A method, system, medium and device for detecting the draft depth of a sailing ship

Abstract

The present invention provides a method, system, medium and equipment for detecting the draft of a ship at sea. The method comprises: acquiring laser point cloud data and image data of the ship at sea; extracting the instant feature surface of the ship at sea, comparing the instant feature surface with the typical feature surfaces of various typical ship types, and selecting similar typical ship types; marking the side parts of the ship at sea according to the side parts on the typical feature surfaces, and separating the side part point cloud set; calculating the bow, middle and stern freeboard heights at the side of the ship at sea, obtaining the freeboard height of the ship at sea, and calculating the confidence; based on the image data, identifying the waterline of the ship at sea, so as to calculate the bow, middle and stern drafts, and the confidence, and obtain the initial draft; acquiring the static structure data of the ship at sea; calculating the final draft of the ship at sea. The present invention can accurately calculate the final draft of the ship at sea by using the laser point cloud data and the image data.

Description

Technical Field

[0001] The present invention relates to the field of ship detection technology, and in particular to a method, system, medium and equipment for detecting the draft depth of a sailing ship. Background Art

[0002] The draft of a ship refers to the depth of the ship submerged in water, that is, the distance between the bottom of the ship and the water surface. When the ship is too large or loaded with too much cargo, the draft of the ship may exceed or approach the depth of the lock threshold, which may cause accidents such as the bottom of the ship colliding with the lock threshold, damaging the ship and the lock infrastructure. Therefore, the detection of the draft of the ship is an important task to ensure the safety of ships passing through the lock.

[0003] In the current navigation safety management work, the detection of ship draft depth generally adopts the method of manual monitoring. First, when the ship is moored, the staff will go on board and use hooks and other tools to manually measure the part of the ship submerged in the water; second, the staff will visually read the draft data of the ship by observing the draft line on the side of the ship. The former method requires the ship to be docked before it can be operated, which is time-consuming and there are safety risks for the staff to get on and off the ship. The latter method relies on the experience of the staff to obtain data, with low data accuracy and poor objectivity, and high requirements for light at the observation site. Recently, there are also methods that use video, ultrasonic and other measurement methods to replace manual methods, but due to factors such as cost, accuracy, and environmental dependence, they cannot meet the requirements of actual engineering applications. Summary of the invention

[0004] In view of the deficiencies in the prior art, an object of the present invention is to provide a method for detecting the draft depth of a ship underway, aiming to solve the technical problems mentioned in the background technology.

[0005] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0006] A method for detecting the draft depth of a sailing ship comprises the following steps:

[0007] Obtain laser point cloud data and image data of ships at sea;

[0008] Based on the laser point cloud data of the ship underway, a plurality of instant feature surfaces of the ship underway are extracted, and the plurality of instant feature surfaces are traversed and compared with typical feature surfaces of various typical ship types in a historical database to select a typical ship type similar to the ship underway;

[0009] According to the side parts on the typical characteristic surface of the typical ship type, the side parts of the instant characteristic surface of the ship at sea are marked, and a point cloud set of the side parts of the instant characteristic surface is separated;

[0010] Based on the side point cloud set, the bow freeboard height, the middle freeboard height and the stern freeboard height at the side of the ship underway are calculated to obtain the freeboard height of the ship underway, and the confidence of the freeboard height of the ship underway is calculated;

[0011] Based on the image data of the ship underway, the waterline at the side of the ship underway is identified to calculate the bow draft, the midship draft, the stern draft, and the corresponding confidence levels, thereby obtaining the initial draft of the ship underway;

[0012] Obtaining static structural data of a specific ship type consistent with the ship underway or a similar ship type close to the ship underway from a ship characteristic database as the static structural data of the ship underway;

[0013] Based on the freeboard height data and the initial draft depth data with confidence levels meeting the requirements, the final draft depth of the ship underway is calculated through a correlation algorithm.

[0014] According to one aspect of the above technical solution, the acquisition of laser point cloud data and image data of the ship underway specifically includes:

[0015] Setting up laser scanning sensors, panoramic video surveillance cameras and detail capture surveillance cameras on the shore of the channel of the ship at sea;

[0016] Wherein, the laser scanning sensor, the panoramic video surveillance camera and the detail snapshot surveillance camera all face the waterway, and the laser scanning sensor is electrically connected to the panoramic video surveillance camera and the detail snapshot surveillance camera;

[0017] The laser scanning sensor continuously scans the water space of the waterway, obtains laser point cloud data of the ship at sea when the ship at sea passes by, and sends a shooting signal to the panoramic video surveillance camera and the detail capture surveillance camera;

[0018] After receiving the shooting signal, the panoramic video monitoring camera and the detail snapshot monitoring camera respectively shoot the full ship image of the ship at sea and the detailed image of the side of the ship at sea.

[0019] According to one aspect of the above technical solution, the bow freeboard height, the middle freeboard height and the stern freeboard height at the side of the ship underway are calculated based on the side point cloud set to obtain the freeboard height of the ship underway, and the confidence of the freeboard height of the ship underway is calculated, which specifically includes:

[0020] The side part point cloud set is divided into side bow point cloud data, side middle point cloud data and side stern point cloud data according to the position of the side surface;

[0021] Calculating the bow freeboard height based on the bow point cloud data;

[0022] L 首 =T 首 -B 首 ;

[0023] Among them, L 首 Indicates the bow freeboard height, T 首 represents the average value of the point cloud height coordinates at the top of the bow, B 首 Indicates the average value of the point cloud height coordinates at the bottom of the bow;

[0024] Calculating the middle freeboard height based on the side middle point cloud data;

[0025] L 中 =T 中 -B 中 ;

[0026] Among them, L 中 Indicates the mid-section freeboard height, T 中 represents the average value of the point cloud height coordinates at the top of the middle part of the side, B 中 It represents the average value of the point cloud height coordinates at the bottom of the middle part of the side;

[0027] Calculating the stern freeboard height based on the side stern point cloud data;

[0028] L 尾 =T 尾 -B 尾 ;

[0029] Among them, L 尾 Indicates the aft freeboard height, T 尾 represents the average value of the point cloud height coordinates at the top of the side tail, B 尾 It represents the average value of the point cloud height coordinates at the bottom of the side stern;

[0030] Take the average of the bow freeboard height, the middle freeboard height and the stern freeboard height as the freeboard height L of the ship underway. 点云 ;

[0031] ;

[0032] The confidence level Conf of the freeboard height of the ship underway is calculated based on the feature value of the side point cloud set. 点云 ;

[0033] ;

[0034] Among them, k1 is the confidence adjustment factor of the valid point cloud, k2 is the confidence adjustment factor of the noise point, N1 is the number of valid point clouds at the side, N2 is the number of noise points at the side, and N0 is the total number of point clouds in the side processing theory.

[0035] According to one aspect of the above technical solution, based on the image data of the ship under navigation, the waterline at the side of the ship under navigation is identified to calculate the bow draft, the midship draft, the stern draft, and the corresponding confidence, and then obtain the initial draft of the ship under navigation, specifically including:

[0036] Inputting the image data of the ship underway into a pre-trained image recognition model to identify the waterline of the side of the ship underway;

[0037] The image recognition model is used to output the bow draft, midship draft, stern draft and corresponding confidence levels to obtain the initial draft of the ship underway. 图像 ;

[0038] ;

[0039] Among them, D 首 Indicates the bow draft depth, Conf 首 Indicates the confidence level of bow draft, D 中 Indicates the draft depth among ships, Conf 中 Indicates the confidence level of the midship draft, D 尾 Indicates the stern draft depth, Conf 尾 Indicates the confidence level of the stern draft;

[0040] Calculate the confidence level Conf of the initial draft of the ship underway 图像 ;

[0041] .

[0042] According to one aspect of the above technical solution, the step of obtaining static structural data of a specific ship type consistent with the ship at sea or a similar ship type close to the ship at sea from the ship characteristic database as the static structural data of the ship at sea specifically includes:

[0043] Setting up an AIS receiver on the shore of the channel of the ship underway;

[0044] S1, continuously receiving the AIS signal broadcasted by the ship at sea through the AIS receiver, and parsing the identity information of the ship at sea;

[0045] S2, simultaneously obtaining the name of the first ship through the detail capture monitoring camera, and performing video recognition to obtain the identity information of the ship underway;

[0046] If the identity information of the ship underway is successfully obtained in steps S1 and S2, the corresponding specific ship type that matches is searched in the ship feature database, and the static structure data of the specific ship type is used as the static structure data Md of the ship underway;

[0047] If the steps S1 and S2 fail to obtain the identity information of the ship at sea, the panoramic video surveillance camera is used to capture the entire ship image of the ship at sea, similar ship types are matched from the ship feature database, and the static structure data of the similar ship types are referenced as the static structure data Md of the ship at sea.

[0048] According to one aspect of the above technical solution, the freeboard height data and the initial draft depth data with confidence meeting the requirements are used to calculate the final draft depth of the ship underway through a correlation algorithm, which specifically includes:

[0049] A freeboard height confidence threshold is preset, and the freeboard height of the ship underway that is higher than the freeboard height confidence threshold is retained;

[0050] Preset an initial draft depth threshold, and retain the initial draft depth of the ship underway that is higher than the initial draft depth threshold;

[0051] Based on the static structural data Md of the underway ship, combined with the retained freeboard height of the underway ship and the initial draft of the underway ship, the final draft of the underway ship D is calculated. 船舶 ;

[0052] ;

[0053] Calculating the confidence level of the final draft of the ship under navigation, and retaining the final draft of the ship under navigation that meets the confidence level;

[0054] .

[0055] The present invention also provides a system for detecting the draft depth of a sailing ship, comprising:

[0056] The first acquisition module is used to acquire laser point cloud data and image data of the ship underway;

[0057] The first acquisition module is specifically used to: set up a laser scanning sensor, a panoramic video surveillance camera and a detail capture surveillance camera on the shore of the channel of the ship at sea;

[0058] Wherein, the laser scanning sensor, the panoramic video surveillance camera and the detail snapshot surveillance camera all face the waterway, and the laser scanning sensor is electrically connected to the panoramic video surveillance camera and the detail snapshot surveillance camera;

[0059] The laser scanning sensor continuously scans the water space of the waterway, obtains laser point cloud data of the ship at sea when the ship at sea passes by, and sends a shooting signal to the panoramic video surveillance camera and the detail capture surveillance camera;

[0060] After receiving the shooting signal, the panoramic video surveillance camera and the detail snapshot surveillance camera respectively shoot a full ship image of the ship at sea and a detailed image of the side of the ship at sea;

[0061] A selection module is used to extract multiple instant feature surfaces of the ship underway based on the laser point cloud data of the ship underway, traverse and compare the multiple instant feature surfaces with typical feature surfaces of various typical ship types in the historical database, and select a typical ship type similar to the ship underway;

[0062] Separation module: used for marking the side parts of the instant characteristic surface of the ship under navigation according to the side parts on the typical characteristic surface of the typical ship type, and separating the side parts point cloud set of the instant characteristic surface;

[0063] A first calculation module: used for calculating the bow freeboard height, the middle freeboard height and the stern freeboard height at the side of the ship underway based on the side point cloud set, so as to obtain the freeboard height of the ship underway, and calculating the confidence of the freeboard height of the ship underway;

[0064] The first calculation module is specifically used to: divide the side part point cloud set into side bow point cloud data, side middle point cloud data and side stern point cloud data according to the position of the side surface;

[0065] Calculating the bow freeboard height based on the bow point cloud data;

[0066] L 首 =T 首 -B 首 ;

[0067] Among them, L 首 Indicates the bow freeboard height, T 首 represents the average value of the point cloud height coordinates at the top of the bow, B 首 Indicates the average value of the point cloud height coordinates at the bottom of the bow;

[0068] Calculating the middle freeboard height based on the side middle point cloud data;

[0069] L 中 =T 中 -B 中 ;

[0070] Among them, L中 Indicates the mid-section freeboard height, T 中 represents the average value of the point cloud height coordinates at the top of the middle part of the side, B 中 It represents the average value of the point cloud height coordinates at the bottom of the middle part of the side;

[0071] Calculating the stern freeboard height based on the side stern point cloud data;

[0072] L 尾 =T 尾 -B 尾 ;

[0073] Among them, L 尾 Indicates the aft freeboard height, T 尾 represents the average value of the point cloud height coordinates at the top of the side tail, B 尾 It represents the average value of the point cloud height coordinates at the bottom of the side stern;

[0074] Take the average of the bow freeboard height, the middle freeboard height and the stern freeboard height as the freeboard height L of the ship underway. 点云 ;

[0075] ;

[0076] The confidence level Conf of the freeboard height of the ship underway is calculated based on the feature value of the side point cloud set. 点云 ;

[0077] ;

[0078] Among them, k1 is the confidence adjustment factor of the effective point cloud, k2 is the confidence adjustment factor of the noise point, N1 is the number of effective point clouds at the side, N2 is the number of noise points at the side, and N0 is the number of all point clouds in the side processing theory;

[0079] A second calculation module is used to identify the waterline of the side of the ship under navigation based on the image data of the ship under navigation, so as to calculate the bow draft, the midship draft, the stern draft, and the corresponding confidence, and then obtain the initial draft of the ship under navigation;

[0080] The second calculation module is specifically used to: input the image data of the ship underway into a pre-trained image recognition model to identify the waterline of the side of the ship underway;

[0081] The image recognition model is used to output the bow draft, midship draft, stern draft and corresponding confidence levels to obtain the initial draft of the ship underway. 图像 ;

[0082] ;

[0083] Among them, D 首 Indicates the bow draft depth, Conf 首 Indicates the confidence level of bow draft, D 中 Indicates the draft depth among ships, Conf 中 Indicates the confidence level of the midship draft, D 尾 Indicates the stern draft depth, Conf 尾 Indicates the confidence level of the stern draft;

[0084] Calculate the confidence level Conf of the initial draft of the ship underway 图像 ;

[0085] ;

[0086] The second acquisition module is used to acquire static structural data of a specific ship type consistent with the ship at sea or a similar ship type close to the ship at sea from the ship characteristic database, so as to serve as the static structural data of the ship at sea;

[0087] The second acquisition module is specifically used to: set up an AIS receiver on the shore of the channel of the ship at sea;

[0088] S1, continuously receiving the AIS signal broadcasted by the ship at sea through the AIS receiver, and parsing the identity information of the ship at sea;

[0089] S2, simultaneously obtaining the name of the first ship through the detail capture monitoring camera, and performing video recognition to obtain the identity information of the ship underway;

[0090] If the identity information of the ship underway is successfully obtained in steps S1 and S2, the corresponding specific ship type that matches is searched in the ship feature database, and the static structure data of the specific ship type is used as the static structure data Md of the ship underway;

[0091] If the identity information of the ship underway cannot be obtained in steps S1 and S2, the full ship image of the ship underway is captured by the panoramic video surveillance camera, a similar ship type is matched from the ship feature database, and the static structure data of the similar ship type is referenced as the static structure data Md of the ship underway;

[0092] The third calculation module is used to calculate the final draft of the ship underway through a correlation algorithm based on the freeboard height data and the initial draft data that meet the confidence requirements;

[0093] The third calculation module is specifically used to: preset a freeboard height confidence threshold, and retain the freeboard height of the ship underway that is higher than the freeboard height confidence threshold;

[0094] Preset an initial draft depth threshold, and retain the initial draft depth of the ship underway that is higher than the initial draft depth threshold;

[0095] Based on the static structural data Md of the underway ship, combined with the retained freeboard height of the underway ship and the initial draft of the underway ship, the final draft of the underway ship D is calculated. 船舶 ;

[0096] ;

[0097] Calculating the confidence level of the final draft of the ship under navigation, and retaining the final draft of the ship under navigation that meets the confidence level;

[0098] .

[0099] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for detecting the draft depth of a ship underway is implemented.

[0100] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for detecting the draft depth of a ship underway when executing the computer program.

[0101] Compared with the prior art, the present invention has the following beneficial effects:

[0102] By using laser point cloud data and image data, the freeboard height and draft of the ship are calculated respectively, and the static structure data of the ship is obtained based on the ship's identity. The final draft of the ship at sea is calculated through the association algorithm, which can make the calculation result more accurate. At the same time, the corresponding confidence level is calculated at each step, making the judgment result more reliable, overcoming the shortcomings of a single perception method in the complex environment of the waterway site, and the problem that factors such as water surface fluctuations and difficulty in identifying the waterline affect the accuracy of draft detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0103] Figure 1 This is a flow chart of a method for detecting the draft depth of a ship underway in the first embodiment of the present invention;

[0104] Figure 2 This is a structural block diagram of a system for detecting the draft depth of a ship underway in a second embodiment of the present invention;

[0105] Figure 3 is a structural block diagram of an electronic device in a third embodiment of the present invention;

[0106] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0107] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0108] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0109] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0110] See also Figure 1 , shown is a method for detecting the draft of a ship underway in the first embodiment of the present invention, comprising the following steps:

[0111] S10, acquiring laser point cloud data and image data of the ship underway;

[0112] S20, based on the laser point cloud data of the ship underway, extracting a plurality of instant feature surfaces of the ship underway, traversing and comparing the plurality of instant feature surfaces with typical feature surfaces of various typical ship types in a historical database, and selecting a typical ship type similar to the ship underway;

[0113] S30, marking the side parts of the instant characteristic surface of the ship under navigation according to the side parts on the typical characteristic surface of the typical ship type, and separating the side part point cloud set of the instant characteristic surface;

[0114] S40, based on the side part point cloud set, calculating the bow freeboard height, the middle freeboard height and the stern freeboard height at the side of the ship under way to obtain the freeboard height of the ship under way, and calculating the confidence of the freeboard height of the ship under way;

[0115] S50, based on the image data of the ship under navigation, identifying the waterline at the side of the ship under navigation, so as to calculate the bow draft, the midship draft, the stern draft, and the corresponding confidences, and then obtain the initial draft of the ship under navigation;

[0116] S60, acquiring static structural data of a specific ship type consistent with the ship underway or a similar ship type close to the ship underway from a ship characteristic database, as static structural data of the ship underway;

[0117] S70, calculating the final draft of the ship under navigation by a correlation algorithm based on the freeboard height data and the initial draft data with confidence levels meeting the requirements.

[0118] It can be understood that the present invention calculates the freeboard height and draft of the ship respectively by using laser point cloud data and image data, obtains the static structure data of the ship based on the ship identity, and calculates the final draft of the ship at sea through an association algorithm, so that the calculation result can be made more accurate. At the same time, the corresponding confidence level is calculated at each step, making the judgment result more reliable, overcoming the shortcomings of a single perception method in the complex environment of the waterway site, and the problem that factors such as water surface fluctuations and difficulty in identifying the waterline affect the accuracy of draft detection.

[0119] Specifically, the specific steps of step S10 include:

[0120] Setting up laser scanning sensors, panoramic video surveillance cameras and detail capture surveillance cameras on the shore of the channel of the ship at sea;

[0121] Wherein, the laser scanning sensor, the panoramic video surveillance camera and the detail snapshot surveillance camera all face the waterway, and the laser scanning sensor is electrically connected to the panoramic video surveillance camera and the detail snapshot surveillance camera;

[0122] The laser scanning sensor continuously scans the water space of the waterway, obtains laser point cloud data of the ship at sea when the ship at sea passes by, and sends a shooting signal to the panoramic video surveillance camera and the detail capture surveillance camera;

[0123] After receiving the shooting signal, the panoramic video monitoring camera and the detail snapshot monitoring camera respectively shoot the full ship image of the ship at sea and the detailed image of the side of the ship at sea.

[0124] It is understandable that in order to obtain accurate data on the draft depth of the ship, it is necessary to obtain the above-water and underwater information of the ship through as many channels and means as possible, so as to avoid the limitations of a single information acquisition method in certain special scenarios. In this embodiment, laser scanning sensors, panoramic video surveillance cameras and detail capture surveillance cameras are set up on the shore of the channel of the ship at sea, which can basically cover the side of the ship at sea, and thus obtain complete laser point cloud data and image data. The laser scanning sensor needs to scan continuously. In order to avoid power consumption of the panoramic video surveillance camera and the detail capture surveillance camera, the laser scanning sensor is used as a trigger switch for the two. When the laser scanning sensor scans the target and obtains the point cloud data, it will send a signal to the panoramic video surveillance camera and the detail capture surveillance camera, so that the two can respectively capture the full ship image and the side detail image of the ship at sea.

[0125] Furthermore, in step S20, multiple instant feature surfaces are extracted from the ship point cloud data acquired by the laser scanning sensor according to the geometric relative positions, and the data of the currently sailing ship containing the multiple instant feature surfaces is traversed and compared with a preset historical database containing typical feature surface data of various typical ship types, and the ship type with the highest degree of similarity is selected as the typical ship type.

[0126] Furthermore, in step S30, each instant characteristic surface of the current ship is labeled according to the characteristic part name labeled in the preset typical ship type. For the area range of the side characteristic surface of the current ship, the side point cloud data is separated from the ship point cloud data as the side part point cloud set.

[0127] Furthermore, the specific steps of step S40 include:

[0128] The side part point cloud set is divided into side bow point cloud data, side middle point cloud data and side stern point cloud data according to the position of the side surface;

[0129] Calculating the bow freeboard height based on the bow point cloud data;

[0130] L 首 =T 首 -B 首 ;

[0131] Among them, L 首 Indicates the bow freeboard height, T 首 represents the average value of the point cloud height coordinates at the top of the bow, B 首 Indicates the average value of the point cloud height coordinates at the bottom of the bow;

[0132] Calculating the middle freeboard height based on the side middle point cloud data;

[0133] L中 =T 中 -B 中 ;

[0134] Among them, L 中 Indicates the mid-section freeboard height, T 中 represents the average value of the point cloud height coordinates at the top of the middle part of the side, B 中 It represents the average value of the point cloud height coordinates at the bottom of the middle part of the side;

[0135] Calculating the stern freeboard height based on the side stern point cloud data;

[0136] L 尾 =T 尾 -B 尾 ;

[0137] Among them, L 尾 Indicates the aft freeboard height, T 尾 represents the average value of the point cloud height coordinates at the top of the side tail, B 尾 It represents the average value of the point cloud height coordinates at the bottom of the side stern;

[0138] Take the average of the bow freeboard height, the middle freeboard height and the stern freeboard height as the freeboard height L of the ship underway. 点云 ;

[0139] ;

[0140] The confidence level Conf of the freeboard height of the ship underway is calculated based on the feature value of the side point cloud set. 点云 ;

[0141] ;

[0142] Among them, k1 is the confidence adjustment factor of the valid point cloud, k2 is the confidence adjustment factor of the noise point, N1 is the number of valid point clouds at the side, N2 is the number of noise points at the side, and N0 is the total number of point clouds in the side processing theory.

[0143] It can be understood that by respectively calculating the bow point cloud data, the middle point cloud data and the stern point cloud data at the side surface, the bow freeboard height, the middle freeboard height and the stern freeboard height can be obtained respectively, and then the freeboard height of the ship at sea is calculated using the average value of the three, and the confidence is calculated. The freeboard height of the ship at sea can basically reflect the overall height of the side of the ship at sea.

[0144] Furthermore, the specific steps of step S50 include:

[0145] Inputting the image data of the ship underway into a pre-trained image recognition model to identify the waterline of the side of the ship underway;

[0146] The image recognition model is used to output the bow draft, midship draft, stern draft and corresponding confidence levels to obtain the initial draft of the ship underway. 图像 ;

[0147] ;

[0148] Among them, D 首 Indicates the bow draft depth, Conf 首 Indicates the confidence level of bow draft, D 中 Indicates the draft depth among ships, Conf 中 Indicates the confidence level of the midship draft, D 尾 Indicates the stern draft depth, Conf 尾 Indicates the confidence level of the stern draft;

[0149] Calculate the confidence level Conf of the initial draft of the ship underway 图像 ;

[0150] .

[0151] It can be understood that by deploying detail capture monitoring cameras on the shore side, detailed photos of the bow, midship and stern are obtained, and by matching with the ship's waterline feature database, the waterline image range is determined, and the image with the determined range is input into the pre-trained ship draft depth image recognition model to obtain the bow, midship and stern drafts and their corresponding confidence levels, and on this basis, the initial draft of the ship at sea is identified and calculated; at the same time, according to the matching degree between the waterline image and the feature library, the confidence level of the image recognition result of the initial draft of the ship at sea is calculated.

[0152] Furthermore, the specific steps of step S60 include:

[0153] Setting up an AIS receiver on the shore of the channel of the ship underway;

[0154] S1, continuously receiving the AIS signal broadcasted by the ship at sea through the AIS receiver, and parsing the identity information of the ship at sea;

[0155] S2, simultaneously obtaining the name of the first ship through the detail capture monitoring camera, and performing video recognition to obtain the identity information of the ship underway;

[0156] If the identity information of the ship underway is successfully obtained in steps S1 and S2, the corresponding specific ship type that matches is searched in the ship feature database, and the static structure data of the specific ship type is used as the static structure data Md of the ship underway;

[0157] If the steps S1 and S2 fail to obtain the identity information of the ship at sea, the panoramic video surveillance camera is used to capture the entire ship image of the ship at sea, similar ship types are matched from the ship feature database, and the static structure data of the similar ship types are referenced as the static structure data Md of the ship at sea.

[0158] It can be understood that the static structural data of a ship refers to the length, width, draft, full load draft, etc. of the ship in the ship registration data. This data is determined when the ship is designed and manufactured, and is measured and recorded by the statutory inspection agency when the ship is registered. It has high data accuracy and authority.

[0159] Among them, the ship's molded depth (static structural data Md) refers to the vertical distance from the upper edge of the flat keel to the upper edge of the upper continuous deck beam along the ship's side at the mid-transverse section of the ship, which can be approximately regarded as the vertical distance from the ship's deck to the bottom of the ship. The ship's fully loaded draft refers to the vertical distance measured from the keel line of the ship's bottom (or the ship's baseline) to the designed waterline, which can be approximately regarded as the vertical distance from the upper edge of the ship's waterline to the bottom of the ship.

[0160] Furthermore, the specific steps of step S70 include:

[0161] A freeboard height confidence threshold is preset, and the freeboard height of the ship underway that is higher than the freeboard height confidence threshold is retained;

[0162] Preset an initial draft depth threshold, and retain the initial draft depth of the ship underway that is higher than the initial draft depth threshold;

[0163] Based on the static structural data Md of the underway ship, combined with the retained freeboard height of the underway ship and the initial draft of the underway ship, the final draft of the underway ship D is calculated. 船舶 ;

[0164] ;

[0165] Calculating the confidence level of the final draft of the ship under navigation, and retaining the final draft of the ship under navigation that meets the confidence level;

[0166] .

[0167] It can be understood that after obtaining the freeboard height of the ship at sea based on the laser point cloud data, the initial draft of the ship at sea based on the video recognition data, and the ship's draft data based on the ship's static structure data, the confidence of the data and the correlation between the freeboard height, draft depth and draft data can be obtained according to different acquisition methods to accurately calculate the current ship's draft.

[0168] In summary, the method for detecting the draft of a ship at sea in the above-mentioned embodiment of the present invention, by using laser point cloud data and image data, respectively calculates the freeboard height and draft of the ship, and obtains the static structure data of the ship based on the identity of the ship, and calculates the final draft of the ship at sea through an association algorithm, can make the calculation result more accurate. At the same time, the corresponding confidence level is calculated at each step, making the judgment result more reliable, overcoming the shortcomings of a single sensing method in a complex environment of the waterway site, and the problem that factors such as water surface fluctuations and difficulty in identifying the waterline affect the accuracy of draft detection.

[0169] Please refer to Figure 2 , shown is a system for detecting the draft depth of a ship underway in a second embodiment of the present invention, comprising:

[0170] The first acquisition module 11 is used to acquire laser point cloud data and image data of the ship underway;

[0171] The first acquisition module 11 is specifically used to: set up a laser scanning sensor, a panoramic video surveillance camera and a detail capture surveillance camera on the shore of the channel of the ship at sea;

[0172] Wherein, the laser scanning sensor, the panoramic video surveillance camera and the detail snapshot surveillance camera all face the waterway, and the laser scanning sensor is electrically connected to the panoramic video surveillance camera and the detail snapshot surveillance camera;

[0173] The laser scanning sensor continuously scans the water space of the waterway, obtains laser point cloud data of the ship at sea when the ship at sea passes by, and sends a shooting signal to the panoramic video surveillance camera and the detail capture surveillance camera;

[0174] After receiving the shooting signal, the panoramic video surveillance camera and the detail snapshot surveillance camera respectively shoot a full ship image of the ship at sea and a detailed image of the side of the ship at sea;

[0175] Selection module 12: used for extracting multiple instant feature surfaces of the ship underway based on the laser point cloud data of the ship underway, traversing and comparing the multiple instant feature surfaces with typical feature surfaces of various typical ship types in the historical database, and selecting a typical ship type similar to the ship underway;

[0176] The separation module 13 is used to mark the side parts of the instant characteristic surface of the ship under navigation according to the side parts on the typical characteristic surface of the typical ship type, and separate the side parts point cloud set of the instant characteristic surface;

[0177] The first calculation module 14 is used to calculate the bow freeboard height, the middle freeboard height and the stern freeboard height at the side of the ship underway based on the side point cloud set to obtain the freeboard height of the ship underway, and calculate the confidence of the freeboard height of the ship underway;

[0178] The first calculation module 14 is specifically used to: divide the side part point cloud set into side bow point cloud data, side middle part point cloud data and side stern part point cloud data according to the position of the side surface;

[0179] Calculating the bow freeboard height based on the bow point cloud data;

[0180] L 首 =T 首 -B 首 ;

[0181] Among them, L 首 Indicates the bow freeboard height, T 首 represents the average value of the point cloud height coordinates at the top of the bow, B 首 Indicates the average value of the point cloud height coordinates at the bottom of the bow;

[0182] Calculating the middle freeboard height based on the side middle point cloud data;

[0183] L 中 =T 中 -B 中 ;

[0184] Among them, L 中 Indicates the mid-section freeboard height, T 中 represents the average value of the point cloud height coordinates at the top of the middle part of the side, B 中 It represents the average value of the point cloud height coordinates at the bottom of the middle part of the side;

[0185] Calculating the stern freeboard height based on the side stern point cloud data;

[0186] L 尾 =T 尾 -B 尾 ;

[0187] Among them, L 尾 Indicates the aft freeboard height, T 尾 represents the average value of the point cloud height coordinates at the top of the side tail, B 尾 It represents the average value of the point cloud height coordinates at the bottom of the side stern;

[0188] Take the average of the bow freeboard height, the middle freeboard height and the stern freeboard height as the freeboard height L of the ship underway. 点云 ;

[0189] ;

[0190] The confidence level Conf of the freeboard height of the ship underway is calculated based on the feature value of the side point cloud set. 点云 ;

[0191] ;

[0192] Among them, k1 is the confidence adjustment factor of the effective point cloud, k2 is the confidence adjustment factor of the noise point, N1 is the number of effective point clouds at the side, N2 is the number of noise points at the side, and N0 is the number of all point clouds in the side processing theory;

[0193] The second calculation module 15 is used to identify the waterline of the side of the ship under navigation based on the image data of the ship under navigation, so as to calculate the bow draft, the midship draft, the stern draft, and the corresponding confidence, and then obtain the initial draft of the ship under navigation;

[0194] The second calculation module 15 is specifically used to: input the image data of the ship underway into a pre-trained image recognition model to identify the waterline of the side of the ship underway;

[0195] The image recognition model is used to output the bow draft, midship draft, stern draft and corresponding confidence levels to obtain the initial draft of the ship underway. 图像 ;

[0196] ;

[0197] Among them, D 首 Indicates the bow draft depth, Conf 首 Indicates the confidence level of bow draft, D 中 Indicates the draft depth among ships, Conf 中 Indicates the confidence level of the midship draft, D 尾 Indicates the stern draft depth, Conf 尾 Indicates the confidence level of the stern draft;

[0198] Calculate the confidence level Conf of the initial draft of the ship underway 图像 ;

[0199] ;

[0200] The second acquisition module 16 is used to acquire static structural data of a specific ship type consistent with the ship underway or a similar ship type close to the ship underway from the ship characteristic database, so as to serve as the static structural data of the ship underway;

[0201] The second acquisition module 16 is specifically used to: set up an AIS receiver on the shore of the channel of the ship at sea;

[0202] S1, continuously receiving the AIS signal broadcasted by the ship at sea through the AIS receiver, and parsing the identity information of the ship at sea;

[0203] S2, simultaneously obtaining the name of the first ship through the detail capture monitoring camera, and performing video recognition to obtain the identity information of the ship underway;

[0204] If the identity information of the ship underway is successfully obtained in steps S1 and S2, the corresponding specific ship type that matches is searched in the ship feature database, and the static structure data of the specific ship type is used as the static structure data Md of the ship underway;

[0205] If the identity information of the ship underway cannot be obtained in steps S1 and S2, the full ship image of the ship underway is captured by the panoramic video surveillance camera, a similar ship type is matched from the ship feature database, and the static structure data of the similar ship type is referenced as the static structure data Md of the ship underway;

[0206] The third calculation module 17 is used to calculate the final draft of the ship underway through a correlation algorithm based on the freeboard height data and the initial draft data that meet the confidence requirements;

[0207] The third calculation module 17 is specifically used to: preset a freeboard height confidence threshold, and retain the freeboard height of the ship underway that is higher than the freeboard height confidence threshold;

[0208] Preset an initial draft depth threshold, and retain the initial draft depth of the ship underway that is higher than the initial draft depth threshold;

[0209] Based on the static structural data Md of the underway ship, combined with the retained freeboard height of the underway ship and the initial draft of the underway ship, the final draft of the underway ship D is calculated. 船舶 ;

[0210] ;

[0211] Calculating the confidence level of the final draft of the ship under navigation, and retaining the final draft of the ship under navigation that meets the confidence level;

[0212] .

[0213] The present invention also provides an electronic device, see Figure 3, shown is an electronic device in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned method for detecting the draft depth of a ship at sea is implemented.

[0214] Among them, the memory 10 includes at least one type of storage medium, and the storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 10 can be an internal storage unit of an electronic device, such as a hard disk of the electronic device. In other embodiments, the memory 10 can also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Further, the memory 10 can also include both an internal storage unit of the electronic device and an external storage device. The memory 10 can not only be used to store application software and various types of data installed in the electronic device, but also can be used to temporarily store data that has been output or is to be output.

[0215] Among them, in some embodiments, the processor 20 can be an electronic control unit (Electronic Control Unit, abbreviated as ECU, also known as a vehicle computer), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run the program code stored in the memory 10 or process data, such as executing access restriction programs, etc.

[0216] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than those shown in the figure, or combine certain components, or arrange the components differently.

[0217] The embodiment of the present invention further provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for detecting the draft depth of a ship underway as described above is implemented.

[0218] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0219] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0220] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0221] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", 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 present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0222] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for detecting the draft depth of a ship underway, characterized in that: The steps include: Obtain laser point cloud data and image data of ships at sea; Based on the laser point cloud data of the ship underway, a plurality of instant feature surfaces of the ship underway are extracted, and the plurality of instant feature surfaces are traversed and compared with typical feature surfaces of various typical ship types in a historical database to select a typical ship type similar to the ship underway; According to the side parts on the typical characteristic surface of the typical ship type, the side parts of the instant characteristic surface of the ship at sea are marked, and a point cloud set of the side parts of the instant characteristic surface is separated; Based on the side point cloud set, the bow freeboard height, the middle freeboard height and the stern freeboard height at the side of the ship underway are calculated to obtain the freeboard height of the ship underway, and the confidence of the freeboard height of the ship underway is calculated; Based on the image data of the ship underway, the waterline at the side of the ship underway is identified to calculate the bow draft, the midship draft, the stern draft, and the corresponding confidence levels, thereby obtaining the initial draft of the ship underway; Obtaining static structural data of a specific ship type consistent with the ship underway or a similar ship type close to the ship underway from a ship characteristic database as the static structural data of the ship underway; Based on the freeboard height data and the initial draft depth data with confidence levels meeting the requirements, the final draft depth of the vessel underway is calculated by a correlation algorithm; The method of calculating the final draft of the ship underway by a correlation algorithm based on the freeboard height data and the initial draft data that meet the confidence requirements specifically includes: A freeboard height confidence threshold is preset, and the freeboard height of the ship underway that is higher than the freeboard height confidence threshold is retained; Preset an initial draft depth threshold, and retain the initial draft depth of the ship underway that is higher than the initial draft depth threshold; Based on the static structural data of the underway ship, combined with the retained freeboard height of the underway ship and the initial draft of the underway ship, the final draft of the underway ship D is calculated. 船舶 ; ； Where Md represents the static structural data of the ship underway, L 点云 Indicates the freeboard height of the ship underway, Conf 点云 The confidence level of the freeboard height of a ship underway, D 图像 Indicates the initial draft of the ship underway, Conf 图像 Indicates the confidence level of the initial draft of the ship underway; Calculating the confidence level of the final draft of the ship under navigation, and retaining the final draft of the ship under navigation that meets the confidence level; 。 2. The method for detecting the draft depth of a ship underway according to claim 1, characterized in that: The obtaining of laser point cloud data and image data of the ship underway specifically includes: Setting up laser scanning sensors, panoramic video surveillance cameras and detail capture surveillance cameras on the shore of the channel of the ship at sea; Wherein, the laser scanning sensor, the panoramic video surveillance camera and the detail snapshot surveillance camera all face the waterway, and the laser scanning sensor is electrically connected to the panoramic video surveillance camera and the detail snapshot surveillance camera; The laser scanning sensor continuously scans the water space of the waterway, obtains laser point cloud data of the ship at sea when the ship at sea passes by, and sends a shooting signal to the panoramic video surveillance camera and the detail capture surveillance camera; After receiving the shooting signal, the panoramic video monitoring camera and the detail snapshot monitoring camera respectively shoot the full ship image of the ship at sea and the detailed image of the side of the ship at sea.

3. The method for detecting the draft depth of a ship underway according to claim 2, characterized in that: The step of calculating the bow freeboard height, the middle freeboard height and the stern freeboard height at the side of the ship under way based on the side point cloud set to obtain the freeboard height of the ship under way, and calculating the confidence of the freeboard height of the ship under way, specifically includes: The side part point cloud set is divided into side bow point cloud data, side middle point cloud data and side stern point cloud data according to the position of the side surface; Calculating the bow freeboard height based on the bow point cloud data; L 首 =T 首 -B 首 ; Among them, L 首 Indicates the bow freeboard height, T 首 represents the average value of the point cloud height coordinates at the top of the bow, B 首 Indicates the average value of the point cloud height coordinates at the bottom of the bow; Calculating the middle freeboard height based on the side middle point cloud data; L 中 =T 中 -B 中 ; Among them, L 中 Indicates the mid-section freeboard height, T 中 represents the average value of the point cloud height coordinates at the top of the middle part of the side, B 中 It represents the average value of the point cloud height coordinates at the bottom of the middle part of the side; Calculating the stern freeboard height based on the side stern point cloud data; L 尾 =T 尾 -B 尾 ; Among them, L 尾 Indicates the aft freeboard height, T 尾 represents the average value of the point cloud height coordinates at the top of the side tail, B 尾 It represents the average value of the point cloud height coordinates at the bottom of the side stern; Take the average of the bow freeboard height, the middle freeboard height and the stern freeboard height as the freeboard height L of the ship underway. 点云 ; ； The confidence level Conf of the freeboard height of the ship underway is calculated based on the feature value of the side point cloud set. 点云 ; ； Among them, k1 is the confidence adjustment factor of the valid point cloud, k2 is the confidence adjustment factor of the noise point, N1 is the number of valid point clouds at the side, N2 is the number of noise points at the side, and N0 is the total number of point clouds in the side processing theory.

4. The method for detecting the draft depth of a ship underway according to claim 3, characterized in that: The method of identifying the waterline of the side of the ship under navigation based on the image data of the ship under navigation to calculate the bow draft, the midship draft, the stern draft, and the corresponding confidence levels, and then obtaining the initial draft of the ship under navigation, specifically includes: Inputting the image data of the ship underway into a pre-trained image recognition model to identify the waterline of the side of the ship underway; The image recognition model is used to output the bow draft, midship draft, stern draft and corresponding confidence levels to obtain the initial draft of the ship underway. 图像 ; ； Among them, D 首 Indicates the bow draft depth, Conf 首 Indicates the confidence level of bow draft, D 中 Indicates the draft depth among ships, Conf 中 Indicates the confidence level of the midship draft, D 尾 Indicates the stern draft depth, Conf 尾 Indicates the confidence level of the stern draft; Calculate the confidence level Conf of the initial draft of the ship underway 图像 ; 。 5. The method for detecting the draft depth of a ship underway according to claim 4, characterized in that: The acquiring of static structural data of a specific ship type consistent with the ship at sea or a similar ship type close to the ship at sea from the ship characteristic database as the static structural data of the ship at sea specifically includes: Setting up an AIS receiver on the shore of the channel of the ship underway; S1, continuously receiving the AIS signal broadcasted by the ship at sea through the AIS receiver, and parsing the identity information of the ship at sea; S2, simultaneously obtaining the name of the first ship through the detail capture monitoring camera, and performing video recognition to obtain the identity information of the ship underway; If the identity information of the ship underway is successfully obtained in steps S1 and S2, the corresponding specific ship type that matches is searched in the ship feature database, and the static structure data of the specific ship type is used as the static structure data Md of the ship underway; If the steps S1 and S2 fail to obtain the identity information of the ship at sea, the panoramic video surveillance camera is used to capture the entire ship image of the ship at sea, similar ship types are matched from the ship feature database, and the static structure data of the similar ship types are referenced as the static structure data Md of the ship at sea.

6. A system for detecting the draft depth of a ship underway, characterized in that: include: The first acquisition module is used to acquire laser point cloud data and image data of the ship underway; A selection module is used to extract multiple instant feature surfaces of the ship underway based on the laser point cloud data of the ship underway, traverse and compare the multiple instant feature surfaces with typical feature surfaces of various typical ship types in the historical database, and select a typical ship type similar to the ship underway; Separation module: used for marking the side parts of the instant characteristic surface of the ship under navigation according to the side parts on the typical characteristic surface of the typical ship type, and separating the side parts point cloud set of the instant characteristic surface; A first calculation module: used for calculating the bow freeboard height, the middle freeboard height and the stern freeboard height at the side of the ship underway based on the side point cloud set, so as to obtain the freeboard height of the ship underway, and calculating the confidence of the freeboard height of the ship underway; A second calculation module is used to identify the waterline of the side of the ship under navigation based on the image data of the ship under navigation, so as to calculate the bow draft, the midship draft, the stern draft, and the corresponding confidence, and then obtain the initial draft of the ship under navigation; The second acquisition module is used to acquire static structural data of a specific ship type consistent with the ship at sea or a similar ship type close to the ship at sea from the ship characteristic database, so as to serve as the static structural data of the ship at sea; The third calculation module is used to calculate the final draft of the ship underway through a correlation algorithm based on the freeboard height data and the initial draft data that meet the confidence requirements; The third calculation module is specifically used for: A freeboard height confidence threshold is preset, and the freeboard height of the ship underway that is higher than the freeboard height confidence threshold is retained; Preset an initial draft depth threshold, and retain the initial draft depth of the ship underway that is higher than the initial draft depth threshold; Based on the static structural data of the underway ship, combined with the retained freeboard height of the underway ship and the initial draft of the underway ship, the final draft of the underway ship D is calculated. 船舶 ; ； Where Md represents the static structural data of the ship underway, L 点云 Indicates the freeboard height of the ship underway, Conf 点云 The confidence level of the freeboard height of a ship underway, D 图像 Indicates the initial draft of the ship underway, Conf 图像 Indicates the confidence level of the initial draft of the ship underway; Calculating the confidence level of the final draft of the ship under navigation, and retaining the final draft of the ship under navigation that meets the confidence level; 。 7. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting the draft depth of a ship underway as described in any one of claims 1 to 5 is implemented.

8. 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 computer program, the method for detecting the draft depth of a ship underway as described in any one of claims 1 to 5 is implemented.

Images