Ship type detection method, device, electronic device and readable storage medium

Abstract

This application discloses a ship type detection method, device, electronic device, and readable storage medium, relating to the field of image processing technology. The ship type detection method comprises: obtaining a ship area image of the area where the monitored ship is located; and based on the ship area image, performing ship type detection on the monitored ship to obtain a ship type detection result. The ship type includes at least one of a modified ship, an overloaded ship, or an unsealed ship. This application solves the technical problem of low comprehensiveness of ship supervision in the existing technology.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a ship type detection method, device, electronic device and readable storage medium. Background Art

[0002] With the development of the water transport industry, how to supervise ships has become increasingly important. Currently, ship supervision mainly relies on AIS (Automatic Identification System) and radar data. However, the ship supervision method relying on AIS and radar data can usually only supervise the ship's trajectory, but it is difficult to supervise ship anomalies outside the ship's trajectory, such as overloading or unsealed ships, which leads to incomplete ship supervision. Summary of the Invention

[0003] The main purpose of this application is to provide a ship type detection method, device, electronic device and readable storage medium, aiming to solve the technical problem of low comprehensiveness of ship supervision in the existing technology.

[0004] To achieve the above objectives, the present application provides a ship type detection method, which includes:

[0005] Acquire a ship area image of the area where the ship to be monitored is located;

[0006] Based on the ship area image, the ship to be monitored is subjected to ship type detection to obtain a ship type detection result, wherein the ship type includes at least one of a modified hull, an overloaded ship, or an unsealed ship.

[0007] The present application also provides a ship type detection device, which is applied to a ship type detection device, and includes:

[0008] An image acquisition module is used to acquire an image of a ship area where the ship to be monitored is located;

[0009] The ship type detection module is used to detect the ship type of the ship to be monitored based on the ship area image to obtain a ship type detection result, where the ship type includes at least one of: a modified hull, an overloaded ship, or an unsealed ship.

[0010] The present application also provides an electronic device, which is a physical device, and includes: a memory, a processor, and a program of the ship type detection method stored in the memory and runnable on the processor. When the program of the ship type detection method is executed by the processor, the steps of the ship type detection method as described above can be implemented.

[0011] The present application also provides a computer-readable storage medium, on which is stored a program for implementing the ship type detection method. When the program of the ship type detection method is executed by a processor, the steps of the ship type detection method as described above are implemented.

[0012] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned ship type detection method when executed by a processor.

[0013] The present application provides a ship type detection method, device, electronic device and readable storage medium. Compared with the technical means used in the prior art for ship supervision that relies on AIS and radar data, the present application first obtains a ship area image of the area where the ship to be monitored is located; based on the ship area image, the ship to be monitored is detected as a ship type to obtain a ship type detection result, and the ship type includes at least one of a modified hull, an overloaded ship or an unsealed ship. The present application can supervise ships from three aspects: ship modification, ship overloading and ship unsealed, rather than being limited to supervising the ship's trajectory. This overcomes the technical defect of the prior art ship supervision method that relies on AIS and radar data, which usually can only supervise the ship's trajectory, but is difficult to supervise other ship anomalies outside the ship's trajectory, thereby resulting in incomplete ship supervision, and improves the comprehensiveness of ship supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 This is a flow chart of the first embodiment of the ship type detection method of the present application;

[0017] Figure 2 This is a schematic diagram of the framework of the ship type detection system in the ship type detection method of this application;

[0018] Figure 3 This is a flow chart of the second embodiment of the ship type detection method of the present application;

[0019] Figure 4 This is a flow chart of the third embodiment of the ship type detection method of the present application;

[0020] Figure 5 This is a flow chart of a fourth embodiment of the ship type detection method of the present application;

[0021] Figure 6 Schematic diagram of the equipment structure of the hardware operating environment involved in the ship type detection method in the embodiment of the present application.

[0022] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0023] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0024] At present, when conducting ship supervision, we mainly rely on AIS and radar data to locate the ship's trajectory information, and then determine whether there are any abnormalities in the ship's trajectory. However, some ship abnormalities other than trajectory abnormalities are usually not supervised, such as ship modification and ship overloading. Therefore, the current ship supervision method is relatively simple and ship supervision is not comprehensive enough.

[0025] The present application provides a method for detecting the type of ship. In the first embodiment of the method for detecting the type of ship, refer to Figure 1 , the ship type detection method includes:

[0026] Step S10, obtaining a ship area image of the area where the ship to be monitored is located;

[0027] Step S20: performing ship type detection on the ship to be monitored based on the ship area image to obtain a ship type detection result, wherein the ship type includes at least one of a modified ship, an overloaded ship, or an unsealed ship.

[0028] After acquiring an image of the area where the ship to be monitored is located, the embodiment of the present application performs ship type detection on the ship to be monitored through image recognition, obtaining a ship type detection result. The ship type includes at least one of a modified ship, an overloaded ship, or an unsealed ship. This achieves the purpose of detecting ship anomalies through image recognition. Since image data contains richer information than AIS and radar data, the image data can reflect the vast majority of ship anomalies, such as ship modifications and overloading. Therefore, ship type detection through image recognition can cover a more comprehensive range of ship anomalies. This overcomes the technical defect of the existing ship monitoring method that relies on AIS and radar data, which usually can only monitor the ship's trajectory and has difficulty monitoring other ship anomalies outside the ship's trajectory, thereby resulting in incomplete ship monitoring. This improves the comprehensiveness of ship monitoring.

[0029] Regarding step S10, it should be noted that, for example, the vessel area image is a surveillance image of the area where the vessel is located, including an image of the vessel itself and an image of the vessel's surroundings, wherein the vessel's surroundings may be a water surface or a dock. The vessel area image may be any one of a real-time video frame, a patrol video frame, a timed snapshot image, or an offline image.

[0030] Exemplarily, in step S20, based on the ship area image, ship type detection is performed on the ship to be monitored to obtain a ship type detection result, where the ship type includes at least one of: a modified ship, an overloaded ship, or an unsealed ship, including:

[0031] By inputting the ship area image into a preset ship type detection model, the ship to be monitored is classified to obtain a ship type label, and the ship type label is used as the ship type detection result. Based on the ship area image, the ship to be monitored is subjected to ship type detection to obtain a ship type detection result, wherein the ship type includes at least one of a modified ship, an overloaded ship, or an unsealed ship. The ship type label is an identifier that identifies the ship type to which the ship to be monitored belongs. For example, when the label is set to 1, the ship type to which the ship to be monitored belongs is a hull modification type; when the label is set to 2, the ship type to which the ship to be monitored belongs is a ship overload type; when the label is set to 3, the ship type to which the ship to be monitored belongs is a ship unsealed type. The hull modification type, the ship overload type, and the ship unsealed type can all be considered abnormal ship types. When the label is set to 0, the ship type to which the ship to be monitored belongs is a normal ship type. The preset ship type detection model can be a convolutional neural network model or a decision tree model, which is not limited here.

[0032] As an example, it should be noted that a modified ship is usually modified at some specific locations, such as the stern engine location and the cabin location. In step S20, the ship type includes the hull modification type, and the ship type detection result includes the hull modification detection result, including:

[0033] Target detection is performed on the ship area image to select a preset specific location of the ship to be monitored in the ship area image to obtain each hull modification area image; each hull modification area image is subjected to binary classification to obtain a binary classification label for each hull modification; and the hull modification binary classification label is used as the hull modification detection result. The hull modification binary classification label can be set to 1 to indicate that the portion of the ship to be monitored corresponding to the corresponding hull modification area image has undergone hull modification, and the hull modification binary classification label can be set to 0 to indicate that the portion of the ship to be monitored corresponding to the corresponding hull modification area image has not undergone hull modification.

[0034] As an example, it should be noted that in order to obtain a faster driving speed, most abnormally modified ships will choose to modify the engine, for example, adding multiple engines.

[0035] The ship type includes a hull modification type, and the ship type detection result includes a hull modification detection result.

[0036] Image segmentation is performed on the ship area image to segment an engine area image from the ship area image; the number of engines in the engine area image is identified; if the number of engines is greater than a preset engine number threshold, it is determined that the ship to be monitored has undergone hull modification; if the number of engines is not greater than the preset engine number threshold, it is determined that the ship to be monitored has not undergone hull modification, thereby achieving the purpose of identifying the number of engines of the ship to be monitored by image recognition, and then based on the number of engines of the ship to be monitored, it can be directly determined that the ship type to which the ship to be monitored belongs is a hull modification type.

[0037] As an example, in step S20, the ship type includes a flag-free type, and the ship type detection result includes a flag-hanging detection result.

[0038] The step of performing ship type detection on the ship to be monitored based on the ship area image to obtain a ship type detection result includes:

[0039] Target detection is performed on the ship area image to frame each image area of ​​the hanging objects suspected to be flags in the ship area image to obtain at least one first framed area image; each of the first framed area images is subjected to binary classification to obtain an image binary classification label corresponding to each of the first framed area features; by judging whether there is a flag in the corresponding first framed area image based on each of the image binary classification labels, whether the ship to be monitored is hanging a flag is identified to obtain a flag hanging detection result, thereby achieving the purpose of detecting whether the ship to be monitored is not hanging a flag by image type detection.

[0040] As an example, it should be noted that since a flag may be easily obscured by the ship itself, when it is detected from the image of the ship area that no flag is hoisted, it cannot be determined with absolute certainty that the monitored ship is hoisting a flag. Therefore, after step A10, the following steps are further performed:

[0041] If the flag hoisting detection result is that the flag is not hoisted, the cumulative number of times the monitored vessel is detected as not hoisting a flag is obtained; if the cumulative number exceeds a preset cumulative number threshold, it is determined that the monitored vessel is not hoisting a flag. Since multiple images of the vessel area corresponding to the monitored vessel can be captured by cameras at multiple positions and angles, if the flag hoisting detection results determined based on multiple images of the vessel area are all that the flag is not hoisted, it proves that the monitored vessel is observed as not hoisting a flag at different observation positions at multiple angles, and therefore it can be determined that the monitored vessel is not hoisting a flag.

[0042] As an example, in step S20, the ship type includes the type of crew members not wearing life jackets, and the ship type detection result includes the life jacket wearing detection result.

[0043] The step of performing ship type detection on the ship to be monitored based on the ship area image to obtain a ship type detection result includes:

[0044] The target detection is performed on the ship area image to frame each image area in the ship area image where crew members are suspected to be present, and obtain each second framed area image; crew identification is performed on each second framed area image to determine whether there are crew members in each second framed area image; if there are no crew members in each second framed area image, it is determined that there are no crew members on the ship to be monitored; if there are crew members in each second framed area image, the second framed area image with crew members is determined as the framed area image to be detected; each framed area image to be detected is binary-classified to obtain each crew member's clothing binary classification label; based on each crew member's clothing binary classification label, it is determined whether the crew members in the corresponding framed area image to be detected are wearing life jackets, and the crew member wearing detection result is obtained. Wherein, when the crew member wearing binary classification label is set to 1, it is indicated that the crew members in the framed area image to be detected are wearing life jackets, and when the crew member wearing binary classification label is set to 0, it is indicated that the crew members in the framed area image to be detected are not wearing life jackets, thereby achieving the purpose of detecting whether the crew members on the ship to be monitored are wearing life jackets by image type detection.

[0045] As an example, Figure 2 The framework diagram of the ship type detection system shown is shown, wherein the camera can be an ordinary front-end camera or a front-end AI smart camera, which can be specifically set at a fixed point on the shore (both sides of the waterway, bridges, docks, etc.), or can be set at a mobile point (drone, video equipment on a buoy), etc.; the ordinary front-end camera transmits the video image of the ship to be monitored obtained through the network to the back-end intelligent analysis server, and the back-end intelligent analysis server performs real-time analysis of the video data according to the analysis task, that is, executes the implementation process of steps S10 to S20 and its detailed steps in the embodiment of the present application; if the camera is an AI smart camera at the front end, the front-end AI smart camera directly performs real-time analysis of the video image of the ship to be monitored according to the analysis task, that is, executes the implementation process of steps S10 to S20 and its detailed steps in the embodiment of the present application; finally, the analysis result (ship type detection result) is pushed to the ship dynamic supervision subsystem.

[0046] The embodiment of the present application provides a method for detecting ship types. Compared to the technical means used in the prior art for ship monitoring that relies on AIS and radar data, the embodiment of the present application first obtains a ship area image of the area where the ship to be monitored is located; based on the ship area image, the ship to be monitored is detected as a ship type to obtain a ship type detection result, wherein the ship type includes at least one of: hull modification type, ship overload type, or ship unsealed type. In the embodiment of the present application, a ship can be monitored from up to three aspects: ship modification, ship overload, and ship unsealed type, rather than being limited to monitoring the ship's trajectory. This overcomes the technical defect of the prior art ship monitoring method that relies on AIS and radar data, which usually can only monitor the ship's trajectory and is difficult to monitor other ship anomalies outside the ship's trajectory, thereby resulting in incomplete ship monitoring, and improves the comprehensiveness of ship monitoring.

[0047] Reference Figure 3 Based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated hereafter. On this basis, step S20, detecting the type of the ship to be monitored based on the ship area image, includes:

[0048] Step A10, identifying the stern wave characteristics of the ship to be monitored in the ship area image;

[0049] Step A20: judging whether the ship to be monitored has undergone hull modification based on the stern wave characteristics.

[0050] In this embodiment, it should be noted that when the ambient light is poor and the monitored vessel is in motion, if the image of the hull itself is not prominent in the vessel area image, the recognition accuracy will be low if the hull modification identification is performed directly on the hull itself. The preset ship type detection model includes a stern wave feature extractor and a stern wave feature classifier. The stern wave feature extractor is used to extract stern wave features from the vessel area image, and the stern wave feature classifier is used to map the stern wave features to corresponding stern wave classification labels.

[0051] Exemplarily, target detection is performed on the ship area image to select the stern water wave area in the ship area image to obtain the stern water wave area image; the stern water wave area image is input into a stern water wave feature extractor, and feature extraction is performed on the stern water wave area image to obtain stern water wave features, wherein the stern water wave features can be a feature extraction matrix obtained by feature extraction of the stern water wave area image, and the numerical distribution in the feature extraction matrix corresponding to stern water waves with different shapes or appearances is different; the stern water wave features are input into a stern water wave feature classifier, and the stern water wave features are mapped into a stern water wave classification label. Based on the stern water wave classification label, it is determined whether the ship to be monitored has undergone hull modification. If the ship to be monitored has undergone hull modification, the ship type to which the ship to be monitored belongs is a hull modification type. If the ship to be monitored has not undergone hull modification, the ship type to which the ship to be monitored belongs is not a hull modification type.

[0052] Wherein, step A20, judging whether the ship to be monitored has undergone hull modification based on the stern wave characteristics, further includes:

[0053] Step A21, judging whether the ship to be monitored is suspected of undergoing hull modification based on the stern wave characteristics;

[0054] Step A22: if it is determined that the ship to be monitored is suspected of undergoing hull modification, obtaining radar data of the ship to be monitored;

[0055] Step A23: measuring the speed of the ship to be monitored based on the radar data;

[0056] Step A24: determining whether the ship to be monitored has undergone hull modification based on the travel speed.

[0057] Exemplarily, the stern water wave feature is input into a stern water wave feature classifier, and the stern water wave feature is mapped into a stern water wave classification label. Based on the stern water wave classification label, it is determined whether the ship to be monitored is suspected of undergoing hull modification. If the ship to be monitored is suspected of undergoing hull modification, radar data of the ship to be monitored is obtained, wherein the radar data records the driving trajectory data of the ship to be monitored that changes with time; based on the radar data, the driving speed of the ship to be monitored is measured. If the driving speed is greater than a preset driving speed threshold, it is determined that the ship to be monitored has undergone hull modification, and the ship type of the ship to be monitored is a hull modification type; if the driving speed is not greater than the preset driving speed threshold, it is determined that the ship to be monitored has not undergone hull modification, and the ship type of the ship to be monitored is not a hull modification type. The embodiment of the present application realizes that on the basis of hull modification detection based on the stern water wave characteristics of the ship to be monitored, radar data is further used to determine whether the ship to be monitored has been modified. This achieves the purpose of accurately judging whether the ship to be monitored has been modified when the hull characteristics of the ship to be monitored itself are not obvious, thereby improving the accuracy of ship modification detection.

[0058] As an example, it should be noted that since the task ship performing patrol tasks usually travels at a faster speed, in order to avoid misjudging the task ship as a ship that has undergone hull modification, when the first ship category identification result is that the ship to be monitored is determined to be a modified ship, communication with the ship to be monitored can be carried out through AIS to further determine whether the ship to be monitored is a task ship. If it is determined that the ship to be monitored is not a task ship, the ship to be monitored is determined to be a ship that has undergone hull modification.

[0059] The embodiment of the present application provides a method for detecting hull modifications based on stern water wave characteristics. The embodiment of the present application first identifies the stern water wave characteristics of the ship to be monitored in the ship area image, and then determines whether the ship to be monitored has undergone hull modifications based on the stern water wave characteristics. When the hull characteristics of the ship to be monitored itself are not significant, it is difficult to directly perform hull modification detection based on the hull characteristics of the ship to be monitored itself. However, since the image area occupied by the stern water waves in the ship area image is much larger than the image area occupied by the hull, the stern water waves are more significant in the image than the hull. Therefore, hull modification detection can be indirectly performed based on the stern water wave characteristics. That is, based on the stern water wave characteristics, it is indirectly determined whether the ship type to be monitored is a hull modification type. When the hull characteristics of the ship to be monitored itself are not significant, the accuracy of hull modification detection can be improved.

[0060] Reference Figure 4Based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be described in detail. On this basis, step S20, the ship type detection of the ship to be monitored based on the ship area image, also includes:

[0061] Step B10, identifying the distance between the ship plane of the ship to be monitored and the horizontal plane in the ship area image to obtain a load determination distance;

[0062] In this embodiment, it should be noted that the load determination distance is a distance used to determine the load of the ship to be monitored, and can be the actual distance between the ship plane and the horizontal plane, or can be an estimated value for determining the ship load.

[0063] Exemplarily, the ship area image is segmented to obtain a ship plane area image and a horizontal plane area image; based on the coordinate values ​​of each pixel point in the ship plane area and the coordinate values ​​of each pixel point in the horizontal plane area image, the distance between the ship plane of the ship to be monitored and the horizontal plane in the ship area image is calculated to obtain the image plane distance; the image scale is obtained, and the load discrimination distance is calculated based on the image plane distance and the image scale. The image scale is the ratio between the image and the actual object.

[0064] The step of identifying the distance between the ship plane of the ship to be monitored and the horizontal plane in the ship area image to obtain the load determination distance includes:

[0065] Step B11, identifying the ship plane outline and the horizontal plane outline in the ship area image;

[0066] Step B12, calculating the outline distance between the ship plane outline and the horizontal plane outline, and obtaining the ship size of the ship to be monitored in the ship area image;

[0067] Step B13: Calculate the ratio between the contour spacing and the ship size to obtain the load determination distance.

[0068] For example, image recognition is performed on the ship area image to obtain the ship's planar outline and horizontal plane outline. The shortest distance between the ship's planar outline and the horizontal plane outline is calculated as the outline spacing, and the vertical dimension of the monitored ship in the ship area image is obtained to obtain the ship's size. The ratio between the outline spacing and the ship's size is calculated to obtain the load discrimination distance. Alternatively, the area of ​​the monitored ship in the ship area image can be used as the ship's size.

[0069] Step B20: judging whether the ship to be monitored is overloaded based on the load determination distance.

[0070] In this embodiment, exemplarily, the maximum load discrimination distance threshold of the ship to be monitored is determined; if the load discrimination distance is greater than the maximum load discrimination distance threshold, it is determined that the ship to be monitored is overloaded, and the ship type to which the ship to be monitored belongs is a ship overload type; if the load discrimination distance is not greater than the maximum load discrimination distance threshold, it is determined that the ship to be monitored is not overloaded, and the ship type to which the ship to be monitored belongs is not a ship overload type.

[0071] As an example, the step of determining the maximum load determination distance threshold of the ship to be monitored includes:

[0072] Based on the vessel area image, a normal ship category detection is performed on the vessel to be monitored to identify the normal ship category to which the vessel to be monitored belongs, where the normal ship category includes a mission ship category or a transport ship category. Based on a mapping relationship between normal ship categories and preset load discrimination distances, the preset load discrimination distance corresponding to the vessel to be monitored is queried, and the preset load discrimination distance corresponding to the vessel to be monitored is used as the maximum load discrimination distance threshold.

[0073] In another implementable manner, if the load determination distance is within the load determination distance range, it is determined that the ship to be monitored is lightly loaded, and the ship type to which the ship to be monitored belongs is a lightly loaded ship type; if the load determination distance is greater than the upper threshold value of the maximum load determination distance range, it is determined that the ship to be monitored is heavily loaded, and the ship type to which the ship to be monitored belongs is a heavy loaded ship type; if the load determination distance is less than the lower threshold value of the maximum load determination distance range, it is determined that the ship to be monitored is unloaded, and the ship type to which the ship to be monitored belongs is an unloaded ship type.

[0074] An embodiment of the present application provides a method for detecting the load level of a ship. The embodiment of the present application first identifies the distance between the ship plane of the ship to be monitored and the horizontal plane in the ship area image to obtain the load judgment distance. Based on the load judgment distance, it is judged whether the ship to be monitored is overloaded, thereby achieving the purpose of detecting the load level of the ship to be monitored by image recognition, that is, achieving the purpose of accurately and quantitatively detecting the load level of the ship to be monitored, and can quantitatively judge whether the ship type to which the ship to be monitored belongs is a ship overload type, thereby improving the comprehensiveness of ship type detection.

[0075] Reference Figure 5Based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated hereafter. On this basis, the ship type detection result includes the ship cabin sealing detection result. Step S20, based on the ship area image, performs ship type detection on the ship to be monitored, and further includes:

[0076] Step C10, acquiring a cabin area image in the ship area image;

[0077] Step C20 , determining whether the cabin of the ship to be monitored is not sealed by performing image classification on the cabin area image.

[0078] In this embodiment, it should be noted that the preset ship type detection model includes a cabin area image classification model, which is used to perform binary classification on the cabin area image to determine whether the ship to be monitored has an unsealed cabin.

[0079] Exemplarily, image segmentation is performed on the ship area to obtain a cabin area image; the cabin area image is input into a cabin area image classification model to perform binary classification on the cabin area image to obtain a binary classification label; based on the binary classification label, it is determined whether the ship to be monitored is sealed; if the ship to be monitored is not sealed, the ship type to which the ship to be monitored belongs is a ship with unsealed cabin type; if the ship to be monitored is sealed, the ship type to which the ship to be monitored belongs is not a ship with unsealed cabin type.

[0080] As an example, the binary label can be set to 0 and 1, where if the binary label is 0, it proves that the ship to be monitored is not sealed, and if the binary label is 1, it proves that the ship to be monitored is sealed or the ship to be monitored is in an empty state.

[0081] It should be noted that in the embodiment of the present application, a series of acquired ship area image samples can be labeled in advance, and the series of ship area image samples and the corresponding labeled image sample labels can be used to construct an image classification model or an image binary classification model for ship category recognition and ship type detection.

[0082] The present embodiment provides a method for detecting sealed hatches on a ship. The method first obtains a cabin area image from a ship area image, and then classifies the cabin area image to determine whether the monitored ship has unsealed hatches. This method accurately identifies whether the monitored ship has sealed hatches through image recognition, and accurately determines whether the monitored ship belongs to an unsealed type, thereby improving the comprehensiveness of ship type detection.

[0083] The present application also provides a ship type detection device, which is applied to a ship type detection device. The ship type detection device includes:

[0084] An image acquisition module is used to acquire an image of a ship area where the ship to be monitored is located;

[0085] The ship type detection module is used to detect the ship type of the ship to be monitored based on the ship area image to obtain a ship type detection result, where the ship type includes at least one of: a modified ship, an overloaded ship or an unsealed ship.

[0086] Optionally, the ship type detection module includes:

[0087] an identification unit, configured to identify the stern wave characteristics of the ship to be monitored in the ship area image;

[0088] The hull modification detection unit is used to determine whether the hull modification of the ship to be monitored has been carried out based on the stern wave characteristics.

[0089] Optionally, the hull modification detection unit includes:

[0090] a judgment subunit, configured to judge whether the monitored ship is suspected of undergoing hull modification based on the stern wave characteristics;

[0091] a radar data acquisition subunit, configured to acquire radar data of the ship to be monitored if it is determined that the ship to be monitored is suspected of undergoing hull modification;

[0092] A speed measurement subunit, configured to measure the speed of the ship to be monitored based on the radar data;

[0093] The determination subunit is used to determine whether the ship to be monitored has undergone hull modification based on the travel speed.

[0094] Optionally, the ship type detection module further includes:

[0095] a load determination distance acquisition unit, configured to identify the distance between the ship plane of the ship to be monitored and the horizontal plane in the ship area image, and obtain the load determination distance;

[0096] The ship overload detection unit is used to determine whether the ship to be monitored is overloaded based on the load determination distance.

[0097] Optionally, the load determination distance acquisition unit includes:

[0098] a contour recognition subunit, configured to recognize a ship plane contour and a horizontal plane contour in the ship area image;

[0099] A first calculation subunit is configured to calculate a distance between the ship plane contour and the horizontal plane contour, and obtain a size of the ship to be monitored in the ship area image;

[0100] The second calculation subunit is used to calculate the ratio between the outline spacing and the ship size to obtain the load determination distance.

[0101] Optionally, the ship type detection module further includes:

[0102] a cabin image acquisition unit, configured to acquire a cabin area image from the ship area image;

[0103] The ship unsealed cabin detection unit is used to determine whether the ship to be monitored has an unsealed cabin by performing image classification on the cabin area image.

[0104] The ship type detection device provided by the present invention utilizes the ship type detection method described in the aforementioned embodiment, addressing the technical issue of inadequate ship supervision. Compared to the prior art, the ship type detection device provided by the present invention achieves the same beneficial effects as the ship type detection method described in the aforementioned embodiment. Other technical features of the device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0105] An embodiment of the present invention provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the ship type detection method in the above-mentioned embodiment 1.

[0106] Reference below Figure 6 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0107] like Figure 6As shown, the electronic device may include a processing device (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0108] Typically, the following systems can be connected to the I / O interface: input devices such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices such as a magnetic tape, hard disk, etc.; and communication devices. The communication device can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figures show electronic devices with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have instead.

[0109] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0110] The electronic device provided by the present invention utilizes the ship type detection method described in the above-mentioned embodiment to address the technical issue of inadequate ship supervision. Compared to the prior art, the electronic device provided by the present invention achieves the same beneficial effects as the ship type detection method described in the above-mentioned embodiment. Other technical features of the electronic device are the same as those disclosed in the above-mentioned embodiment and are not further elaborated here.

[0111] It should be understood that various parts of the present disclosure can be implemented with hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in an appropriate manner.

[0112] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0113] This embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon, and the computer-readable program instructions are used to execute the ship type detection method in the above-mentioned embodiment 1.

[0114] The computer-readable storage medium provided in the embodiment of the present invention can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0115] The computer-readable storage medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0116] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device: obtains a ship area image of the area where the ship to be monitored is located; performs ship type detection on the ship to be monitored based on the ship area image, and obtains a ship type detection result, wherein the ship type includes: at least one of a hull modification type, a ship overloaded type, or a ship unsealed type.

[0117] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0118] The flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0119] The modules involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0120] The computer-readable storage medium provided by the present invention stores computer-readable program instructions for executing the aforementioned ship type detection method, thereby resolving the technical issue of insufficiently comprehensive ship supervision. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided by the embodiments of the present invention are similar to those of the ship type detection method provided by the aforementioned embodiments, and are not further elaborated here.

[0121] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned ship type detection method when executed by a processor.

[0122] The computer program product provided in this application solves the technical problem of low comprehensiveness of ship supervision. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present invention are the same as the beneficial effects of the ship type detection method provided by the above embodiment, and will not be repeated here.

[0123] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A method for detecting ship type, characterized in that: The ship type detection method comprises: Acquire a ship area image of the area where the ship to be monitored is located; Performing ship type detection on the ship to be monitored based on the ship area image to obtain a ship type detection result; The detecting of the type of the ship to be monitored based on the ship area image includes: Identifying the stern wave characteristics of the ship to be monitored in the ship area image; judging whether the ship to be monitored is suspected of undergoing hull modification based on the stern wave characteristics; If it is determined that the ship to be monitored is suspected of undergoing hull modification, radar data of the ship to be monitored is obtained; wherein the radar data records the trajectory data of the ship to be monitored that changes over time; Measuring the speed of the ship to be monitored based on the radar data; According to the traveling speed, it is determined whether the ship to be monitored is undergoing hull modification.

2. The ship type detection method according to claim 1, characterized in that: The detecting of the type of the ship to be monitored based on the ship area image further includes: Identifying the distance between the ship plane of the ship to be monitored and the horizontal plane in the ship area image to obtain a load determination distance; Based on the load determination distance, it is determined whether the ship to be monitored is overloaded.

3. The ship type detection method according to claim 2, characterized in that: The step of identifying the distance between the ship plane of the ship to be monitored and the horizontal plane in the ship area image to obtain the load determination distance includes: Identifying a ship plane outline and a horizontal plane outline in the ship area image; Calculating the outline distance between the ship plane outline and the horizontal plane outline, and obtaining the ship size of the ship to be monitored in the ship area image; The ratio between the outline spacing and the ship size is calculated to obtain the load determination distance.

4. The ship type detection method according to claim 1, wherein: The detecting of the type of the ship to be monitored based on the ship area image further includes: Acquiring a cabin area image in the ship area image; By performing image classification on the cabin area image, it is determined whether the cabin of the ship to be monitored is not sealed.

5. A ship type detection device, characterized in that: The ship type detection device comprises: An image acquisition module is used to acquire an image of a ship area where the ship to be monitored is located; A ship type detection module is used to detect the ship type of the ship to be monitored based on the ship area image to obtain a ship type detection result; Wherein, the ship type detection module includes: an identification unit, configured to identify the stern wave characteristics of the ship to be monitored in the ship area image; a hull modification detection unit, configured to determine whether the monitored ship has undergone hull modification based on the stern wave characteristics; The hull modification detection unit includes: a judgment subunit, configured to judge whether the ship to be monitored is suspected of undergoing hull modification based on the stern wave characteristics; a radar data acquisition subunit, configured to acquire radar data of the ship to be monitored if it is determined that the ship to be monitored is suspected of undergoing hull modification; wherein the radar data records the trajectory data of the ship to be monitored that changes over time; A speed measurement subunit, configured to measure the speed of the ship to be monitored based on the radar data; The determination subunit is used to determine whether the ship to be monitored has undergone hull modification based on the travel speed.

6. The ship type detection device according to claim 5, characterized in that: The ship type detection module also includes: a load determination distance acquisition unit, configured to identify the distance between the ship plane of the ship to be monitored and the horizontal plane in the ship area image, and obtain the load determination distance; a ship overload detection unit, configured to determine whether the monitored ship is overloaded based on the load determination distance; The load determination distance acquisition unit includes: a contour recognition subunit, configured to recognize a ship plane contour and a horizontal plane contour in the ship area image; A first calculation subunit is configured to calculate a distance between the ship plane contour and the horizontal plane contour, and obtain a size of the ship to be monitored in the ship area image; A second calculation subunit is configured to calculate a ratio between the contour spacing and the ship size to obtain the load determination distance; The ship type detection module also includes: a cabin image acquisition unit, configured to acquire a cabin area image from the ship area image; The ship unsealed cabin detection unit is used to determine whether the ship to be monitored has an unsealed cabin by performing image classification on the cabin area image.

7. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the ship type detection method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program for implementing the ship type detection method, and the program for implementing the ship type detection method is executed by a processor to implement the steps of the ship type detection method according to any one of claims 1 to 4.

Images