A target identification method and device, electronic equipment and storage medium

Abstract

The application provides a target identification method and device, electronic equipment and storage medium, relates to the intelligent transportation technical field, and obtains accurate target object information by obtaining the information of the target object, fusing the information corresponding to the maximum similarity. The method comprises the following steps: obtaining first information of a first object; determining a first range with the position of the first object as the center under the condition that the position of the first object is within a preset region range; determining second information of at least one second object in the first range; determining a first similarity between the first information and the second information; the first similarity comprises one of a position similarity, a heading angle similarity and an identification similarity between the first information and the second information; and fusing the second information corresponding to the maximum first similarity in the at least one first similarity and the first information to obtain target information of the first object.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a target recognition method, device, electronic device and storage medium. Background Technology

[0002] With the rapid development of global shipping, ship target identification has become a challenging task for maritime transportation departments. Radar systems and Automatic Identification Systems (AIS) are important methods for ensuring the safety of ship navigation and achieving maritime supervision.

[0003] In existing technologies, ship information acquired through radar systems and ship information collected through Automatic Identification Systems (AIS) is typically fused. During this fusion process, error processing is required to address the errors in the information obtained from both methods, thus yielding more accurate ship information. However, current fusion methods rely on relatively simple error processing techniques and cannot guarantee the accuracy of the fused ship information. Summary of the Invention

[0004] This application provides a target identification method, device, electronic device, and storage medium. It acquires information about a target object through radar equipment and a preset data collection method, determines the positional similarity, heading angle similarity, or identification similarity between the target object information acquired by the above two methods, eliminates information corresponding to smaller similarities, and fuses the information corresponding to the largest similarity, thereby obtaining more accurate information about the target object and reducing the error problems existing in the fusion process.

[0005] In a first aspect, this application provides a target identification method, the method comprising: acquiring first information of a first object, the first information including the position, heading angle, and identification information of the first object, the first information of the first object being acquired by radar equipment; determining a first range centered on the position of the first object if the position of the first object is within a preset area; determining second information of at least one second object within the first range; the second information including the predicted position, speed, heading angle, and identification information of the second object; determining a first similarity between the first information and at least one second information; the first similarity including one of positional similarity, heading angle similarity, and identification similarity between the first information and the second information; fusing the second information corresponding to the largest first similarity among the at least one first similarity with the first information to obtain target information of the first object; the target information including the target position of the first object, the heading angle of the first object at the target position, and the target identification information of the first object.

[0006] Understandably, the second information corresponding to the highest first similarity is the information sent by the first object. This method can reduce interference from the second information corresponding to other objects, determine the second information corresponding to the first object from at least one set of second information, and then fuse it with the first information about the first object acquired by the radar equipment to obtain more accurate information about the first object's position, heading angle, and identification. This method overcomes the shortcomings of inaccurate and large-error object information obtained by single-device reported object information and existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained through final fusion can help managers gain a more accurate understanding of the actual situation of ports, ships, etc.

[0007] In some embodiments, the second information for determining at least one second object within a first range includes: selecting data signals transmitted by at least one second object located within a first range from data signals received by the Automatic Identification System (AIS) within a preset time period; the data signals include: the transmission time of the data signals, the position of the second object at the transmission time, and the speed, heading angle, and identification information of the second object; the preset time period is determined based on the acquisition time of the first information; for each of the at least one second object, determining the predicted position of the second object at the acquisition time of the first information based on the acquisition time of the first information and the data signals transmitted by the second object; and determining the second information of at least one second object based on the data signals transmitted by the at least one second object and the predicted position of the second object.

[0008] In some embodiments, determining the first similarity between the first information and at least one second information includes: obtaining at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; and determining the distance difference as the first similarity.

[0009] In some embodiments, determining the first similarity between the first information and at least one second information includes: obtaining at least one distance difference between the position of the first object in the first information and the predicted position in each second information; if, among the at least one distance difference, there is a target distance difference within a preset distance difference range, obtaining at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target distance difference; if, among the at least one identifier similarity, there is a target identifier similarity within a preset identifier similarity range, obtaining the angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target identifier similarity; and determining the angle difference as the first similarity.

[0010] In some embodiments, determining the first similarity between the first information and at least one second information includes: obtaining at least one distance difference between the position of the first object in the first information and the predicted position in each second information; if, among the at least one distance difference, there is a target distance difference within a preset distance difference range, obtaining at least one angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target distance difference; if, among the at least one angle difference, there is a target angle difference within a preset angle difference range, obtaining at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target angle difference; and determining the identifier similarity as the first similarity.

[0011] In some embodiments, the above-mentioned method of fusing the second information corresponding to the largest first similarity among at least one first similarity with the first information to obtain the target information of the first object includes: when the first similarity is an identifier similarity and there is a corresponding second information for the largest identifier similarity, fusing the second information corresponding to the largest identifier similarity with the first information to obtain the target information of the first object.

[0012] In some embodiments, the above-mentioned method of fusing the second information corresponding to the largest first similarity among at least one first similarity with the first information to obtain the target information of the first object includes: when the first similarity is an identifier similarity and there are multiple corresponding second information for the largest identifier similarity, obtaining the distance difference between the location of the first object and the predicted location of the second information corresponding to each largest identifier similarity; and fusing the second information corresponding to the smallest distance difference with the first information to obtain the target information of the first object.

[0013] In some embodiments, the above-mentioned fusion of the second information corresponding to the largest first similarity among at least one first similarity with the first information to obtain the target information of the first object includes: using the position of the first object in the first information as the target position in the target information of the first object; using the heading angle in the first information as the heading angle in the target information of the first object; and using the identification information in the second information corresponding to the largest first similarity as the target identification information in the target information of the first object.

[0014] Secondly, this application provides a target identification device, comprising: an acquisition unit, a determination unit, and a fusion unit; the acquisition unit is configured to acquire first information of a first object, the first information including the position, heading angle, and identification information of the first object, the first information of the first object being collected by radar equipment; the determination unit is configured to determine a first range centered on the position of the first object when the position of the first object is within a preset area; the determination unit is configured to determine second information of at least one second object within the first range; the second information including the predicted position, speed, heading angle, and identification information of the second object; the determination unit is configured to determine a first similarity between the first information and at least one second information; the first similarity includes one of positional similarity, heading angle similarity, and identification similarity between the first information and the second information; the fusion unit is configured to fuse the second information corresponding to the largest first similarity among the at least one first similarity with the first information to obtain target information of the first object; the target information includes the target position of the first object, the heading angle of the first object at the target position, and the target identification information of the first object.

[0015] In some embodiments, the apparatus further includes: a selection unit; the selection unit is configured to select, from data signals received by the Automatic Identification System (AIS) within a preset time period, data signals transmitted by at least one second object whose location is within a first range; the data signals include: the transmission time of the data signals, the position of the second object at the transmission time, and the speed, heading angle, and identification information of the second object; the preset time period is determined based on the acquisition time of the first information; a determination unit is configured to, for each of the at least one second object, determine the predicted position of the second object at the acquisition time of the first information based on the acquisition time of the first information and the data signals transmitted by the second object; the determination unit is further configured to determine second information of at least one second object based on the data signals transmitted by at least one second object and the predicted position of the second object.

[0016] In some embodiments, the acquisition unit is configured to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; the determination unit is configured to determine the distance difference as a first similarity.

[0017] In some embodiments, the acquisition unit is configured to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; the acquisition unit is configured to acquire at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target distance difference if there is a target identifier similarity within the preset distance difference range among the at least one distance difference; the acquisition unit is configured to acquire the angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target identifier similarity if there is a target identifier similarity within the preset identifier similarity range among the at least one identifier similarity; and the determination unit is configured to determine the angle difference as the first similarity.

[0018] In some embodiments, the acquisition unit is configured to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; the acquisition unit is configured to acquire at least one angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target distance difference if there is a target distance difference within a preset distance difference range in the at least one distance difference; the acquisition unit is configured to acquire at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target angle difference if there is a target angle difference within a preset angle difference range in the at least one angle difference; and the determination unit is configured to determine the identifier similarity as a first similarity.

[0019] In some embodiments, the fusion unit is configured to fuse the second information corresponding to the largest identifier similarity with the first information to obtain the target information of the first object, provided that the first similarity is the identifier similarity and there is a corresponding second information for the largest identifier similarity.

[0020] In some embodiments, the acquisition unit is configured to acquire the distance difference between the location of the first object and the predicted location of the second information corresponding to each maximum identifier similarity when the first similarity is an identifier similarity and there are multiple corresponding second information when the maximum identifier similarity exists; the fusion unit is configured to fuse the second information corresponding to the minimum distance difference with the first information to acquire the target information of the first object.

[0021] In some embodiments, the fusion unit is configured to use the position of the first object in the first information as the target position in the target information of the first object; the fusion unit is configured to use the heading angle in the first information as the heading angle in the target information of the first object; and the fusion unit is configured to use the identification information in the second information corresponding to the largest first similarity as the target identification information in the target information of the first object.

[0022] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor; the memory and the processor are coupled; the memory is used to store computer program code, the computer program code including computer instructions; wherein, when the processor executes the computer instructions, the electronic device performs a target recognition method as described in the first aspect and any of its possible design schemes.

[0023] Fourthly, this application provides a computer-readable storage medium comprising: computer software instructions; which, when executed in an electronic device, cause the electronic device to implement the method described in the first aspect.

[0024] Fifthly, this application provides a computer program product that, when run on an electronic device, causes the electronic device to perform the steps of the relevant method described in the first aspect above, so as to implement the method of the first aspect above.

[0025] The beneficial effects of the second to fifth aspects mentioned above can be referred to the corresponding description of the first aspect, and will not be repeated here. Attached Figure Description

[0026] Figure 1 A schematic diagram of the structure of a target recognition system provided in this application;

[0027] Figure 2 A flowchart illustrating a target recognition method provided in this application. Figure 1 ;

[0028] Figure 3 A schematic diagram of an aquatic environment provided for this application Figure 1 ;

[0029] Figure 4 This application provides a flowchart illustrating the process of determining second information of a second object.

[0030] Figure 5 A schematic diagram of an aquatic environment provided for this application Figure 2 ;

[0031] Figure 6 A flowchart illustrating a target recognition method provided in this application. Figure 2 ;

[0032] Figure 7 A flowchart illustrating a target recognition method provided in this application. Figure 3 ;

[0033] Figure 8 A flowchart illustrating a target recognition method provided in this application. Figure 4 ;

[0034] Figure 9A flowchart illustrating a target recognition method provided in this application. Figure 5 ;

[0035] Figure 10 A flowchart illustrating a target recognition method provided in this application. Figure 6 ;

[0036] Figure 11 A schematic diagram of a target recognition device provided in this application;

[0037] Figure 12 This is a schematic diagram of the hardware structure of an electronic device provided in this application. Detailed Implementation

[0038] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0039] It should be noted that in the embodiments of this application, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplarily" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0040] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0041] The prior art involved in this disclosure is explained below.

[0042] I. Automatic Identification System (AIS): A new type of navigation aid. The basic function of AIS is to automatically and periodically broadcast dynamic information such as the precise position, heading, speed (vector line), turning speed, and nearest encounter distance of the vessel and other vessels, as well as static information such as the vessel's name, call sign, type, length, and beam, via VHF. Vessels equipped with AIS within the VHF coverage area (20 nautical miles) can automatically receive this information.

[0043] II. The World Geodetic System (WGS84 coordinate system) is a geodetic system standard used in cartography, geodesy, and navigation (including the Global Positioning System).

[0044] 3. PI represents the ratio of the circumference to the diameter of a circle, which is approximately 3.14159.

[0045] IV. Rhinestein distance: This refers to the minimum number of editing operations required to transform one string into another. The Rhinestein distance can be used to calculate the similarity between two strings.

[0046] With the rapid development of global shipping, ship target identification has become a challenging task for maritime transportation departments. Radar systems and AIS systems are important methods for ensuring ship navigation safety and achieving maritime surveillance.

[0047] Both radar and AIS systems have their advantages and disadvantages. Radar signals are stable and can acquire information such as the position, speed, and bearing of targets in a fixed area within a fixed time frame. However, they cannot accurately acquire static information about targets; for example, the accuracy of a ship's name cannot be guaranteed. Furthermore, radar often only acquires information about targets within its scanning range, and in the presence of blind spots, it may be unable to receive the latest information about ships in a timely manner. Automatic Identification Systems (AIS) can acquire dynamic information about ships, such as their position, speed, heading angle, and rotation angle, as well as static information such as their name, Maritime Mobile Service Identifier (MMSI), call sign, and ship type. However, AIS suffers from unstable signals and the inability to periodically receive AIS data.

[0048] In existing technologies, ship information acquired through radar systems and ship information collected through Automatic Identification Systems (AIS) is typically fused. During this fusion process, error processing is required to address the errors in the information obtained from both methods, thus yielding more accurate ship information. However, current fusion methods rely on relatively simple error processing techniques and cannot guarantee the accuracy of the fused ship information.

[0049] To address this problem, embodiments of this application provide a target identification method, apparatus, electronic device, and storage medium. In this method, the position, heading angle, and identification information of a first object are acquired; the position, speed, heading angle, and identification information of at least one second object are determined; by determining one of the position similarity, heading angle similarity, and identification similarity between the first information and at least one second information, the second object sending the second information corresponding to the highest first similarity can be identified as the first object. Therefore, fusing the second information corresponding to the highest first similarity with the first information yields more accurate information about the position, heading angle, and identification of the first object.

[0050] The method provided in this application can reduce interference from second information corresponding to other objects, determine the second information corresponding to the first object from at least one set of second information, and then fuse it with the first information about the first object acquired by the radar device to obtain more accurate information about the position, heading angle, and identification of the first object. This method overcomes the shortcomings of object information reported by a single device and the inaccuracy and large error of object information obtained by existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained by the final fusion can help managers grasp a more accurate understanding of the actual situation of ports, ships, etc.

[0051] The target identification method provided in this application embodiment can be applied to, for example... Figure 1 The identification device 103 shown is used in the target identification system 11, which includes radar device 101, ship data collection device 102, and identification device 103.

[0052] The target recognition system 11 can be applied in aquatic environments such as sea areas, rivers, coastlines, inland rivers, and lakes, with ships in the aquatic environment as the target objects for recognition.

[0053] Radar device 101 can periodically acquire radar data about the target object from the radar base station via network. The radar data of the target object mainly includes information such as the target object's position, relative position (between the target object and the radar device), speed, heading angle, and relative distance (the distance between the target object and the radar device).

[0054] Radar device 101 may include an image capturing device. Through the image capturing device, radar device 101 can acquire video image information about a target object, and analyze and identify the target object's identification information using image recognition technology. For example, by acquiring video image information containing a ship's name, the image recognition technology can be used to analyze the video image information and identify the ship's name.

[0055] The ship data collection device 102 can acquire AIS signals actively reported by the target object (ship) and thus obtain AIS data about the target object. The ship data collection device 102 can acquire AIS messages from the AIS signals. The AIS data contained in the AIS messages includes the reporting time (sending time) of the AIS signal, ship dynamic information, and ship static information. The ship dynamic information mainly includes the ship's position, speed, and heading angle, while the ship static information mainly includes the ship's name, maritime mobile communication service identifier, length, beam, location of the AIS device, and port of arrival.

[0056] In some embodiments, the ship data collection device 102 parses AIS data according to the standard AIS message protocol.

[0057] In other embodiments, the target identification system 11 can obtain AIS messages in the AIS signal by accessing the ship data collection device 102, and parse the AIS data according to the standard AIS message protocol.

[0058] In some embodiments, radar device 101 acquires the target position and relative position of the ship in polar coordinates (range and bearing) or WGS84 coordinates (latitude and longitude). Ship data collection device 102 acquires the ship's position in the AIS signal in polar coordinates (range and bearing) or WGS84 coordinates (latitude and longitude). To unify the coordinate systems for easier subsequent data processing, the ship positions acquired by the two devices can be unified into WGS84 coordinates (latitude and longitude) or polar coordinates (range and bearing), thus facilitating comparison of the ship positions acquired by the two devices.

[0059] In some embodiments, the identification device 103 unifies the ship positions acquired by the two devices into latitude and longitude information in the WGS84 coordinate system or distance and bearing information in the polar coordinate system.

[0060] The identification device 103 can determine whether the target position of the target object acquired by the radar device 101 is within a preset area, and determine the positional similarity, heading angle similarity, or identification similarity between the radar data of the target object acquired by the radar device 101 and the AIS data of the target object acquired by the ship data collection device 102. The identification device 103 can also remove information corresponding to lower similarities and fuse the information corresponding to the highest similarities, thereby obtaining more accurate information about the target object and reducing errors in the fusion process.

[0061] It is understandable that the radar device 101 of the target identification system 11 acquires the position, heading angle, and identification information of the first object; the ship data collection device 102 acquires the position, heading angle, and identification information of at least one second object (the second object includes the first object); and the identification device 103 determines one of the position similarity, heading angle similarity, and identification similarity between the first information and at least one second information. This allows us to identify the second object that sends the second information with the highest first similarity as the first object. Therefore, by fusing the second information with the highest first similarity by the identification device 103, we can obtain more accurate information about the position, heading angle, and identification of the first object. This method overcomes the shortcomings of inaccurate and error-prone object information reported by a single device and existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained through fusion can help managers gain a more accurate understanding of the actual situation of ports, ships, etc.

[0062] Figure 2 This is a schematic flowchart illustrating a target recognition method provided in an embodiment of this application. For example, the target recognition method provided in this embodiment can be applied to... Figure 1 The identification device 103 shown is an example. Figure 2 As shown, the target identification method provided in this application embodiment may specifically include the following steps S101 to S105.

[0063] S101, Obtain the first information of the first object.

[0064] The first information includes the position, heading angle, and identification information of the first object; the first information of the first object is collected by radar equipment.

[0065] In some embodiments, theoretical location markers are typically marked within the target environment, and the latitude and longitude information of the theoretical location markers is recorded. When a first object actually passes through the theoretical location marker, first information about the first object is acquired through radar equipment.

[0066] The location of the first object can be represented by latitude and longitude or by polar coordinates.

[0067] S102. If the position of the first object is within a preset area, determine a first range centered on the position of the first object.

[0068] The preset area can be a 5m, 10m, or 20m radius around a pre-recorded theoretical position marker. Determining whether the position of the first object is within the preset area involves checking if the distance between the first object's position and the theoretical position marker is within the preset area.

[0069] In some embodiments, if the latitude and longitude of the first object's location are not within a preset area, the first information is discarded. It is understood that if the location is within the preset area, the first information acquired by the radar device regarding the first object is considered valid; otherwise, it is considered invalid. Discarding invalid information can remove interfering information, such as information about pedestrians or vehicles outside the aquatic environment, thereby reducing the impact on acquiring information about the first object.

[0070] For example, such as Figure 3 As shown, if the radar device obtains the position of the first object as radar position 1, and the radar distance 1 between radar position 1 and the theoretical position marker is within the preset area, then the information corresponding to radar position 1 is valid information, and the first range is determined with radar position 1 as the center; if the radar distance 1 between radar position 2 and the theoretical position marker is not within the preset area, then the information corresponding to radar position 2 is invalid information, and the information corresponding to radar position 2 is discarded.

[0071] In some embodiments, when the latitude and longitude of the location of the first object are within a preset area, the first range may be a circle with the location of the first object as the center and a radius of 20m, 50m, 100m or 200m.

[0072] S103. Determine the second information of at least one second object within the first range.

[0073] The second information includes the predicted position, speed, heading angle, and identification information of the second object. The predicted position can be represented by latitude and longitude or by polar coordinates.

[0074] In some embodiments, please refer to Figure 4 S103 may include S1031-S1033:

[0075] S1031. Select, from the data signals received by the Automatic Identification System of Ships within a preset time period, the data signals sent by at least one second object located within a first range.

[0076] The data signals include: the time of transmission of the data signals, the position of the second object at the time of transmission, and the speed, heading angle and identification information of the second object; the preset time period is determined according to the time of collection of the first information.

[0077] S1032. For each of the at least one second object, determine the predicted position of the second object at the time of acquisition of the first information based on the acquisition time of the first information and the data signal sent by the second object.

[0078] S1033. Determine the second information of at least one second object based on the data signal sent by at least one second object and the predicted position of the second object.

[0079] In some embodiments, the data signal may be an AIS signal. The AIS signal transmitted by at least one second object within a first range via the Automatic Identification System (AIS) can be received by a ship signal collection device, i.e., an AIS collection device.

[0080] In marine, riverine, coastal, inland, and lake environments, ships equipped with AIS equipment can transmit AIS signals. Within a first range centered on the location of a marker obtained by the radar system, AIS collection equipment can receive AIS signals transmitted by at least one ship within a preset time period (e.g., within 10, 20, 30 minutes, or 1 hour prior to the current time). These AIS signals can be transmitted by the same ship or by different ships.

[0081] AIS signals consist of AIS messages, which contain the reporting time (send time), vessel dynamic information, and vessel static information. The vessel dynamic information mainly includes the vessel's position, speed, and heading angle at the time of transmission, while the vessel static information mainly includes the vessel's name, type, MMS (Main Service Registry), length, beam, AIS device location, and port of arrival. The transmission time, vessel dynamic data, and static data can be parsed according to the standard AIS message protocol.

[0082] In some embodiments, when the AIS message contains the ship's position at the time of transmission in terms of latitude and longitude, the predicted position of the ship at the time of the first information acquisition can be calculated by referring to trigonometric functions. For example, let the latitude and longitude of the first point A be (LonA, LatA) and the latitude and longitude of the second point B be (LonB, LatB). Based on the 0-degree meridian, the positive value of longitude is taken for east longitude, the negative value of longitude is taken for west longitude, the latitude is taken as 90 minus the latitude value (90-Latitude) for north latitude, and the latitude is taken as 90 plus the latitude value (90+Latitude) for south latitude. Then, the two points after the above processing are counted as (MLonA, MLatA) and (MLonB, MLatB). Based on the derivation of trigonometric functions, we can obtain the following formula for calculating the distance between two points: C=sin(MLatA)*sin(MLatB)*cos(MLonA-MLonB)+cos(MLatA)*cos(MLatB); Distance=R*Arccos(C)*Pi / 180.

[0083] For example, a circular area with a radius of 100m centered on radar position 1 acquired by the radar system is defined as the first range. AIS signals transmitted within the first range in the 30 minutes prior to the current time are collected, and the transmission time corresponding to each AIS signal, as well as the ship's position, speed, and heading angle at that transmission time, are obtained for each AIS signal. Figure 5 As shown, based on the five collected AIS signals, the ship's transmission position 1 corresponding to AIS signal 1, the ship's transmission position 2 corresponding to AIS signal 2, the ship's transmission position 3 corresponding to AIS signal 3, the ship's transmission position 4 corresponding to AIS signal 4, and the ship's transmission position 5 corresponding to AIS signal 5 can be obtained. Ship transmission position 2 and ship transmission position 3 represent the same ship's position at different times. Furthermore, based on the transmission time of each AIS signal, the acquisition time of the first information, and the ship's position, speed, and heading angle at the transmission time, the predicted ship position 1 corresponding to AIS signal 1, the predicted ship position 2 corresponding to AIS signals 2 and 3, the predicted ship position 4 corresponding to AIS signal 4, and the predicted ship position 5 corresponding to AIS signal 5 at the acquisition time of the first information can be predicted.

[0084] S104. Determine the first similarity between the first information and at least one second information.

[0085] The first similarity includes one of the following: positional similarity, heading angle similarity, and identifier similarity between the first information and the second information.

[0086] Location similarity is the similarity between the location of a first object in the first set of information and its predicted location in the second set of information. When the location of the first object and the predicted location are represented using the same coordinate type, location similarity can be determined by the similarity of their latitude and longitude coordinates or their polar coordinates. Location similarity can also be determined by the distance difference between the location of the first object in the first set of information and its predicted location in the second set of information; the smaller the distance difference, the greater the location similarity.

[0087] Heading angle similarity is the similarity between the heading angles in the first piece of information and the heading angles in the second piece of information. Heading angle similarity can be determined by calculating the absolute difference between the heading angles in the first piece of information and the heading angles in the second piece of information; the smaller the absolute difference, the greater the heading angle similarity.

[0088] Icon similarity is the similarity between icon information in the first set of information and icon information in the second set of information. It is generally expressed as ship name similarity; the greater the ship name similarity, the greater the icon similarity. Ship name similarity can be calculated using the Levenstein distance algorithm.

[0089] The Levenstein distance algorithm is based on the idea of ​​dynamic programming, as follows:

[0090] 1. Let the length of s (ship name acquired by radar equipment) be n, and the length of t (ship name acquired by AIS acquisition equipment) be m. If n = 0, return m and exit; if m = 0, return n and exit. Otherwise, construct an array d[0..m,0..n].

[0091] 2. Initialize row 0 to 0..n and column 0 to 0..m. Check each letter of s in turn (i = 1..n) and check each letter of t in turn (j = 1..m).

[0092] 3. If s[i] = t[j], then cost = 0; if s[i] ! = t[j], then cost = 1. Set d[i,j] to the minimum of the following three values:

[0093] (1) Increment the value of the cell immediately above the current cell by one, i.e., d[i-1,j]+1.

[0094] (2) Increment the value of the cell immediately to the left of the current cell by one, i.e., d[i,j-1]+1.

[0095] (3) Add cost to the value of the cell to the left of the current cell, i.e., d[i-1,j-1]+cos.

[0096] 4. Repeat steps 3-6 until the loop ends. d[n,m] is the Rhinestein distance.

[0097] For example, consider two strings, abc and abe.

[0098] a b c 0 1 2 3 a 1 Point A 0 D location 1 G2 b 2 Location B, 1 E point 0 H1 e 3 C2 F1 I.

[0099] In this case, the two 'a's at point A are the same, so s[i] = t[j], and cost = 0. According to (1), the value of the cell immediately above the current cell is increased by one, so 1 + 1 = 2. According to (2), the value of the cell immediately to the left of the current cell is increased by one, so 1 + 1 = 2. According to (3), the value of the cell to the upper left of the current cell is increased by cost, and the value of the upper left corner is increased by 0, so 0 + 0 = 0. The minimum value among 2, 2, and 0 is taken at point A, so point A is 0. Similarly, the values ​​at points B, C, D, E, F, G, H, and I are 1.

[0100] The meaning of each value is as follows: A indicates that 'a' and 'a' require 0 operations; B indicates that 'ab' and 'a' require 1 operation; C indicates that 'abe' and 'a' require 2 operations; D indicates that 'a' and 'ab' require 1 operation; E indicates that 'ab' and 'ab' require 0 operations; F indicates that 'abe' and 'ab' require 1 operation; G indicates that 'a' and 'abc' require 2 operations; H indicates that 'ab' and 'abc' require 1 operation; I indicates that 'abe' and 'abc' require 1 operation.

[0101] Therefore, at position I, it indicates that abe and abc require one operation, where the similarity calculation formula is: The similarity between abe and abc is 1 - 1 / 3 = 0.666.

[0102] S105. Merge the second information corresponding to the largest first similarity among at least one first similarity with the first information to obtain the target information of the first object.

[0103] Among them, the largest first similarity refers to the largest positional similarity, the largest heading angle similarity, or the largest identifier similarity in the first similarity; the target information includes the target position of the first object, the heading angle of the first object at the target position, and the target identifier information of the first object.

[0104] It is understandable that the second information corresponding to the highest first similarity is the information sent by the first object. That is, the second object corresponding to the second information of the highest first similarity can be identified as the first object. Therefore, the second information corresponding to the highest first similarity is fused with the first information to obtain the target information of the first object.

[0105] The above embodiments offer at least the following advantages: they reduce interference from second information corresponding to other objects, determine the second information corresponding to the first object from at least one set of second information, and then fuse it with the first information about the first object acquired by the radar equipment to obtain more accurate information about the first object's position, heading angle, and identification. This method overcomes the shortcomings of inaccurate and error-prone object information reported by a single device and the object information obtained by existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained through final fusion can help managers gain a more accurate understanding of the actual situation of ports, ships, etc.

[0106] In some embodiments, since the dynamic information about the target vessel acquired by the radar equipment, such as the target vessel's position, speed, and heading angle, is relatively accurate, while the static information about the target vessel possessed by the AIS signal, such as the target vessel's name, type, and MMS, is relatively accurate, the second information corresponding to the largest first similarity among at least one first similarity values ​​is fused with the first information to obtain the target information of the first object, such as... Figure 6 As shown, the specific steps may include S1051 to S1053.

[0107] S1051. The position of the first object in the first information is taken as the target position in the target information of the first object.

[0108] Generally, radar equipment obtains the position of the first object in the first information with high accuracy, so the position of the first object obtained by the radar equipment is taken as the target position of the first object.

[0109] S1052. Use the heading angle in the first information as the heading angle in the target information of the first object.

[0110] Generally, the heading angle obtained by radar equipment in the first information is highly accurate, so the heading angle obtained by radar equipment is used as the heading angle of the first object.

[0111] S1053. Take the identification information in the second information corresponding to the largest first similarity as the target identification information in the target information of the first object.

[0112] Generally, radar equipment acquires identification information by capturing video images of a target object using an image capture device. Image recognition technology is then used to analyze and identify the target object's identification information. For example, by acquiring a video image containing a ship's name, image recognition technology can be used to analyze the video image and identify the ship's name. However, the accuracy of acquiring identification information via image capture is low when the radar equipment is too far from the target object, the video image is not clear, the image capture device is malfunctioning, or parts of the target object's identification information are obscured.

[0113] The AIS signal acquired through the AIS collection device is a signal actively reported by the second object through its own AIS device. The AIS signal includes an AIS message, which contains the reporting time (sending time), ship dynamic information, and ship static information, with high accuracy. Therefore, using the identification information in the second information corresponding to the highest first similarity as the target identification information in the target information of the first object is a highly accurate method.

[0114] Understandably, the position and heading angles in the first information about the first object acquired by radar equipment are highly accurate. Therefore, these positions and heading angles are used as the position and heading angles of the first object. Conversely, the identification information in the second information about the first object acquired through a preset data collection method (AIS collection equipment) is highly accurate. Therefore, this identification information is used as the identification information of the first object. This method overcomes the shortcomings of inaccurate and error-prone object information reported by a single device and existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained through fusion can help managers gain a more accurate understanding of the actual situation of ports, ships, etc.

[0115] In some embodiments, when the first similarity between the first information and at least one piece of second information is the distance difference between the location of the first object and the predicted location, such as... Figure 7 As shown, steps S201 to S202 may be included.

[0116] S201. Obtain at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information, and determine the distance difference as the first similarity.

[0117] S202. Merge the second information corresponding to the largest first similarity among at least one first similarity with the first information to obtain the target information of the first object.

[0118] That is, the second information corresponding to the smallest distance difference among at least one distance difference is fused with the first information to obtain the target information of the first object. The second object corresponding to the second information of the smallest distance difference among the distance differences can be identified as the first object. Therefore, the second information corresponding to the largest first similarity is fused with the first information to obtain the target information of the first object.

[0119] The step of fusing the second information with the first information can be referred to steps S1051 to S1053.

[0120] Understandably, by obtaining at least one distance difference between the location of the first object in the first information and the predicted location in each of the second information, and then identifying the minimum distance difference, the second object in the second information corresponding to the minimum distance difference can be determined as the first object. Therefore, by eliminating other second information and fusing the second information corresponding to the minimum distance difference with the first information, the potential information error after fusion can be reduced, resulting in more accurate target information for the first object. This method overcomes the shortcomings of inaccurate and error-prone object information reported by a single device and existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained through fusion can help managers gain a more accurate understanding of the actual situation of ports, ships, etc.

[0121] In some embodiments, when the first similarity between the first information and at least one piece of second information is the distance difference between the location of the first object and the predicted location, such as... Figure 8 As shown, steps S301 to S305 may be included.

[0122] S301. Obtain at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information.

[0123] S302. If, in at least one distance difference, there exists a target distance difference within a preset distance difference range, obtain at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target distance difference.

[0124] In some embodiments, the preset distance difference range can be set to 10 meters, 20 meters, 0.1 kilometers, 0.5 kilometers, 1 kilometer, etc.

[0125] In other embodiments, at least one identifier similarity can be selected among the identifier information in the second information corresponding to the n smallest distance differences. Here, n can be 3, 5, etc.

[0126] It is understandable that the identification information in the first information is obtained and the second information corresponding to the distance difference of each target is removed, and the second information corresponding to the distance difference that is not within the preset distance difference range is eliminated, thereby eliminating the interference of the second information sent by non-first objects, such as the interference of the second information sent by other pedestrians' mobile devices, other vehicles and other objects.

[0127] For example, as described above Figure 5 As shown, three predicted ship positions that are relatively close to the radar position can be selected: predicted ship position 1, predicted ship position 2, and predicted ship position 5. The similarity between the identifier information in the first information and the identifier information in AIS signal 1 corresponding to predicted ship position 1, the similarity between the identifier information in the first information and the identifier information in AIS signal 2 corresponding to predicted ship position 2, and the similarity between the identifier information in the first information and the identifier information in AIS signal 5 corresponding to predicted ship position 5 are obtained.

[0128] Icon similarity is the similarity between icon information in the first set of information and icon information in the second set of information. It is generally expressed as ship name similarity; the greater the ship name similarity, the greater the icon similarity. Ship name similarity can be calculated using the Levenstein distance algorithm.

[0129] S303. If, in at least one identifier similarity, there exists a target identifier similarity within a preset identifier similarity range, obtain the angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target identifier similarity.

[0130] S304. Determine the angle difference as the first similarity.

[0131] S305. Merge the second information corresponding to the largest first similarity among at least one first similarity with the first information to obtain the target information of the first object.

[0132] That is, the second information corresponding to the smallest angle difference among at least one angle difference is fused with the first information to obtain the target information of the first object. The second object corresponding to the second information of the smallest angle difference can be identified as the first object. Therefore, the second information corresponding to the largest first similarity is fused with the first information to obtain the target information of the first object.

[0133] The step of fusing the second information with the first information can be referred to steps S1051 to S1053.

[0134] Understandably, the method involves first removing second information corresponding to distance differences outside the preset distance difference range, then obtaining second information corresponding to target distance differences within the preset range. From the second information corresponding to at least one target distance difference, second information with low similarity to the identifier information of the first information is removed, and the second information with high similarity is selected. Finally, the angle difference between the heading angle of at least one highly similar second information and the first heading angle is obtained, and this angle difference is determined as the first similarity. The second information corresponding to the largest first similarity can then be fused with the first information, i.e., the second information corresponding to the largest angle difference is fused with the first information. This method can reduce potential information errors after fusion, obtaining more accurate target information for the first object. This method overcomes the shortcomings of inaccurate and error-prone object information obtained from single-device reported object information and existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained through fusion can help managers gain a more accurate understanding of the actual situation of ports, ships, etc.

[0135] In some embodiments, when the first similarity between the first information and at least one piece of second information is the difference in heading between the position of the first object and the predicted position, such as... Figure 9 As shown, steps S401 to S405 may be included.

[0136] S401. Obtain at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information.

[0137] In some embodiments, among at least one distance difference, the distance differences are arranged in ascending order, and at least one identifier similarity is obtained between the identifier information in the first information and the identifier information in the second information corresponding to the first n distance differences. Here, n can be 3, 5, etc.

[0138] For example, as described above Figure 5 As shown, three predicted ship positions that are relatively close to the radar position can be selected: predicted ship position 1, predicted ship position 2, and predicted ship position 5. The similarity between the identifier information in the first information and the identifier information in AIS signal 1 corresponding to predicted ship position 1, the similarity between the identifier information in the first information and the identifier information in AIS signal 2 corresponding to predicted ship position 2, and the similarity between the identifier information in the first information and the identifier information in AIS signal 5 corresponding to predicted ship position 5 are obtained.

[0139] S402. If, in at least one distance difference, there is a target distance difference within a preset distance difference range, obtain at least one angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target distance difference.

[0140] In some embodiments, among at least one distance difference, the distance differences are arranged in ascending order, and at least one identifier similarity is obtained between the heading angle in the first information and the identifier information in the second information corresponding to the first n distance differences. Here, n can be 3, 5, etc.

[0141] S403. If, in at least one angle difference, there is a target angle difference within a preset angle difference range, obtain at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target angle difference.

[0142] Icon similarity is the similarity between icon information in the first set of information and icon information in the second set of information. It is generally expressed as ship name similarity; the greater the ship name similarity, the greater the icon similarity. Ship name similarity can be calculated using the Levenstein distance algorithm.

[0143] S404. The identifier similarity is determined as the first similarity.

[0144] S405. Merge the second information corresponding to the largest first similarity among at least one first similarity with the first information to obtain the target information of the first object.

[0145] That is, the second information corresponding to the minimum identifier similarity among at least one identifier similarity is fused with the first information to obtain the target information of the first object. The second object corresponding to the second information of the minimum identifier similarity among the identifier similarities can be determined as the first object. Therefore, the second information corresponding to the maximum first similarity is fused with the first information to obtain the target information of the first object.

[0146] The step of fusing the second information with the first information can be referred to steps S1051 to S1053.

[0147] Understandably, the method involves first removing second information corresponding to distance differences outside the preset distance difference range, then obtaining second information corresponding to target distance differences within the preset range. From the second information corresponding to at least one target distance difference, second information with a large angle difference from the first information is removed, and second information with a small angle difference from the first information is selected. Finally, the similarity between the heading angle of at least one second information with a small angle difference and the first heading angle is obtained, and this similarity is determined as the first similarity. The second information corresponding to the largest first similarity is then fused with the first information, i.e., the second information corresponding to the largest label similarity is fused with the first information. This method can reduce potential information errors after fusion, obtaining more accurate target information for the first object. This method overcomes the shortcomings of inaccurate and error-prone object information obtained from single-device reported object information and existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained through fusion can help managers gain a more accurate understanding of the actual situation of ports, ships, etc.

[0148] In some embodiments, when the first similarity is the identifier similarity, the largest identifier similarity may have a corresponding second information, which may include step S4011.

[0149] S4011. If the first similarity is the identifier similarity, and there is a corresponding second information for the largest identifier similarity, the second information corresponding to the largest identifier similarity is fused with the first information to obtain the target information of the first object.

[0150] The step of fusing the second information with the first information can be referred to steps S1051 to S1053.

[0151] In other embodiments, when the first similarity is the identifier similarity, the largest identifier similarity may have multiple corresponding second information, which may include steps S4021 to S4022.

[0152] S4021. When the first similarity is the identifier similarity and there are multiple corresponding second information for the largest identifier similarity, obtain the distance difference between the position of the first object of the first object and the position of the second information corresponding to each largest identifier similarity.

[0153] For example, AIS signal 1 contains the ship name 1 as CSCL LE HAVRE, AIS signal 2 contains the ship name 2 as CSCL LH HAVRE, AIS signal 5 contains the ship name 5 as CSHF LE HAVRE, and the ship name of the first object acquired by the radar is CSCL LK HAVRE. Using the Levinstein distance algorithm, the similarity between ship name 1 and the ship name of the first object is 0.909, the similarity between ship name 2 and the ship name of the first object is 0.909, and the similarity between ship name 5 and the ship name of the first object is 0.727. It can be seen that ship name 1 and ship name 2 have the highest similarity to the ship name of the first object, and they are identical.

[0154] In the above case, the distance difference 1 between the ship's predicted position 1 corresponding to AIS signal 1 and the position of the first object acquired by the radar is obtained, and the distance difference 2 between the ship's predicted position 2 corresponding to AIS signal 2 and the position of the first object acquired by the radar is obtained.

[0155] S4022. Merge the second information corresponding to the minimum distance difference with the first information to obtain the target information of the first object.

[0156] The step of fusing the second information with the first information can be referred to steps S1051 to S1053.

[0157] For example, as described above Figure 5 As shown, distance difference 1 is 0.1 km and distance difference 2 is 0.5 km, indicating that the second object sending AIS signal 1 is the first object. Therefore, the second information corresponding to AIS signal 1 is fused with the first information to obtain the target information of the first object.

[0158] Understandably, when the first similarity is the identifier similarity, the highest identifier similarity corresponds to a second piece of information, which can be directly fused with the first information. However, when the highest identifier similarity has multiple corresponding second pieces of information, it is necessary to further obtain the distance difference between the location of the first object and the location of the second piece of information corresponding to each highest identifier similarity, and determine the second piece of information corresponding to the smallest distance difference. The second object corresponding to this second piece of information is the actual first object. The method in this implementation can reduce the interference of second information corresponding to other objects, determine the second information corresponding to the first object from at least one piece of second information, and then fuse it with the first information to obtain more accurate target information of the first object. This method overcomes the shortcomings of object information reported by a single device and the inaccuracy and large error of object information obtained by existing fusion methods. Furthermore, when this method is applied to ships, the highly accurate ship information obtained by the final fusion can help managers grasp a more accurate understanding of the actual situation of ports, ships, etc.

[0159] In some embodiments, such as Figure 10 As shown, it may also include steps S1 to S14.

[0160] S1. Mark the theoretical position of the target environment. When a target ship actually passes through the theoretical position mark, obtain the first information about the target ship through radar equipment. The first information includes the latitude and longitude position of the target ship, the heading angle of the target ship, and the ship name.

[0161] S2. Determine the error value between the latitude and longitude position of the target ship acquired by the radar equipment and the latitude and longitude position of the theoretical position marker. If the error value is within the preset error range, proceed to step S3; if the error value is not within the preset error range, proceed to step S14.

[0162] S3. Acquire multiple Automatic Identification Signals (AIS) received within one hour prior to the current time using ship signal collection equipment; each AIS includes information such as the time of transmission, the ship's heading angle, speed, name, type, and MMSI.

[0163] S4. Based on the transmission time of each ship's automatic identification signal, the current time, and the corresponding ship's speed and heading angle, determine the predicted latitude and longitude position of the corresponding ship at the current time.

[0164] S5. Calculate the distance difference between the latitude and longitude position of the target ship obtained by the radar equipment and each predicted latitude and longitude position.

[0165] S6. Obtain the automatic identification signals of the three closest distance differences from multiple distance differences.

[0166] S7. If the target recognition system is configured with ship name similarity rules, execute steps S8 and S9. If the target recognition system is not configured with ship name similarity rules, execute step S10.

[0167] S8. Calculate the similarity between the ship names in the Automatic Identification Signals corresponding to the three closest distance differences and the ship names acquired by the radar equipment.

[0168] S9. Determine the ship automatic identification signal corresponding to the maximum similarity within the preset similarity range, and then execute step S11.

[0169] S10. If the target identification system is configured with heading calculation rules, execute steps S11 and S12; if the target identification system is not configured with heading calculation rules, execute step S12.

[0170] S11. Calculate the angle difference between the heading angle in the ship's automatic identification signal and the heading angle obtained by the radar equipment. If the angle difference meets the preset angle difference range, proceed to step S12; if the angle difference is not within the preset angle difference range, proceed to step S14.

[0171] S12. From the automatic identification signals of ships that meet the conditions, determine the automatic identification signal of the ship corresponding to the minimum distance difference or the automatic identification signal of the ship corresponding to the maximum similarity.

[0172] S13. The information in the Automatic Identification Signal of the vessel is fused with the first information obtained by the radar system. Specifically, this includes: using the vessel name, vessel type, and MMSI of the vessel in the Automatic Identification Signal as the vessel name, vessel type, and MMSI of the target vessel, and using the latitude and longitude position and heading angle of the first information obtained by the radar system as the latitude and longitude position and heading angle of the target vessel.

[0173] S14. Remove this information; no data fusion is required.

[0174] The above embodiments offer at least the following advantages: By acquiring the position, heading angle, and identification information of the target vessel through radar equipment, determining the position, heading angle, and identification information of at least one vessel (including the target vessel), and obtaining first information from the information of the automatic identification signal of the vessel that meets the conditions and the radar system, more accurate information about the target vessel's position, heading angle, and identification can be obtained. The method in this embodiment can reduce interference from second information corresponding to other objects (other vessels), determine the second information corresponding to the target vessel from at least one set of second information, and then fuse it with the first information to obtain more accurate target information for the first object. This method overcomes the shortcomings of inaccurate and large-error object information obtained from object information reported by a single device and existing fusion methods. Furthermore, when this method is applied to vessels, the highly accurate vessel information obtained through final fusion can help managers grasp a more accurate understanding of the actual situation of ports, vessels, etc.

[0175] This application also provides a target recognition device; please refer to [link / reference]. Figure 11 The device includes: an acquisition unit 201, a determination unit 202, and a fusion unit 203.

[0176] Acquisition unit 201 is used to acquire first information of a first object, the first information including the position, heading angle, and identification information of the first object, the first information of the first object being acquired by radar equipment; determination unit 202 is used to determine a first range centered on the position of the first object when the position of the first object is within a preset area; determination unit 202 is used to determine second information of at least one second object within the first range; the second information includes the predicted position, speed, heading angle, and identification information of the second object; determination unit 202 is used to determine a first similarity between the first information and at least one second information; the first similarity includes one of position similarity, heading angle similarity, and identification similarity between the first information and the second information; fusion unit 203 is used to fuse the second information corresponding to the largest first similarity among at least one first similarity with the first information to obtain target information of the first object; the target information includes the target position of the first object, the heading angle of the first object at the target position, and the target identification information of the first object.

[0177] In some embodiments, the device further includes: a selection unit 204; the selection unit 204 is configured to select, from data signals received by the Automatic Identification System (AIS) within a preset time period, data signals transmitted by at least one second object whose location is within a first range; the data signals include: the transmission time of the data signals, the position of the second object at the transmission time, and the speed, heading angle, and identification information of the second object; the preset time period is determined based on the acquisition time of the first information; a determination unit 202 is configured to, for each of the at least one second object, determine the predicted position of the second object at the acquisition time of the first information based on the acquisition time of the first information and the data signals transmitted by the second object; the determination unit 202 is further configured to determine second information of at least one second object based on the data signals transmitted by at least one second object and the predicted position of the second object.

[0178] In some embodiments, the acquisition unit 201 is configured to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; the determination unit 202 is configured to determine the distance difference as a first similarity.

[0179] In some embodiments, the acquisition unit 201 is configured to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; the acquisition unit 201 is configured to acquire at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target distance difference when there is a target distance difference within a preset distance difference range among the at least one distance difference; the acquisition unit 201 is configured to acquire the angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target identifier similarity when there is a target identifier similarity within a preset identifier similarity range among the at least one identifier similarity; and the determination unit 202 is configured to determine the angle difference as the first similarity.

[0180] In some embodiments, the acquisition unit 201 is configured to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; the acquisition unit 201 is configured to acquire at least one angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target distance difference if there is a target distance difference within a preset distance difference range in the at least one distance difference; the acquisition unit 201 is configured to acquire at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target angle difference if there is a target angle difference within a preset angle difference range in the at least one angle difference; and the determination unit 202 is configured to determine the identifier similarity as a first similarity.

[0181] In some embodiments, the fusion unit 203 is used to fuse the second information corresponding to the largest identifier similarity with the first information to obtain the target information of the first object, when the first similarity is the identifier similarity and there is a corresponding second information for the largest identifier similarity.

[0182] In some embodiments, the acquisition unit 201 is used to acquire the distance difference between the location of the first object and the predicted location of the second information corresponding to each maximum identifier similarity when the first similarity is the identifier similarity and there are multiple corresponding second information when the maximum identifier similarity exists; the fusion unit 203 is used to fuse the second information corresponding to the minimum distance difference with the first information to acquire the target information of the first object.

[0183] In some embodiments, the fusion unit 203 is configured to use the position of the first object in the first information as the target position in the target information of the first object; the fusion unit 203 is configured to use the heading angle in the first information as the heading angle in the target information of the first object; and the fusion unit 203 is configured to use the identification information in the second information corresponding to the largest first similarity as the target identification information in the target information of the first object.

[0184] In the case where the functions of the integrated units described above are implemented in hardware, embodiments of this application provide a schematic diagram of the hardware composition of an electronic device. For example... Figure 12 As shown, the electronic device also includes: a processor 401, a communication interface 402, and a bus 404. Optionally, the electronic device may also include a memory 403.

[0185] Processor 401 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 401 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 401 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0186] Communication interface 402 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0187] The memory 403 may be a read-only memory 403 (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory 403 (RAM) or other type of dynamic storage device capable of storing information and instructions, or an electrically erasable programmable read-only memory 403 (EEPROM), a disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0188] As one possible implementation, the memory 403 can exist independently of the processor 401. The memory 403 can be connected to the processor 401 via a bus 404 and is used to store instructions or program code. When the processor 401 calls and executes the instructions or program code stored in the memory 403, it can implement the target recognition method provided in the embodiments of this application.

[0189] In another possible implementation, the memory 403 can also be integrated with the processor 401.

[0190] Bus 404 can be an extended industry standard architecture (EISA) bus, etc. Bus 404 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 12 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0191] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the electronic device can be divided into different functional modules to complete all or part of the functions described above.

[0192] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware. The program can be stored in the computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be any of the foregoing embodiments or memory. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Further, the computer-readable storage medium can include both internal storage units of the target identification device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0193] This application also provides a computer program product, which includes a computer program that, when run on an electronic device, causes the electronic device to perform the target recognition method provided in the above embodiments.

[0194] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple components. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0195] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0196] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A target recognition method characterized by, The method includes: Acquire first information about the first object, the first information including the position, heading angle and identification information of the first object, the first information of the first object being collected by radar equipment; If the location of the first object is within a preset area, a first range centered on the location of the first object is determined. Determine second information about at least one second object within the first range; the second information includes the predicted position, speed, heading angle, and identification information of the second object; Determine a first similarity between the first information and at least one piece of second information; the first similarity includes one of positional similarity, heading angle similarity, and identifier similarity between the first information and the second information; The second information corresponding to the largest first similarity in at least one of the first similarities is fused with the first information to obtain the target information of the first object; the target information includes the target location of the first object, the heading angle of the first object at the target location, and the target identification information of the first object; The step of fusing the second information corresponding to at least one of the largest first similarities with the first information to obtain the target information of the first object includes: When the first similarity is the identifier similarity, and there are multiple corresponding second information for the largest identifier similarity, the distance difference between the location of the first object and the predicted location of the second information corresponding to each of the largest identifier similarities is obtained; the second information corresponding to the smallest distance difference is fused with the first information to obtain the target information of the first object.

2. The method of claim 1, wherein, The second information for determining at least one second object within the first range includes: From the data signals received by the Automatic Identification System (AIS) within a preset time period, data signals transmitted by at least one second object whose location is within the first range are selected; the data signals include: the transmission time of the data signal, the position of the second object at the transmission time, and the speed, heading angle, and identification information of the second object; the preset time period is determined based on the acquisition time of the first information; For each of the at least one second object, the predicted position of the second object at the time of acquisition of the first information is determined based on the acquisition time of the first information and the data signal sent by the second object. Second information about the at least one second object is determined based on the data signal sent by the at least one second object and the predicted position of the second object.

3. The method according to claim 1 or 2, characterized in that, Determining the first similarity between the first information and at least one piece of second information includes: Obtain at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; The distance difference is determined as the first similarity.

4. The method according to claim 1 or 2, characterized in that, Determining the first similarity between the first information and at least one piece of second information includes: Obtain at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; If there is a target distance difference within the preset distance difference range in the at least one distance difference, obtain at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target distance difference; If, among the at least one identifier similarity, there exists a target identifier similarity within a preset identifier similarity range, the angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target identifier similarity is obtained; The angle difference is determined as the first similarity.

5. The method according to claim 1 or 2, characterized in that, Determining the first similarity between the first information and at least one piece of second information includes: Obtain at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; If, among the at least one distance difference, there is a target distance difference within a preset distance difference range, at least one angle difference is obtained between the heading angle in the first information and the heading angle in the second information corresponding to each target distance difference; If there is a target angle difference within a preset angle difference range in the at least one angle difference, at least one identifier similarity is obtained between the identifier information in the first information and the identifier information in the second information corresponding to each target angle difference. The identifier similarity is determined as the first similarity.

6. The method of claim 1, wherein, The step of fusing the second information corresponding to the largest first similarity among at least one of the first similarities with the first information to obtain the target information of the first object further includes: When the first similarity is the identifier similarity, and there is a corresponding second information for the largest identifier similarity, the second information corresponding to the largest identifier similarity is fused with the first information to obtain the target information of the first object.

7. The method according to claim 1 or 2, characterized in that, The step of fusing the second information corresponding to the largest first similarity among at least one of the first similarities with the first information to obtain the target information of the first object further includes: The position of the first object in the first information is taken as the target position in the target information of the first object; The heading angle in the first information is used as the heading angle in the target information of the first object; The identifier information in the second information corresponding to the highest first similarity is used as the target identifier information in the target information of the first object.

8. A target recognition device, characterized by The device includes: an acquisition unit, a determination unit, and a fusion unit; The acquisition unit is used to acquire first information of the first object, the first information including the position, heading angle and identification information of the first object, and the first information of the first object is acquired by radar equipment. The determining unit is used to determine a first range centered on the position of the first object when the position of the first object is within a preset area. The determining unit is configured to determine second information of at least one second object within the first range; the second information includes the predicted position, speed, heading angle, and identification information of the second object; The determining unit is configured to determine a first similarity between the first information and at least one piece of second information; the first similarity includes one of positional similarity, heading angle similarity, and identifier similarity between the first information and the second information; The fusion unit is used to fuse the second information corresponding to the largest first similarity in at least one of the first similarities with the first information to obtain the target information of the first object; the target information includes the target position of the first object, the heading angle of the first object at the target position, and the target identification information of the first object; The acquisition unit is used to acquire the distance difference between the location of the first object and the predicted location of the second information corresponding to each of the largest identifier similarities when the first similarity is the identifier similarity and there are multiple corresponding second information for the largest identifier similarity; the fusion unit is used to fuse the second information corresponding to the smallest distance difference with the first information to acquire the target information of the first object.

9. The apparatus of claim 8, wherein, Also includes: Select unit; The selection unit is used to select, from the data signals received by the Automatic Identification System (AIS) within a preset time period, the data signals transmitted by at least one second object whose location is within the first range; the data signals include: the transmission time of the data signal, the position of the second object at the transmission time, and the speed, heading angle, and identification information of the second object; the preset time period is determined based on the acquisition time of the first information; The determining unit is configured to, for each of the at least one second object, determine the predicted position of the second object at the time of acquisition of the first information based on the acquisition time of the first information and the data signal sent by the second object; the determining unit is further configured to determine the second information of the at least one second object based on the data signal sent by the at least one second object and the predicted position of the second object.

10. The apparatus according to claim 8 or 9, characterized in that, The acquisition unit is configured to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; the determination unit is configured to determine the distance difference as the first similarity. or, The acquisition unit is used to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; The acquisition unit is configured to, when there is a target distance difference within a preset distance difference range in the at least one distance difference, acquire at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target distance difference; the acquisition unit is configured to, when there is a target identifier similarity within a preset identifier similarity range in the at least one identifier similarity range, acquire the angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target identifier similarity. The determining unit is used to determine the angle difference as the first similarity. or, The acquisition unit is used to acquire at least one distance difference between the position of the first object in the first information and the predicted position in each of the second information; The acquisition unit is configured to, when there is a target distance difference within a preset distance difference range among the at least one distance difference, acquire at least one angle difference between the heading angle in the first information and the heading angle in the second information corresponding to each target distance difference; the acquisition unit is configured to, when there is a target angle difference within a preset angle difference range among the at least one angle difference, acquire at least one identifier similarity between the identifier information in the first information and the identifier information in the second information corresponding to each target angle difference; the determination unit is configured to determine the identifier similarity as the first similarity.

11. The apparatus of claim 8 or 9, wherein, The fusion unit is used to take the position of the first object in the first information as the target position in the target information of the first object; The fusion unit is used to use the heading angle in the first information as the heading angle in the target information of the first object; The fusion unit is used to take the identification information in the second information corresponding to the largest first similarity as the target identification information in the target information of the first object.

12. The apparatus of claim 8 or 9, wherein, The fusion unit is further configured to, when the first similarity is the identifier similarity and there is a corresponding second information for the largest identifier similarity, fuse the second information corresponding to the largest identifier similarity with the first information to obtain the target information of the first object.

13. An electronic device, comprising: It includes one or more processors and a memory; the processors and the memory are coupled; the memory is used to store computer program code, the computer program code including computer instructions; When the processor executes the computer instructions, it causes the electronic device to perform the method as described in any one of claims 1-7.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: computer software instructions; when the computer software instructions are executed in an electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-7.

Images