Unmanned surface vessel multivariate information combined sensing method and system

Abstract

The invention relates to the technical field of multi-information joint sensing, in particular to a multi-information joint sensing method and system for an unmanned surface vessel. The method comprises the following steps: acquiring target detection data of the water surface environment of the unmanned surface vessel; coordinate transformation and point cloud coordinate correction are carried out on the target detection data, and grid situation maps are constructed respectively; performing target segmentation and contour feature extraction on the grid situation map to obtain a target contour; a shore-based target and an overwater target are distinguished according to the complexity and the area of the target contour; many-to-one target matching and target attribute establishment of the laser radar and the navigation radar are completed; completing frame-by-frame matching of the target and updating of a target state list; and completing many-to-many matching of the target and the target state list established by Kalman filtering, and updating the attribute information of the target. According to the invention, advantage complementation of the laser radar and the navigation radar can be realized, leak detection and loss of the target are reduced, false alarm of the target is reduced, and tracking precision and stability of the target are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-information joint perception, and in particular to a method and system for multi-information joint perception of an unmanned surface vessel. Background Art

[0002] Unmanned boats have the advantages of strong maneuverability, easy deployment, wide coverage, and low cost. They can adapt to more dangerous working environments and have very broad application prospects. The quality of environmental perception is an important manifestation of the autonomy of unmanned boats. It mainly uses sensors on unmanned intelligent devices to obtain the state of the body and the environmental parameters in the environment, surrounding dynamics, relative distance, angle and motion state of multi-scale targets. However, due to the characteristics of wide sources, multiple levels, complex forms, strong timeliness, massive data, and uneven time and space scales of marine environmental information, the comprehensive and accurate perception of the environment by unmanned boats has become one of the biggest challenges to achieving fully autonomous navigation of unmanned boats.

[0003] Navigation radar can provide relative position and distance information of surrounding obstacles in a large range, and has many functions such as sea clutter, rain and snow suppression, and co-frequency interference suppression. It is a standard navigation sensor for target tracking and collision avoidance, but it can only reflect obstacle information in two-dimensional space, the target in the image is relatively rough, and there is a certain blind spot at close range. In addition, the radar update frequency is slow, which is prone to missed detection and loss of targets, resulting in a single navigation radar that cannot well reflect the current environmental information. LiDAR, which has been successfully used in self-driving cars, is suitable for close-range measurement. It has high accuracy and fast scanning frequency. It can provide accurate position and distance information of obstacles in the offshore range, but it has the disadvantages of being unable to detect blocked targets, only detecting one side of the target, missing data due to the swaying of the target and the unmanned boat, and inaccurate target segmentation. It is difficult for any single sensor to achieve complete and thorough perception of the environment. For the joint perception of multiple sensors, it is necessary to solve how to extract useful information from a large amount of overlapping and complementary environmental data collected through detection, so as to correctly and reliably perceive the environment and realize the complementary advantages of different sensors. Therefore, there is an urgent need to provide a method and system for joint perception of multi-information of unmanned surface vessels. Summary of the invention

[0004] In view of the shortcomings of the prior art mentioned above, the purpose of the present invention is to provide a method and system for the joint perception of multi-information of unmanned surface vessels, which can realize the complementary advantages of lidar and navigation radar, reduce missed detection and loss of targets, reduce false alarms of targets, and improve the tracking accuracy and stability of targets.

[0005] In order to achieve the above-mentioned and other related purposes, the present invention provides a method for joint perception of multi-information of an unmanned surface vessel, comprising:

[0006] S1. Use navigation radar and laser radar to obtain target detection data of the unmanned surface vehicle water environment;

[0007] S2, performing coordinate conversion and point cloud coordinate correction on the target detection data, and constructing grid situation maps respectively;

[0008] S3, performing target segmentation and contour feature extraction on the grid situation map to obtain a target contour;

[0009] S4, distinguishing shore-based targets from water-based targets by using the complexity and area of ​​the target contour;

[0010] S5, every first preset time, that is, the laser radar scans the first preset number of cycles, using the minimum distance between the center point of the target contour and the target contour to complete the many-to-one target matching of the laser radar and the navigation radar and establish the target attributes;

[0011] S6. Every second preset time, that is, the navigation radar scans the second preset number of cycles, completes frame-by-frame matching of the target and updates the target state list based on the Kalman filter, and realizes accurate tracking of the target and calculation of motion elements;

[0012] S7. Every third preset time, use the features of the current frame target to complete a many-to-many match between the target and the target state list established by the Kalman filter, and update the target's attribute information.

[0013] In one embodiment of the present invention, the first preset time is 200 ms, and the first preset number of cycles is two weeks; the second preset time is 1200 ms, and the second preset number of cycles is one week; and the third preset time is 200 ms.

[0014] In one embodiment of the present invention, the step S2 of performing coordinate conversion and point cloud coordinate correction on the target detection data and constructing grid situation maps respectively includes:

[0015] Step S2.1: The coordinate conversion is to convert the coordinates (d, θ) in the spherical coordinate system obtained by the laser radar real-time scanning into vertical ,θ horizon ) is converted to the Cartesian coordinate system, which are the distance, vertical angle and horizontal offset angle of the target point respectively. The conversion formula is as follows:

[0016]

[0017] The point cloud coordinate correction is that as the heading, pitch and sway of the unmanned boat change, the data obtained by the three-dimensional laser radar deviates from the real data. The combined navigation installed on the boat is used to obtain the unmanned boat's motion posture (α, β, θ) in real time, which are the roll angle, pitch angle and heading angle of the unmanned boat respectively. The correction formula is as follows:

[0018]

[0019] Among them, R is the attitude transformation matrix, T is the translation matrix;

[0020]

[0021] Step S2.2, the coordinate conversion is to convert the coordinates (d, γ) in the polar coordinate system obtained by real-time scanning of the navigation radar into the Cartesian coordinate system, which are the distance and horizontal angle of the target point respectively. The conversion formula is as follows:

[0022]

[0023] Navigation radar image correction, according to the current heading angle, the radar image is corrected, and the combined navigation installed on the boat is used to obtain the unmanned boat heading information θ in real time, so that the top of the radar image remains in the due north direction. The formula is:

[0024]

[0025] Step S2.3, the construction of the grid situation map is to divide the map into a series of grid units in rows and columns according to the range of the navigation radar. The unmanned boat is always the center of the grid map. The resolution r of the grid can be adjusted and set. The target points detected by the laser radar and the navigation radar are projected into the grid map. The conversion formula is as follows:

[0026]

[0027] Among them, (l, l) are the horizontal and vertical coordinates of the center point of the raster image, and the length and width of the raster map are equal; r is the resolution of the raster map; (x, y) are the coordinates of the target in the Cartesian coordinate system; (a, b) are the horizontal and vertical coordinates of the target point in the raster map, and the grayscale value of the coordinate point in the raster image is set to 1, that is, 1 in the raster image indicates that there is a target at this position, and 0 indicates that there is no target at this position.

[0028] In one embodiment of the present invention, performing target segmentation and contour feature extraction on the grid situation map in step S3 to obtain the target contour includes:

[0029] Step S3.1, segment the connected domain of the target by calling the cv::findContours function in the Opencv image processing library, extract the contour of each target in the image, and store all continuous contour points on the target boundary into the vector contours;

[0030] Step S3.2, calculate the minimum circumscribed rotation rectangle of the target contour through cv::minAreaRect in the Opencv image processing library, determine the coordinates of the target's center point, the length and width of the target, the angle and distance of the target relative to the unmanned boat, and the contour features of the target are expressed as:

[0031] TarFeature={(x,y),(w,l),(dis,angle),contour}.

[0032] In one embodiment of the present invention, the step S4 of distinguishing between shore-based targets and water-based targets by using the complexity and area of ​​the target contour includes:

[0033] Step S4.1, polygonal approximation is performed on the target contour point set by using the cv::approxPolyDP function in the Opencv image processing library, and the precision value of the approximation is epsilon. The output is the number of polylines and polyline coordinates of the target contour point set approximation. The more polylines there are, the more complex the target edge is, and vice versa, the simpler the target edge is;

[0034] Step S4.2, calculating the area of ​​the target contour by using the cv::contourArea function in the Opencv image processing library or the length and width in the target contour feature;

[0035] Step S4.3, set the target area threshold and contour complexity threshold, and divide the targets into shore-based targets and water targets. The shore-based targets are confirmed as static targets, and there is no need to calculate the motion attributes of the targets.

[0036] In one embodiment of the present invention, the step S5 of completing the many-to-one target matching of the laser radar and the navigation radar and establishing the target attributes by using the minimum distance between the center point of the target contour and the target contour at every first preset time, that is, the laser radar scans the first preset number of cycles, includes:

[0037] Step S5.1, call the cv::pointPolygonTest function in the Opencv image processing library to calculate the shortest distance between the center point of the laser radar target and the contour of the navigation radar target, and use it as the matching standard to match the targets detected by the laser radar and the navigation radar. Multiple laser radar targets can correspond to one navigation radar target, and the laser radar updates the matching once every two rotations;

[0038] Step S5.2: Establish target attributes based on the matching results, which can be expressed as:

[0039] TarAttribute={ID,TarFeature,MatchID,Confidence,MotionEle,TarSource}

[0040] Among them, ID is the number of the target; TarFeature is the target contour feature calculated in step S3; MatchID is the number of the target state list corresponding to the Kalman filter, which is currently empty; Confidence is the confidence of the target. Currently, the confidence of the target detected by the navigation radar is set to 0.3, and the confidence of the target detected by the lidar is set to 0.4. The confidence of the target that is successfully matched by the lidar and navigation radar is modified to 0.7; MotionEle is the motion element of the target, which is currently empty; TarSource is the source of the target.

[0041] In one embodiment of the present invention, the step S6 includes completing frame-by-frame matching of the target and updating the target state list based on Kalman filtering every second preset time, i.e., the navigation radar scans the second preset number of cycles, and realizing accurate tracking of the target and calculation of motion elements, which includes:

[0042] Step S6.1, the target state information in Kalman filtering is described as:

[0043] KAL_MEAN={x,y,angle,width,length,v x ,v y},

[0044] Among them, (v x ,v y ) is the speed of the target on the x and y axes, x and y are the coordinates of the center point of the target respectively. Since the coordinates (a, b) are in the grid map coordinate system, they need to be converted to adapt to the coordinate system of the speed. The formula is as follows:

[0045]

[0046] The state of the target is set during the Kalman filter process. When the number of target unmatched times age is greater than MaxAge, the target is in the deleted state, that is, the target is deleted from the target state list; when the target is a new target, that is, there is no matching value between the target and the target state list, the target is in an uncertain state; when the number of consecutive matches n_init is greater than Init, the target is expressed as a determined state, and cascade matching is used in the target matching process, that is, the targets with matching values ​​in the target state list are matched first; the matching method uses Hungarian matching; the matching criteria are based on the distance between the target center points, the length, width, and angle of the target, and the formula is as follows:

[0047] dis=α*euclideanDistance+β*min(Diffwidth,Difflength)+λ*AngleDiff,

[0048] Among them, euclideanDistance is the Euclidean distance between target points; min(Diffwidth, Difflength) is the minimum value of the target length and width difference; AngleDiff is the angle difference of the target; α = 0.8, β = 0.1, λ = 0.1 are weight values ​​respectively;

[0049] Step S6.2: According to the target state information (v x ,v y ), (x, y) and the real-time speed, heading, and position of the unmanned boat to calculate the speed, heading, distance, angle, longitude and latitude of the corresponding target;

[0050] Distance calculation formula:

[0051] Speed ​​calculation formula:

[0052] Heading calculation formula:

[0053] Angle calculation formula: angle = atan2((xx o )*r,(yy o )*r);

[0054] in, is the speed of the unmanned boat on the x and y axes, (x o ,y o ) is the coordinate point of the unmanned boat; r is the resolution of the grid map, and the constructed target state list is expressed as:

[0055] TarState i ={id,KAL_MEAN,l,angle,v,head,lat,lon}.

[0056] In one embodiment of the present invention, in step S7, every third preset time, using the features of the current frame target to complete the many-to-many matching of the target and the target state list established by the Kalman filter, and updating the attribute information of the target includes:

[0057] The current frame target and the target state list are matched in many-to-many manner to complete the attribute update of each target. The matching standard adopts the minimum distance between the target center point and the target contour, which is calculated by calling the cv::pointPolygonTest function in the Opencv image processing library. After the match is successful, the MatchID, MotionEle, and Confidence in the current frame target attributes constructed in step S5 are updated, and the confidence of the successfully matched target will increase.

[0058] The present invention also provides an unmanned surface vessel multi-information joint perception system, comprising:

[0059] The target detection data module is used to obtain target detection data of the unmanned surface vehicle surface environment using navigation radar and laser radar;

[0060] A grid situation map construction module is used to perform coordinate conversion and point cloud coordinate correction on the target detection data, and to construct a grid situation map respectively;

[0061] An extraction module is used to perform target segmentation and contour feature extraction on the grid situation map to obtain a target contour;

[0062] A distinguishing module, used for distinguishing shore-based targets and water-based targets by using the complexity and area of ​​the target contour;

[0063] A target matching and target attribute establishment module, used to complete the many-to-one target matching and target attribute establishment of the laser radar and the navigation radar by using the minimum distance between the center point of the target contour and the target contour every first preset time, that is, the laser radar scans the first preset number of cycles;

[0064] A calculation module is used to complete frame-by-frame matching of the target and update the target state list based on Kalman filtering every second preset time, that is, the navigation radar scans the second preset number of cycles, to achieve accurate tracking of the target and calculation of motion elements;

[0065] The target attribute information module is used to complete the many-to-many matching of the target and the target state list established by the Kalman filter every third preset time using the characteristics of the current frame target, and update the target attribute information.

[0066] The present invention also provides an electronic device, including a processor and a memory, wherein the memory stores program instructions, and the processor executes the program instructions to implement the above-mentioned unmanned surface vessel multi-information joint perception method.

[0067] As described above, the unmanned surface vessel multi-information joint perception method and system of the present invention has the following beneficial effects:

[0068] (1) The multi-information joint perception method of the unmanned surface vessel of the present invention can realize the complementary advantages of laser radar and navigation radar, reduce missed detection and loss of targets, reduce false alarms of targets, and improve the tracking accuracy and stability of targets.

[0069] (2) The unmanned surface vessel multi-information joint perception method of the present invention can reduce the missed detection rate of the unmanned vessel for close-range small targets, and can improve the accuracy and stability of dynamic target motion elements and the integrity of the target tracking chain.

[0070] (3) The unmanned surface vessel multi-information joint perception method of the present invention can reduce the interference of wake waves and waves on the unmanned surface vessel collision avoidance planning, and adapt to high sea conditions and complex situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 A flowchart of a method for joint perception of multi-information of an unmanned surface vessel provided in an embodiment of the present application.

[0072] Figure 2 A schematic diagram of a three-dimensional laser radar coordinate system used in a method for joint perception of multi-information of an unmanned surface vessel provided in an embodiment of the present application.

[0073] Figure 3 A schematic diagram of the navigation radar coordinate system conversion adopted by a method for joint perception of multi-information of an unmanned surface vessel provided in an embodiment of the present application.

[0074] Figure 4 A fusion situation diagram of the navigation radar and lidar of a method for joint perception of multi-information of an unmanned surface vessel provided in an embodiment of the present application.

[0075] Figure 5 A display diagram of target motion elements calculated by a method for multi-information joint perception of an unmanned surface vessel provided in an embodiment of the present application. DETAILED DESCRIPTION

[0076] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0077] It should be noted that the illustrations provided in the following embodiments are only used to illustrate the basic concept of the present invention in a schematic manner, and thus the illustrations only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0078] Terms such as first or second can be used to describe various components, but these components are not limited by the above terms. The above terms are used to distinguish one component from another component, for example, without departing from the scope of the concept according to the present disclosure, a first component can be referred to as a second component, and similarly, a second component can be referred to as a first component.

[0079] In addition, "connected / coupled" means that one component is directly electrically coupled to another component or is indirectly electrically coupled through another component. The singular form may include the plural form unless explicitly stated in the sentence. In addition, "include / comprise" or "includes / comprises" used in this specification indicates that one or more components, steps, operations, and elements exist or have been added. The specific structural or functional descriptions of the examples of the implementation of the concepts disclosed in this specification are only illustrated to describe the examples of the implementation of the concepts, and the examples of the implementation of the concepts can be implemented in various forms, but these descriptions are not limited to the examples of the implementation described in this specification.

[0080] According to the concept, various modifications and changes can be applied to the examples of the embodiments, so that the examples of the embodiments will be illustrated in the drawings and described in the specification. However, the examples of the embodiments according to the concept are not limited to the specific embodiments, but include all changes, equivalents or replacements included in the spirit and technical scope of the present disclosure.

[0081] It should be understood that when an element is described as being "coupled" or "connected" to another element, the element may be directly coupled or directly connected to the other element, or may be coupled or connected to the other element through a third element. Conversely, it should be understood that when an element is referred to as being "directly coupled to" or "directly coupled to" another element, no other element is placed between them. Other expressions describing the relationship between components (i.e., "between" and "directly between" or "adjacent to" and "directly adjacent to") need to be interpreted in the same manner.

[0082] The terms used in this specification are only used to describe specific examples of the embodiments and are not intended to limit the present disclosure. If there is no clear opposite meaning in the context, the singular form may include the plural form. In this specification, it should be understood that the term "including" or "having" indicates the presence of the features, quantities, steps, operations, components, parts or combinations thereof described in the specification, but the possibility of the presence or addition of one or more other features, quantities, steps, operations, components, parts or combinations thereof cannot be precluded.

[0083] If there is no contrary definition, all terms (including technical terms or scientific terms) used herein have the same meaning as those generally understood by ordinary technicians in the field. If the terms defined in the commonly used dictionary are not clearly defined in this specification, they should be interpreted as having the same meaning as in the context of the relevant technology, and not interpreted as ideal or overly formal meanings.

[0084] Descriptions of well-known components and processing techniques may be omitted so as not to unnecessarily obscure the embodiments of the disclosure.

[0085] Throughout the specification, the same reference numerals refer to the same elements. Thus, even if a reference numeral is not mentioned or described with reference to one figure, it may be mentioned or described with reference to another figure. Furthermore, even if a reference numeral is not shown in one figure, it may be mentioned or described with reference to another figure.

[0086] In addition, the logic level of the signal may be different or opposite to the described logic level. For example, a signal described as having a logic "high" level may alternatively have a logic "low" level, and a signal described as having a logic "low" level may alternatively have a logic "high" level.

[0087] The following will describe the various embodiments of the present disclosure in detail with reference to the accompanying drawings. However, it will be appreciated by those skilled in the art that in the various embodiments of the present disclosure, many technical details are provided in order to enable the reader to better understand the present disclosure. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present disclosure can be implemented.

[0088] See also Figure 1 , Figure 1 The present invention provides a method for the joint perception of multi-information of an unmanned surface vessel, which can realize the complementary advantages of laser radar and navigation radar, reduce missed detection and loss of targets, reduce false alarms of targets, and improve the tracking accuracy and stability of targets, including:

[0089] Step S1: using navigation radar and laser radar to obtain target detection data of the unmanned boat surface environment;

[0090] Step S2: coordinate conversion and point cloud coordinate correction are performed on the acquired target detection data, and grid situation maps are constructed respectively;

[0091] Step S3: performing target segmentation and contour feature extraction on the constructed grid situation map to obtain the target contour;

[0092] Step S4: distinguishing shore-based targets from water-based targets by using the complexity and area of ​​the target contours. Shore-based targets are static targets, and there is no need to calculate the target's motion elements.

[0093] Step S5: Every 200ms, i.e., the laser radar scans two weeks, the minimum distance between the center point of the target contour and the target contour is used to complete the many-to-one target matching and target attribute establishment of the laser radar and the navigation radar;

[0094] Step S6: Every 1200ms, i.e., one scan of the navigation radar, frame-by-frame matching of the target and updating of the target status list are completed based on the Kalman filter, so as to achieve accurate tracking of the target and calculation of motion elements;

[0095] Step S7: Every 200ms, the target characteristics of the current frame are used to complete the many-to-many matching between the target and the target state list established by the Kalman filter, and the attribute information of the target is updated.

[0096] Specifically, the step S2 of performing coordinate conversion and point cloud coordinate correction on the acquired target detection data and constructing grid situation maps respectively includes:

[0097] Step S2.1: The coordinate conversion is to convert the spherical coordinates (d, θ vertical ,θ horizon ) is converted to the Cartesian coordinate system. The conversion formula is as follows:

[0098]

[0099] The point cloud coordinate correction uses the combined navigation installed on the boat to obtain the rolling angle, pitch angle, and heading angle (α, β, θ) of the unmanned boat's motion posture in real time. The correction formula is as follows:

[0100]

[0101] Among them, R is the attitude transformation matrix, T is the translation matrix;

[0102]

[0103] Step S2.2: The coordinate conversion is to convert the coordinates (d, γ) in the polar coordinate system obtained by real-time scanning of the navigation radar into the Cartesian coordinate system. The conversion formula is as follows:

[0104]

[0105] Navigation radar image correction uses the combined navigation installed on the boat to obtain the unmanned boat heading information θ in real time, so that the top of the radar image remains in the true north direction. The formula is:

[0106]

[0107] Step S2.3: The grid situation map is constructed by dividing the map into a series of grid units in rows and columns according to the range of the navigation radar. The unmanned boat is always the center of the grid map, and the target points detected by the laser radar and the navigation radar are projected into the grid map. The conversion formula is as follows:

[0108]

[0109] Among them, (l, l) are the horizontal and vertical coordinates of the center point of the raster image, and the length and width of the raster map are equal; r is the resolution of the raster map; (x, y) are the coordinates of the target in the Cartesian coordinate system; (a, b) are the horizontal and vertical coordinates of the target point in the raster map, and the grayscale value of the coordinate point in the raster image is set to 1, that is, 1 in the raster image indicates that there is a target at this position, and 0 indicates that there is no target at this position.

[0110] Specifically, the step S3 of performing target segmentation and contour feature extraction on the grid situation map to obtain the target contour specifically includes:

[0111] Step S3.1: The edge information of the target contour in the image contains most of the information of the connected domain corresponding to the target. The present invention performs connected domain segmentation on the target by calling the cv::findContours function in the Opencv image processing library, extracts the contour of each target in the image, and stores all continuous contour points on the target boundary into the vector contours.

[0112] Step S3.2: The minimum circumscribed rotation rectangle of the target contour is calculated by cv::minAreaRect in the Opencv image processing library, and then the coordinates of the target's center point, the length and width of the target, and the angle and distance of the target relative to the unmanned boat are determined. The contour features of the target can be expressed as:

[0113] TarFeature={(x,y),(w,l),(dis,angle),contour},

[0114] Specifically, the step S4 of distinguishing between shore-based targets and water-based targets by using the complexity and area of ​​the target contours specifically includes:

[0115] Step S4.1: There are many targets in the radar image, and the targets need to be divided to extract the targets of interest. Large targets on the sea are mostly large islands, coasts and bridges, and small targets are mostly ships and buoys. The cv::approxPolyDP function in the Opencv image processing library is used to perform polygonal approximation on the target contour point set. The approximation accuracy is epsilon, and the output is the number of polylines and polyline coordinates of the target contour point set approximation. The more polylines there are, the more complex the target edge is, and vice versa, the simpler the target edge is.

[0116] Step S4.2: Calculate the area of ​​the target contour by using the cv::contourArea function in the Opencv image processing library or the length and width in the target contour feature.

[0117] Step S4.3: Based on the understanding of the detection principles and image construction of navigation radar, it is found that the target shapes of obstacles such as surface ships and buoys in the navigation radar images are mostly elliptical, while most shore-based targets have large areas and complex contour edges; based on this understanding and the working environment of the unmanned boat, the ratio of the navigation radar image to the actual size, the target area threshold and contour complexity threshold are set, and the targets are divided into shore-based targets and water targets. The shore-based targets are confirmed as static targets, and there is no need to calculate the motion properties of the targets.

[0118] Specifically, the step S5 of using the minimum distance between the center point of the target contour and the target contour to complete the many-to-one target matching of the laser radar and the navigation radar and establish the target attributes specifically includes:

[0119] Step S5.1: Due to the detection principle of laser radar, it has the disadvantages of short detection distance, inability to detect obstructed targets, detection data of only one side of the target, missing data due to the swaying of the target and the unmanned boat, inaccurate target segmentation, etc.; due to the short-range clutter suppression and slow scanning frequency of navigation radar, there are disadvantages such as discontinuity, loss or interference of sea wave clutter of small targets at close range; in order to increase the detection accuracy and stability of the target, call the cv::pointPolygonTest function in the Opencv image processing library to calculate the closest distance between the center point of the laser radar target and the contour of the navigation radar target, and use it as the matching standard to match the targets detected by the laser radar and the navigation radar. Multiple laser radar targets can correspond to one navigation radar target, and the laser radar updates the match once every two rotations.

[0120] Step S5.2: Establish target attributes based on the matching results, which can be expressed as:

[0121] TarAttribute={ID,TarFeature,MatchID,Confidence,MotionEle,TarSource},

[0122] Where ID is the number of the target; TarFeature is the target contour feature calculated in step S3; MatchID is the number of the target state list corresponding to the Kalman filter, which is currently empty; Confidence is the confidence of the target. Currently, the confidence of the target detected by the navigation radar is set to 0.3, the confidence of the target detected by the lidar is set to 0.4, and the confidence of the target successfully matched by the lidar and navigation radar is modified to 0.7; MotionEle is the motion element of the target, which is currently empty; TarSource is the source of the target.

[0123] In particular, the frame-by-frame matching of the target and the updating of the target state list based on Kalman filtering in step S6, and the accurate tracking of the target and the calculation of the motion elements are specifically comprised of:

[0124] Step S6.1: Since the interval between radar image acquisition is very short, the change range of each target position in a short time is relatively small. Therefore, based on this feature, one-to-one matching can be performed on the targets in the continuous images. Based on the Kalman filter, the motion elements of the moving target can be estimated recursively from the noisy measurement signal. In view of the problem that the target is occasionally lost in the radar image, the Kalman filter can be used to predict the position information of the target in a short time and establish a complete target tracking chain. However, due to the movement of the unmanned boat and the drift and instability of the radar image, the center point position of the target is offset. Therefore, the present invention performs matching tracking every 1200ms to increase the stability of the target motion element prediction. The target state information in the Kalman filter is described as follows:

[0125] KAL_MEAN={x,y,angle,width,length,v x ,v y},

[0126] Among them, (v x ,v y ) is the speed of the target on the x and y axes, and x and y are the coordinates of the center point of the target. Since the coordinates (a, b) in step S3 are in the grid map coordinate system, they need to be converted to adapt to the coordinate system of the speed. The formula is as follows:

[0127]

[0128] The state of the target is set during the Kalman filter process. When the number of times the target is not matched age is greater than MaxAge, the target is in the deleted state, that is, the target is deleted from the target state list; when the target is a new target, that is, there is no matching value between the target and the target state list, the target is in an uncertain state; when the number of consecutive matches n_init is greater than Init, the target is expressed as a certain state. Cascade matching is used in the target matching process, that is, the targets with matching values ​​in the target state list are matched first; the matching method uses the Hungarian matching algorithm to complete as many pairs of matches as possible; the matching criteria are based on the distance between the target center points, the length, width, and angle of the target, and the formula is as follows:

[0129] dis=α*euclideanDistance+β*min(Diffwidth,Difflength)+λ*AngleDiff,

[0130] Among them, euclideanDistance is the Euclidean distance between target points; min(Diffwidth, Difflength) is the minimum value of the target length and width difference; AngleDiff is the angle difference of the target; α = 0.8, β = 0.1, λ = 0.1 are weight values ​​respectively;

[0131] Step S6.2: Based on the target state information (v x ,v y ), (x, y) and the real-time speed, heading, and position of the unmanned boat to calculate the speed, heading, distance, angle, longitude and latitude of the corresponding target; distance calculation formula: Speed ​​calculation formula:

[0132] Heading calculation formula: Angle calculation formula: angle = atan2((xx o )*r,(yy o )*r); where is the speed of the unmanned boat on the x and y axes, (x o ,y o ) is the coordinate point of the unmanned boat; r is the resolution of the grid map. The constructed target state list is expressed as:

[0133] TarState i ={id,KAL_MEAN,l,angle,v,head,lat,lon}

[0134] Specifically, the step S7 uses the features of the current frame target to complete the many-to-many matching of the target with the target state list established by the Kalman filter, and updates the attribute information of the target specifically including:

[0135] Step S7.1: To meet the real-time requirements of unmanned boat perception, the present invention updates the target attributes once every 200ms; since the radar image may divide a target into multiple targets, the present invention adopts many-to-many matching between the current frame target and the target status list to complete the attribute update of each target; the matching standard adopts the minimum distance between the target center point and the target contour, which is calculated by calling the cv::pointPolygonTest function in the Opencv image processing library; after the match is successful, the MatchID, MotionEle, and Confidence in the current frame target attributes constructed in step S5 will be updated, and the confidence of the successfully matched target will increase.

[0136] See also Figures 2 to 5 , Figure 2 A schematic diagram of a three-dimensional laser radar coordinate system used in a method for joint perception of multi-information of an unmanned surface vessel provided in an embodiment of the present application. Figure 3 A schematic diagram of the navigation radar coordinate system conversion adopted by a method for joint perception of multi-information of an unmanned surface vessel provided in an embodiment of the present application. Figure 4 A fusion situation diagram of the navigation radar and lidar of a method for joint perception of multi-information of an unmanned surface vessel provided in an embodiment of the present application. Figure 5 A display diagram of target motion elements calculated by a method for joint perception of multi-information of an unmanned surface vessel provided in an embodiment of the present application. In one embodiment of the present invention, the present invention provides a method for joint perception of multi-information of an unmanned surface vessel, specifically comprising:

[0137] Step S1. Use navigation radar and lidar to obtain target detection data of the unmanned boat surface environment.

[0138] In this example, RS80 laser radar and GYRadar navigation radar are used. The radars are horizontally installed in an unobstructed position on the top of the unmanned boat. The laser radar rotates and scans at a constant speed of 10 Hz, and the navigation radar rotates and scans at a rate of 48 rad / min. The scanning data is analyzed according to the radar's network communication protocol.

[0139] Step S2: coordinate conversion and correction are performed on the acquired data, and grid situation maps are constructed respectively.

[0140] Step S2.1: Coordinate conversion, converting the coordinates in the radar coordinate system obtained in step S1 to the Cartesian coordinate system (x, y, z).

[0141] Step S2.2: Correction: Use the real-time unmanned boat motion posture (α, β, θ) output by the integrated navigation equipment installed on the unmanned boat to correct the data obtained in step S2.1. During the correction process, due to the large amount of radar data, the matrix library is used for parallel calculation.

[0142] Step S2.3: Situation grid map construction. First, initialize the matrix Mat according to the range of the navigation radar. The length and width of the matrix are the detection distance of the navigation radar / resolution of the grid map. The unmanned boat is the center of the grid map. Then, the target points detected by the calibrated laser radar and the navigation radar are projected into the grid map to fill the matrix Mat. The laser radar grid map is constructed by two frames of laser radar data. The schematic diagram of the laser radar spherical coordinate system is as follows: Figure 2 As shown, the coordinate system of the navigation radar and the coordinate system of the grid map are as follows Figure 3 shown.

[0143] Step S3: Perform target segmentation and contour feature extraction on the constructed situation map.

[0144] Step S3.1: The binary grid map is processed by calling the cv::findContours function in the Opencv image processing library to complete the connected domain segmentation of the target, extract the contour of each target in the image, and store all continuous contour points on the target boundary into the vector contours.

[0145] Step S3.2: Calculate the minimum circumscribed rotation rectangle of the target contours through cv::minAreaRect in the Opencv image processing library, and then determine the center point coordinates of the target, the length and width of the target, and the angle and distance of the target relative to the unmanned boat.

[0146] Step S4: Differentiate between shore-based targets and water-based targets by using the complexity and size of the target contours.

[0147] Step S4.1: Use the cv::approxPolyDP function in the Opencv image processing library to perform polygonal approximation on the target contour point set contours, with the approximation accuracy being epsilon, and output the number of polylines Conc of the target contour point set approximation.

[0148] Step S4.2: Calculate the area TarArea of ​​the target contour by using the cv::contourArea function in the Opencv image processing library or the length and width in the target contour feature.

[0149] Step S4.3: Set the target area threshold AreaTh and the contour complexity threshold CTh, and regard the targets whose target area is greater than the threshold and whose contour complexity is greater than the threshold as shore-based targets.

[0150] Step S5. Every 200 ms, the minimum distance between the center point of the target contour and the target contour is used to complete the many-to-one target matching of the laser radar and the navigation radar and the establishment of target attributes.

[0151] Step S5.1: Call the cv::pointPolygonTest function in the Opencv image processing library to calculate the shortest distance between the center point of the lidar target and the outline of the navigation radar target, and use it as the matching standard to match the targets detected by the lidar and the navigation radar. Multiple lidar targets can correspond to one navigation radar target, and the lidar updates the matching once every two rotations.

[0152] Step S5.2: Establish target attributes based on the matching results, which can be expressed as:

[0153] TarAttribute={ID,TarFeature,MatchID,Confidence,MotionEle,TarSource}

[0154] Step S6. Every 1200ms, complete the frame-by-frame matching of the target and the update of the target state list based on the Kalman filter to achieve accurate tracking of the target and calculation of motion elements;

[0155] Step S6.1: The target state information in the Kalman filter is described as:

[0156] KAL_MEAN={x,y,angle,width,length,v x ,v y},

[0157] The state of the target is set during the Kalman filter process. When the number of times the target is not matched age is greater than MaxAge, the target is in the deleted state, that is, the target is deleted from the target state list; when the target is a new target, that is, there is no matching value between the target and the target state list, the target is in an uncertain state; when the number of consecutive matches n_init is greater than Init, the target is expressed as a certain state. Cascade matching is used in the target matching process, that is, the targets with matching values ​​in the target state list are matched first; the matching method uses the Hungarian matching algorithm to complete as many pairs of matches as possible; the matching criteria are based on the distance between the target center points, the length, width, and angle of the target, and the formula is as follows:

[0158] dis=α*euclideanDistance+β*min(Diffwidth,Difflength)+λ*AngleDiff,

[0159] Step S6.2: Based on the target state information (v x ,v y ), (x, y) and the real-time speed, heading, and position of the unmanned boat to calculate the speed, heading, distance, angle, longitude and latitude of the corresponding target; the constructed target state list is expressed as:

[0160] TarStatei ={id,KAL_MEAN,l,angle,v,head,lat,lon},

[0161] Step S7. Every 200ms, the features of the target in the current frame are used to complete the many-to-many matching between the target and the target state list established by the Kalman filter, and the attribute information of the target is updated.

[0162] Step S7.1: The current frame target is matched with the target state list using a many-to-many method to complete the attribute update of each target; the matching standard uses the minimum distance between the target center point and the target contour, which is calculated by calling the cv::pointPolygonTest function in the Opencv image processing library; after the match is successful, the MatchID, MotionEle, and Confidence in the current frame target attributes constructed in step S5 will be updated, and the confidence of the successfully matched target will increase by 0.3.

[0163] like Figure 4 , Figure 5 As described above, the red target in the figure is a shore-based target, the blue target is a navigation radar target, and the purple target is a fusion target of the navigation radar and lidar. The batch number, heading, and speed of the target are marked for the moving target, and the red arrow indicates the movement direction of the target. The target batch number is marked for the static target. The center point in the figure is the position of the unmanned boat, and the red arrow indicates the movement direction of the unmanned boat.

[0164] Similar to the principle of the unmanned surface vessel multi-information joint perception method of the present invention, the present invention also provides an unmanned surface vessel multi-information joint perception system, comprising:

[0165] The target detection data module is used to obtain target detection data of the unmanned surface vehicle surface environment using navigation radar and laser radar;

[0166] A grid situation map construction module is used to perform coordinate conversion and point cloud coordinate correction on the target detection data, and to construct a grid situation map respectively;

[0167] An extraction module is used to perform target segmentation and contour feature extraction on the grid situation map to obtain a target contour;

[0168] A distinguishing module, used for distinguishing shore-based targets and water-based targets by using the complexity and area of ​​the target contour;

[0169] A target matching and target attribute establishment module, used to complete the many-to-one target matching and target attribute establishment of the laser radar and the navigation radar by using the minimum distance between the center point of the target contour and the target contour every first preset time, that is, the laser radar scans the first preset number of cycles;

[0170] A calculation module is used to complete frame-by-frame matching of the target and update the target state list based on Kalman filtering every second preset time, that is, the navigation radar scans the second preset number of cycles, to achieve accurate tracking of the target and calculation of motion elements;

[0171] The target attribute information module is used to complete the many-to-many matching of the target and the target state list established by the Kalman filter every third preset time using the characteristics of the current frame target, and update the target attribute information.

[0172] The present invention also proposes an electronic device, which includes a processor and a memory, wherein the memory stores program instructions, and the processor runs the program instructions to implement the above-mentioned unmanned surface vessel multi-information joint perception method. The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components; the memory may include a random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The memory can also be an internal memory of the random access memory (RAM) type, and the processor and memory can be integrated into one or more independent circuits or hardware, such as an application-specific integrated circuit (ASIC). It should be noted that the computer program in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, an electronic device, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention.

[0173] The present invention also proposes a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned unmanned surface vessel multi-information joint perception method. The computer-readable storage medium can be an electronic medium, a magnetic medium, an optical medium, an electromagnetic medium, an infrared medium, or a semiconductor system or a propagation medium. The computer-readable storage medium can also include a semiconductor or solid-state memory, a magnetic tape, a removable computer disk, a random access memory (RAM), a read-only memory (ROM), a hard disk, and an optical disk. The optical disk can include a compact disk-read only memory (CD-ROM), a compact disk-read / write (CD-RW), and a DVD.

[0174] In summary, the unmanned surface vessel multi-information joint perception method of the present invention can realize the complementary advantages of laser radar and navigation radar, reduce missed detection and loss of targets, reduce false alarms of targets, and improve the tracking accuracy and stability of targets.

[0175] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for joint perception of multi-information of unmanned surface vessels, characterized in that: include: S1. Use navigation radar and laser radar to obtain target detection data of the unmanned surface vehicle water environment; S2, performing coordinate conversion and point cloud coordinate correction on the target detection data, and constructing grid situation maps respectively; S3, performing target segmentation and contour feature extraction on the grid situation map to obtain a target contour; S4, distinguishing shore-based targets from water-based targets by using the complexity and area of ​​the target contour; S5, every first preset time, that is, the laser radar scans the first preset number of cycles, using the minimum distance between the center point of the target contour and the target contour to complete the many-to-one target matching of the laser radar and the navigation radar and establish the target attributes; S6. Every second preset time, that is, the navigation radar scans the second preset number of cycles, completes frame-by-frame matching of the target and updates the target state list based on the Kalman filter, and realizes accurate tracking of the target and calculation of motion elements; S7. Every third preset time, use the features of the current frame target to complete a many-to-many match between the target and the target state list established by the Kalman filter, and update the target's attribute information.

2. The method for joint perception of multi-information of unmanned surface vessels according to claim 1 is characterized by: The first preset time is 200ms, and the first preset number of weeks is two weeks; the second preset time is 1200ms, and the second preset number of weeks is one week; The third preset time is 200ms.

3. The method for joint perception of multi-information of unmanned surface vessels according to claim 1 is characterized in that: The step S2 of performing coordinate conversion and point cloud coordinate correction on the target detection data and constructing grid situation maps respectively includes: Step S2.1: The coordinate conversion is to convert the coordinates (d, θ) in the spherical coordinate system obtained by the laser radar real-time scanning into vertical ,θ horizon ) is converted to the Cartesian coordinate system, which are the distance, vertical angle and horizontal offset angle of the target point respectively. The conversion formula is as follows: The point cloud coordinate correction is that as the heading, pitch and sway of the unmanned boat change, the data obtained by the three-dimensional laser radar deviates from the real data. The combined navigation installed on the boat is used to obtain the unmanned boat's motion posture (α, β, θ) in real time, which are the roll angle, pitch angle and heading angle of the unmanned boat respectively. The correction formula is as follows: Among them, R is the attitude transformation matrix, T is the translation matrix; Step S2.2, the coordinate conversion is to convert the coordinates (d, γ) in the polar coordinate system obtained by real-time scanning of the navigation radar into the Cartesian coordinate system, which are the distance and horizontal angle of the target point respectively. The conversion formula is as follows: Navigation radar image correction, according to the current heading angle, the radar image is corrected, and the combined navigation installed on the boat is used to obtain the unmanned boat heading information θ in real time, so that the top of the radar image remains in the due north direction. The formula is: Step S2.3, the construction of the grid situation map is to divide the map into a series of grid units in rows and columns according to the range of the navigation radar. The unmanned boat is always the center of the grid map. The resolution r of the grid can be adjusted and set. The target points detected by the laser radar and the navigation radar are projected into the grid map. The conversion formula is as follows: Among them, (l, l) are the horizontal and vertical coordinates of the center point of the raster image, and the length and width of the raster map are equal; r is the resolution of the raster map; (x, y) are the coordinates of the target in the Cartesian coordinate system; (a, b) are the horizontal and vertical coordinates of the target point in the raster map, and the grayscale value of the coordinate point in the raster image is set to 1, that is, 1 in the raster image indicates that there is a target at this position, and 0 indicates that there is no target at this position.

4. The method for joint perception of multi-information of unmanned surface vessels according to claim 3 is characterized in that: The step S3 of performing target segmentation and contour feature extraction on the grid situation map to obtain the target contour includes: Step S3.1, segment the connected domain of the target by calling the cv::findContours function in the Opencv image processing library, extract the contour of each target in the image, and store all continuous contour points on the target boundary into the vector contours; Step S3.2, calculate the minimum circumscribed rotation rectangle of the target contour through cv::minAreaRect in the Opencv image processing library, determine the coordinates of the target's center point, the length and width of the target, the angle and distance of the target relative to the unmanned boat, and the contour features of the target are expressed as: TarFeature={(x,y),(w,l),(dis,angle),contour}.

5. The method for joint perception of multi-information of unmanned surface vessels according to claim 4 is characterized in that: The step S4 of distinguishing shore-based targets from water-based targets by using the complexity and area of ​​the target contour includes: Step S4.1, polygonal approximation is performed on the target contour point set by using the cv::approxPolyDP function in the Opencv image processing library, and the precision value of the approximation is epsilon. The output is the number of polylines and polyline coordinates of the target contour point set approximation. The more polylines there are, the more complex the target edge is, and vice versa, the simpler the target edge is; Step S4.2, calculating the area of ​​the target contour by using the cv::contourArea function in the Opencv image processing library or the length and width in the target contour feature; Step S4.3, set the target area threshold and contour complexity threshold, and divide the targets into shore-based targets and water targets. The shore-based targets are confirmed as static targets, and there is no need to calculate the motion attributes of the targets.

6. The method for joint perception of multi-information of unmanned surface vessels according to claim 5 is characterized in that: The step S5 includes completing the many-to-one target matching of the laser radar and the navigation radar and establishing the target attributes by using the minimum distance between the center point of the target contour and the target contour at every first preset time, i.e., the laser radar scans the first preset number of cycles, including: Step S5.1, call the cv::pointPolygonTest function in the Opencv image processing library to calculate the shortest distance between the center point of the laser radar target and the contour of the navigation radar target, and use it as the matching standard to match the targets detected by the laser radar and the navigation radar. Multiple laser radar targets can correspond to one navigation radar target, and the laser radar updates the matching once every two rotations; Step S5.2: Establish target attributes based on the matching results, which can be expressed as: TarAttribute={ID,TarFeature,MatchID,Confidence,MotionEle,TarSource} Among them, ID is the number of the target; TarFeature is the target contour feature calculated in step S3; MatchID is the number of the target state list corresponding to the Kalman filter, which is currently empty; Confidence is the confidence of the target. Currently, the confidence of the target detected by the navigation radar is set to 0.3, and the confidence of the target detected by the lidar is set to 0.

4. The confidence of the target that is successfully matched by the lidar and navigation radar is modified to 0.7; MotionEle is the motion element of the target, which is currently empty; TarSource is the source of the target.

7. The method for joint perception of multi-information of unmanned surface vessels according to claim 6 is characterized in that: The step S6 includes completing frame-by-frame matching of the target and updating the target state list based on Kalman filtering at every second preset time, i.e., the navigation radar scans the second preset number of cycles, to achieve accurate tracking of the target and calculation of motion elements, which includes: Step S6.1, the target state information in Kalman filtering is described as: KAL_MEAN={x,y,angle,width,length,v x ,v y }, Among them, (v x ,v y ) is the speed of the target on the x and y axes, x and y are the coordinates of the center point of the target respectively. Since the coordinates (a, b) are in the grid map coordinate system, they need to be converted to adapt to the coordinate system of the speed. The formula is as follows: The state of the target is set during the Kalman filter process. When the number of target unmatched times age is greater than MaxAge, the target is in the deleted state, that is, the target is deleted from the target state list; when the target is a new target, that is, there is no matching value between the target and the target state list, the target is in an uncertain state; when the number of consecutive matches n_init is greater than Init, the target is expressed as a determined state, and cascade matching is used in the target matching process, that is, the targets with matching values ​​in the target state list are matched first; the matching method uses Hungarian matching; the matching criteria are based on the distance between the target center points, the length, width, and angle of the target, and the formula is as follows: dis=α*euclideanDistance+β*min(Diffwidth,Difflength)+λ*AngleDiff, Among them, euclideanDistance is the Euclidean distance between target points; min(Diffwidth, Difflength) is the minimum value of the target length and width difference; AngleDiff is the angle difference of the target; α = 0.8, β = 0.1, λ = 0.1 are weight values ​​respectively; Step S6.2: According to the target state information (v x ,v y ), (x, y) and the real-time speed, heading, and position of the unmanned boat to calculate the speed, heading, distance, angle, longitude and latitude of the corresponding target; Distance calculation formula: Speed ​​calculation formula: Heading calculation formula: Angle calculation formula: angle = atan2((xx o )*r,(yy o )*r); in, is the speed of the unmanned boat on the x and y axes, (x o ,y o ) is the coordinate point of the unmanned boat; r is the resolution of the grid map, and the constructed target state list is expressed as: TarState i ={id,KAL_MEAN,l,angle,v,head,lat,lon}.

8. The method for joint perception of multi-information of unmanned surface vessels according to claim 7 is characterized in that: In step S7, at every third preset time, the target state list established by the Kalman filter is matched with the target using the features of the current frame, and the attribute information of the target is updated, including: The current frame target and the target state list are matched in many-to-many manner to complete the attribute update of each target. The matching standard adopts the minimum distance between the target center point and the target contour, which is calculated by calling the cv::pointPolygonTest function in the Opencv image processing library. After the match is successful, the MatchID, MotionEle, and Confidence in the current frame target attributes constructed in step S5 are updated, and the confidence of the successfully matched target will increase.

9. An unmanned surface vessel multi-information joint perception system, characterized in that: include: The target detection data module is used to obtain target detection data of the unmanned surface vehicle surface environment using navigation radar and laser radar; A grid situation map construction module is used to perform coordinate conversion and point cloud coordinate correction on the target detection data, and to construct a grid situation map respectively; An extraction module is used to perform target segmentation and contour feature extraction on the grid situation map to obtain a target contour; A distinguishing module, used for distinguishing shore-based targets and water-based targets by using the complexity and area of ​​the target contour; A target matching and target attribute establishment module, used to complete the many-to-one target matching and target attribute establishment of the laser radar and the navigation radar by using the minimum distance between the center point of the target contour and the target contour every first preset time, that is, the laser radar scans the first preset number of cycles; A calculation module is used to complete frame-by-frame matching of the target and update the target state list based on Kalman filtering every second preset time, that is, the navigation radar scans the second preset number of cycles, to achieve accurate tracking of the target and calculation of motion elements; The target attribute information module is used to complete the many-to-many matching of the target and the target state list established by the Kalman filter every third preset time using the characteristics of the current frame target, and update the target attribute information.

10. An electronic device, comprising a processor and a memory, wherein the memory stores program instructions, characterized in that: The processor runs program instructions to implement the unmanned surface vessel multi-information joint perception method as described in any one of claims 1 to 8.

Images