Method, device, terminal and medium for identifying sand mining in water area

Abstract

The present application discloses a method, device, terminal and medium for identifying sand mining in waters. The method includes: obtaining target area information corresponding to a target area, sand mining operation area information corresponding to a sand mining operation area in the target area information, device information of a target vessel, and navigation information of the target vessel in the target area information; obtaining a first evaluation result according to the target area information, the sand mining operation area information and the navigation information through a preset first model; obtaining a second evaluation result according to the device information and pre-stored sand mining operation device information through a preset second model; and determining a target identification result based on the first evaluation result, the second evaluation result and a preset evaluation result threshold. The purpose of the present application is to comprehensively evaluate a target vessel from multiple angles by identifying the navigation information of the target vessel and the equipment on the vessel, so as to accurately determine whether the target vessel is engaged in sand mining operation.

Description

Technical Field

[0001] This application relates to the technical field of sand mining management, and particularly to a method, device, terminal and medium for identifying sand mining in waters. Background Art

[0002] According to relevant laws and regulations, water administrative departments at all levels bear the main responsibility for managing sand mining in waters. Sand mining vessels usually operate within the designated sand mining areas. These areas are generally places with rich sand and gravel resources determined through geological exploration, such as the inner side of river bends, near river shoals or estuaries. Because the water flow dynamic conditions in these areas make it easier for sand and gravel to deposit, sand mining vessels will frequently operate at these specific locations, and their navigation tracks also concentrate in these areas. Common sand mining equipment on sand mining vessels includes sand pumps and grabs. A sand pump is a device that sucks underwater sand and gravel onto the ship through strong suction, and is suitable for waters with finer sand and deeper water sources. A grab, on the other hand, controls the opening and closing of the grab through a robotic arm to grab sand and gravel, and this device is more effective for sand mining operations on blocky, larger-grained sand and gravel or in shallower waters.

[0003] However, some existing methods for supervising sand mining in waters include relying on manual inspections, simple video monitoring or sand mining identification methods in waters based only on a certain type of sensor data. Traditional manual inspections may miss sand mining behaviors due to factors such as limited field of vision, poor weather conditions or long inspection intervals. At the same time, abnormal tracks in navigation information may imply that a vessel is carrying out sand mining operations, but this evidence alone may not be sufficient; similarly, it is impossible to determine whether a vessel is carrying out sand mining operations just by the equipment of the vessel. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, terminal and medium for identifying sand mining in waters, aiming to comprehensively evaluate a target vessel from multiple angles by identifying the navigation information and on-board equipment of the target vessel, and then accurately determine whether the target vessel is carrying out sand mining operations.

[0005] To achieve the above object, this application provides a method for identifying sand mining in waters, the method comprising:

[0006] Obtain target area information corresponding to a target area, sand mining operation area information corresponding to the sand mining operation area in the target area information, equipment information of a target vessel, and navigation information of the target vessel in the target area information, wherein the target area information is used to characterize the condition of the monitored waters, and the sand mining operation area is used to characterize the condition of the sand mining operation area in the target area; the target area information includes target area coordinate data, the sand mining operation area information includes sand mining operation area coordinate data, and the navigation information includes navigation track data and navigation speed data;

[0007] By presetting a first model, a first evaluation result is obtained according to the target area information, the sand mining operation area information, and the navigation information, where the first evaluation result is used to characterize the evaluation of the navigation status of the target vessel in the target area;

[0008] By presetting a second model, a second evaluation result is obtained according to the equipment information and the pre-stored sand mining operation equipment information, where the second evaluation result is used to characterize the evaluation of the equipment status on the target vessel; the equipment information includes equipment type information, equipment power data, and equipment size data;

[0009] Based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold, a target recognition result is determined, where the target recognition result is used to characterize the determination result of whether the target vessel is carrying out sand mining operations in the target area.

[0010] Specifically, the preset first model includes a first input layer, a first convolutional layer, a first pooling layer, a first fully connected layer, and a first output layer;

[0011] The step of obtaining the first evaluation result by presetting the first model according to the target area information, the sand mining operation area information, and the navigation information includes:

[0012] According to the target area coordinate data, the sand mining operation area coordinate data, the navigation trajectory data, and the navigation speed data, a first input vector is obtained through the first input layer;

[0013] According to the first input vector, a first convolutional feature map is obtained through the first convolutional layer;

[0014] According to the first convolutional feature map, a first tensor is obtained through the first pooling layer;

[0015] According to the first tensor, a first feature vector is obtained through the first fully connected layer;

[0016] According to the first feature vector, the first evaluation result is obtained through the first output layer.

[0017] Specifically, the first output layer contains 3 first neurons, the first evaluation result is a three-dimensional output vector, the three-dimensional output vector includes 3 first output probabilities, and the first output probabilities correspond to the first neurons one by one;

[0018] The step of obtaining the first evaluation result according to the first feature vector through the first output layer includes:

[0019] Input the first feature vector into the first output layer to obtain the three-dimensional output vector. Among them, the three first output probabilities are respectively used to represent the probability that the target vessel sails normally, the probability that the target vessel approaches the sand mining operation area but does not conduct sand mining operations, and the probability that the target vessel conducts sand mining operations in the sand mining operation area.

[0020] Specifically, the first output layer includes one second neuron, and the first evaluation result is the behavior probability corresponding to the target vessel.

[0021] Obtaining the first evaluation result through the first output layer according to the first feature vector includes:

[0022] Input the first feature vector into the first output layer to obtain the behavior probability, where the behavior probability is used to represent the probability that the target vessel conducts sand mining operations in the sand mining operation area.

[0023] Specifically, the device information includes device type information, device power data, and device size data. The preset second model includes a second input layer, a second convolutional layer, a second pooling layer, a second fully connected layer, and a second output layer.

[0024] Obtaining the second evaluation result through the preset second model according to the device information and the pre-stored sand mining operation device information includes:

[0025] According to the device type information, device power data, device size data, and the sand mining operation device information, obtain a second input vector through the second input layer.

[0026] According to the second input vector, obtain a second convolutional feature map through the second convolutional layer.

[0027] According to the second convolutional feature map, obtain a second tensor through the second pooling layer.

[0028] According to the second tensor, obtain a second feature vector through the second fully connected layer.

[0029] According to the second feature vector, obtain the second evaluation result through the second output layer.

[0030] Specifically, the first output layer includes one third neuron, and the second evaluation result is the device matching probability corresponding to the target vessel.

[0031] Obtaining the second evaluation result through the second output layer according to the second feature vector includes:

[0032] Input the second feature vector into the second output layer to output the device matching probability, where the device matching probability is used to characterize the probability that the device on the target vessel is a sand dredging operation device.

[0033] Specifically, the preset evaluation result threshold includes a first evaluation result threshold and a second evaluation result threshold;

[0034] Determining the target recognition result based on the first evaluation result, the second evaluation result, and the preset evaluation result threshold includes:

[0035] If the probability of the first behavior is not less than the first evaluation result threshold and the device matching probability is not less than the second evaluation result threshold, then determine the target recognition result as the target vessel performing sand dredging operations in the sand dredging operation area.

[0036] To achieve the above object, the present application also provides a water area sand dredging recognition device, the device includes:

[0037] The first unit is used to obtain the target area information corresponding to the target area, the sand dredging operation area information corresponding to the sand dredging operation area in the target area information, the device information of the target vessel, and the navigation information of the target vessel in the target area information, where the target area information is used to characterize the condition of the monitored water area, and the sand dredging operation area is used to characterize the condition of the sand dredging operation area in the target area;

[0038] The second unit is used to obtain a first evaluation result through a preset first model according to the target area information, the sand dredging operation area information, and the navigation information, where the first evaluation result is used to characterize the evaluation of the navigation condition of the target vessel in the target area; the target area information includes target area coordinate data, the sand dredging operation area information includes sand dredging operation area coordinate data, and the navigation information includes navigation trajectory data and navigation speed data;

[0039] The third unit is used to obtain a second evaluation result through a preset second model according to the device information and the pre-stored sand dredging operation device information, where the second evaluation result is used to characterize the evaluation of the device condition on the target vessel; the device information includes device type information, device power data, and device size data;

[0040] The fourth unit is used to determine the target recognition result based on the first evaluation result, the second evaluation result, and the preset evaluation result threshold, where the target recognition result is used to characterize the determination result of whether the target vessel performs sand dredging operations in the target area.

[0041] To achieve the above object, the present application further provides a terminal, including a memory storing multiple instructions; the processor loads the instructions from the memory to execute the steps in any of the methods provided by the present application.

[0042] To achieve the above object, the present application further provides a computer-readable storage medium, the medium storing multiple instructions, and the instructions being suitable for being loaded by a processor to execute the steps in any of the methods provided by the present application.

[0043] A water area sand mining identification method, device, terminal and medium provided by the present application can first obtain target area information corresponding to a target area, sand mining operation area information corresponding to a sand mining operation area in the target area information, device information of a target ship, and navigation information of the target ship in the target area information, where the target area information is used to characterize the condition of the monitored water area, and the sand mining operation area is used to characterize the condition of the sand mining operation area in the target area; then, through a preset first model, according to the target area information, the sand mining operation area information, and the navigation information, obtain a first evaluation result, where the first evaluation result is used to characterize the evaluation of the navigation condition of the target ship in the target area; then, through a preset second model, according to the device information and pre-stored sand mining operation device information, obtain a second evaluation result, where the second evaluation result is used to characterize the evaluation of the device condition on the target ship; finally, based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold, accurately determine a target identification result, where the target identification result is used to characterize an accurate determination result of whether the target ship is implementing sand mining operation in the target area.

[0044] The present application can comprehensively evaluate a target ship from multiple angles by identifying the navigation information of the target ship and the equipment on the ship, and then accurately determine whether the target ship is conducting sand mining operation. Brief Description of the Drawings

[0045] Figure 1 It is a flowchart of the method provided by an embodiment of the present application;

[0046] Figure 2 It is a structural diagram of the device provided by an embodiment of the present application;

[0047] Figure 3 It is a structural diagram of the terminal provided by an embodiment of the present application. Detailed Embodiments

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0049] Since some existing water area sand mining supervision methods include relying on manual inspections, simple video monitoring, or water area sand mining identification methods based only on a certain type of sensor data. Traditional manual inspections may miss sand mining behaviors due to factors such as limited vision, poor weather conditions, or long inspection intervals. At the same time, abnormal trajectories in navigation information may imply that a ship is carrying out sand mining operations, but this evidence alone may not be sufficient; similarly, a ship's equipment alone cannot determine whether the ship is carrying out sand mining operations.

[0050] Therefore, the embodiments of the present application provide a water area sand mining identification method, device, terminal, and medium to solve practical technical problems.

[0051] In some embodiments, the device can be specifically integrated into an electronic device, and the electronic device can be a device such as a terminal or a server.

[0052] In some embodiments, the server can also be implemented in the form of a terminal.

[0053] Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0054] Among them, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, and the present application does not limit this.

[0055] The following will be described in detail respectively. It should be noted that the serial numbers of the following embodiments do not limit the preferred order of the embodiments.

[0056] The embodiments of the present application provide a water area sand mining identification method, as Figure 1 shown, the specific process of the method can be as follows:

[0057] S110. Obtain the target area information corresponding to the target area, the sand mining operation area information corresponding to the sand mining operation area in the target area information, the equipment information of the target vessel, and the navigation information of the target vessel in the target area information. Herein, the target area information is used to characterize the condition of the monitored water area, and the sand mining operation area is used to characterize the condition of the sand mining operation area in the target area; the target area information includes target area coordinate data, the sand mining operation area information includes sand mining operation area coordinate data, and the navigation information includes navigation trajectory data and navigation speed data.

[0058] In some embodiments, the target area information may include the geographical range information of the target area. The boundary coordinates of the target area can be determined through a Geographic Information System (GIS). For example, longitude and latitude coordinates can be used to accurately define its range. Take a section of a river as an example, the upstream endpoint coordinates are (longitude X1, latitude Y1), and the downstream endpoint coordinates are (longitude X2, latitude Y2), thus delineating the approximate range of the target area. At the same time, basic geometric data such as the area and perimeter of this area can also be obtained, which helps to overall grasp the size of the water area.

[0059] Satellite remote sensing images can also be utilized, combined with image processing technology, to further clearly present the land-water boundary, surrounding topography, etc. of the target area. For example, it can be determined whether the riverbank is steep or gentle, and whether there are special terrains such as mid-river shoals and river branches. These topographical features are of reference value for subsequent judgment of the rationality of vessel navigation and sand mining activities.

[0060] In some embodiments, the sand mining operation area information can be obtained by means of GIS technology. By accurately determining the boundary coordinates of the sand mining operation area, its shape and range are clearly presented in a digital form, which is convenient for subsequent comparison and analysis with the real-time position of the vessel. For example, this area may be a polygon, and the coordinates of each vertex can be accurately recorded in the database.

[0061] In some embodiments, the equipment information can be obtained by manually checking the detailed list of the vessel's equipment, including operation equipment (such as parameters like model, power, capacity, opening and closing angle, etc.), power equipment (power, type of the engine, etc.), auxiliary operation equipment (screening specifications of the screening equipment, conveying capacity of the conveying equipment, etc.), and safety guarantee equipment (equipment configuration of life-saving equipment, fire-fighting equipment, etc.).

[0062] In some embodiments, the navigation information can be obtained by using the Automatic Identification System (AIS) of ships. This system can transmit information such as the position coordinates (latitude and longitude), course, and speed of the ship in real time. By receiving this data, the dynamic position change of the target ship in the target area can be clearly grasped. For example, it can be seen whether the ship is sailing downstream along the riverbank or approaching the sand mining operation area within a certain period of time.

[0063] S120. Through a preset first model, based on the target area information, the sand mining operation area information, and the navigation information, obtain a first evaluation result, where the first evaluation result is used to characterize the evaluation of the navigation status of the target ship in the target area.

[0064] In some embodiments, the target area information includes target area coordinate data, the sand mining operation area information includes sand mining operation area coordinate data, the navigation information includes navigation trajectory data and navigation speed data, and the preset first model includes a first input layer, a first convolutional layer, a first pooling layer, a first fully connected layer, and a first output layer.

[0065] Specifically, the step of obtaining the first evaluation result through the preset first model according to the target area information, the sand mining operation area information, and the navigation information includes the following steps S121 to S125:

[0066] S121. According to the target area coordinate data, the sand mining operation area coordinate data, the navigation trajectory data, and the navigation speed data, obtain a first input vector through the first input layer.

[0067] In some embodiments, the water area near a port can be used as the target area. The area range of the target area is a rectangle, represented by the coordinates of the upper left corner and the lower right corner, such as (x1, y1) and (x2, y2). There is a demarcated sand mining operation area within the target area, and its coordinate range is (x3, y3) and (x4, y4). The target ship can be monitored by radar, and the movement trajectory (recording a position coordinate every 10 seconds) and speed (unit: m / s) of the target ship in the target area can be recorded.

[0068] Specifically, the first input layer can have 4 neurons, corresponding to the coordinates x1, y1, x2, y2 of the target area respectively, and another 4 neurons corresponding to the x3, y3, x4, y4 coordinates of the sand mining operation area. Plus n neurons for inputting the movement trajectory coordinates of the target ship in the time series (assuming the coordinates of n time points are recorded), and n neurons for inputting the corresponding speed values. The total number of input neurons is 8 + 2n.

[0069] Specifically, after normalizing the target area coordinate data, the sand mining operation area coordinate data, the navigation trajectory data, and the navigation speed data, the first input layer obtains the first input vector.

[0070] S122. According to the first input vector, a first convolutional feature map is obtained through the first convolutional layer.

[0071] In some embodiments, the first convolutional layer may be a convolutional layer with a convolutional kernel size of 3*3, a stride of 1, and 4 convolutional kernels. The target area, the sand mining operation area, and the vessel movement trajectory can be regarded as a special form of "image" data. Then, the data of the input layer is input into the first convolutional layer according to a certain spatial layout (for example, arranging the coordinate and speed values into a two-dimensional matrix).

[0072] Specifically, after convolution operation, 4 feature maps are obtained, that is, the first convolutional feature map. Each feature map highlights the local features in the input data, such as the spatial relationship between the vessel trajectory and the operation area boundary, the local direction change of the trajectory, etc. The size of each feature map is m*m (the value of m depends on the layout of the input data and the convolutional kernel parameters).

[0073] S123. According to the first convolutional feature map, a first tensor is obtained through the first pooling layer.

[0074] In some embodiments, the first pooling layer may be a max pooling layer with a pooling window size of 2*2 and a stride of 2. After performing the pooling operation of the first pooling layer on the 4 feature maps, a tensor of 4*m / 2*m / 2 is output, that is, the first tensor.

[0075] S124. According to the first tensor, a first feature vector is obtained through the first fully connected layer.

[0076] In some embodiments, the first fully connected layer may be a fully connected layer with 128 neurons. The flattened first tensor after pooling is input as a vector. After being processed by the weighted summation of neurons and an activation function (such as the ReLU function), a 128-dimensional vector is obtained. This vector is used to further integrate and abstract the previously extracted features to obtain intermediate features related to the evaluation of the navigation status. This 128-dimensional vector is the first feature vector.

[0077] S125. According to the first feature vector, the first evaluation result is obtained through the first output layer.

[0078] In some embodiments, the first output layer includes three first neurons, the first evaluation result is a three-dimensional output vector, the three-dimensional output vector includes three first output probabilities, and the first output probabilities correspond one-to-one to the first neurons.

[0079] Specifically, obtaining the first evaluation result according to the first feature vector through the first output layer includes the following specific implementation process:

[0080] The first feature vector is input into the first output layer, and the three-dimensional output vector is output, wherein the three first output probabilities are respectively used to characterize the probability of the target ship sailing normally, the probability that the target ship is close to the sand mining operation area but does not carry out sand mining operations, and the probability that the target ship carries out sand mining operations in the sand mining operation area.

[0081] Specifically, the output layer has 3 neurons, corresponding to 3 navigation status evaluation categories: normal navigation, entering the sand mining area but not operating, and sand mining in progress. After the first output layer, the three-dimensional output vector is obtained, and the three-dimensional output vector represents the probability that the target ship belongs to each navigation status evaluation category. For example, the three-dimensional output vector is (0.8, 0.1, 0.1), indicating that the target ship has an 80% probability of normal navigation, a 10% probability of entering the sand mining area but not operating, and a 10% probability of sand mining in progress.

[0082] In some embodiments, the first output layer includes one second neuron, and the first evaluation result is a behavior probability corresponding to the target vessel.

[0083] Specifically, obtaining the first evaluation result through the first output layer according to the first feature vector includes the following specific implementation process:

[0084] The first feature vector is input into the first output layer, and the behavior probability is outputted, wherein the behavior probability is used to characterize the probability that the target vessel performs sand mining operations in the sand mining operation area.

[0085] S130. By presetting a second model, a second evaluation result is obtained according to the equipment information and pre-stored sand mining equipment information, wherein the second evaluation result is used to characterize the evaluation of the equipment status on the target vessel; the equipment information includes equipment type information, equipment power data and equipment size data.

[0086] In some embodiments, the device information includes device type information, device power data, and device size data, and the preset second model includes a second input layer, a second convolutional layer, a second pooling layer, a second fully connected layer, and a second output layer.

[0087] Specifically, the second evaluation result is obtained by presetting the second model according to the equipment information and the pre-stored sand mining equipment information, including the steps S131 to S135 as shown below:

[0088] S131. Obtain a second input vector through the second input layer according to the equipment type information, equipment power data, equipment size data and the sand mining equipment information.

[0089] In some embodiments, the equipment type information can be represented by a numerical value; the equipment power data can include two numerical values, namely, the upper limit and the lower limit of the power range; the equipment size data can include two numerical values, namely, the volume and the capacity; in contrast, the sand mining equipment information can be the standard range of the sand mining equipment, and the standard range is represented by an interval. Thus, the second input layer can be provided with 15 neurons, corresponding to each numerical value.

[0090] Specifically, each numerical value is input into the second input layer, and the second input vector is obtained after normalization.

[0091] S132. According to the second input vector, obtain a second convolutional feature map through the second convolutional layer.

[0092] Continuing with the above embodiment, the second convolution layer can be a convolution layer with a convolution kernel size of 2×2, a step size of 1, and 3 convolution kernels. Specifically, the values corresponding to the 15 neurons of the input layer are arranged in a certain order into a 3×5 (hypothetical two-dimensional layout form, a more reasonable layout can be adjusted according to actual conditions) matrix form, and input into the convolution layer as image-like data, so that the convolution kernel can be used to mine the local correlation features between different parameters and between actual equipment and standard equipment. After the second convolution layer, 3 feature maps are obtained, namely the second convolution feature maps, and the size of each feature map is assumed to be 2×4 (the specific size depends on factors such as the input matrix and the convolution kernel parameters).

[0093] S133. According to the second convolutional feature map, obtain a second tensor through the second pooling layer.

[0094] Continuing with the above embodiment, the second pooling layer can be a maximum pooling layer with a pooling window size of 2×2 and a step size of 2. Specifically, after the three feature maps are pooled, the size of the feature maps becomes 1×2, and the output is a 3×1×2 tensor, i.e., the second tensor, which effectively reduces the data dimension while retaining important information such as the main difference features after comparing various parameters of the device with the standard.

[0095] S134. Obtain a second feature vector through the second fully-connected layer according to the second tensor.

[0096] Continuing the description based on the above embodiments, the second fully-connected layer can be a fully-connected layer with 32 neurons. Specifically, the second fully-connected layer flattens the pooled tensor of 3×1×2 into a vector of length 6. After weighted summation by neurons and processing by an activation function (such as the ReLU function), a 32-dimensional vector is output, which is the second feature vector. The second feature vector further integrates and abstracts the previously extracted device-related features, extracting intermediate features more relevant to the evaluation of the device status.

[0097] S135. Obtain the second evaluation result through the second output layer according to the second feature vector.

[0098] In some embodiments, the first output layer includes 1 third neuron, and the second evaluation result is the device matching probability corresponding to the target vessel.

[0099] Specifically, the process of obtaining the second evaluation result through the second output layer according to the second feature vector includes the following specific implementation process:

[0100] Input the second feature vector into the second output layer, and the device matching probability is output, where the device matching probability is used to represent the probability that the device on the target vessel is a sand mining operation device.

[0101] Continuing the description based on the above embodiments, perform a weighted summation operation on the 32-dimensional vector and the weight vector in the third neuron, and then process it through an activation function (such as the sigmoid function, etc., a suitable function that can map the output value to the 0 - 1 interval). Finally, a value between 0 and 1 is obtained, and this value is the device matching probability. For example, if the finally calculated device matching probability is 0.8, it means that from the judgment of the preset second model, there is an 80% probability that the device on the target vessel is a sand mining operation device.

[0102] S140. Determine a target recognition result based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold, where the target recognition result is used to represent the determination result of whether the target vessel is performing sand mining operations in the target area.

[0103] Continuing the description based on the above embodiments, the preset evaluation result threshold includes a first evaluation result threshold and a second evaluation result threshold.

[0104] Specifically, determining the target recognition result based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold includes the following specific implementation process:

[0105] If the probability of the first behavior is not less than the first evaluation result threshold and the equipment matching probability is not less than the second evaluation result threshold, then determine the target recognition result as the target vessel is conducting sand mining operations in the sand mining operation area.

[0106] In some embodiments, the first evaluation result threshold can be set comprehensively based on various factors such as a large amount of past actual monitoring data, law enforcement experience, and analysis of the sand mining operation rules in this water area. For example, through statistical analysis of numerous confirmed sand mining operation cases in history, it is found that when the probability of the behavior characteristics presented by the target vessel in the sand mining operation area conforming to sand mining operations reaches 0.6 (this is an example value) and above, there is a high probability that it is indeed conducting sand mining operations. Then, the first evaluation result threshold can be set to 0.6. The first evaluation result threshold provides a reference boundary for judging whether it is sand mining from the perspective of the vessel's behavior performance.

[0107] Meanwhile, the second evaluation result threshold is determined based on the standard situation of legal sand mining vessel equipment, past identification experience of different types of equipment, etc. For example, by analyzing the characteristic parameters of various legal sand mining equipment and the results of detecting a large number of actual vessel equipment, it is found that when the equipment matching probability reaches 0.5 (example value) and above, the equipment basically meets the requirements of sand mining operation equipment. At this time, the second evaluation result threshold is set to 0.5, setting a standard boundary for judging whether it is sand mining equipment from the equipment perspective.

[0108] Suppose the behavior probability of a certain target vessel is 0.7 and the equipment matching probability is 0.6. Given that the set first evaluation result threshold is 0.6 and the second evaluation result threshold is 0.5. At this time, since 0.7 (behavior probability) is not less than 0.6 (the first evaluation result threshold), and 0.6 (equipment matching probability) is not less than 0.5 (the second evaluation result threshold), meeting the determination conditions, then the target recognition result can be determined as the target vessel is conducting sand mining operations in the sand mining operation area; conversely, if the behavior probability of the target vessel is 0.5 and the equipment matching probability is 0.4, even if one of the probabilities is close to the threshold, as long as one does not meet the corresponding threshold condition (such as the behavior probability is less than the first evaluation result threshold), it cannot be determined that the vessel is conducting sand mining operations in the sand mining operation area, and such a target recognition result will not be determined.

[0109] In summary, the present application provides a method for identifying sand mining in water areas. By identifying the navigation information of the target vessel and the equipment on the vessel, the target vessel is comprehensively evaluated from multiple angles, and then it can be accurately determined whether the target vessel is engaged in sand mining operations.

[0110] To better implement the above method, an embodiment of the present application further provides a device for identifying sand mining in water areas. This device can be specifically integrated into an electronic device, which can be a terminal, a server, or other devices. Among them, the terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, a personal computer, or other devices; the server can be a single server or a server cluster composed of multiple servers.

[0111] For example, in this embodiment, taking the water area sand mining identification device being specifically integrated into the terminal as an example, the method of the embodiment of the present application will be described in detail.

[0112] For example, as Figure 2 shown, the water area sand mining identification device 200 may include a first unit 201, a second unit 202, a third unit 203, and a fourth unit 204. The device includes:

[0113] The first unit 201 is used to obtain the target area information corresponding to the target area, the sand mining operation area information corresponding to the sand mining operation area in the target area information, the equipment information of the target vessel, and the navigation information of the target vessel in the target area information. Among them, the target area information is used to characterize the condition of the monitored water area, and the sand mining operation area is used to characterize the condition of the sand mining operation area in the target area;

[0114] The second unit 202 is used to obtain a first evaluation result based on the target area information, the sand mining operation area information, and the navigation information through a preset first model. Among them, the first evaluation result is used to characterize the evaluation of the navigation condition of the target vessel in the target area;

[0115] The third unit 203 is used to obtain a second evaluation result based on the equipment information and the pre-stored sand mining operation equipment information through a preset second model. Among them, the second evaluation result is used to characterize the evaluation of the equipment condition on the target vessel;

[0116] The fourth unit 204 is used to determine a target recognition result based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold. Among them, the target recognition result is used to characterize the determination result of whether the target vessel is carrying out sand mining operations in the target area.

[0117] In specific implementation, each of the above units can be implemented as an independent entity, or can be arbitrarily combined and implemented as the same or several entities. For the specific implementation of each of the above units, reference can be made to the foregoing method embodiments and will not be elaborated herein.

[0118] As can be seen from the above, the embodiments of the present application can comprehensively evaluate a target vessel from multiple perspectives by identifying the navigation information of the target vessel and the on-board equipment, and then accurately determine whether the target vessel is engaged in sand mining operations.

[0119] The embodiments of the present application further provide an electronic device, which can be a device such as a terminal or a server. Among them, the terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a notebook computer, a personal computer, etc.; the server can be a single server or a server cluster composed of multiple servers, etc.

[0120] In some embodiments, the product processing device can also be integrated in multiple electronic devices. For example, the product processing device can be integrated in multiple servers, and the water area sand mining identification method of the present application can be implemented by multiple servers.

[0121] In this embodiment, the electronic device in this embodiment will be described in detail by taking the example that the electronic device is a terminal. For example, as Figure 3 shown, it shows a schematic structural diagram of a terminal 300 involved in the embodiments of the present application. Specifically:

[0122] The terminal 300 may include a processor 301 with one or more processing cores, a memory 302 with one or more media, a power supply 303, an input module 304, a communication module 305 and other components. Those skilled in the art can understand that Figure 3 the structure of the terminal 300 shown in

[0123] does not constitute a limitation on the terminal 300, and it may include more or fewer components than shown in the figure, or combine some components, or arrange different components. Among them:

[0124] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The memory 302 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the terminal 300. In addition, the memory 302 can include a high-speed random access memory and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 can also include a memory controller to provide the processor 301 with access to the memory 302.

[0125] The terminal 300 further includes a power supply 303 for supplying power to each component. In some embodiments, the power supply 303 can be logically connected to the processor 301 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 303 can also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0126] The terminal 300 may further include an input module 304, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0127] The terminal 300 may further include a communication module 305. In some embodiments, the communication module 305 can include a wireless module. The terminal 300 can perform short-range wireless transmission through the wireless module of the communication module 305, thereby providing users with wireless broadband Internet access. For example, the communication module 305 can be used to help users send and receive emails, browse web pages, and access streaming media, etc.

[0128] Although not shown, the terminal 300 may further include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 301 in the terminal 300 will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302 to implement various functions as follows:

[0129] Obtain the target area information corresponding to the target area, the sand mining operation area information corresponding to the sand mining operation area in the target area information, the equipment information of the target vessel, and the navigation information of the target vessel in the target area information, where the target area information is used to characterize the condition of the monitored water area, and the sand mining operation area is used to characterize the condition of the sand mining operation area in the target area;

[0130] Through a preset first model, obtain a first evaluation result according to the target area information, the sand mining operation area information, and the navigation information, where the first evaluation result is used to characterize the evaluation of the navigation condition of the target vessel in the target area;

[0131] Through a preset second model, obtain a second evaluation result according to the equipment information and the pre-stored sand mining operation equipment information, where the second evaluation result is used to characterize the evaluation of the equipment condition on the target vessel;

[0132] Based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold, determine a target recognition result, where the target recognition result is used to characterize the determination result of whether the target vessel is carrying out sand mining operations in the target area.

[0133] For the specific implementation of each of the above operations, reference may be made to the previous embodiments, which will not be elaborated here.

[0134] As can be seen from the above, the embodiments of the present application can comprehensively evaluate the target vessel from multiple angles by identifying the navigation information of the target vessel and the equipment on the vessel, and then accurately determine whether the target vessel is carrying out sand mining operations.

[0135] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. These instructions can be stored in a medium and loaded and executed by a processor.

[0136] For this reason, the embodiments of the present application provide a medium in which multiple instructions are stored, and these instructions can be loaded by a processor to execute the steps in any of the water area sand mining recognition methods provided by the embodiments of the present application. For example, the instructions can execute the following steps:

[0137] Obtain the target area information corresponding to the target area, the sand mining operation area information corresponding to the sand mining operation area in the target area information, the equipment information of the target vessel, and the navigation information of the target vessel in the target area information, where the target area information is used to characterize the condition of the monitored water area, and the sand mining operation area is used to characterize the condition of the sand mining operation area in the target area;

[0138] By presetting a first model, a first evaluation result is obtained according to the target area information, the sand mining operation area information, and the navigation information, where the first evaluation result is used to characterize the evaluation of the navigation status of the target vessel in the target area;

[0139] By presetting a second model, a second evaluation result is obtained according to the equipment information and the pre-stored sand mining operation equipment information, where the second evaluation result is used to characterize the evaluation of the equipment status on the target vessel;

[0140] Based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold, a target recognition result is determined, where the target recognition result is used to characterize the determination result of whether the target vessel is carrying out sand mining operations in the target area.

[0141] Wherein, the medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0142] According to one aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a medium. The processor of the computer device reads the computer instructions from the medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the various alternative implementation manners provided in the above embodiments.

[0143] Since the instructions stored in the medium can execute the steps in any of the water area sand mining recognition methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the water area sand mining recognition methods provided in the embodiments of the present application can be realized. For details, see the previous embodiments and will not be elaborated here.

[0144] The above has introduced in detail a water area sand mining recognition method, device, terminal, and medium provided by the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for identifying sand mining in water areas, characterized in that, The method includes: Obtaining target area information corresponding to a target area, sand mining operation area information corresponding to the sand mining operation area in the target area information, equipment information of a target vessel, and navigation information of the target vessel in the target area information, where the target area information is used to characterize the condition of the monitored water area, and the sand mining operation area is used to characterize the condition of the sand mining operation area in the target area; the target area information includes target area coordinate data, the sand mining operation area information includes sand mining operation area coordinate data, and the navigation information includes navigation trajectory data and navigation speed data; Obtaining a first evaluation result according to the target area information, the sand mining operation area information, and the navigation information through a preset first model, where the first evaluation result is used to characterize the evaluation of the navigation condition of the target vessel in the target area; Obtaining a second evaluation result according to the equipment information and pre-stored sand mining operation equipment information through a preset second model, where the second evaluation result is used to characterize the evaluation of the equipment condition of the target vessel; the equipment information includes equipment type information, equipment power data, and equipment size data; Determining a target recognition result based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold, where the target recognition result is used to characterize the determination result of whether the target vessel is conducting sand mining operations in the target area.

2. The method according to claim 1, wherein, The preset first model includes a first input layer, a first convolutional layer, a first pooling layer, a first fully connected layer, and a first output layer; The step of obtaining a first evaluation result according to the target area information, the sand mining operation area information, and the navigation information through a preset first model includes: Obtaining a first input vector through the first input layer according to the target area coordinate data, the sand mining operation area coordinate data, the navigation trajectory data, and the navigation speed data; Obtaining a first convolutional feature map through the first convolutional layer according to the first input vector; Obtaining a first tensor through the first pooling layer according to the first convolutional feature map; Obtaining a first feature vector through the first fully connected layer according to the first tensor; Obtaining the first evaluation result through the first output layer according to the first feature vector.

3. The method according to claim 2, wherein The first output layer includes 3 first neurons, the first evaluation result is a three-dimensional output vector, the three-dimensional output vector includes 3 first output probabilities, and the first output probabilities correspond to the first neurons one by one; The step of obtaining the first evaluation result through the first output layer according to the first feature vector includes: Inputting the first feature vector into the first output layer, and outputting the three-dimensional output vector, where the 3 first output probabilities are respectively used to characterize the probability that the target vessel sails normally, the probability that the target vessel approaches the sand mining operation area but does not conduct sand mining operations, and the probability that the target vessel conducts sand mining operations in the sand mining operation area.

4. The method according to claim 2, wherein The first output layer includes 1 second neuron, and the first evaluation result is the behavior probability corresponding to the target vessel; The obtaining of the first evaluation result through the first output layer according to the first feature vector includes: Inputting the first feature vector into the first output layer, and outputting the behavior probability, where the behavior probability is used to represent the probability that the target vessel conducts sand mining operations in the sand mining operation area.

5. The method according to claim 4, characterized in that The preset second model includes a second input layer, a second convolutional layer, a second pooling layer, a second fully connected layer, and a second output layer; The obtaining of the second evaluation result through the preset second model according to the device information and the pre-stored sand mining operation device information includes: Obtaining a second input vector through the second input layer according to the device type information, device power data, device size data, and the sand mining operation device information; Obtaining a second convolutional feature map through the second convolutional layer according to the second input vector; Obtaining a second tensor through the second pooling layer according to the second convolutional feature map; Obtaining a second feature vector through the second fully connected layer according to the second tensor; Obtaining the second evaluation result through the second output layer according to the second feature vector.

6. The method according to claim 5, wherein The first output layer includes 1 third neuron, and the second evaluation result is the device matching probability corresponding to the target vessel; The obtaining of the second evaluation result through the second output layer according to the second feature vector includes: Inputting the second feature vector into the second output layer, and outputting the device matching probability, where the device matching probability is used to represent the probability that the device on the target vessel is a sand mining operation device.

7. The method according to claim 6, characterized in that The preset evaluation result threshold includes a first evaluation result threshold and a second evaluation result threshold; The determining of the target recognition result based on the first evaluation result, the second evaluation result, and the preset evaluation result threshold includes: If the behavior probability is not less than the first evaluation result threshold and the device matching probability is not less than the second evaluation result threshold, then determining the target recognition result as that the target vessel conducts sand mining operations in the sand mining operation area.

8. An underwater sand mining identification device, characterized in that, The device includes: A first unit, configured to obtain the target area information corresponding to the target area, the sand mining operation area information corresponding to the sand mining operation area in the target area information, the device information of the target vessel, and the navigation information of the target vessel in the target area information, where the target area information is used to represent the condition of the monitored water area, and the sand mining operation area is used to represent the condition of the sand mining operation area in the target area; A second unit, configured to obtain a first evaluation result through a preset first model according to the target area information, the sand mining operation area information, and the navigation information, where the first evaluation result is used to represent the evaluation of the navigation condition of the target vessel in the target area; the target area information includes target area coordinate data, the sand mining operation area information includes sand mining operation area coordinate data, and the navigation information includes navigation trajectory data and navigation speed data; The third unit is configured to obtain a second evaluation result according to the device information and the pre-stored sand mining operation device information through a preset second model, where the second evaluation result is used to characterize the evaluation of the device condition on the target vessel; the device information includes device type information, device power data, and device size data; The fourth unit is configured to determine a target recognition result based on the first evaluation result, the second evaluation result, and a preset evaluation result threshold, where the target recognition result is used to characterize the determination result of whether the target vessel is performing sand mining operations in the target area.

9. A terminal, characterized in that, It includes a processor and a memory, and the memory stores multiple instructions; the processor loads the instructions from the memory to execute the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The medium stores multiple instructions, and the instructions are suitable for being loaded by the processor to execute the steps in the method according to any one of claims 1 to 7.

Images