An alarm method for judging the navigation of super-high ships in bridge area

Abstract

The present invention discloses an alarm method for judging the navigation of super-high ships in bridge areas, comprising the following steps: S01, obtaining the clearance height of the bridge area and the AIS data of the ship; S02, obtaining multiple first data of scattered point distribution in the video image; S03, performing data cleaning on the obtained first data, wherein the data cleaning refers to performing function fitting on the obtained first data of scattered point distribution and forming a first fitting track, and assigning a first ID to each first fitting track; S04, performing fitting correction analysis on the AIS data based on a correction algorithm, and obtaining the ship AIS analysis track. The alarm method for judging the navigation of super-high ships in bridge areas provided by the invention identifies ships through the YOLO target detection algorithm of image deep learning, matches AIS to obtain ship information, and then uses OpenCV background modeling to filter static targets and non-navigable ship targets, thereby achieving accurate positioning and remote intervention of super-high ordinary ships.

Description

Technical Field

[0001] The invention relates to the technical field of early warning systems, and in particular to an alarm method for judging the navigation of super-high ships in a bridge area. Background Art

[0002] There are three main methods for preventing ultra-high ship collisions in bridge areas through video. One is to install a laser in a direction parallel to the bridge clearance height, and after the laser is triggered by an ultra-high ship, an alarm is triggered through video linkage; another is to capture multiple video images, manually calibrate the ship height in the image, and then measure the ship height and then alarm; the third is to calibrate and identify the ship height through video and shore-based height calibration objects, and then alarm.

[0003] The main drawbacks are:

[0004] 1. High cost, laser sensors need frequent maintenance, other solutions require multiple videos, additional calibration columns, etc.

[0005] 2. The video image capture accuracy is low or it is difficult to know the actual water surface height of the ship. The error value of manual calibration or reference calibration is large. In addition, the first method of laser detection cannot determine the actual height of the ship, and cannot provide users with decision-making support such as whether to intervene and the consequences of collision. Summary of the invention

[0006] The purpose of the present invention is to provide an alarm method for judging the navigation of super-high ships in bridge areas, accurately identify the water surface height of ships at ultra-long distances, and reduce the occurrence of ship-bridge collision accidents caused by super-high ships.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] An alarm method for judging the navigation of super-high ships in a bridge area comprises the following steps:

[0009] S01. Obtain the bridge area clearance height and the ship's AIS data;

[0010] S02, obtaining a plurality of first data distributed at scattered points in the video image;

[0011] S03, performing data cleaning on the first data obtained, wherein the data cleaning refers to performing function fitting on the first data obtained in scattered point distribution to form a first fitting track, and assigning a first ID to each of the first fitting tracks;

[0012] S04, performing fitting correction analysis on the AIS data based on a correction algorithm to obtain an AIS analysis track of the ship;

[0013] S05. Determine a second fitting track and a confidence of the second fitting track based on the ship AIS analysis track, the first fitting track and a confidence algorithm, and assign a second ID to each second fitting track, wherein the confidence is used to characterize the possibility that the second fitting track is a ship;

[0014] S06. When the confidence level is greater than a threshold, the height of the ship of the second ID is obtained, a ship shape matching is performed on the ship of the second ID based on a ship shape algorithm, and a ship track judgment is performed on the ship of the second ID based on a second fitting track and a track judgment algorithm;

[0015] S07. If the ship shape is a preset ship shape, and based on the ship track, it is judged that the ship of the second ID is going to pass through the bridge area, then the height of the ship of the second ID is compared with the passing height of the bridge area. If the height of the ship of the second ID is less than the passing height of the bridge area, an alarm message is sent to the electronic device.

[0016] Preferably, the step S01 includes:

[0017] At preset time intervals, a plurality of first height data distributed at scattered points in the video image and first position data corresponding to the first height data are acquired.

[0018] Preferably, the step S03 includes:

[0019] Based on the random forest algorithm, data cleaning is performed on the multiple first position data of scattered point distribution. The data cleaning refers to performing function fitting on the acquired first position data of scattered point distribution to form a first fitting track, and assigning a first ID function to each of the first fitting tracks.

[0020] Preferably, the AIS data of the ship is multiple and scattered, and the step S04 includes:

[0021] The AIS data is fitted and corrected based on the time series, position information and vector track information to obtain the ship AIS analysis track.

[0022] Preferably, the correction algorithm includes a gradient boosting tree algorithm;

[0023] In the step S05, after the first fitting track and the ship AIS analysis track are matched and fitted, the first fitting track matches at least one of the ship AIS analysis tracks, and a confidence level is generated between each of the first fitting tracks and one of the ship AIS analysis tracks, and the fitting result with the highest confidence level is selected to generate the second fitting track and the second ID.

[0024] Preferably, in step S06, the ship morphology algorithm includes a YOLO target detection algorithm, and the ship morphology algorithm includes:

[0025] Based on the MSAM networking, the edge value is taken to identify the height feature of the ship of the second ID, and the positioning image xy coordinate value of the ship of the second ID in the video image is obtained, and the shape of the ship of the second ID is determined according to the positioning image XY coordinate value.

[0026] Preferably, in step S06, the track determination algorithm includes an OpenCV background modeling algorithm, and the track determination algorithm includes:

[0027] The video images are dynamically framed, and multiple images after dynamic framing are compared to filter out static targets and non-navigable ship targets in the images.

[0028] Preferably, the static target includes at least one of mountains, roads, docks, and buildings;

[0029] The non-navigable ship targets include: mobile ships and movable non-ship objects, wherein the mobile ships include ships that will not pass through the bridge area according to the ship track, and the movable non-ship objects include at least one of birds and airplanes;

[0030] and / or,

[0031] In step S07, the ship type includes at least one of a container ship, a fishing boat, a passenger ship, an ore carrier or a bulk carrier.

[0032] In the above technical solution, the present invention provides an alarm method for judging the navigation of super-high ships in a bridge area, which has the following beneficial effects:

[0033] By analyzing the track, the first fitting track and the confidence algorithm of the ship AIS, the second fitting track and the confidence of the second fitting track are determined, which can improve the accuracy of ship identification and reduce the probability of mislabeling ships; by assigning each ship a unique second ID, the second ID can be displayed on the display interface at all times, which is convenient for management personnel to manage the ship; in addition, the application also analyzes the ship shape based on the ship shape algorithm to determine what type of ship the ship is, so as to manage different types of ships and predict future dynamics; it also analyzes the track of each ship based on the track judgment algorithm, and determines whether the ship is going to pass through the bridge area. If it passes through the bridge area, it determines whether the ship height can pass through the bridge area smoothly. If it is determined that the ship does not need to pass through the bridge area, there is no need to determine whether the ship height can pass through the bridge area smoothly. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0035] Figure 1 A schematic diagram of the process structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] like Figure 1 As shown, a method for alarming the passage of super-high ships in a bridge area includes the following steps:

[0038] S01. Obtain the bridge area clearance height and the ship's AIS data;

[0039] S02, obtaining a plurality of first data distributed at scattered points in the video image;

[0040] S03, performing data cleaning on the acquired first data, where data cleaning refers to performing function fitting on the acquired scattered point distributed first data to form first fitting tracks, and assigning a first ID to each first fitting track;

[0041] S04, performing fitting correction analysis on the AIS data based on the correction algorithm to obtain the ship AIS analysis track;

[0042] S05. Based on the ship AIS analysis track, the first fitting track and the confidence algorithm, determine the second fitting track and the confidence of the second fitting track, and assign a second ID to each second fitting track, wherein the confidence is used to characterize the possibility that the second fitting track is a ship;

[0043] S06. When the confidence level is greater than the threshold, the height of the ship of the second ID is obtained, the ship of the second ID is matched based on the ship shape algorithm, and the ship track of the ship of the second ID is judged based on the second fitting track and the track judgment algorithm;

[0044] S07. If the ship shape is the preset ship shape, and based on the ship track, it is judged that the ship of the second ID will pass through the bridge area, then the ship height of the second ID is compared with the passage height of the bridge area. If the ship height of the second ID is less than the passage height of the bridge area, an alarm message is sent to the electronic device.

[0045] As an embodiment further provided by the present invention, step S01 includes:

[0046] At preset time intervals, a plurality of first height data distributed at scattered points in the video image and first position data corresponding to the first height data are acquired.

[0047] As another embodiment further provided by the present invention, step S03 includes:

[0048] Data cleaning is performed on multiple scattered point distributed first position data based on the random forest algorithm. Data cleaning refers to performing function fitting on the acquired scattered point distributed first position data to form a first fitting track, and assigning a first ID function to each first fitting track.

[0049] As another embodiment further provided by the present invention, there are multiple AIS data of the ship, and they are scattered and distributed, and step S04 includes:

[0050] Based on the time series, position information and vector track information, the AIS data is fitted and corrected to obtain the ship's AIS analysis track.

[0051] As another embodiment further provided by the present invention, the correction algorithm includes a gradient boosting tree algorithm;

[0052] In step S05, after the first fitting track and the ship AIS analysis track are matched and fitted, the first fitting track matches at least one ship AIS analysis track, and a confidence level is generated between each first fitting track and a ship AIS analysis track, and the fitting result with the highest confidence level is selected to generate a second fitting track and a second ID.

[0053] As another embodiment further provided by the present invention, in step S06, the ship morphology algorithm includes a YOLO target detection algorithm, and the ship morphology algorithm includes:

[0054] Based on the MSAM network, the edge value is taken to identify the height feature of the ship of the second ID, and the xy coordinate value of the positioning image of the ship of the second ID in the video image is obtained, and the shape of the ship of the second ID is determined according to the XY coordinate value of the positioning image.

[0055] As another embodiment further provided by the present invention, in step S06, the track determination algorithm includes an OpenCV background modeling algorithm, and the track determination algorithm includes:

[0056] The video images are dynamically framed, and multiple images after dynamic framing are compared to filter out static targets and non-navigable ship targets in the images.

[0057] As another embodiment further provided by the present invention, the static target includes: at least one of a mountain, a road, a dock, and a building;

[0058] Non-navigable ship targets include: mobile ships and movable non-ship objects, wherein mobile ships include ships that will not pass through the bridge area according to the ship track, and movable non-ship objects include at least one of birds and aircraft;

[0059] and / or,

[0060] In step S07, the ship type includes at least one of a container ship, a fishing boat, a passenger ship, an ore carrier or a bulk carrier.

[0061] The present application determines the second fitting track and the confidence of the second fitting track through the ship AIS analysis track, the first fitting track and the confidence algorithm, which can improve the accuracy of ship identification and reduce the probability of mislabeling ships; by giving each ship a unique second ID, the second ID can be displayed on the display interface at all times, which is convenient for management personnel to manage the ship; in addition, the present application also analyzes the ship shape based on the ship shape algorithm to determine what type of ship the ship is, so as to manage different types of ships and predict future dynamics; it also analyzes the track of each ship based on the track judgment algorithm, and determines whether the ship is going to pass through the bridge area. If it passes through the bridge area, it determines whether the ship height can pass through the bridge area smoothly. If it is determined that the ship does not need to pass through the bridge area, there is no need to determine whether the ship height can pass through the bridge area smoothly.

[0062] In summary, based on the image-based ship height measurement technology, algorithm models adapted to the application scenarios are superimposed, ships are identified through the YOLO target detection algorithm based on image deep learning, ship information is obtained by matching AIS, and OpenCV background modeling is used to filter static targets and non-navigable ship targets, so as to achieve accurate positioning and remote intervention of ultra-high ships.

[0063] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0064] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0065] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0067] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0068] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all steps of the method in the above embodiments, and the electronic device specifically includes the following contents:

[0069] Processor, memory, communications interface and bus;

[0070] Wherein, the processor, memory, and communication interface communicate with each other via the bus;

[0071] The processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the method in the above embodiment are implemented.

[0072] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps of the method in the above embodiments are implemented.

[0073] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Although the embodiment of this specification provides the method operation steps as described in the embodiment or flowchart, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way of executing the order of many steps, and does not represent the only execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] Those skilled in the art should understand that the embodiments of this specification can be provided as methods, systems or computer program products. Therefore, the embodiments of this specification can be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of this specification can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification.

[0075] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradicting each other. The above is only an embodiment of the embodiment of this specification and is not intended to limit the embodiment of this specification. For those skilled in the art, the embodiment of this specification may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of this specification shall be included in the scope of the claims of the embodiment of this specification.

Claims

1. An alarm method for judging the navigation of super-high ships in a bridge area, characterized in that: The following steps are involved: S01. Obtain the bridge area clearance height and the ship's AIS data; S02, obtaining a plurality of first data distributed at scattered points in the video image; S03, performing data cleaning on the first data obtained, wherein the data cleaning refers to performing function fitting on the first data obtained in scattered point distribution to form a first fitting track, and assigning a first ID to each of the first fitting tracks; S04, performing fitting correction analysis on the AIS data based on a correction algorithm to obtain an AIS analysis track of the ship; S05. Determine a second fitting track and a confidence of the second fitting track based on the ship AIS analysis track, the first fitting track and a confidence algorithm, and assign a second ID to each second fitting track, wherein the confidence is used to characterize the possibility that the second fitting track is a ship; S06. When the confidence level is greater than a threshold, the height of the ship of the second ID is obtained, a ship shape matching is performed on the ship of the second ID based on a ship shape algorithm, and a ship track judgment is performed on the ship of the second ID based on a second fitting track and a track judgment algorithm; S07, if the ship shape is a preset ship shape, and based on the ship track, it is judged that the ship of the second ID will pass through the bridge area, then compare the height of the ship of the second ID with the passage height of the bridge area, and if the height of the ship of the second ID is greater than the passage height of the bridge area, send an alarm message to the electronic device; The step S02 comprises: Acquire a plurality of first height data scattered at points in a video image and first position data corresponding to the first height data at preset time intervals; The step S03 comprises: Performing data cleaning on the plurality of scattered point distributed first position data based on a random forest algorithm, wherein the data cleaning refers to performing function fitting on the obtained scattered point distributed first position data to form a first fitting track, and assigning a first ID function to each of the first fitting tracks; The AIS data of the ship is multiple and scattered, and the step S04 includes: Perform fitting correction analysis on the AIS data based on time series, position information, and vector trajectory information to obtain the ship AIS analysis track; The correction algorithm includes a gradient boosting tree algorithm; In the step S05, after the first fitting track and the ship AIS analysis track are matched and fitted, the first fitting track matches at least one of the ship AIS analysis tracks, and a confidence level is generated between each of the first fitting tracks and one of the ship AIS analysis tracks, and the fitting result with the highest confidence level is selected to generate the second fitting track and the second ID.

2. The alarm method for judging the navigation of super-high ships in a bridge area according to claim 1 is characterized in that: In step S06, the ship morphology algorithm includes a YOLO target detection algorithm, and the ship morphology algorithm includes: Based on the MSAM networking, the edge value is taken to identify the height feature of the ship of the second ID, and the positioning image xy coordinate value of the ship of the second ID in the video image is obtained, and the shape of the ship of the second ID is determined according to the positioning image xy coordinate value.

3. The alarm method for judging the navigation of super-high ships in a bridge area according to claim 1 is characterized in that: In step S06, the track determination algorithm includes an OpenCV background modeling algorithm, and the track determination algorithm includes: The video images are dynamically framed, and multiple images after dynamic framing are compared to filter out static targets and non-navigable ship targets in the images.

4. The alarm method for judging the navigation of super-high ships in a bridge area according to claim 3 is characterized in that: The static target includes: at least one of mountains, roads, docks, and buildings; The non-navigable ship targets include: mobile ships and movable non-ship objects, wherein the mobile ships include ships that will not pass through the bridge area according to the ship track, and the movable non-ship objects include at least one of birds and airplanes; and / or, In step S07, the ship type includes at least one of a container ship, a fishing boat, a passenger ship, an ore carrier or a bulk carrier.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the alarm method for judging the navigation of super-high ships in the bridge area as described in any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the alarm method for judging the navigation of super-high ships in the bridge area as described in any one of claims 1 to 4 are implemented.

Images