Marine litter recycling method, unmanned boat, unmanned aerial vehicle and system

Abstract

The present invention belongs to the technical field of environmental protection, and discloses a method for recycling marine garbage, an unmanned boat, an unmanned aerial vehicle and a system. The method includes: after receiving the target fusion information of the unmanned aerial vehicle, determining the sea area information of the unmanned boat and the sea area information of the garbage to be recycled according to the target fusion information; establishing an unmanned boat model according to the sea area information of the unmanned boat to generate an unmanned boat motion model; establishing a model of the garbage to be recycled according to the sea area information of the garbage to generate a garbage motion model; performing path planning according to the unmanned boat motion model and the garbage motion model to generate a target recovery path; and tracking and recovering the garbage to be recycled according to the target recovery path. Through the above method, based on the unmanned boat motion model and the garbage motion model, precise tracking of the garbage to be recycled is realized, and the recycling work of the garbage to be recycled is realized based on the target recovery path, which improves the safety during garbage recycling, and at the same time has a wide application range, high efficiency, and saves labor costs.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental protection, and particularly relates to a method for recycling marine garbage, an unmanned boat, an unmanned aerial vehicle and a system. Background Art

[0002] With the continuous deepening of the exploitation of marine energy, marine oil accidents occur frequently, such as the capsizing of drilling platforms, the bursting of oil pipelines, the wreck of oil tankers, etc., which have caused serious damage and threats to China's economic development, personnel safety and marine ecology. Timely and effective accident handling measures are urgently needed to reduce losses. A large amount of wreckage of ships and oil well platform equipment will be generated in oil accidents caused by ship collisions and oil well platform explosions. In addition, the currently commonly used methods for handling marine oil accidents mainly involve deploying oil-absorbing materials (oil-absorbing felts / cotton, oil-absorbing barrels, etc.) and biochemical agents for decomposing oil stains. After the oil-absorbing materials complete the adsorption of oil stains, a large amount of oil-absorbing materials need to be recycled in a timely manner.

[0003] Currently, for the recycling of mobile wastes such as ship wreckage, oil well platform wreckage and oil-absorbing materials used for oil stain treatment in oil accidents, it mainly relies on manned ships for manual search and salvage recycling. However, this method has the disadvantages of high risk of casualties, low efficiency and high cost. First of all, operating in the oil stain area, direct contact, volatilization and inhalation will all endanger human health. There may be secondary explosions or fires in the handling of oil accidents, posing a great risk of casualties. In addition, under the complex interference of sea waves, currents and winds, ship wreckage, oil well platform wreckage and oil-absorbing materials will be affected by sea waves and keep moving, greatly increasing the search difficulty. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method for recycling marine garbage, an unmanned boat, an unmanned aerial vehicle and a system, aiming to solve the technical problem that the prior art cannot achieve efficient and low-cost salvage and recycling of marine garbage.

[0005] To achieve the above object, the present invention provides a method for recycling marine garbage. The method for recycling marine garbage is applied to an unmanned boat, and the method for recycling marine garbage includes:

[0006] After receiving the target fusion information of the unmanned aerial vehicle, determining the unmanned boat sea area information of the unmanned boat and the garbage sea area information of the garbage to be recycled according to the target fusion information;

[0007] Establishing an unmanned boat model according to the unmanned boat sea area information to generate an unmanned boat motion model;

[0008] Establishing a garbage model to be recycled according to the garbage sea area information to generate a garbage motion model;

[0009] Perform path planning based on the unmanned boat motion model and the garbage motion model to generate a target recovery path;

[0010] Track and recover the garbage to be recycled according to the target recovery path.

[0011] Optionally, the establishment of the unmanned boat model according to the unmanned boat sea area information to generate the unmanned boat motion model includes:

[0012] When the unmanned boat sea area information is clean sea area information, establish a model according to the clean sea area information and the preset second-order dynamic model to generate the first unmanned boat motion model;

[0013] When the unmanned boat sea area information is polluted sea area information, establish a model according to the polluted sea area information and the preset fractional-order dynamic model to generate the second unmanned boat motion model.

[0014] Optionally, the establishment of the garbage model to be recycled according to the garbage sea area information to generate the garbage motion model includes:

[0015] When the garbage sea area information is clean sea area information, establish a model according to the clean sea area information and the preset first-order neural network to generate the first garbage motion model;

[0016] When the garbage sea area information is polluted sea area information, establish a model according to the polluted sea area information and the preset fractional-order neural network to generate the second garbage motion model.

[0017] In addition, to achieve the above object, the present invention also proposes a method for recovering marine garbage, and the method for recovering marine garbage is applied to a first unmanned aerial vehicle. The method for recovering marine garbage includes:

[0018] Collect the garbage image of the garbage to be recycled;

[0019] Locate the position of the garbage to be recycled according to the garbage image to determine the garbage position of the garbage to be recycled;

[0020] Determine the garbage sea area information of the garbage to be recycled according to the garbage position and the garbage image, and send the garbage sea area information to a second unmanned aerial vehicle.

[0021] Perform edge detection on the garbage image to determine the pollution edge line in the garbage image;

[0022] Determine the polluted sea area position according to the pollution edge line;

[0023] Determine the garbage sea area information of the garbage to be recycled according to the polluted sea area position and the garbage position.

[0024] Detect whether the information of the garbage sea area has changed;

[0025] When the information of the garbage sea area changes, send the changed information of the garbage sea area to the second unmanned aerial vehicle.

[0026] In addition, to achieve the above object, the present invention also provides a method for recycling marine garbage, which is applied to a second unmanned aerial vehicle. The method for recycling marine garbage includes:

[0027] Collect the image of the unmanned boat and obtain the information of the garbage sea area sent by the first unmanned aerial vehicle;

[0028] Locate the position of the unmanned boat according to the image of the unmanned boat to determine the position of the unmanned boat;

[0029] Determine the sea area information of the unmanned boat according to the position of the unmanned boat and the image of the unmanned boat;

[0030] Determine the target fusion information according to the information of the garbage sea area and the sea area information of the unmanned boat, and send the target fusion information to the unmanned boat.

[0031] Perform edge detection on the image of the unmanned boat to determine the pollution edge line in the image of the unmanned boat;

[0032] Determine the position of the polluted sea area according to the pollution edge line;

[0033] Determine the sea area information of the unmanned boat according to the position of the polluted sea area and the position of the unmanned boat.

[0034] Detect whether the target fusion information has changed;

[0035] When the target fusion information changes, send the changed target fusion information to the unmanned boat.

[0036] In addition, to achieve the above object, the present invention also provides an unmanned boat, which includes: a memory, a processor, and a marine garbage recycling program stored on the memory and executable on the processor. The marine garbage recycling program is configured to implement the marine garbage recycling method as described above.

[0037] In addition, to achieve the above object, the present invention also provides an unmanned aerial vehicle, which includes: a memory, a processor, and a marine garbage recycling program stored on the memory and executable on the processor. The marine garbage recycling program is configured to implement the marine garbage recycling method as described above.

[0038] In addition, to achieve the above object, the present invention further provides an ocean recovery system, which includes an unmanned boat and a number of unmanned aerial vehicles.

[0039] After receiving the target fusion information of the unmanned aerial vehicle, the present invention determines the sea area information of the unmanned boat and the sea area information of the garbage to be recycled according to the target fusion information; establishes an unmanned boat model according to the sea area information of the unmanned boat to generate an unmanned boat motion model; establishes a garbage model to be recycled according to the sea area information of the garbage to generate a garbage motion model; performs path planning according to the unmanned boat motion model and the garbage motion model to generate a target recovery path; and tracks and recycles the garbage to be recycled according to the target recovery path. In the above manner, based on the target fusion information sent by the unmanned aerial vehicle, the sea area information of the unmanned boat and the sea area information of the garbage are determined. The unmanned boat generates an unmanned boat motion model and a garbage motion model according to the sea area information of the unmanned boat and the sea area information of the garbage, realizes precise tracking of the garbage to be recycled, and performs path planning based on the unmanned boat motion model and the garbage motion model to generate a target recovery path, thereby realizing the recycling work of the garbage to be recycled, improving the safety when recycling the garbage to be recycled on the ocean, having a wide application range and high efficiency, and saving the labor salvage cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a schematic structural diagram of an ocean garbage recovery device in the hardware operating environment related to the embodiment solution of the present invention;

[0041] Figure 2 is a schematic flowchart of the first embodiment of the ocean garbage recovery method of the present invention;

[0042] Figure 3 is a schematic flowchart of the working process of the unmanned boat in an embodiment of the ocean garbage recovery method of the present invention;

[0043] Figure 4 is a schematic flowchart of the second embodiment of the ocean garbage recovery method of the present invention;

[0044] Figure 5 is a schematic flowchart of the third embodiment of the ocean garbage recovery method of the present invention;

[0045] Figure 6 is a schematic diagram of the physical object in an embodiment of the ocean garbage recovery method of the present invention;

[0046] Figure 7 is a schematic overall flowchart of an embodiment of the ocean garbage recovery method of the present invention;

[0047] Figure 8 is a structural block diagram of the first embodiment of the ocean garbage recovery system of the present invention.

[0048] The implementation, functional features, and advantages of the objectives of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] Refer to Figure 1 , Figure 1 which is a schematic structural diagram of a marine garbage recycling device for the hardware operating environment involved in the embodiment solution of the present invention.

[0051] As Figure 1 shown, the marine garbage recycling device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless-fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0052] Those skilled in the art can understand that Figure 1 the structure shown in

[0053] As Figure 1 shown, the memory 1005, as a storage medium, may include an operating system, a network communication module, a user interface module, and a marine garbage recycling program.

[0054] In Figure 1In the shown marine litter collection device, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the marine litter collection device of the present invention can be arranged in the marine litter collection device. The marine litter collection device calls the marine litter collection program stored in the memory 1005 through the processor 1001 and executes the marine litter collection method provided by the embodiments of the present invention.

[0055] Embodiments of the present invention provide a marine litter collection method. Refer to Figure 2 , Figure 2 which is a schematic flowchart of the first embodiment of a marine litter collection method of the present invention.

[0056] The marine litter collection method is applied to an unmanned boat. The marine litter collection method includes the following steps:

[0057] Step S10: After receiving the target fusion information of the unmanned aerial vehicle, determine the sea area information of the unmanned boat and the sea area information of the litter to be collected according to the target fusion information.

[0058] It should be noted that the execution subject of this embodiment is the unmanned boat in the marine litter collection system. The marine litter collection system includes an unmanned boat and several unmanned aerial vehicles. The several unmanned aerial vehicles include a first unmanned aerial vehicle and a second unmanned aerial vehicle. Information interaction can be carried out between the unmanned boat and the second unmanned aerial vehicle, and information interaction can be carried out between the first unmanned aerial vehicle and the second unmanned aerial vehicle. The first unmanned aerial vehicle detects and tracks the litter to be collected on the sea area to be managed, and the second unmanned aerial vehicle detects and tracks the unmanned boat on the sea area to be managed, and generates target fusion information based on the sea area information of the litter of the first unmanned aerial vehicle and the sea area information of the unmanned boat of the second unmanned aerial vehicle, and transmits the target fusion information to the unmanned boat. After receiving the target fusion information of the unmanned aerial vehicle, the unmanned boat determines the sea area information of the unmanned boat and the sea area information of the litter to be collected according to the target fusion information, establishes an unmanned boat model according to the sea area information of the unmanned boat to generate an unmanned boat motion model, establishes a litter model to be collected according to the sea area information of the litter to generate a litter motion model, conducts path planning according to the unmanned boat operation model and the litter motion model to generate a target recovery path, and tracks and recovers the litter to be collected according to the target recovery path.

[0059] It can be understood that the target fusion information includes the sea area information where the garbage to be recycled is located, the position information of the garbage to be recycled, the sea area information where the unmanned boat is located, and the position information of the unmanned boat. The sea area information of the unmanned boat includes, but is not limited to, the sea area information where the unmanned boat is located and the position information of the unmanned boat. The garbage sea area information includes, but is not limited to, the sea area information where the garbage to be recycled is located and the position information of the garbage to be recycled. The garbage to be recycled is the marine mobile waste existing on the sea to be managed, and the unmanned boat needs to salvage and recycle the garbage to be recycled.

[0060] In a specific implementation, the second unmanned aircraft in the unmanned aerial vehicle sends the target fusion information to the unmanned boat, and the unmanned boat distinguishes various types of information according to the identification code in the target fusion information, so as to obtain the sea area information of the unmanned boat and the garbage sea area information of the garbage to be recycled.

[0061] Step S20: Establish an unmanned boat model according to the sea area information of the unmanned boat, and generate an unmanned boat motion model.

[0062] It should be noted that the unmanned boat motion model refers to the model obtained by the unmanned boat's own dynamic modeling.

[0063] It can be understood that after the unmanned boat obtains the sea area information of the unmanned boat, it makes an event judgment according to the sea area information of the unmanned boat to determine whether the unmanned boat is currently in the polluted sea area of the sea to be managed, and determines the corresponding method for dynamic modeling according to the judgment result, so as to obtain the unmanned boat motion model.

[0064] In a specific implementation, in order to establish an accurate unmanned boat motion model based on the sea area information of the unmanned boat, further, the establishing an unmanned boat model according to the sea area information of the unmanned boat and generating an unmanned boat motion model includes: when the sea area information of the unmanned boat is clean sea area information, establishing a model according to the clean sea area information and a preset second-order dynamic model to generate a first unmanned boat motion model; when the sea area information of the unmanned boat is polluted sea area information, establishing a model according to the polluted sea area information and a preset fractional-order dynamic model to generate a second unmanned boat motion model.

[0065] It should be noted that when the sea area information of the unmanned boat is clean sea area information, it means that the unmanned boat is currently in the unpolluted sea area of the sea to be managed. The preset second-order dynamic model is an ordinary second-order dynamic model. At this time, based on the clean sea area information, the unmanned boat itself is modeled using the preset second-order dynamic model to generate a model after preset second-order dynamic modeling, and the model generated by the preset second-order dynamic modeling is the first unmanned boat motion model.

[0066] It can be understood that when the unmanned boat sea area information is polluted sea area information, it means that the unmanned boat is currently in the polluted sea area of the sea area to be managed. The preset fractional-order kinetic model is the ordinary fractional-order kinetic model. At this time, based on the polluted sea area information, the unmanned boat itself uses the preset fractional-order kinetic model to establish a model, generating a model after preset fractional-order kinetic modeling. The model generated by the preset fractional-order kinetic modeling is the second unmanned boat motion model.

[0067] Step S30: Establish a model of the garbage to be recycled according to the garbage sea area information, generating a garbage motion model.

[0068] It should be noted that the garbage motion model refers to the model obtained by the unmanned boat performing kinetic modeling on the garbage to be recycled.

[0069] It can be understood that after the unmanned boat obtains the garbage sea area information, it makes an event judgment according to the garbage sea area information to determine whether the garbage to be recycled is currently in the polluted sea area of the sea area to be managed, and determines the corresponding method for kinetic modeling according to the judgment result, so as to obtain the garbage motion model.

[0070] In a specific implementation, in order to establish an accurate garbage motion model based on the garbage sea area information, further, the establishing a model of the garbage to be recycled according to the garbage sea area information and generating a garbage motion model includes: when the garbage sea area information is clean sea area information, establishing a model according to the clean sea area information and a preset first-order neural network, generating a first garbage motion model; when the garbage sea area information is polluted sea area information, establishing a model according to the polluted sea area information and a preset fractional-order neural network, generating a second garbage motion model.

[0071] It should be noted that when the garbage sea area information is clean sea area information, it means that the garbage to be recycled is currently in the unpolluted sea area of the sea area to be managed. The preset first-order neural network is the ordinary first-order neural network. At this time, based on the clean sea area information, the garbage to be recycled uses the preset first-order neural network to establish a model, and the generated model is the first garbage motion model.

[0072] It can be understood that when the garbage sea area information is polluted sea area information, it means that the garbage to be recycled is currently in the polluted sea area of the sea area to be managed. The preset fractional-order neural network is the ordinary fractional-order neural network. At this time, based on the polluted sea area information, the garbage to be recycled uses the preset fractional-order neural network to establish a model, and the generated model is the second garbage motion model.

[0073] Step S40: Perform path planning according to the unmanned boat motion model and the garbage motion model, generating a target recovery path.

[0074] It should be noted that after obtaining the unmanned boat motion model of the unmanned boat and the garbage motion model of the garbage to be recycled, the unmanned boat inputs the model information of the garbage motion model of the garbage to be recycled into the unmanned boat path planning module for path planning, so as to obtain the path for the unmanned boat to track, salvage and recycle the garbage to be recycled. The unmanned boat path planning module is a path planning model established based on the unmanned boat motion model.

[0075] Step S50: Track and recycle the garbage to be recycled according to the target recovery path.

[0076] It should be noted that after the path planning module in the unmanned boat generates the target recovery path, it generates a path control command based on the target recovery path. The unmanned boat drives the unmanned boat according to the double-loop PID and the path control command, so as to realize the tracking and recovery of the garbage to be recycled.

[0077] It can be understood that as Figure 3 shown, after the unmanned boat receives the target fusion information transmitted by the second unmanned aerial vehicle, it determines the unmanned boat sea area information and the garbage sea area information according to the target fusion information, and makes an event judgment based on the unmanned boat sea area information and the garbage sea area information. When the sea area information where the unmanned boat is located changes, it determines whether the sea area where the unmanned boat is located is a clean sea area. When the sea area where the unmanned boat is located is a clean sea area, it establishes an integer-order motion control model for itself. When the sea area where the unmanned boat is located is not a clean sea area, it establishes a fractional-order motion control model for itself, and further judges whether the sea area where the garbage to be recycled is located is a clean sea area. When the sea area where the garbage to be recycled is located is a clean sea area, it conducts ordinary neural network modeling on the garbage to be recycled. When the sea area where the garbage to be recycled is located is not a clean sea area, it conducts fractional-order neural network modeling on the garbage to be recycled. After the model is established, it generates the target recovery path and executes the motion control. When the sea area information where the unmanned boat is located does not change, it directly enters the step of judging whether the sea area where the garbage to be recycled is located is a clean sea area.

[0078] In this embodiment, after receiving the target fusion information of the unmanned aerial vehicle (UAV), the unmanned boat sea area information of the unmanned boat and the garbage sea area information of the garbage to be recycled are determined according to the target fusion information; an unmanned boat model is established according to the unmanned boat sea area information to generate an unmanned boat motion model; a garbage model to be recycled is established according to the garbage sea area information to generate a garbage motion model; path planning is performed according to the unmanned boat motion model and the garbage motion model to generate a target recovery path; and the garbage to be recycled is tracked and recovered according to the target recovery path. By the above method, the unmanned boat sea area information and the garbage sea area information are determined based on the target fusion information sent by the UAV. The unmanned boat generates an unmanned boat motion model and a garbage motion model according to the unmanned boat sea area information and the garbage sea area information, so as to achieve precise tracking of the garbage to be recycled. And path planning is performed based on the unmanned boat motion model and the garbage motion model to generate a target recovery path, thereby realizing the recovery work of the garbage to be recycled, improving the safety during the recovery of the garbage to be recycled on the ocean, having a wide application range and high efficiency, and saving the labor salvage cost.

[0079] Reference Figure 4 , Figure 4 is a schematic flowchart of the second embodiment of a method for recycling marine garbage according to the present invention.

[0080] Based on the above first embodiment, the method for recycling marine garbage in this embodiment is applied to a first UAV. The method for recycling marine garbage includes:

[0081] Step S01: Collect garbage images of the garbage to be recycled.

[0082] It should be noted that the execution subject of this embodiment is the first UAV in the marine garbage recovery system. The marine garbage recovery system includes an unmanned boat and several UAVs. The several UAVs include a first UAV and a second UAV. Information interaction can be carried out between the unmanned boat and the second UAV, and information interaction can be carried out between the first UAV and the second UAV. A normal camera and a wide-area camera are mounted on the first UAV. The normal camera is used for precise tracking of the garbage to be recycled, and the wide-area camera is used for edge detection of the polluted sea area on the managed ocean. The first UAV collects the garbage images of the garbage to be recycled in real time, locates the position of the garbage to be recycled according to the garbage images, determines the garbage sea area information of the garbage to be recycled according to the garbage position and the garbage images, and sends the garbage sea area information to the second UAV.

[0083] It can be understood that the normal camera and the wide-area camera on the first UAV collect the moving tracking images of the garbage to be recycled and the boundary position images of the polluted sea area in real time. The moving tracking images of the garbage to be recycled and the boundary position images of the polluted sea area are the garbage images.

[0084] Step S02: Locate the position of the recyclable waste according to the waste image to determine the waste position of the recyclable waste.

[0085] It should be noted that the first drone performs target detection on the recyclable waste based on the moving tracking image and YOLO algorithm of the recyclable waste in the waste image to determine the recyclable waste. After locking the recyclable waste, the deepsort algorithm is used to track the position of the recyclable waste, so as to determine the current geographical location information of the recyclable waste. The current geographical location information of the recyclable waste is the waste position of the recyclable waste.

[0086] Step S03: Determine the waste sea area information of the recyclable waste according to the waste position and the waste image, and send the waste sea area information to the second drone.

[0087] It should be noted that the first drone performs edge detection on the sea area to be managed according to the boundary position image of the polluted sea area in the waste image and the watershed algorithm, so as to identify the polluted sea area and the clean sea area of the sea area to be managed.

[0088] It can be understood that after the first drone marks the polluted sea area and the clean sea area, based on the waste position of the recyclable waste, the sea area information where the recyclable waste is located is determined. The sea area information where it is located refers to the information on whether the sea area is a clean sea area. According to the sea area information where the recyclable waste is located and the position information of the recyclable waste, the waste sea area information can be obtained. The position information refers to the waste position of the recyclable waste.

[0089] In a specific implementation, in order to obtain accurate waste sea area information, further, the determining the waste sea area information of the recyclable waste according to the waste position and the waste image includes: performing edge detection on the waste image to determine the polluted edge line in the waste image; determining the polluted sea area position according to the polluted edge line; and determining the waste sea area information of the recyclable waste according to the polluted sea area position and the waste position.

[0090] It should be noted that the first drone performs edge detection on the boundary position image of the polluted sea area in the waste image using the watershed algorithm, so as to determine the polluted edge line in the boundary position image of the polluted sea area. Based on the polluted edge line, the sea area of the boundary position image of the polluted sea area is divided, so as to determine the polluted sea area and the clean sea area, and further obtain the polluted sea area position of the polluted sea area. According to the polluted sea area position and the waste position, the sea area information where the recyclable waste is located is determined, that is, whether the recyclable waste is in a clean sea area. According to the sea area information where the recyclable waste is located and the position information of the recyclable waste, the waste sea area information can be obtained.

[0091] It can be understood that, in order to ensure the accuracy of subsequent tracking and recovery of the unmanned boat, further, after determining the garbage sea area information of the garbage to be recovered according to the garbage position and the garbage image and sending the garbage sea area information to the second unmanned aerial vehicle, it further includes: detecting whether the garbage sea area information changes; when the garbage sea area information changes, sending the changed garbage sea area information to the second unmanned aerial vehicle.

[0092] In a specific implementation, detecting whether the garbage sea area information changes refers to detecting whether the sea area information where the garbage to be recovered is located changes. When the sea area where the garbage to be recovered is located changes from a clean sea area to a polluted sea area or when the sea area where the garbage to be recovered is located changes from a polluted sea area to a clean sea area, it indicates that the garbage sea area information has changed. At this time, the first unmanned aerial vehicle immediately sends the changed garbage sea area information to the second unmanned aerial vehicle. When the garbage sea area information does not change, there is no need to send the garbage sea area information to the second unmanned aerial vehicle again.

[0093] In this embodiment, by collecting the garbage image of the garbage to be recovered; positioning the position of the garbage to be recovered according to the garbage image to determine the garbage position of the garbage to be recovered; determining the garbage sea area information of the garbage to be recovered according to the garbage position and the garbage image, and sending the garbage sea area information to the second unmanned aerial vehicle. By determining the garbage sea area information of the garbage to be recovered through the first unmanned aerial vehicle, accurate locking and tracking of the garbage to be recovered are realized.

[0094] Consider Figure 5 , Figure 5 is a schematic flowchart of the third embodiment of a method for recovering marine garbage according to the present invention.

[0095] Based on the above third embodiment, the method for recovering marine garbage in this embodiment is applied to the second unmanned aerial vehicle, and the method for recovering marine garbage includes:

[0096] Step S04: Collect the image of the unmanned boat and obtain the garbage sea area information sent by the first unmanned aerial vehicle.

[0097] It should be noted that the execution subject of this embodiment is the second unmanned aerial vehicle (UAV) in the marine garbage recycling system. The marine garbage recycling system includes an unmanned boat and several UAVs. The several UAVs include a first UAV and a second UAV. Information interaction can be carried out between the unmanned boat and the second UAV, and information interaction can be carried out between the first UAV and the second UAV. A general camera and a wide-area camera are carried on the second UAV. The general camera is used to accurately track the unmanned boat, and the wide-area camera is used for edge detection of the polluted sea area on the sea to be managed. The second UAV collects the image of the unmanned boat in real time, obtains the garbage sea area information sent by the first UAV, locates the position of the unmanned boat according to the image of the unmanned boat to determine the position of the unmanned boat, determines the sea area information of the unmanned boat according to the position of the unmanned boat and the image of the unmanned boat, determines the target fusion information according to the sea area information of the unmanned boat and the garbage sea area information, and sends the target fusion information to the unmanned boat.

[0098] It can be understood that the general camera and the wide-area camera on the second UAV collect the moving tracking image of the unmanned boat and the boundary position image of the polluted sea area in real time. The moving tracking image of the unmanned boat and the boundary position image of the polluted sea area are the images of the unmanned boat.

[0099] Step S05: Locate the position of the unmanned boat according to the image of the unmanned boat to determine the position of the unmanned boat.

[0100] It should be noted that the second UAV performs target detection on the unmanned boat according to the moving tracking image of the unmanned boat in the image of the unmanned boat and the YOLO algorithm to determine the unmanned boat. After locking the unmanned boat, the deepsort algorithm is used to track the position of the unmanned boat, so as to determine the current geographical location information of the unmanned boat. The current geographical location information of the unmanned boat is the position of the unmanned boat.

[0101] Step S06: Determine the sea area information of the unmanned boat according to the position of the unmanned boat and the image of the unmanned boat.

[0102] It should be noted that the second UAV performs edge detection on the sea to be managed according to the boundary position image of the polluted sea area in the image of the unmanned boat and the watershed algorithm, so as to identify the polluted sea area and the clean sea area of the sea to be managed.

[0103] It can be understood that after the second UAV marks the polluted sea area and the clean sea area, based on the garbage position of the garbage to be recycled, the sea area information where the garbage to be recycled is located is determined. The sea area information refers to the information on whether the sea area is a clean sea area. The sea area information of the unmanned boat can be obtained according to the sea area information where the unmanned boat is located and the position information of the unmanned boat. The position information refers to the garbage position of the unmanned boat.

[0104] In a specific implementation, in order to obtain accurate information about the unmanned boat's sea area, further, determining the unmanned boat's sea area information based on the position of the unmanned boat and the image of the unmanned boat includes: performing edge detection on the image of the unmanned boat to determine the pollution edge line in the image of the unmanned boat; determining the position of the polluted sea area according to the pollution edge line; and determining the unmanned boat's sea area information based on the position of the polluted sea area and the position of the unmanned boat.

[0105] It should be noted that the second unmanned aerial vehicle uses the watershed algorithm to perform edge detection on the boundary position image of the polluted sea area in the image of the unmanned boat, so as to determine the pollution edge line in the boundary position image of the polluted sea area. Based on the pollution edge line, the sea area of the boundary position image of the polluted sea area is divided, so as to determine the polluted sea area and the clean sea area, and further obtain the position of the polluted sea area of the polluted sea area. According to the position of the polluted sea area and the position of the unmanned boat, the sea area information where the unmanned boat is located is determined, that is, whether the unmanned boat is in a clean sea area. According to the sea area information where the unmanned boat is located and the position information of the unmanned boat, the unmanned boat's sea area information can be obtained.

[0106] Step S07: Determine target fusion information according to the garbage sea area information and the unmanned boat's sea area information, and send the target fusion information to the unmanned boat.

[0107] It should be noted that the second unmanned aerial vehicle fuses the received garbage sea area information and the unmanned boat's sea area information obtained by itself, so as to obtain target fusion information including the sea area information where the garbage to be recycled is located, the position information of the garbage to be recycled, the sea area information where the unmanned boat is located, and the position information of the unmanned boat, and sends the target fusion information to the unmanned boat.

[0108] It can be understood that, in order to ensure the accuracy of the subsequent unmanned boat in tracking and recycling, further, after determining the target fusion information according to the garbage sea area information and the unmanned boat's sea area information and sending the target fusion information to the unmanned boat, it further includes: detecting whether the target fusion information has changed; when the target fusion information has changed, sending the changed target fusion information to the unmanned boat.

[0109] In a specific implementation, detecting whether the target fusion information has changed refers to detecting whether the sea area information of any one of the sea area information of the garbage to be recycled and the sea area where the unmanned boat is located has changed. When the sea area where the garbage to be recycled enters a polluted sea area from a clean sea area or the sea area where the garbage to be recycled enters a clean sea area from a polluted sea area, it indicates that the garbage sea area information has changed. Or when the sea area where the unmanned boat is located enters a polluted sea area from a clean sea area or the sea area where the unmanned boat is located enters a clean sea area from a polluted sea area, it indicates that the unmanned boat sea area information has changed. At this time, the second UAV immediately sends the changed target fusion information to the unmanned boat. When the target fusion information has not changed, there is no need to send the target fusion information to the unmanned boat again.

[0110] It should be noted that, as Figure 6 and Figure 7 shown, both the first UAV and the second UAV in the marine garbage recovery system are equipped with an ordinary camera and a wide-area camera. The ordinary camera in the first UAV detects the position of the garbage to be recycled and tracks and locks it, and the wide-area camera detects the pollution edge line, so as to complete the scene recognition of the polluted sea area and the clean sea area of the sea area to be managed, and finally sends the garbage sea area information to the second UAV. The ordinary camera in the second UAV detects the position of the unmanned boat and tracks and locks it, and the wide-area camera detects the pollution edge line, so as to complete the scene recognition of the polluted sea area and the clean sea area of the sea area to be managed, determine the unmanned boat sea area information, and fuse the unmanned boat sea area information and the garbage sea area information to obtain the target fusion information. After the first sending of the target fusion information, the unmanned boat models the kinematics of the unmanned boat and the garbage to be recycled based on the target fusion information, and determines the target recovery path based on the modeling result. Finally, the actuator tracks and recovers based on the target recovery path. After the initial sending of the target fusion information, the first UAV triggers communication with the second UAV only when the sea area where the garbage to be recycled has changed, and sends the changed garbage sea area information to the second UAV. The second UAV triggers communication with the unmanned boat only when the sea area where the garbage to be recycled or the sea area where the unmanned boat is located has changed, and sends the changed target sea area information to the unmanned boat. The unmanned boat changes the control strategy based on the changed target sea area information, remodels the kinematics of the unmanned boat and the garbage to be recycled based on the changed target sea area information, and finally completes the tracking and recovery of the garbage to be recycled.

[0111] In this embodiment, an unmanned boat image of the unmanned boat is collected, and garbage sea area information sent by a first unmanned aerial vehicle (UAV) is obtained; the position of the unmanned boat is located based on the unmanned boat image to determine the unmanned boat position of the unmanned boat; the unmanned boat sea area information of the unmanned boat is determined according to the unmanned boat position and the unmanned boat image; target fusion information is determined according to the garbage sea area information and the unmanned boat sea area information, and the target fusion information is sent to the unmanned boat. The unmanned boat sea area information of the unmanned boat is determined by a second UAV, achieving precise locking and tracking of the unmanned boat.

[0112] In addition, referring to Figure 8 , an embodiment of the present invention further provides a marine garbage recovery system, where the marine garbage recovery system includes an unmanned boat 10 and a plurality of UAVs 20. The plurality of UAVs 20 are further divided into a first UAV and a second UAV.

[0113] In addition, it should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or system. Without more limitations, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0114] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0116] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the description and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for recovering marine litter, the method for recovering marine litter being applied to an unmanned boat, characterized in that, The marine garbage recovery method includes: After receiving the target fusion information of the drone, determining the unmanned boat sea area information of the unmanned boat and the garbage sea area information of the garbage to be recovered according to the target fusion information; Establishing an unmanned boat model according to the unmanned boat sea area information to generate an unmanned boat motion model; Establishing a garbage model to be recovered according to the garbage sea area information to generate a garbage motion model; Performing path planning according to the unmanned boat motion model and the garbage motion model to generate a target recovery path; Tracking and recovering the garbage to be recovered according to the target recovery path; Among them, the establishing an unmanned boat model according to the unmanned boat sea area information to generate an unmanned boat motion model includes: When the unmanned boat sea area information is clean sea area information, establishing a model according to the clean sea area information and a preset second-order dynamic model to generate a first unmanned boat motion model; When the unmanned boat sea area information is polluted sea area information, establishing a model according to the polluted sea area information and a preset fractional-order dynamic model to generate a second unmanned boat motion model.

2. The marine litter recycling method according to claim 1, wherein, The establishing a garbage model to be recovered according to the garbage sea area information to generate a garbage motion model includes: When the garbage sea area information is clean sea area information, establishing a model according to the clean sea area information and a preset first-order neural network to generate a first garbage motion model; When the garbage sea area information is polluted sea area information, establishing a model according to the polluted sea area information and a preset fractional-order neural network to generate a second garbage motion model.

3. A method for recovering marine garbage, the marine garbage recovery method being applied to a first unmanned aerial vehicle, characterized in that, The marine garbage recovery method includes: Collecting a garbage image of the garbage to be recovered; Locating the position of the garbage to be recovered according to the garbage image to determine the garbage position of the garbage to be recovered; Determining the garbage sea area information of the garbage to be recovered according to the garbage position and the garbage image, and sending the garbage sea area information to a second drone; Among them, the determining the garbage sea area information of the garbage to be recovered according to the garbage position and the garbage image includes: Performing edge detection on the garbage image to determine the pollution edge line in the garbage image; Determining the polluted sea area position according to the pollution edge line; Determining the garbage sea area information of the garbage to be recovered according to the polluted sea area position and the garbage position.

4. The marine garbage recovery method according to claim 3, after the determining the garbage sea area information of the garbage to be recovered according to the garbage position and the garbage image, and sending the garbage sea area information to a second drone, further includes: Detecting whether the garbage sea area information has changed; When the garbage sea area information has changed, sending the changed garbage sea area information to the second drone.

5. A method for recycling marine litter, the method for recycling marine litter being applied to a second unmanned aerial vehicle, characterized in that, The marine garbage recovery method includes: Collecting an unmanned boat image of the unmanned boat, and obtaining the garbage sea area information sent by a first drone; Locating the position of the unmanned boat according to the unmanned boat image to determine the unmanned boat position of the unmanned boat; Determining the unmanned boat sea area information of the unmanned boat according to the unmanned boat position and the unmanned boat image; Determine target fusion information based on the garbage sea area information and the unmanned boat sea area information, and send the target fusion information to the unmanned boat; Among them, the determining the unmanned boat sea area information of the unmanned boat according to the position of the unmanned boat and the image of the unmanned boat includes: Perform edge detection on the image of the unmanned boat to determine the pollution edge line in the image of the unmanned boat; Determine the position of the polluted sea area according to the pollution edge line; Determine the unmanned boat sea area information of the unmanned boat according to the position of the polluted sea area and the position of the unmanned boat.

6. The marine garbage recycling method according to claim 5, wherein After determining the target fusion information based on the garbage sea area information and the unmanned boat sea area information and sending the target fusion information to the unmanned boat, it further includes: Detect whether the target fusion information has changed; When the target fusion information changes, send the changed target fusion information to the unmanned boat.

7. An unmanned boat, characterized in that, The unmanned boat includes: a memory, a processor, and a marine garbage recovery program stored on the memory and executable on the processor, and the marine garbage recovery program is configured to implement the marine garbage recovery method described in claim 1 or 2.

8. A drone, characterized in that, The unmanned aerial vehicle includes: a memory, a processor, and a marine garbage recovery program stored on the memory and executable on the processor, and the marine garbage recovery program is configured to implement the marine garbage recovery method described in any one of claims 3 to 4 or 5 to 6.

9. A marine garbage recycling system, characterized in that, It includes an unmanned boat and several unmanned aerial vehicles.

Images