Sea condition identification method and device

Abstract

The invention provides a sea condition identification method and device. The method comprises the steps that a standard sea-sky line is set on a shooting picture of a camera installed on the center line of a ship; acquiring video data of the sea surface in real time according to a preset shooting frequency through the camera; based on the standard sea-sky-line, performing target identification and feature extraction on the video data to obtain a wave-surface sea-sky-line; calculating a rolling angle between the standard sea-sky-line and the wave-surface sea-sky-line; and determining a sea condition result based on the rolling angle. The method comprises the following steps of: shooting video data in navigation through a camera mounted on a midline of a ship, extracting a wave-surface sea-sky-line by using a visual identification technology, and calculating a rolling angle between a standard sea-sky-line and the wave-surface sea-sky-line through a geometrical relationship, so as to determine a final sea condition result.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a method and device for recognizing sea conditions. Background Art

[0002] When the crew is driving a ship or working on a ship autonomously, they often need to identify the ship's sea conditions to help control the ship. Currently, observations are mainly based on visual observation of sea surface signs. According to the shape of the wave crest, the degree of crest breakage and the amount of waves, the sea condition level is judged and filled in the record table. In addition, a float-type accelerometer is used to observe the waves.

[0003] However, there are still the following shortcomings:

[0004] 1. Visual observation of sea surface phenomena is greatly affected by personal factors and is easily influenced by subjectivity, resulting in large deviations in the results.

[0005] 2. The buoy of the floating ball acceleration wave meter is mainly used for routine wave observation work and monitoring of offshore marine environmental projects in coastal marine environmental monitoring stations. It can also be used on board marine survey ships, but it cannot be used on ocean-going ships.

[0006] Therefore, it is of great significance to propose an objective sea condition identification method that can be applied on ocean-going ships. Summary of the invention

[0007] The present invention provides a sea condition recognition method and device, which are used to capture video data during navigation by a camera installed on the centerline of a ship, and to obtain the sea condition of the ship during navigation by using visual recognition technology.

[0008] In a first aspect, the present invention provides a method for identifying sea conditions, comprising:

[0009] Set the standard sea-sky line on the shooting screen of the camera installed on the centerline of the ship;

[0010] By using the camera, video data of the sea surface is obtained in real time according to a preset shooting frequency;

[0011] Based on the standard sea-sky line, target recognition and feature extraction are performed on the video data to obtain a wave surface sea-sky line;

[0012] Calculating the roll angle between the standard sea-sky line and the wavefront sea-sky line;

[0013] Based on the roll angle, a sea state result is determined.

[0014] Optionally, the sea condition result includes: sea surface condition, wind force level and wave height; based on the roll angle, determining the sea condition result includes:

[0015] Based on the roll angle, matching is performed from a preset roll angle range to obtain a target roll angle range;

[0016] The sea surface condition, the wind force level and the wave height are determined according to the preset correspondence between the sea condition and the roll angle interval.

[0017] Optionally, a standard sea-sky line is set in the shooting picture of a camera installed on the centerline of the ship, including:

[0018] Based on the camera installed on the centerline of the ship, the camera position is pre-calibrated and the center of gravity of the camera is marked as the origin of the video screen;

[0019] The standard sea-sky line is arranged on a plane where the origin is parallel to the sea level.

[0020] Optionally, based on the standard sea-sky line, target recognition and feature extraction are performed on the video data to obtain a wave surface sea-sky line, including:

[0021] Based on the standard sea-sky line, target recognition is performed on the video data to obtain key points related to wave morphology;

[0022] The highest point of the wave and the lowest point of the wave are determined from the key points, and the wave surface sea-sky line is generated based on the highest point of the wave and the lowest point of the wave.

[0023] In a second aspect, the present invention provides a sea condition identification device, comprising:

[0024] A standard sea-sky line setting module is used to set the standard sea-sky line in the camera's shooting picture;

[0025] A video data acquisition module, used to acquire video data of the sea surface in real time through the camera according to a preset shooting frequency;

[0026] A wave-surface sea-sky-line determination module is used to perform target recognition and feature extraction on the video data based on the standard sea-sky-line to obtain a wave-surface sea-sky-line;

[0027] A roll angle calculation module, used to calculate the roll angle between the standard sea-sky line and the wave-front sea-sky line;

[0028] The sea condition recognition module is used to determine the sea condition result based on the roll angle.

[0029] Optionally, the sea condition result includes: sea surface conditions, wind force level and wave height; the sea condition identification module includes:

[0030] A roll angle interval determination submodule, configured to match a preset roll angle interval based on the roll angle to obtain a target roll angle interval;

[0031] The sea condition determination submodule is used to determine the sea surface condition, the wind force level and the wave height according to the preset corresponding relationship between the sea condition and the roll angle interval.

[0032] Optionally, the standard sea-sky line setting module includes:

[0033] The origin marking submodule is used to mark the center of gravity of the camera as the origin of the video screen based on the camera installed on the centerline of the ship and the camera position obtained by pre-calibration;

[0034] The marked sea-sky line configuration submodule is used to configure the standard sea-sky line on a plane where the origin is parallel to the sea level.

[0035] Optionally, the wave surface sea-sky line determination module includes:

[0036] A target recognition submodule, for performing target recognition on the video data based on the standard sea-sky line to obtain key points related to wave morphology;

[0037] The wave surface sea-sky line generation submodule is used to determine the highest wave point and the lowest wave point from the key points, and generate the wave surface sea-sky line based on the highest wave point and the lowest wave point.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, runs the steps of the method provided in the first aspect above.

[0039] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0040] It can be seen from the above technical solutions that the present invention has the following advantages:

[0041] The present invention provides a method and device for identifying sea conditions, the method comprising: setting a standard sea-sky line in the shooting picture of a camera installed on the centerline of a ship; obtaining video data of the sea surface in real time through the camera according to a preset shooting frequency; performing target recognition and feature extraction on the video data based on the standard sea-sky line to obtain a wave-surface sea-sky line; calculating the roll angle between the standard sea-sky line and the wave-surface sea-sky line; and determining the sea condition result based on the roll angle. The video data during navigation is shot by a camera installed on the centerline of the ship, the wave-surface sea-sky line is extracted by using visual recognition technology, and the roll angle between the standard sea-sky line and the wave-surface sea-sky line is calculated by geometric relationship, thereby determining the final sea condition result. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0043] Figure 1 This is a flow chart of a first embodiment of a method for identifying sea conditions according to the present invention;

[0044] Figure 2 This is a flow chart of a second embodiment of a method for identifying sea conditions according to the present invention;

[0045] Figure 3 It is a schematic diagram of the camera installation of the present invention;

[0046] Figure 4 It is a structural schematic diagram of the sea condition calculation platform where the camera is located at the initial moment of the present invention;

[0047] Figure 5 This is a schematic diagram of camera shooting at the initial moment of the present invention;

[0048] Figure 6 A diagram showing the roll angle at a non-stationary moment of the present invention;

[0049] Figure 7 The camera image of the present invention at a non-stationary moment;

[0050] Figure 8 The present invention is a structural block diagram of a sea condition identification device embodiment of the present invention. DETAILED DESCRIPTION

[0051] The embodiment of the present invention provides a sea condition recognition method and device, which are used to capture video data during navigation by a camera installed on the centerline of a ship, and use visual recognition technology to obtain the sea condition of the ship during navigation.

[0052] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below 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.

[0053] Embodiment 1

[0054] See also Figure 1 , Figure 1This is a flow chart of a method embodiment 1 of the present invention, the method comprising:

[0055] Step S101, setting a standard sea-sky line in the shooting picture of a camera installed on the centerline of the ship;

[0056] In the embodiment of the present application, a hypothetical standard sea-sky line is set in the initial shooting picture of the camera as an ideal straight line set at the sea-sky boundary at the initial moment according to the image processing technology, and serves as a reference benchmark for subsequent calculations.

[0057] Step S102, obtaining video data of the sea surface in real time according to a preset shooting frequency through the camera;

[0058] In the embodiment of the present application, the camera continuously captures sea surface images at a preset frequency, and transmits these image data in real time to form a continuous video stream.

[0059] Step S103, based on the standard sea-sky line, performing target recognition and feature extraction on the video data to obtain a wavefront sea-sky line;

[0060] Due to the influence of waves, the sea-sky boundary line may deviate from the initially set standard sea-sky line. In the embodiment of the present application, target recognition and feature extraction are performed on the video data to prepare for locating the position of the wave surface sea-sky line.

[0061] Step S104, calculating the roll angle between the standard sea-sky line and the wavefront sea-sky line;

[0062] In the embodiment of the present application, by comparing the initially set standard sea-sky line position and the actually extracted wavefront sea-sky line position, the angular difference between the two in the vertical direction is calculated to determine the corresponding roll angle.

[0063] Step S105, determining the sea condition result based on the roll angle.

[0064] In the embodiment of the present application, the calculated roll angle is mapped to the corresponding sea condition level or state through a preset roll angle and sea condition level correspondence table to obtain the corresponding sea condition result.

[0065] A method for identifying sea conditions provided by an embodiment of the present invention includes: setting a standard sea-sky line in the shooting picture of a camera installed on the centerline of a ship; acquiring video data of the sea surface in real time through the camera according to a preset shooting frequency; performing target recognition and feature extraction on the video data based on the standard sea-sky line to obtain a wave-surface sea-sky line; calculating the roll angle between the standard sea-sky line and the wave-surface sea-sky line; and determining the sea condition result based on the roll angle. The video data during navigation is shot by a camera installed on the centerline of the ship, the wave-surface sea-sky line is extracted using visual recognition technology, and the roll angle between the standard sea-sky line and the wave-surface sea-sky line is calculated through geometric relationships, thereby determining the final sea condition result.

[0066] Embodiment 2

[0067] See also Figure 2 , Figure 2 This is a flow chart of a second embodiment of a method for identifying sea conditions of the present invention, the steps comprising:

[0068] Step S201, based on the camera installed on the centerline of the ship, the camera position is pre-calibrated and the center of gravity of the camera is marked as the origin of the video screen;

[0069] See also Figure 3 , Figure 3 This is a schematic diagram of the camera installation of the present invention. In the embodiment of the present application, the camera is installed in the ship at the center line of the compass deck.

[0070] It should be noted that the centerline position is the most stable part of the ship structure. Installing a camera here can reduce the impact of the ship's swaying or bumping on the camera, thereby obtaining a more stable video image. It can also provide a relatively wide field of view, allowing the camera to capture a wider range of surrounding environment information.

[0071] The centerline position is the center line of the ship, which best represents the ship's sailing direction and attitude. Installing the camera at the centerline of the compass deck is related to the ship's sailing attitude and navigation equipment, making calibration and maintenance work more convenient.

[0072] Step S202, configuring the standard sea-sky line on a plane parallel to the origin and the sea level;

[0073] In the embodiment of the present application, the camera position obtained by pre-calibration is used to mark the center of gravity of the camera as the origin of the video screen, and a standard sea-sky line is configured on a plane parallel to the horizontal plane based on the origin.

[0074] See also Figure 3 The standard sea-sky line is a stable sea-sky line under sea condition level 0, which is a sea-sky line under ideal sea condition. At this time, it can be ensured that the sea-sky line and the center line of the ship are in a static vertical state.

[0075] Step S203, obtaining video data of the sea surface in real time according to a preset shooting frequency through the camera;

[0076] When the camera and the ship are both in a stationary state, a standard sea-sky line is preset for the video picture taken by the camera, and the camera is used to capture video data of the ship during navigation.

[0077] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of the sea condition calculation platform where the camera is located at the initial moment of the present invention. L1 is the wave surface sea sky line. At this time, the angle between the standard sea sky line L and the wave surface sea sky line L1 is α. Since the ship itself will consider this pitch and roll when it is built in the shipyard, when the ship is only affected by the force in the lateral direction, the ship rolls. The ship and the camera are rigidly connected, so the camera's own shaking can be excluded from affecting the image analysis. The maximum roll angle is defined as β. Therefore, the following can be calculated through geometric relationships: α = β.

[0078] Step S204, based on the standard sea-sky line, performing target recognition on the video data to obtain key points related to wave morphology;

[0079] In the embodiment of the present application, after the image is captured, target recognition and feature extraction are performed on it, and L is determined to be a standard sea-sky line. At this time, the video data captured by the camera is as follows Figure 5 The initial moment camera shooting schematic diagram of the present invention is shown in FIG.

[0080] Step S205, determining the highest point and the lowest point of the wave from the key points, and generating the wave surface sea-sky line based on the highest point and the lowest point of the wave;

[0081] In an embodiment of the present application, a standard sea-sky line is used as a reference benchmark, and image processing algorithms such as edge detection or gradient analysis are used to identify and extract the characteristic points of these waves, thereby determining the highest and lowest points of the waves and generating a wave surface sea-sky line.

[0082] In a specific implementation, in the video data, the distances from the highest point of the wave and the lowest point of the wave to the standard sea-sky line are respectively the high wave height and the low wave height, and the height value with the larger value between the high wave height and the low wave height is marked as the wave height.

[0083] Step S206, calculating the roll angle between the standard sea-sky line and the wavefront sea-sky line;

[0084] The embodiment of the present application calculates the final roll angle through the geometric relationship between the standard sea-sky line and the wave-surface sea-sky line. Figure 6 , Figure 6The pan angle β of the present invention is shown in the non-stationary moment, and the shooting image at this time is as shown in FIG. Figure 7 shown.

[0085] Step S207, based on the roll angle, matching is performed from a preset roll angle interval to obtain a target roll angle interval;

[0086] In the embodiment of the present application, the preset roll angle interval is divided into intervals according to the size of the roll angle, and the roll angle intervals include (0, β1), [β1, β2), [β2, β3), [β3, β4) and [β4, β5], where β1<β2<β3<β4<β5.

[0087] Step S208, determining the sea surface conditions, wind force level and wave height according to the preset correspondence between the sea conditions and the roll angle interval.

[0088] In the embodiment of the present application, the correspondence between the sea condition and the roll angle interval includes a plurality of sea condition division intervals, and different sea surface conditions, wind force levels and wave heights are represented based on different sea condition division areas.

[0089] In a specific implementation, when the roll angle is 0, it represents a steady sea-sky line under sea condition level 0, that is, it corresponds to the standard sea-sky line; when the roll angle interval is (0, β1), [β1, β2), [β2, β3), [β3, β4) and [β4, β5], it represents sea condition level 1, sea condition level 2, sea condition level 3, sea condition level 4 and sea condition level 5, respectively, corresponding to the sea surface conditions, wind wave heights and maximum roll angles numbered 1-5 in the sea condition and ship roll correspondence table, as shown in the following table:

[0090]

[0091] The embodiment of the present invention discloses a method for identifying sea conditions, including: setting a standard sea-sky line in the shooting picture of a camera installed on the centerline of a ship; obtaining video data of the sea surface in real time through the camera according to a preset shooting frequency; performing target recognition and feature extraction on the video data based on the standard sea-sky line to obtain a wave-surface sea-sky line; calculating the roll angle between the standard sea-sky line and the wave-surface sea-sky line; and determining the sea condition result based on the roll angle. The video data during navigation is shot by a camera installed on the centerline of the ship, the wave-surface sea-sky line is extracted using visual recognition technology, and the roll angle between the standard sea-sky line and the wave-surface sea-sky line is calculated through geometric relationships, thereby determining the sea condition level, wind force and wave height around the ship during navigation.

[0092] Embodiment 3

[0093] See also Figure 8 , Figure 8This is a structural block diagram of an embodiment of a sea condition identification device of the present invention, the device comprises:

[0094] The standard sea-sky-line setting module 301 is used to set the standard sea-sky-line in the shooting picture of the camera;

[0095] The video data acquisition module 302 is used to acquire video data of the sea surface in real time through the camera according to a preset shooting frequency;

[0096] A wave-surface sea-sky-line determination module 303 is used to perform target recognition and feature extraction on the video data based on the standard sea-sky-line to obtain a wave-surface sea-sky-line;

[0097] A roll angle calculation module 304, used to calculate the roll angle between the standard sea-sky line and the wavefront sea-sky line;

[0098] The sea state identification module 305 is used to determine the sea state result based on the roll angle.

[0099] In an optional embodiment, the sea condition result includes: sea surface conditions, wind force level and wave height; the sea condition identification module 30 includes:

[0100] A roll angle interval determination submodule, configured to match a preset roll angle interval based on the roll angle to obtain a target roll angle interval;

[0101] The sea condition determination submodule is used to determine the sea surface condition, the wind force level and the wave height according to the preset corresponding relationship between the sea condition and the roll angle interval.

[0102] In an optional embodiment, the standard sea-sky line setting module 301 includes:

[0103] The origin marking submodule is used to mark the center of gravity of the camera as the origin of the video screen based on the camera installed on the centerline of the ship and the camera position obtained by pre-calibration;

[0104] The marked sea-sky line configuration submodule is used to configure the standard sea-sky line on a plane where the origin is parallel to the sea level.

[0105] In an optional embodiment, the wavefront sea-sky-line determination module 303 includes:

[0106] A target recognition submodule, for performing target recognition on the video data based on the standard sea-sky line to obtain key points related to wave morphology;

[0107] The wave surface sea-sky line generation submodule is used to determine the highest wave point and the lowest wave point from the key points, and generate the wave surface sea-sky line based on the highest wave point and the lowest wave point.

[0108] Embodiment 4

[0109] An embodiment of the present invention further provides a computer storage medium having a computer program stored thereon. When the computer program is executed by the processor, the steps of implementing a sea condition identification method of any embodiment include:

[0110] Set the standard sea-sky line on the shooting screen of the camera installed on the centerline of the ship;

[0111] By using the camera, video data of the sea surface is obtained in real time according to a preset shooting frequency;

[0112] Based on the standard sea-sky line, target recognition and feature extraction are performed on the video data to obtain a wave surface sea-sky line;

[0113] Calculating the roll angle between the standard sea-sky line and the wavefront sea-sky line;

[0114] Based on the roll angle, a sea state result is determined.

[0115] In an optional embodiment, the sea condition result includes: sea surface condition, wind force level and wave height; based on the roll angle, determining the sea condition result includes:

[0116] Based on the roll angle, matching is performed from a preset roll angle range to obtain a target roll angle range;

[0117] The sea surface condition, the wind force level and the wave height are determined according to the preset correspondence between the sea condition and the roll angle interval.

[0118] In an optional embodiment, setting a standard sea-sky line in a shooting picture of a camera installed on the centerline of a ship includes:

[0119] Based on the camera installed on the centerline of the ship, the camera position is pre-calibrated and the center of gravity of the camera is marked as the origin of the video screen;

[0120] The standard sea-sky line is arranged on a plane where the origin is parallel to the sea level.

[0121] In an optional embodiment, based on the standard sea-sky line, target recognition and feature extraction are performed on the video data to obtain a wave surface sea-sky line, including:

[0122] Based on the standard sea-sky line, target recognition is performed on the video data to obtain key points related to wave morphology;

[0123] The highest point of the wave and the lowest point of the wave are determined from the key points, and the wave surface sea-sky line is generated based on the highest point of the wave and the lowest point of the wave.

[0124] Embodiment 5

[0125] An embodiment of the present invention further provides a computer program product, on which a computer program is stored. When the computer program is executed by the processor, the steps of implementing a bridge crack detection method in any embodiment include:

[0126] Set the standard sea-sky line on the shooting screen of the camera installed on the centerline of the ship;

[0127] By using the camera, video data of the sea surface is obtained in real time according to a preset shooting frequency;

[0128] Based on the standard sea-sky line, target recognition and feature extraction are performed on the video data to obtain a wave surface sea-sky line;

[0129] Calculating the roll angle between the standard sea-sky line and the wavefront sea-sky line;

[0130] Based on the roll angle, a sea state result is determined.

[0131] In an optional embodiment, the sea condition result includes: sea surface condition, wind force level and wave height; based on the roll angle, determining the sea condition result includes:

[0132] Based on the roll angle, matching is performed from a preset roll angle range to obtain a target roll angle range;

[0133] The sea surface condition, the wind force level and the wave height are determined according to the preset correspondence between the sea condition and the roll angle interval.

[0134] In an optional embodiment, setting a standard sea-sky line in a shooting picture of a camera installed on the centerline of a ship includes:

[0135] Based on the camera installed on the centerline of the ship, the camera position is pre-calibrated and the center of gravity of the camera is marked as the origin of the video screen;

[0136] The standard sea-sky line is arranged on a plane where the origin is parallel to the sea level.

[0137] In an optional embodiment, based on the standard sea-sky line, target recognition and feature extraction are performed on the video data to obtain a wave surface sea-sky line, including:

[0138] Based on the standard sea-sky line, target recognition is performed on the video data to obtain key points related to wave morphology;

[0139] The highest point of the wave and the lowest point of the wave are determined from the key points, and the wave surface sea-sky line is generated based on the highest point of the wave and the lowest point of the wave.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0141] In the several embodiments provided in the present application, it should be understood that the methods, devices, electronic devices and storage media disclosed in the present invention can be implemented in other ways. For example, 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.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0144] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a readable storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0145] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying sea conditions, characterized in that: include: Set the standard sea-sky line on the shooting screen of the camera installed on the centerline of the ship; By using the camera, video data of the sea surface is obtained in real time according to a preset shooting frequency; Based on the standard sea-sky line, target recognition and feature extraction are performed on the video data to obtain a wave surface sea-sky line; Calculating the roll angle between the standard sea-sky line and the wavefront sea-sky line; Based on the roll angle, a sea state result is determined.

2. The sea condition identification method according to claim 1, characterized in that: The sea condition result includes: sea surface condition, wind force level and wave height; based on the roll angle, the sea condition result is determined, including: Based on the roll angle, matching is performed from a preset roll angle range to obtain a target roll angle range; The sea surface condition, the wind force level and the wave height are determined according to the preset correspondence between the sea condition and the roll angle interval.

3. The sea condition identification method according to claim 1, characterized in that: The standard sea-sky line is set for the camera mounted on the centerline of the ship, including: Based on the camera installed on the centerline of the ship, the camera position is pre-calibrated and the center of gravity of the camera is marked as the origin of the video screen; The standard sea-sky line is arranged on a plane where the origin is parallel to the sea level.

4. The sea condition identification method according to claim 1, characterized in that: Based on the standard sea-sky line, target recognition and feature extraction are performed on the video data to obtain a wave surface sea-sky line, including: Based on the standard sea-sky line, target recognition is performed on the video data to obtain key points related to wave morphology; The highest point of the wave and the lowest point of the wave are determined from the key points, and the wave surface sea-sky line is generated based on the highest point of the wave and the lowest point of the wave.

5. A sea condition identification device, characterized in that: include: A standard sea-sky line setting module is used to set the standard sea-sky line in the camera's shooting picture; A video data acquisition module, used to acquire video data of the sea surface in real time through the camera according to a preset shooting frequency; A wave-surface sea-sky-line determination module is used to perform target recognition and feature extraction on the video data based on the standard sea-sky-line to obtain a wave-surface sea-sky-line; A roll angle calculation module, used to calculate the roll angle between the standard sea-sky line and the wave-front sea-sky line; The sea condition recognition module is used to determine the sea condition result based on the roll angle.

6. The sea condition identification device according to claim 5, characterized in that: The sea condition results include: sea surface conditions, wind force level and wave height; the sea condition identification module includes: A roll angle interval determination submodule, configured to match a preset roll angle interval based on the roll angle to obtain a target roll angle interval; The sea condition determination submodule is used to determine the sea surface condition, the wind force level and the wave height according to the preset corresponding relationship between the sea condition and the roll angle interval.

7. The sea condition identification device according to claim 5, characterized in that: The standard sea-sky line setting module includes: The origin marking submodule is used to mark the center of gravity of the camera as the origin of the video screen based on the camera installed on the centerline of the ship and the camera position obtained by pre-calibration; The marked sea-sky line configuration submodule is used to configure the standard sea-sky line on a plane where the origin is parallel to the sea level.

8. The sea condition identification device according to claim 5, characterized in that: The wavefront sea-sky-line determination module comprises: A target recognition submodule, for performing target recognition on the video data based on the standard sea-sky line to obtain key points related to wave morphology; The wave surface sea-sky line generation submodule is used to determine the highest wave point and the lowest wave point from the key points, and generate the wave surface sea-sky line based on the highest wave point and the lowest wave point.

9. 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 method according to any one of claims 1 to 4 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images