aircraft is controlled by STATE = [propeller 1 propeller 2 rudder 1 rudder 2 heading];

[0063] When the distance between the transport ship and the aircraft is greater than the maximum safe distance s safe , CONTROL<0, start case1 motion mode: if STATE[0 0 0 0 1] T ≠-1, then STATE[1 1 0 0 0] T = 0 and STATE[0 0 1 1 0] T =0, the aircraft turns around through propellers and rudders; if STATE[0 0 0 0 1] T = -1, then STATE = [1100-1], the aircraft is heading towards the transport ship at full speed;

[0064] When the distance between the transport ship and the aircraft is less than the maximum safe distance s safe And the navigation hazard index k and the mean square error RMSE (E i ) is small (less than a set threshold), the transport ship moves according to the predicted trajectory, CONTROL>1, and case2 motion mode is started: If STATE[00 1 1 0] T =-1, then The aircraft moves forward and turns through the rudder; if STATE[0 0 0 0 1] T ≠-1, then STATE = [1 1 1 1 x], the aircraft moves forward and climbs, thereby identifying a wider ice field;

[0065] When the distance between the transport ship and the aircraft is less than the maximum safe distance s safe And the navigation hazard index k and the mean square error RMSE (E i ) is larger (greater than a set threshold), the transport ship deviates from the predicted trajectory and starts case 3 motion mode: If STATE[0 0 1 1 0] T = -1, then STATE = [1 1 -1 -1 x], the aircraft drives towards the transport ship and descends; if STATE [0 0 0 0 1] T≠-1, then STATE=[-1 -1 -1 -1 x], and the aircraft moves backward and descends. In both cases, the aircraft moves close to the transport ship, thereby identifying the transport ship and the ice field around the channel.

[0066] According to another aspect of the present invention, there is provided a method for intelligently identifying polar ice fields of an unmanned aerial vehicle according to any one of the above-mentioned embodiments of the present invention, comprising:

[0067] Use unmanned aerial vehicles to collect on-site images in real time;

[0068] Using a perspective transformation method, converting the scene image into a standard top view;

[0069] Gray-scaling and denoising the standard bird's-eye view to obtain a channel sea ice image;

[0070] The sea ice image of the channel is segmented by using a threshold method, wherein black is used to represent sea water and white is used to represent sea ice, and a binary result image for distinguishing sea water from sea ice is obtained;

[0071] Obtain the internal and external parameters of the high-definition camera, match the pixel points of the on-site picture, calculate the parallax, and calculate the size of the sea ice based on the binocular ranging principle;

[0072] A sea ice database is constructed using the real-time updated binary result map and the sea ice size. The ice field is classified and the size is calculated based on the sea ice database. The category, size, distribution and density of the sea ice are counted to obtain on-site sea ice data, thereby completing the intelligent identification of polar ice fields.

[0073] Preferably, it also includes:

[0074] Based on the binocular ranging principle, the flight altitude of the UAV and the distance between the UAV and the transport ship are calculated in real time as flight parameter data;

[0075] Calculate the relative motion displacement and speed between the unmanned aerial vehicle and the transport ship according to the flight parameter data;

[0076] According to the relative motion displacement and speed, the rotation angle of the rudder of the unmanned aerial vehicle and / or the rotation direction of the propeller around the axis are controlled to maintain a safe communication distance with the transport ship;

[0077] The acquired on-site sea ice data will be fed back to the transport ship in real time.

[0078] Due to the adoption of the above technical solution, the present invention has at least one of the following beneficial effects compared with the prior art:

[0079] The unmanned aerial vehicle and intelligent identification method for polar ice field provided by the present invention can obtain the navigation parameter data of the aircraft and the transport ship in real time and fly autonomously in an area around the transport ship. The high-definition camera loaded in the monitoring cabin can shoot and record the sea ice around the waterway, and the computer can transform the perspective of the side view, convert the photos and videos into a standard top view, and grayscale and denoise the image on this basis, and extract features and segment the sea ice in the image. Combined with the sea ice database, the ice blocks are identified, the sea ice size is calculated, and the size distribution and sea ice density of the sea ice are counted. At the same time, the data is transmitted to the transport ship and the polar service station in real time to ensure that the transport ship completes the transportation task safely and efficiently, and helps the development of the Arctic waterway.

[0080] The unmanned aerial vehicle and its intelligent identification method for polar ice field provided by the present invention have an inflatable airship as the main body, which can generate a certain lift by itself and does not need to consume too much energy to offset its own weight. The aircraft only needs a small thrust from the propeller in the air, and can freely complete the lifting and rotating movements with the help of the rudder wings on both sides. The overall shape of the aircraft is a delta wing, which can effectively reduce air resistance and further save energy.

[0081] The unmanned aerial vehicle and its intelligent identification method for polar ice field intelligent identification provided by the present invention are based on the premise of not destroying the polar ecological environment. The main body of the aircraft is mainly powered by solar cell groups above the two wings, which is green and environmentally friendly. During the polar day, the solar energy is abundant, the vision is clear, and the sea ice is easy to identify; during the polar night, the lighting warning lights on the leading edges of the two wings of the aircraft will be turned on, which is convenient for observing the sea ice and also convenient for forced landing on the transport ship when energy is insufficient.

[0082] The present invention provides an unmanned aerial vehicle for intelligent identification of polar ice fields and an intelligent identification method thereof. An observation cabin is installed under the main body of the aircraft. The overall shape is a pointed triangle that is narrow in the front and wide in the back. The narrow front structure is subject to less wind resistance and is not easily iced on both sides. A wiper is installed at the rear of the observation cabin where ice is most likely to form, which can clean up water vapor, dust and other debris to prevent ice from forming.

[0083] The unmanned aerial vehicle and its intelligent identification method for intelligent identification of polar ice fields provided by the present invention have a state monitoring module built into the observation cabin, which can monitor in real time whether the operating state of the aircraft is normal and whether the structure is damaged, such as monitoring the pressure in the inflatable airship, controlling pressurization and depressurization, and ensuring the safe operation of the aircraft.

[0084] The unmanned aerial vehicle for intelligent identification of polar ice fields and the intelligent identification method thereof provided by the present invention have a simple aerial vehicle structure, low manufacturing and maintenance costs, and do not require a random pilot.

[0085] The unmanned aerial vehicle for intelligent identification of polar ice fields and the intelligent identification method thereof provided by the present invention are suitable for long-term observation operations in polar regions. Compared with ordinary unmanned aerial vehicles, they can autonomously fly above polar transport ships, identify ice fields around the transport ship's waterway, share data with the transport ship in real time, and help polar transport ships complete transportation tasks safely and efficiently.

[0086] The unmanned aerial vehicle for intelligent identification of polar ice fields and the intelligent identification method thereof provided by the present invention can help polar transport ships navigate, assist captains in decision-making, and reduce the risk of distress; observe the sea ice morphology around the waterway in detail and accurately, obtain precise sea ice data, assist scientific research in the polar field, and provide a reference for the development of Arctic waterways. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0088] Figure 1 A schematic diagram of the overall structural arrangement of an unmanned aerial vehicle in a preferred embodiment of the present invention;

[0089] Figure 2 It is an isometric view of an unmanned aerial vehicle in a preferred embodiment of the present invention;

[0090] Figure 3 A rear view of an unmanned aerial vehicle in a preferred embodiment of the present invention;

[0091] Figure 4 It is an axonometric view of the main body of the aircraft in a preferred embodiment of the present invention;

[0092] Figure 5 A bottom view of the main body of the aircraft in a preferred embodiment of the present invention;

[0093] Figure 6 This is a schematic diagram of the structure of a solar cell group in a preferred embodiment of the present invention;

[0094] Figure 7 A schematic diagram of two solar cell groups (gap or transition) being joined together in a preferred embodiment of the present invention;

[0095] Figure 8 It is a schematic diagram of the structural arrangement of the observation cabin in a preferred embodiment of the present invention;

[0096] Fig. 9 A side view of an observation cabin in a preferred embodiment of the present invention;

[0097] Fig.10 This is a flow chart of intelligent identification of an ice rink by an unmanned aerial vehicle in a preferred embodiment of the present invention.

[0098] Among them: 1 is the main body of the aircraft, 101 is the hull, 102 is the lighting warning light, 103 is the rudder wing; 2 is the solar cell group; 3 is the propeller; 4 is the observation cabin, 401 is the cabin, 402 is the wiper, and 403 is the functional module arranged inside the observation cabin. DETAILED DESCRIPTION

[0099] The following is a detailed description of the embodiments of the present invention: This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given. It should be pointed out that for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

[0100] An embodiment of the present invention provides a long-endurance unmanned aerial vehicle for intelligent identification of polar ice fields. The aircraft can autonomously fly above a transport ship, identify the ice fields around the transport ship's waterway, and share high-precision real-time observation data with the transport ship.

[0101] like Figure 1 As shown, the unmanned aerial vehicle for intelligent identification of polar ice fields provided in this embodiment may include: an aircraft body, a solar cell group, a rudder wing, a propeller and an observation cabin; wherein:

[0102] The main body of the aircraft is used to achieve the flight mission;

[0103] The solar cell array is installed above the flight body to absorb sunlight and convert it into electrical energy;

[0104] The rudder wings are symmetrically installed on both sides of the aircraft body, and are used to achieve the lifting and turning flight tasks of the aircraft body by controlling the rotation angle of the rudder wings;

[0105] The propeller is installed at the tail of the aircraft body. By controlling the propeller to rotate around its axis, it provides propulsion for the aircraft body to achieve forward and backward flight missions of the aircraft body.

[0106] The observation cabin is installed under the main body of the aircraft and is used to carry out identification tasks.

[0107] In a preferred embodiment, the solar cell array is installed directly above the main body of the aircraft.

[0108] In a preferred embodiment, the aircraft body includes: a delta-wing airship, a rudder wing and a lighting warning light; wherein:

[0109] The delta-wing airship uses carbon fiber as its skeleton structure. The outside of the skeleton structure is covered with skin, and the inside of the skeleton structure is filled with helium. By controlling the filling and discharge of nitrogen, auxiliary control of the ascent and descent of the aircraft body is achieved.

[0110] The lighting warning lights are symmetrically installed on the leading edges of the two wings of the delta-wing airship and are connected to the solar cell group for power supply to provide lighting assistance for the observation cabin detection;

[0111] The rudder wings are symmetrically installed on the trailing edges of the two wings of the delta-wing airship.

[0112] In a preferred embodiment, the observation cabin is in the shape of a pointed triangle as a whole.

[0113] In a preferred embodiment, the observation cabin is installed at the center directly below the main body of the aircraft.

[0114] In a preferred embodiment, a wiper is provided at the rear of the observation cabin.

[0115] In a preferred embodiment, the observation cabin is provided with a sea ice identification module, a positioning module, a data transmission module and a status monitoring module; as shown in the figure:

[0116] Sea ice identification module, used to obtain on-site sea ice data and flight parameter data of the aircraft body, and feed it back to the positioning module;

[0117] The positioning module is used to obtain the navigation parameter data of the aircraft and the transport ship in real time, obtain the aircraft motion control parameters between the aircraft body and the transport ship based on the navigation parameter data and the data obtained by the sea ice identification module, obtain the motion mode of the aircraft and the transport ship and feed it back to the status monitoring module for flight control;

[0118] A data transmission module, used to realize data communication within the UAV and between the UAV and the transport ship;

[0119] The status monitoring module is used to monitor the flight parameter data of the aircraft body during flight and the operating parameter data inside and outside the aircraft body in real time, and: control the axial rotation direction of the propeller and / or the rotation angle of the rudder according to the movement mode of the aircraft and the transport ship fed back by the positioning module; and monitor the operating status of the aircraft body in real time based on the operating parameter data obtained through monitoring.

[0120] In a preferred embodiment, the sea ice identification module obtains on-site sea ice data and flight parameter data of the aircraft body, including:

[0121] Collect on-site pictures in real time through the set high-definition camera;

[0122] The perspective transformation method is used to convert the on-site image into a standard top view;

[0123] Grayscale and denoise the standard top view to obtain the channel sea ice image;

[0124] The threshold method is used to segment the channel sea ice image, in which black is used to represent sea water and white is used to represent sea ice, and a binary result image is obtained to distinguish sea water from sea ice.

[0125] Obtain the internal and external parameters of the high-definition camera, match the pixels of the on-site picture, calculate the parallax, and calculate the flight altitude of the aircraft body, the distance between the aircraft body and the transport ship and / or sea ice, and the size of the sea ice based on the principle of binocular ranging, including:

[0126] The internal parameter K of the high-definition camera is obtained by camera calibration. In the geodetic coordinate system O-XYZ, the external parameters of the two high-definition cameras are C 10 and C 20 Indicates that C 10 and C 20 The rotation matrix R and the translation vector t are expressed as:

[0127]

[0128] Transformation matrix C from the first HD camera to the second HD camera 21 Then:

[0129]

[0130] Among them, C 01 C 10 The inverse of

[0131] P h is a point on the sea ice image collected by a high-definition camera that satisfies n h P h The normal vector of the plane where the point is located under the high-definition camera, d is P h The distance between the plane where the point is located and the HD camera, is the projection of the point to the normal vector; for the first high-definition camera, there is a point P on the plane h1 satisfy:

[0132]

[0133] P h1 and P h2 P h Coordinates in the coordinate systems of the first and second high-definition cameras, n h1 P h1 The normal vector of the plane where the point is located under the high-definition camera; according to the projection relationship, Z C1 and Z C2 The external references of the first and second high-definition cameras are obtained respectively, K 1 and K 2are the internal parameters of the first and second high-definition cameras, respectively, 1 P h1 The corresponding pixel points on the collected sea ice image; according to the coordinate transformation, there are:

[0134] P h2 =R 21 P h1 +t 21 (4)

[0135]

[0136] Among them, p 2 P h2 The corresponding pixel points on the collected sea ice image, is a homography matrix, from which the distance data between the aircraft body and the transport ship and / or sea ice are calculated;

[0137] The flight altitude of the aircraft body and the distance between the aircraft body and the transport ship and / or the sea ice updated in real time are used as the flight parameter data of the aircraft body;

[0138] A sea ice database is constructed using the real-time updated binary result map and sea ice size. The ice fields are classified and their sizes are calculated based on the sea ice database. The types, sizes, distribution and density of sea ice are counted to obtain on-site sea ice data.

[0139] In a preferred embodiment, the positioning module obtains the navigation parameter data of the aircraft and the transport ship in real time, obtains the aircraft motion control parameters between the aircraft body and the transport ship according to the navigation parameter data and the data obtained by the sea ice recognition module, and obtains the motion mode of the aircraft and the transport ship for controlling the aircraft to navigate around the transport ship according to the motion mode, including:

[0140] Real-time acquisition of navigation parameter data of the aircraft and the transport ship, including: the travel speed and travel trajectory of the transport ship; wherein, in a preferred embodiment, the travel speed can be directly obtained by a displacement sensor;

[0141] According to the sea ice identification module, the flight parameter data and sea ice data are obtained, and the navigation hazard index k in the rectangular ice field with the transport ship as the center and m times the ship length and n times the ship width is calculated:

[0142]

[0143] Among them, A total Represents the total area of ​​the rectangular ice rink, A ice berg A represents the area occupied by icebergs in this region. ice ridge A represents the area occupied by the ice ridge in the region. level ice A represents the area occupied by the ice layer in this region. rubble iceA represents the area occupied by floating ice in the region. open water A represents the area of ​​open water in the region. extra represents the area occupied by other regions; α, β, γ, λ, μ, τ are the risk coefficients corresponding to each ice condition and satisfy:

[0144]

[0145] According to the displacement and speed of the transport ship in the previous period a, the travel trajectory s a , predict the trajectory s of the transport ship in the next time period b in the geodetic coordinate system b :

[0146] s b =us a +s e (8)

[0147] Among them, s a =[s xa s ya v xa v ya ], where the first two terms are driving displacement and the last two terms are driving speed. is the transfer matrix, s b =[s xb s yb v xb v yb ],s e =[s xe s ye v xe v ye ] is the additional movement of the transport ship caused by avoiding icebergs and ice ridges estimated based on the sea ice binary result map;

[0148] Actual moving position of the transport ship c and predicted trajectory s b The error E is:

[0149]

[0150]

[0151] RMSE(E i ) is the predicted trajectory s of the transport ship b The actual motion position s c The mean square error between ||E i || represents the error E i Take the determinant;

[0152] The error E is used to represent the degree of coincidence between the actual navigation route and the predicted route;

[0153] The distance between the aircraft and the transport ship, the transport ship navigation hazard index, and the overlap between the actual navigation route and the predicted route in the flight parameter data are used as the aircraft motion control parameters to obtain the motion mode of the aircraft and the transport ship, and the aircraft is controlled as follows:

[0154] According to the ice resistance level of the transport ship, the maximum safe distance between the transport ship and the aircraft is set to s. safe and through Control the aircraft to achieve case 1 motion mode full speed to the transport ship to ensure safe navigation, case 2 motion mode to move away from the transport ship to shoot and identify distant sea ice data, or case 3 motion mode to move close to the transport ship to shoot and identify sea ice data near the channel, where ω, η, ξ are constants, and their sizes are determined by the ice resistance level of the transport ship, then:

[0155]

[0156] In a preferred embodiment, the state monitoring module controls the rotation direction of the propeller and / or the rotation angle of the rudder according to the motion mode of the aircraft and the transport ship fed back by the positioning module, including:

[0157] Based on the control algorithm of the motion control equation and the motion mode of the aircraft and the transport ship, the rotation direction of the propeller and / or the rotation angle of the rudder are controlled as follows:

[0158] It is defined that when the aircraft is moving forward, the propeller turns forward and is recorded as 1, when the aircraft is moving backward, the propeller turns reversely and is recorded as -1, and stops turning as 0; when the aircraft is climbing, the two rudders turn forward and are recorded as 1, when the aircraft is diving, the two rudders turn forward and are recorded as -1, and reset as 0; through the principle of binocular ranging of high-definition cameras, it is determined that the aircraft and the transport ship are sailing in the same direction as 1 or in the opposite direction as -1, and other states are recorded as 0. The state of the propeller and the aircraft is controlled by STATE = [propeller 1 propeller 2 rudder 1 rudder 2 heading];

[0159] When the distance between the transport ship and the aircraft is greater than the maximum safe distance s safe , CONTROL<0, start case1 motion mode: if STATE[0 0 0 0 1] T ≠-1, then STATE[1 1 0 0 0] T = 0 and STATE[0 0 1 1 0] T =0, the aircraft turns around through propellers and rudders; if STATE[0 0 0 0 1] T = -1, then STATE = [1 1 0 0 -1], the aircraft is heading towards the transport ship at full speed;

[0160] When the distance between the transport ship and the aircraft is less than the maximum safe distance s safe And the navigation hazard index k and the mean square error RMSE (E i ) is small (can be determined by a set threshold), that is, when the transport ship is moving according to the predicted trajectory, CONTROL>1, and case2 motion mode is started: if STATE[0 0 1 1 0] T =-1, then The aircraft moves forward and turns through the rudder; if STATE[0 0 0 0 1] T ≠-1, then STATE = [1 1 1 1x], the aircraft moves forward and climbs, thereby identifying a wider ice field;

[0161] When the distance between the transport ship and the aircraft is less than the maximum safe distance s safe And the navigation hazard index k and the mean square error RMSE (E i ) is large (which can be determined by a set threshold), that is, when the transport ship deviates from the predicted trajectory, case 3 motion mode is activated: if STATE[0 0 1 1 0] T = -1, then STATE = [1 1 -1 -1 x], the aircraft drives towards the transport ship and descends; if STATE [0 0 0 0 1] T ≠-1, then STATE=[-1 -1 -1 -1 x], the aircraft moves backward and descends; in both cases, the aircraft moves close to the transport ship, thereby identifying the transport ship and the ice field around the channel.

[0162] An embodiment of the present invention further provides a method for intelligently identifying polar ice fields using an unmanned aerial vehicle. The unmanned aerial vehicle used in the method may be any of the unmanned aerial vehicles for intelligently identifying polar ice fields in the above-mentioned embodiments of the present invention.

[0163] The polar ice field intelligent identification method provided in this embodiment may include:

[0164] Use unmanned aerial vehicles to collect on-site images in real time;

[0165] The perspective transformation method is used to convert the on-site image into a standard top view;

[0166] Grayscale and denoise the standard top view to obtain the channel sea ice image;

[0167] The threshold method is used to segment the channel sea ice image, in which black is used to represent sea water and white is used to represent sea ice, and a binary result image is obtained to distinguish sea water from sea ice.

[0168] Obtain the internal and external parameters of the high-definition camera, match the pixel points of the on-site picture, calculate the parallax, and calculate the size of the sea ice based on the binocular ranging principle;

[0169] A sea ice database is constructed using real-time updated binary result maps and sea ice sizes. The ice fields are classified and their sizes are calculated based on the sea ice database. The types, sizes, distribution and density of sea ice are counted to obtain on-site sea ice data and complete intelligent identification of polar ice fields.

[0170] In a preferred embodiment, the method may further include:

[0171] Based on the binocular ranging principle, the flight altitude of the UAV and the distance between the UAV and the transport ship are calculated in real time as flight parameter data;

[0172] Calculate the relative motion displacement and speed between the unmanned aerial vehicle and the transport ship based on the flight parameter data;

[0173] According to the relative motion displacement and speed, the rotation angle of the rudder of the UAV and / or the rotation direction of the propeller around the axis are controlled to maintain a safe communication distance with the transport ship;

[0174] The acquired on-site sea ice data will be fed back to the transport ship in real time.

[0175] In some embodiments of the present invention:

[0176] The main body of the aircraft is a combination of a delta-wing airship, several lighting warning lights and two rudder wings.

[0177] The delta-wing airship has a carbon fiber frame, is covered with linen, silk, rubber and other skins, and is filled with helium inside.

[0178] The lighting warning lights are divided into two warning lights and eight lighting lights (the number can be adjusted as needed). They are symmetrically installed on the leading edges of the two wings of the aircraft and are powered by solar cell arrays. The lighting warning lights will be turned on when the observation cabin detects polar night phenomena or emergencies.

[0179] The rudders are symmetrically installed on the trailing edges of the two wings of the aircraft, and control the rise and fall and steering of the aircraft by rotating the angle.

[0180] The solar cell array is the energy core of the aircraft. It is installed above the main body of the aircraft and can fully absorb solar energy and convert it into electrical energy for the aircraft to use.

[0181] The propeller is the driving core of the aircraft. It is installed at the tail of the aircraft and can rotate around the axis to provide propulsion for the aircraft.

[0182] The observation cabin is arranged under the main body of the aircraft. It is overall in the shape of a pointed triangle and contains multiple modules such as ice field identification, positioning, data transmission and status monitoring, and a wiper is installed at the tail.

[0183] The sea ice recognition module starts the high-definition camera to collect on-site images of polar ship channels and ice fields, and transmits the data to the calculation unit of the sea ice recognition module. The computer uses perspective transformation technology to convert the images taken by the unmanned aerial vehicle into a standard overhead view, and grayscales and denoises the photos and videos to obtain a highly reliable channel sea ice image. The image is then segmented using the threshold method, using black to represent sea water and white to represent sea ice, and a binary result image that accurately distinguishes sea water from sea ice is obtained. At the same time, the computer will read the internal parameters (such as focal length, principal point) and external parameters (such as relative position, orientation) of the two high-definition cameras, match the pixels of the captured images to calculate the parallax, and calculate the aircraft height, the distance between the aircraft and the transport ship, and the size of the sea ice based on the binocular ranging principle. Construct a sea ice database to assist in identifying, classifying ice blocks and calculating sizes, and to count the size distribution and density of sea ice. Among them, sea ice data include: 1. Category (iceberg / ice ridge / layer ice / floating broken ice, one-year ice / multi-year ice, morphological classification such as cake ice, lotus leaf ice, etc.); 2. Size (size, etc.); 3. Broken ice channel data (distribution); 4. Sea ice density, etc.

[0184] The positioning module reads data such as the aircraft's altitude, the distance between the aircraft and the transport ship, etc. from the computer, calculates the relative motion displacement and speed in real time, and uses a control algorithm based on the motion control equation to process and analyze the data and feed it back to the propeller and rudder, thereby controlling the aircraft to move relatively stably above the transport ship.

[0185] The data transmission module reads high-precision sea ice data from the computer and synchronizes it to the transport ship in real time to guide the ship's navigation and assist the captain in making decisions; the captured photos, videos, calculated sea ice size distribution, density and other data are transmitted to the polar scientific research service station to assist scientific research in the polar field and provide reference for the development of Arctic waterways.

[0186] The status monitoring module can monitor the key parameters of the unmanned aerial vehicle in real time during operation, such as altitude, speed, tilt angle, temperature, etc. It will also monitor the key parameters such as air pressure, temperature, humidity inside and outside the aircraft, so as to ensure the long-term safe operation of the aircraft in the high-risk polar environment. The module can also monitor whether the structure of the aircraft is damaged, such as monitoring the internal pressure of the airship, and controlling pressurization and depressurization. The method of monitoring whether the structure of the aircraft is damaged can be: 1. Monitor the internal pressure of the airship through a pressure sensor. The normal pressure is dynamically balanced within a certain range. The pressure of the damaged hull will be abnormal, such as the continuous decrease of leakage pressure, and the pressure increase when a large area is under pressure but not damaged; 2. Whether the flight altitude, speed, tilt angle, cabin temperature, humidity, etc. are abnormal.

[0187] It should be noted that the steps in the method provided by the present invention can be implemented by using the corresponding components in the aircraft, and those skilled in the art can refer to the technical solution of the aircraft to implement the step flow of the method, and can also refer to the technical solution of the method to implement the composition of the aircraft, that is, the embodiments in the aircraft and the embodiments in the method can be understood as preferred examples of each other, which will not be elaborated here.

[0188] The technical solution provided by the above embodiment of the present invention is further described in detail below in conjunction with the accompanying drawings.

[0189] like Figure 1 , Figure 2 , Figure 3 As shown, the unmanned aerial vehicle provided by the above embodiment of the present invention includes an aircraft body 1, a solar cell group 2, a rudder 103, a propeller 3 and an observation cabin 4. A plurality of solar cell groups 2 are symmetrically mounted above the aircraft body 1, the propeller 3 is mounted at the center of the tail of the aircraft body 1, and the observation cabin 4 is mounted at the center directly below the aircraft body 1.

[0190] like Figure 4 , Figure 5 As shown, the aircraft body 1 is composed of a hull 101, a lighting warning light 102, and rudder wings 103 are installed on both sides of the hull 101. Helium is injected into the hull 101 to provide lift. The aircraft body 1 is in the shape of a delta wing, which can effectively reduce the forward resistance and facilitate air steering and acceleration. A plurality of lighting warning lights 102 are installed on the leading edges of the two wings of the aircraft body 1 for lighting and warning during the polar night or in case of emergencies; two rudder wings 103 are installed on the trailing edges of the two wings of the aircraft body 1 for controlling the lifting and steering of the aircraft.

[0191] like Figure 6As shown, the solar cell group 2 is a rectangular solar panel with three blind holes on one side of the panel, three shafts that can cooperate with the blind holes (gaps or transitions) are welded to the surface opposite to the side, and four vertical shafts are welded to the bottom of the panel. The entire solar cell group is connected to the aircraft body 1 through these four shafts. Figure 7 This is a schematic diagram of the blind hole of a solar cell group matching with the axis of another solar cell group. The axes and holes of multiple solar cell groups match each other to form Figure 2 The large solar cell array shown.

[0192] like Figure 8 , Fig. 9 As shown, the observation cabin 4 is composed of a cabin 401, a wiper 402, and functional modules 403 such as a sea ice identification module, a positioning module, a data transmission module, and a status monitoring module arranged inside the cabin 401. The observation cabin 4 and its cabin 401 are in the shape of a pointed triangle with a narrow front and a wide rear. The structure is subject to less air resistance and is not easy to ice up on both sides. The wiper 402 is installed at the tail of the cabin 401, and removes water vapor, dust and other debris attached to the tail of the observation cabin through periodic reciprocating motion to prevent ice formation. Each functional module 403 is installed inside the cabin 401, and performs functions such as ice field identification around the transport ship channel, real-time positioning of the aircraft and the transport ship, real-time transmission of monitoring data, and aircraft operation status monitoring during the operation of the aircraft.

[0193] like Fig.10 The figure shows the operation flow chart of each functional module inside the cabin 401. The sea ice recognition module starts the high-definition camera to collect sea ice images, and the computer processes the binary result of sea water and sea ice to obtain the sea ice size, density, and relative movement data between the aircraft and the transport ship. The positioning module controls the aircraft to move stably around the transport ship, and the data transmission module transmits accurate sea ice data to the transport ship and the scientific research station. The state monitoring module uses the air pressure, temperature, humidity and structural damage inside and outside the aircraft to ensure long-term safe operation. Fig.10 In the process, perspective transformation, image graying, denoising, threshold image segmentation, binary sea ice image, calculation of relative motion based on binocular ranging principle, ice size, distribution characteristics, and ice density calculation and processing can all be completed by a computer.

[0194] Further:

[0195] The aircraft body 1 is filled with helium, and the whole body is subjected to a certain lift, and then the propeller 3 starts to rotate to provide thrust, and the rear ends of the two rudder wings 103 at the rear edge of the main body 1 are tilted upward to provide lift. After the aircraft rises into the air and stabilizes, the rudder wings 103 at the rear edge of the main body 1 and the propeller 3 are used to adjust the motion state.

[0196] During the polar day, the solar cell group 2 receives sunlight and converts it into electrical energy for the aircraft. When the polar night or an emergency occurs, the warning lights 102 on the leading edges of the two wings of the main body 1 are turned on, the hull 101 of the aircraft discharges some helium to relieve pressure, and the propeller 3 and the two rudder wings 103 on the trailing edge of the main body 1 are used to land.

[0197] In normal operation, the status monitoring module in the observation cabin 4 monitors the structural damage of the aircraft and the pressure in the hull 101 in real time, and controls the pressurization and depressurization. The positioning module obtains the navigation parameter data of the aircraft and the transport ship, calculates the motion control parameters such as the distance between the aircraft body and the transport ship, and controls the aircraft to move in an area above the transport ship. The sea ice recognition module intelligently identifies the sea ice around the waterway and focuses on marking dangerous points (such as multi-year thick ice, icebergs, ice ridges, etc. that the transport ship cannot break through). When it is necessary to identify a large range of ice fields, the internal pressurization of the aircraft hull 101 can be controlled by the status monitoring module, and the two rudder wings 103 and the propeller 3 at the rear edge of the main body 1 can be used to control the aircraft to rise; conversely, if it is necessary to obtain accurate ice field data for a small area, the internal pressure relief of the aircraft hull 101 cooperates with the two rudder wings 103 and the propeller 3 at the rear edge of the main body 1 to control the aircraft to descend. The data transmission module will transmit the identified sea ice data and aircraft status monitoring data to the transport ships and polar service stations in real time, ensuring that the transport ships can complete their transportation tasks safely and efficiently, and assisting in the development of Arctic waterways.

[0198] The unmanned aerial vehicle for intelligent identification of polar ice fields provided in the above-mentioned embodiment of the present invention has a certain lift force and autonomously flies above polar ships, uses solar energy to generate electricity, saves energy and ensures long endurance; at the same time, the functional modules loaded in the observation cabin can shoot and record the ice fields around the ice zone waterway, and perform side view perspective transformation, image graying, image denoising and image segmentation and other processing through a computer, identify ice blocks according to the binocular ranging principle combined with the sea ice database and the binary image, calculate the size of sea ice, and count the size distribution and density of sea ice. Finally, the data transmission module is used to synchronize high-precision sea ice data to the transport ship in real time to guide the navigation of the ship and assist the captain in making decisions; the photographs, videos, calculated sea ice size distribution, density and other data are transmitted to the polar service station to assist scientific research in the polar field and provide a reference for the development of Arctic waterways.

[0199] All matters not covered in the above embodiments of the present invention are well known in the art.

[0200] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art may make various modifications or variations within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. An unmanned aerial vehicle for intelligent identification of polar ice fields, characterized in that: include: The aircraft body, solar cell array, rudder wings, propellers and observation cabin; among which: The aircraft body is used to achieve flight missions; The solar cell group is installed above the flying body and is used to absorb solar energy and convert it into electrical energy; The rudder wings are symmetrically mounted on both sides of the aircraft body, and are used to achieve the lifting and steering flight tasks of the aircraft body by controlling the rotation angle of the rudder wings; The propeller is installed at the tail of the aircraft body, and provides propulsion force for the aircraft body by controlling the propeller to rotate around an axis, so as to realize the forward and backward flight missions of the aircraft body; The observation cabin is installed below the aircraft body and is used to achieve the identification task.

2. The unmanned aerial vehicle for intelligent identification of polar ice fields according to claim 1, characterized in that: The solar cell group is installed right above the aircraft body.

3. The unmanned aerial vehicle for intelligent identification of polar ice fields according to claim 1, characterized in that: The aircraft body includes: a delta-wing airship and a lighting warning light; wherein: The delta-wing airship uses carbon fiber as a skeleton structure, the exterior of the skeleton structure is covered with a skin, and the interior of the skeleton structure is filled with helium. By controlling the filling and discharge of the nitrogen, auxiliary control of the ascent and descent of the aircraft body is achieved; The lighting warning lights are symmetrically mounted on the leading edges of the two wings of the delta-wing airship and are connected to the solar cell group for power supply, and are used to provide lighting assistance for the observation cabin detection; The rudder wings are symmetrically mounted on the trailing edges of the two wings of the delta-wing airship.

4. The unmanned aerial vehicle for intelligent identification of polar ice fields according to claim 1, characterized in that: The observation cabin includes any one or more of the following: - The observation cabin is generally in the shape of a triangle that is narrow in the front and wide in the back; -The observation cabin is installed at the center directly below the main body of the aircraft; - A windshield wiper is provided at the rear of the observation cabin.

5. The unmanned aerial vehicle for intelligent identification of polar ice fields according to claim 1 or 4, characterized in that: The observation cabin is provided with a sea ice identification module, a positioning module, a data transmission module and a status monitoring module; wherein: The sea ice identification module is used to obtain on-site sea ice data and flight parameter data of the aircraft body, and feed back to the positioning module; The positioning module is used to obtain the navigation parameter data of the transport ship in real time, obtain the aircraft motion control parameters between the aircraft body and the transport ship according to the navigation parameter data and the data fed back by the sea ice identification module, obtain the motion mode of the aircraft and the transport ship and feed it back to the state monitoring module for flight control; The data transmission module is used to realize data communication within the UAV and between the UAV and the transport ship; The status monitoring module is used to monitor in real time the flight parameter data of the aircraft body during flight and the operating parameter data inside and outside the aircraft body, and: control the axial rotation direction of the propeller and / or the rotation angle of the rudder according to the movement mode of the aircraft and the transport ship fed back by the positioning module; and monitor the operating status of the aircraft body in real time based on the operating parameter data obtained through monitoring.

6. The unmanned aerial vehicle for intelligent identification of polar ice fields according to claim 5, characterized in that: The sea ice identification module obtains on-site sea ice data and flight parameter data of the aircraft body, including: Collect on-site pictures in real time through the set high-definition camera; Using a perspective transformation method, converting the scene image into a standard top view; Gray-scaling and denoising the standard bird's-eye view to obtain a channel sea ice image; The sea ice image of the channel is segmented by using a threshold method, wherein black is used to represent sea water and white is used to represent sea ice, and a binary result image for distinguishing sea water from sea ice is obtained; Obtaining the internal and external parameters of the high-definition camera, matching the pixel points of the on-site picture, calculating the parallax, and calculating the flight altitude of the aircraft body, the distance between the aircraft body and the transport ship and / or the sea ice, and the size of the sea ice based on the binocular ranging principle, including: The internal parameter K of the high-definition camera is obtained by camera calibration. In the geodetic coordinate system O-XYZ, the external parameters of the two high-definition cameras are C 10 and C 20 Indicates that C 10 and C 20 The rotation matrix R and the translation vector t are expressed as: Transformation matrix C from the first HD camera to the second HD camera 21 Then: Among them, C 01 C 10 The inverse of P h is a point on the sea ice image collected by a high-definition camera that satisfies n h P h The normal vector of the plane where the point is located under the high-definition camera, d is P h The distance between the plane where the point is located and the HD camera, is the projection of the point to the normal vector; for the first high-definition camera, there is a point P on the plane h1 satisfy: P h1 and P h2 P h Coordinates in the coordinate systems of the first and second high-definition cameras, n h1 P h1 The normal vector of the plane where the point is located under the high-definition camera; according to the projection relationship, Z C1 and Z C2 They are obtained by the external parameters of the first high-definition camera and the second high-definition camera respectively, K1 and K2 are the internal parameters of the first high-definition camera and the second high-definition camera respectively, and p1 is P h1 The corresponding pixel points on the collected sea ice image; according to the coordinate transformation, there are: P h2 =R 21 P h1 +t 21 (4) Where p2 is P h2 The corresponding pixel points on the collected sea ice image, is a homography matrix, from which the distance data between the aircraft body and the transport ship and / or the sea ice are calculated; Using the flight altitude of the aircraft body and the distance between the aircraft body and the transport ship and / or the sea ice updated in real time as the flight parameter data of the aircraft body; A sea ice database is constructed using the real-time updated binary result map and the sea ice size. The ice field is classified and the size is calculated based on the sea ice database. The category, size, distribution and density of the sea ice are statistically analyzed to obtain on-site sea ice data.

7. The unmanned aerial vehicle for intelligent identification of polar ice fields according to claim 5, characterized in that: The positioning module acquires the navigation parameter data of the aircraft and the transport ship in real time, acquires the aircraft motion control parameters between the aircraft body and the transport ship according to the navigation parameter data and the data obtained by the sea ice recognition module, and obtains the motion mode of the aircraft and the transport ship, including: Real-time acquisition of aircraft and transport ship navigation parameter data, including: transport ship's speed and trajectory; The flight parameter data and sea ice data are obtained by the sea ice identification module, and the navigation hazard index k in the rectangular ice field with the transport ship as the center and extending m times the ship length and n times the ship width is calculated: Among them, A total Represents the total area of ​​the rectangular ice rink, A ice berg A represents the area occupied by icebergs in this region. ice ridge A represents the area occupied by the ice ridge in this region. level ice Indicates the area occupied by the ice layer in this region, A rubble ice A represents the area occupied by floating ice in the region. open water A represents the area of ​​open water in the region. extra represents the area occupied by other regions; α, β, γ, λ, μ, τ are the risk coefficients corresponding to each ice condition and satisfy: According to the displacement and speed of the transport ship in the previous period a, the travel trajectory s a , predict the trajectory s of the transport ship in the next time period b in the geodetic coordinate system b : s b =us a +s e (8) Among them, s a =[s xa s ya v xa v ya ], where the first two terms are driving displacement and the last two terms are driving speed. is the transfer matrix, s b =[s xb s yb v xb v yb ],s e =[s xe s ye v xe v ye ] is the additional movement of the transport ship caused by avoiding icebergs and ice ridges estimated based on the sea ice binary result map; Actual moving position of the transport ship c and predicted trajectory s b The error E is: RMSE(E i ) is the predicted trajectory s of the transport ship b The actual motion position s c The mean square error between ||E i || represents the error E i Take the determinant; The error E represents the degree of coincidence between the actual navigation route and the predicted route; The distance between the aircraft body and the transport ship, the transport ship navigation hazard index, and the overlap between the actual navigation route and the predicted route in the flight parameter data are used as the aircraft motion control parameters to obtain the aircraft and transport ship motion modes, and the aircraft is controlled as follows: According to the ice resistance level of the transport ship, the maximum safe distance between the transport ship and the aircraft is set to s. safe and through Control the aircraft to achieve case 1 motion mode full speed to the transport ship to ensure safe navigation, case 2 motion mode to move away from the transport ship to shoot and identify distant sea ice data, or case 3 motion mode to move close to the transport ship to shoot and identify sea ice data near the channel, where ω, η, ξ are constants, and their sizes are determined by the ice resistance level of the transport ship, then:

8. The unmanned aerial vehicle for intelligent identification of polar ice fields according to claim 7, characterized in that: The state monitoring module controls the rotation direction of the propeller and / or the rotation angle of the rudder according to the motion mode of the aircraft and the transport ship fed back by the positioning module, including: Based on the control algorithm of the motion control equation and the motion mode of the aircraft and the transport ship, the rotation direction of the propeller around the axis and / or the rotation angle of the rudder wing are controlled as follows: It is defined that when the aircraft is moving forward, the propeller is turned forward and recorded as 1, when the aircraft is moving backward, the propeller is turned backward and recorded as -1, and when it stops turning, it is 0; when the aircraft is climbing, the rotation direction of the two rudders is positive and recorded as 1, when the aircraft is diving, the rotation direction of the two rudders is negative and recorded as -1, and reset is 0; through the principle of binocular ranging of high-definition cameras, it is judged that the aircraft and the transport ship are sailing in the same direction as 1 or in the opposite direction as -1, and other states are recorded as 0; the state of the propeller and the aircraft is controlled by STATE = [propeller 1 propeller 2 rudder 1 rudder 2 heading]; When the distance between the transport ship and the aircraft is greater than the maximum safe distance s safe , CONTROL<0, start case1 motion mode: if STATE[0 0 0 0 1] T ≠-1, then STATE[1 1 0 0 0] T = 0 and STATE[0 0 1 1 0] T =0, the aircraft turns around through propellers and rudders; if STATE[0 0 0 0 1] T = -1, then STATE = [1 1 0 0 -1], the aircraft is heading towards the transport ship at full speed; When the distance between the transport ship and the aircraft is less than the maximum safe distance s safe And the navigation hazard index k and the mean square error RMSE (E i ) is small, the transport ship moves according to the predicted trajectory, CONTROL>1, and case2 motion mode is started: If STATE[0 0 1 1 0] T =-1, then The aircraft moves forward and turns through the rudder; if STATE[0 0 0 0 1] T ≠-1, then STATE = [1 1 1 1 x], the aircraft moves forward and climbs, thereby identifying a wider ice field; When the distance between the transport ship and the aircraft is less than the maximum safe distance s safe And the navigation hazard index k and the mean square error RMSE (E i ) is large, the transport ship deviates from the predicted trajectory and starts the case 3 motion mode: if STATE[0 0 1 10] T = -1, then STATE = [1 1 -1 -1 x], the aircraft drives towards the transport ship and descends; if STATE [0 0 0 0 1] T ≠-1, then STATE=[-1 -1 -1 -1 x], the aircraft moves backward and descends; in both cases, the aircraft moves close to the transport ship, thereby identifying the transport ship and the ice field around the channel.

9. A method for intelligently identifying polar ice fields for an unmanned aerial vehicle according to any one of claims 1 to 8, characterized in that: include: Use unmanned aerial vehicles to collect on-site images in real time; Using a perspective transformation method, converting the scene image into a standard top view; Gray-scaling and denoising the standard bird's-eye view to obtain a channel sea ice image; The sea ice image of the channel is segmented by using a threshold method, wherein black is used to represent sea water and white is used to represent sea ice, and a binary result image for distinguishing sea water from sea ice is obtained; Obtain the internal and external parameters of the high-definition camera, match the pixel points of the on-site picture, calculate the parallax, and calculate the size of the sea ice based on the binocular ranging principle; A sea ice database is constructed using the real-time updated binary result map and the sea ice size. The ice field is classified and the size is calculated based on the sea ice database. The category, size, distribution and density of the sea ice are counted to obtain on-site sea ice data, thereby completing the intelligent identification of polar ice fields.

10. The method for intelligently identifying polar ice fields of unmanned aerial vehicles according to claim 9, characterized in that: Also includes: Based on the binocular ranging principle, the flight altitude of the UAV and the distance between the UAV and the transport ship are calculated in real time as flight parameter data; Calculate the relative motion displacement and speed between the unmanned aerial vehicle and the transport ship according to the flight parameter data; According to the relative motion displacement and speed, the rotation angle of the rudder of the unmanned aerial vehicle and / or the rotation direction of the propeller around the axis are controlled to maintain a safe communication distance with the transport ship; The acquired on-site sea ice data will be fed back to the transport ship in real time.

Images