Unmanned boat navigation radar echo processing method, device and equipment

Abstract

The present invention provides a method, device, and equipment for processing unmanned vehicle navigation radar echoes, belonging to the field of computer information processing technology. It solves the problems of low efficiency, unstable target echo signals, and susceptibility to sea clutter in current navigation radar echo processing. The method includes: obtaining a set of unmanned vehicle navigation radar echoes at multiple times; clustering the set of unmanned vehicle navigation radar echoes at multiple times to obtain a set of line segments; determining echo clustering data at multiple times based on the set of line segments; mapping the echo clustering data at multiple times to a grid map to obtain grid clustering data at multiple times; and clustering and merging the grid clustering data at multiple times to obtain radar echo processing data. This solution forms grid clusters by accumulating historical information, effectively improving clustering efficiency, reducing the impact of interference factors, and improving the robustness of track processing.

Description

Technical Field

[0001] The present invention relates to the technical field of computer information processing, and in particular to a method, device and equipment for processing echoes of an unmanned boat navigation radar. Background Art

[0002] Unmanned aerial vehicles (UAVs) rely on the autonomous sensing capabilities of their onboard equipment. Navigation radar is the primary sensory tool for UAVs at sea. Its key advantages include: First, it is less susceptible to weather conditions and can maintain effective detection in adverse weather conditions such as fog, rain, and snow, providing the UAV with continuous situational awareness of its surroundings; Second, it operates stably in complex electromagnetic environments and exhibits excellent anti-interference capabilities, ensuring reliable sensing information in most environments; Finally, its detection range range is between 100m and 15km, meeting the distance requirements for safe navigation. However, existing navigation radars are generally operated by personnel and lack the ability to automatically detect and track obstacles. Current navigation radars output all echo information, but need to be able to cluster the echoes based on this information, and then establish a course and track the target based on the clusters.

[0003] Existing clustering methods are widely applicable to various LiDAR processing and image processing scenarios, achieving good results. However, compared to navigation radar echoes, these methods have the following problems: First, they fail to fully utilize the characteristic of navigation radar echoes being output according to the sideways angle, resulting in low efficiency in processing navigation radar echoes; second, they fail to consider the vulnerability of navigation radars to the electromagnetic environment at sea, resulting in unstable target echo strength and size; and third, they fail to account for the impact of sea waves on navigation radars, resulting in sea clutter often appearing in navigation radar echoes. Summary of the Invention

[0004] The present invention provides a method, device and equipment for processing echoes of an unmanned boat navigation radar, which solves the problems of low efficiency of current navigation radar echo processing, unstable target echo signals and susceptibility to sea clutter.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0006] An embodiment of the present invention provides a method for processing echoes of an unmanned boat navigation radar, comprising:

[0007] Obtain the drone navigation radar echo set at multiple times;

[0008] performing clustering processing on the unmanned boat navigation radar echo sets at the multiple moments to obtain a line segment set;

[0009] Determining echo clustering data at multiple moments according to the line segment set;

[0010] Mapping the echo clustering data at the multiple moments into a grid map to obtain grid clustering data at the multiple moments;

[0011] The grid clustering data at the multiple moments are clustered and merged to obtain radar echo processing data.

[0012] Optionally, clustering is performed on the unmanned boat navigation radar echo sets at the multiple moments to obtain a line segment set, including:

[0013] Analyzing and processing the navigation radar echo sets of the unmanned boat at the multiple moments to obtain navigation radar echo sequences of multiple side angles;

[0014] The navigation radar echo sequences of the multiple side angles are traversed and processed according to preset conditions to obtain multiple single echo information;

[0015] The plurality of single echo information are merged to obtain a line segment set.

[0016] Optionally, determining echo clustering data at multiple moments according to the line segment set includes:

[0017] Determining a plurality of line segment data of a plurality of side angles according to the line segment set;

[0018] determining a plurality of distance maximum values ​​according to the plurality of line segment data of the plurality of side angles;

[0019] Determining the overlap of multiple distance intervals according to the multiple distance maximum values;

[0020] Echo clustering data at multiple moments are determined according to the overlap degrees of the multiple distance intervals.

[0021] Optionally, mapping the echo clustering data at the multiple moments into a grid map to obtain grid clustering data at the multiple moments includes:

[0022] Performing coordinate conversion processing on the echo clustering data at the multiple moments to obtain global coordinate position data of the unmanned boat;

[0023] Mapping the global coordinate position data of the unmanned boat into a grid map to obtain grid data;

[0024] determining echo intensity data according to the grid data;

[0025] Grid clustering data at multiple moments are determined according to the grid data and the echo intensity data.

[0026] Optionally, determining grid clustering data at multiple moments based on the grid data and the echo intensity data includes:

[0027] according to:

[0028] ,

[0029] Determine raster clustering data at multiple moments;

[0030] in, is the grid clustering data at the kth moment, is the x-axis grid position in the global coordinate system, is the y-axis grid position in the global coordinate system, is the grid echo intensity data, is the jth echo distance of the mth side angle at the kth moment, is the jth echo intensity at the mth side angle at the kth moment, where k, m, and j are natural numbers. is the echo clustering data, Indicates echo Map to raster .

[0031] Optionally, clustering and merging the grid cluster data at the multiple moments to obtain radar echo processing data includes:

[0032] Obtaining element occupancy probability data based on the grid clustering data at the plurality of moments;

[0033] performing binarization processing on the element occupation probability data to obtain binarized element occupation probability data;

[0034] Performing screening processing on the element occupation probability data after the binarization processing to obtain a plurality of screened raster clustering data;

[0035] The plurality of filtered grid cluster data are merged to obtain radar echo processing data.

[0036] Optionally, obtaining element occupancy probability data based on the grid clustering data at the multiple moments includes:

[0037] according to:

[0038] ,

[0039] Get element occupancy probability data;

[0040] in, is the probability data of each element in the grid cluster from time 0 to k, is the probability data of each element in the grid cluster from 0 to k-1 time, is the maximum echo intensity, η1 is the probability of non-occupancy, is the x-axis grid position in the global coordinate system from time 0 to k, is the y-axis grid position in the global coordinate system from time 0 to k, is the grid clustering data from time 0 to k-1.

[0041] An embodiment of the present invention further provides an unmanned boat navigation radar echo processing device, comprising:

[0042] The acquisition module is used to obtain the echo sets of the unmanned boat navigation radar at multiple times;

[0043] The processing module is used to cluster the unmanned boat navigation radar echo sets at the multiple moments to obtain a line segment set; determine the echo clustering data at the multiple moments based on the line segment set; map the echo clustering data at the multiple moments to a grid map to obtain grid clustering data at the multiple moments; and cluster and merge the grid clustering data at the multiple moments to obtain radar echo processing data.

[0044] An embodiment of the present invention further provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program executes the above method when executed by the processor.

[0045] An embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above method.

[0046] The technical solution of the present invention includes at least the following effects:

[0047] The above-mentioned solution of the present invention obtains a set of unmanned boat navigation radar echoes at multiple moments; clusters the unmanned boat navigation radar echoes at multiple moments to obtain a set of line segments; determines echo cluster data at multiple moments based on the set of line segments; maps the echo cluster data at multiple moments to a grid map to obtain grid cluster data at multiple moments; and clusters and merges the grid cluster data at multiple moments to obtain radar echo processing data. This solution utilizes the characteristic that navigation radar echoes are arranged in ascending order according to the distance of each side angle, thereby improving processing efficiency; converting to grid clusters and merging multiple echo information reduces the subsequent data volume while ensuring that the amount of information is not reduced, which facilitates the subsequent real-time processing of track such as navigation and tracking; effectively combines historical information and current detection information, reducing the impact of changes in the quality of navigation radar echoes due to changes in the electromagnetic environment, sea clutter, and ship detection angles. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flow chart of a method for processing an unmanned boat navigation radar echo provided by an embodiment of the present invention;

[0049] Figure 2This is a structural diagram of an unmanned boat navigation radar echo processing device provided by an embodiment of the present invention;

[0050] Figure 3 It is a structural diagram of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0052] like Figure 1 As shown, an embodiment of the present invention provides a method for processing echoes of an unmanned boat navigation radar, comprising:

[0053] Step 11, obtaining a set of unmanned boat navigation radar echoes at multiple times;

[0054] Step 12, performing clustering processing on the unmanned boat navigation radar echo sets at the multiple moments to obtain a line segment set;

[0055] Step 13, determining echo clustering data at multiple moments according to the line segment set;

[0056] Step 14, mapping the echo clustering data at the multiple moments into a grid map to obtain grid clustering data at the multiple moments;

[0057] Step 15: cluster and merge the grid cluster data at the multiple moments to obtain radar echo processing data.

[0058] In this embodiment, the navigation radar equipped on the unmanned vehicle continuously emits electromagnetic waves and receives echo signals reflected from the target. These echo signals contain information such as the target's location, distance, and speed. Over a period of time, radar echo data is recorded at regular intervals (e.g., every 1 second, every 0.5 seconds, etc.). The echo data at each moment can be represented as a set of data points, where each data point contains relevant information about the target detected by the radar at that moment, such as the target's polar coordinates (distance, azimuth), etc. The echo data from all recorded moments are integrated to form a set containing the unmanned vehicle's navigation radar echoes at multiple moments. This set can be viewed as a three-dimensional data structure, with two dimensions representing the target's polar coordinates and one dimension representing time.

[0059] For each echo data point, key features are extracted, such as location (distance and azimuth), time, etc. These features will be used for subsequent clustering analysis. The extracted features are input into the clustering processing model to cluster the echo data points at multiple times. During the clustering process, the clustering processing model assigns data points to different clusters based on the similarity between the data points (such as distance, angle, etc.). For each data point in a cluster, a line fitting algorithm (such as the least squares method) is used to fit it to a line segment. This line segment can approximately represent the distribution trend of the data points in the cluster and reflect the movement trajectory or characteristics of the target over a period of time. Finally, the line segments fitted from all clusters are integrated together to form a line segment set.

[0060] For each line segment in the line segment set, its features are analyzed, such as the starting point, end point, length, direction, etc. These features can reflect the target's motion state and distribution at different moments. Based on the relationship between the line segment and time, the line segment corresponding to each moment is determined. For example, the timestamp of the data point on the line segment can be used to determine the echo cluster at which the line segment belongs. For each moment, the features of the associated line segments are integrated to form the echo cluster data at that moment. The echo cluster data can include information such as the number of line segments and the characteristic parameters of each line segment. This information can fully describe the clustering of the echo data at that moment.

[0061] Define a two-dimensional grid space and divide it into several grids of equal size based on the detection range and accuracy requirements of the unmanned boat navigation radar. Each grid can be represented by a unique coordinate. For the echo clustering data at each moment, the line segment features are mapped into the grid space. Specifically, determine which grids each line segment passes through, and assign a weight value to each passed grid based on the line segment's characteristics (such as length, density, etc.). The weight value can reflect the strength or importance of the echo clustering within the grid. After mapping the echo clustering data at all moments into the grid space, grid clustering data for multiple moments is obtained. The grid clustering data can be represented as a two-dimensional matrix, where each element corresponds to the weight value of a grid, and the rows and columns of the matrix correspond to the coordinates of the grid, respectively.

[0062] Grid cluster data from multiple time points is fused, comprehensively considering the changes in grid weight values ​​at different times. For example, a weighted average method can be used to sum the grid weight values ​​at different times to obtain a comprehensive grid weight distribution. Features such as the location, shape, size, and motion trend of the target area are extracted from the fused grid cluster data. Image processing techniques (such as edge detection and morphological analysis) can be used to identify the target area and analyze its characteristic parameters. Based on the extracted features and analysis results, radar echo processing data is generated. Radar echo processing data can include target location information, motion status information, target type determination, and other information. This information can be directly used by the unmanned vehicle for navigation decisions, such as obstacle avoidance and path planning.

[0063] This technical solution is aimed at the needs of autonomous perception of unmanned boats. It uses navigation radar as the main perception means. First, it uses the echo information characteristics of the navigation radar to complete echo clustering; then the echo clusters are mapped to the grid map, and grid clusters are formed through the accumulation of historical information, which effectively improves the clustering efficiency. It also effectively utilizes the grid characteristics and historical information, reduces the impact of environmental factors such as the electromagnetic environment and sea clutter at sea, and improves the robustness of subsequent track processing.

[0064] In an optional embodiment of the present invention, step 12 may include:

[0065] Step 121, performing analytical processing on the navigation radar echo sets of the unmanned boat at the multiple moments to obtain navigation radar echo sequences of multiple side angles;

[0066] Step 122, performing traversal processing on the navigation radar echo sequences of the multiple side angles according to preset conditions to obtain multiple single echo information;

[0067] Step 123 : merging the plurality of single echo information to obtain a line segment set.

[0068] In this embodiment, it is set The echo set of the unmanned boat navigation radar at the moment is ,in For the side angle, is the maximum number of side angles, is the echo set in the direction of the side angle. Represented as an echo sequence , For single echo information, is the echo distance, is the echo intensity, is the number of echoes; in the echo sequence middle is in accordance with Sort in ascending order. The position of the unmanned boat in the global coordinate system at the moment is , respectively, the x-axis coordinate positions , y-axis coordinate position , heading angle . Raster map ,in is the x-axis grid position in the global coordinate system, is the y-axis grid position in the global coordinate system, and the grid size is a predetermined constant .

[0069] The calculation process of the line segment set is as follows: analyzing the navigation radar echo sets of the unmanned boat at multiple moments to obtain the navigation radar echo sequences of multiple side angles; and calculating the echo sequence of each side angle. , cluster each echo point in the sequence into a set of line segments .

[0070] S21, set .

[0071] S22, set , Is an empty set.

[0072] S23, traverse the navigation radar echo sequences of the multiple side angles according to the preset conditions, that is, from Get the first one in sequence so that of ,in is the echo intensity threshold, which is a predetermined constant. Join middle.

[0073] S24, the subsequent ,until , then the line segment is completed Aggregation, placement

[0074] S25, repeat S22 to S24 until the echo sequence All echo points in have been processed, and the line segment set is obtained .

[0075] In an optional embodiment of the present invention, step 13 may include:

[0076] Step 131, determining a plurality of line segment data of a plurality of side angles according to the line segment set;

[0077] Step 132, determining a plurality of distance maximum values ​​based on the plurality of line segment data of the plurality of side angles;

[0078] Step 133, determining the overlap of multiple distance intervals based on the multiple distance maximum values;

[0079] Step 134 : determining echo clustering data at multiple moments according to the overlap of the multiple distance intervals.

[0080] In this embodiment, the calculation process of echo clustering data at multiple moments is specifically as follows:

[0081] S301, set ;

[0082] S302, set ;

[0083] S303, set ;

[0084] S304, remove The first side angle not marked as processed of .calculate The maximum and minimum distances in , , the formula is as follows:

[0085] ,

[0086] ;

[0087] S305, calculation The maximum and minimum distances in , ;

[0088] S306, judgment Is the distance interval consistent with Is there any overlap in the distance intervals of ? If there is an overlap, Join In Chinese, that is:

[0089]

[0090] S307, set , repeat S305 to S306. All The overlap of distance intervals has been determined;

[0091] S308, mark the Processed; in Take the same side angle Another line segment of To label this line segment, repeat S304 to S307 until Take the same side angle All line segments of have been processed;

[0092] S309, set ,if , then set ; Repeat S304 to S308. Until All Mark processed;

[0093] S310, set ;Pick Line segments not marked as processed , set Repeat S302 to S309 for the number of this line segment; All line segments in Processed and assigned to each echo cluster middle.

[0094] In an optional embodiment of the present invention, step 14 may include:

[0095] Step 141, performing coordinate conversion processing on the echo clustering data at the multiple moments to obtain the global coordinate position data of the unmanned boat;

[0096] Step 142, mapping the global coordinate position data of the unmanned boat into a grid map to obtain grid data;

[0097] Step 143, determining echo intensity data based on the grid data;

[0098] Step 144 : determining grid clustering data at multiple moments based on the grid data and the echo intensity data.

[0099] In this embodiment, the calculation process of grid clustering data at multiple moments is specifically as follows:

[0100] S41, for any , according to the position of the unmanned boat in the global coordinate system, it is converted to the position in the global coordinate system , the calculation formula is:

[0101] ;

[0102] S42, will Mapping to a raster in a raster map Above, that is:

[0103] , ;

[0104] in, Indicates rounding down;

[0105] S43, arithmetic average of all maps to the grid Upper echo The echo intensity of the grid is obtained The echo strength , the calculation formula is:

[0106] ;

[0107] in, Indicates echo Mappable to raster , Indicates the number of elements in the collection.

[0108] S44, through the above steps, the Map all the echoes in the grid map In Convert to raster map Raster clustering under , the calculation formula is:

[0109] ,

[0110] in, is the grid clustering data at the kth moment, is the x-axis grid position in the global coordinate system, is the y-axis grid position in the global coordinate system, is the jth echo distance of the mth side angle at the kth moment, is the jth echo intensity at the mth side angle at the kth moment, where k, m, and j are natural numbers. is the echo clustering data.

[0111] In an optional embodiment of the present invention, step 15 may include:

[0112] Step 151, obtaining element occupancy probability data based on the grid clustering data at the multiple moments;

[0113] Step 152: binarize the element occupancy probability data to obtain binarized element occupancy probability data.

[0114] Step 153, filtering the binarized element occupancy probability data to obtain a plurality of filtered grid cluster data;

[0115] Step 154 ​​, merging the plurality of filtered grid cluster data to obtain radar echo processing data.

[0116] In this embodiment, arrive Raster clustering at time and Time grid clustering Merge to get arrive Raster clustering results of time echo information , specifically:

[0117] S51, for Raster clustering at time , directly clustering from the grid at time 0 Obtain. , Indicates the x-axis grid position in the global coordinate system, Indicates the y-axis grid position in the global coordinate system, represents the probability that the grid is occupied. The way to obtain it is as follows:

[0118]

[0119] in, is the maximum echo intensity, which is a predetermined constant;

[0120] S52, using arrive Raster clustering at time and Time grid clustering ,calculate Raster clustering at time The probability of each element occupying , the calculation formula is:

[0121] ,

[0122] in, is the probability data of each element in the grid cluster from time 0 to k, is the probability data of each element in the grid cluster from 0 to k-1 time, is the maximum echo intensity, η1 is the probability of non-occupancy, is the x-axis grid position in the global coordinate system from time 0 to k, is the y-axis grid position in the global coordinate system from time 0 to k, is the grid clustering data from time 0 to k-1;

[0123] S53, cluster the grid Probability of element occupation Less than the occupation probability deletion threshold Set to 0, greater than Set to ,in is a predefined constant;

[0124] S54, for Elements with a probability of 0 in the grid are clustered Delete this element. Merge into one cluster and finally get Raster clustering at time , that is, the radar echo processing data is obtained.

[0125] A specific embodiment of the unmanned boat navigation radar echo processing method provided by the embodiment of the present invention is:

[0126] Located in The echo set of the unmanned boat navigation radar at the moment is ,in For the side angle, is the maximum number of side angles, is the echo set in the direction of the side angle. Represented as an echo sequence , For single echo information, is the echo distance, is the echo intensity, is the number of echoes; in the echo sequence middle is in accordance with Sort in ascending order. The position of the unmanned boat in the global coordinate system at the moment is , respectively, the x-axis coordinate positions , y-axis coordinate position , heading angle . Raster map ,in is the x-axis grid position in the global coordinate system, is the y-axis grid position in the global coordinate system, and the grid size is a predetermined constant .

[0127] Step S10, for each side angle echo sequence , cluster each echo point in the sequence into a set of line segments .

[0128] Step S11, set .

[0129] Step S12, set .

[0130] Step S13, from Get the first one in sequence so that of ,in is the echo intensity threshold, which is a predetermined constant. Join middle.

[0131] Step S14: ,until , then the line segment is completed Aggregation, placement

[0132] Step S15, repeat steps S12 to S14 until the echo sequence All echo points in have been processed, and the line segment set is obtained .

[0133] Step S20: The line segments of each side angle are collected , according to the overlap of distance intervals, the echoes are clustered .

[0134] Step S21, set .

[0135] Step S22, set .

[0136] Step S23, set .

[0137] Step S24, take out The first side angle not marked as processed of .calculate The maximum and minimum distances in , .

[0138]

[0139]

[0140] Step S25, calculate The maximum and minimum distances in , .

[0141] Step S26, determine Is the distance interval consistent with Is there any overlap in the distance intervals of ? If there is an overlap, Join middle.

[0142]

[0143] Step S27, set , repeat steps S25 to S26. All The overlap of distance intervals has been determined.

[0144] Step S28, mark the Processed. Take the same side angle Another line segment of Repeat steps S24 to S27 for the number of this line segment until Take the same side angle All line segments of have been processed.

[0145] Step S29, set ,if , then set Repeat steps S24 to S28 until All Mark processed.

[0146] Step S210: Set .Pick Line segments not marked as processed , set Repeat steps S22 to S29 for the number of this line segment. All line segments in Processed and assigned to each echo cluster middle.

[0147] Step S30: Time echo clustering Mapping to raster maps In the formation Raster clustering at time .

[0148] Step S31, for any , according to the position of the unmanned boat in the global coordinate system, it is converted to the position in the global coordinate system .

[0149]

[0150] Step S32: Mapping to a raster in a raster map superior.

[0151] ,

[0152] in Indicates rounding down.

[0153] Step S33: arithmetically average all the data mapped to the grid. Upper echo The echo intensity of the grid is obtained The echo strength .

[0154]

[0155] in Indicates echo Can be mapped to the grid according to steps 3-1 and 3-2 , Indicates the number of elements in the set. The above steps complete the Map all the echoes in the grid map In Convert to raster map Raster clustering under .

[0156] .

[0157] Step S40: arrive Raster clustering at time and Time grid clustering Merge to get arrive Raster clustering results of time echo information ;

[0158] Step S41, for Raster clustering at time , directly clustering from the grid at time 0 Obtain. , Indicates the x-axis grid position in the global coordinate system, Indicates the y-axis grid position in the global coordinate system, represents the probability that the grid is occupied. The way to obtain it is as follows:

[0159]

[0160] in is the maximum echo intensity, which is a predetermined constant.

[0161] Step S42, using arrive Raster clustering at time and Time grid clustering ,calculate Raster clustering at time The probability of each element occupying .

[0162] ,

[0163] in, is the unoccupied probability, which is a predefined constant.

[0164] Step S43: cluster the grids Probability of element occupation Less than the occupation probability deletion threshold Set to 0, greater than Set to ,in is a predefined constant.

[0165] Step S44, for Elements with a probability of 0 in the grid are clustered Delete this element. Merge into one cluster. Finally, we get Raster clustering at time .

[0166] The unmanned boat navigation radar echo processing method proposed in the present invention is aimed at the needs of unmanned boat autonomous perception. It uses navigation radar as the main perception means and first uses the navigation radar echo information characteristics to complete echo clustering. Then, the echo clusters are mapped to a grid map, and grid clusters are formed by accumulating historical information, which effectively improves the clustering efficiency. In addition, the grid characteristics and historical information are effectively utilized, reducing the influence of environmental factors such as the marine electromagnetic environment and sea clutter, and improving the robustness of subsequent track processing.

[0167] like Figure 2 As shown, the embodiment of the present invention further provides an unmanned boat navigation radar echo processing device 20, comprising:

[0168] An acquisition module 21 is used to acquire a set of unmanned boat navigation radar echoes at multiple moments;

[0169] The processing module 22 is used to cluster the unmanned boat navigation radar echo sets at the multiple moments to obtain a line segment set; determine the echo clustering data at the multiple moments based on the line segment set; map the echo clustering data at the multiple moments to a grid map to obtain grid clustering data at the multiple moments; and cluster and merge the grid clustering data at the multiple moments to obtain radar echo processing data.

[0170] Optionally, the processing module 22 is specifically configured to:

[0171] Analyzing and processing the navigation radar echo sets of the unmanned boat at the multiple moments to obtain navigation radar echo sequences of multiple side angles;

[0172] The navigation radar echo sequences of the multiple side angles are traversed and processed according to preset conditions to obtain multiple single echo information;

[0173] The plurality of single echo information are merged to obtain a line segment set.

[0174] Optionally, the processing module 22 is further specifically configured to:

[0175] Determining a plurality of line segment data of a plurality of side angles according to the line segment set;

[0176] determining a plurality of distance maximum values ​​according to the plurality of line segment data of the plurality of side angles;

[0177] Determining the overlap of multiple distance intervals according to the multiple distance maximum values;

[0178] Echo clustering data at multiple moments are determined according to the overlap degrees of the multiple distance intervals.

[0179] Optionally, the processing module 22 is further configured to:

[0180] Performing coordinate conversion processing on the echo clustering data at the multiple moments to obtain global coordinate position data of the unmanned boat;

[0181] Mapping the global coordinate position data of the unmanned boat into a grid map to obtain grid data;

[0182] determining echo intensity data according to the grid data;

[0183] Grid clustering data at multiple moments are determined according to the grid data and the echo intensity data.

[0184] Optionally, determining grid clustering data at multiple moments based on the grid data and the echo intensity data includes:

[0185] according to:

[0186] ,

[0187] Determine raster clustering data at multiple moments;

[0188] in, is the grid clustering data at the kth moment, is the x-axis grid position in the global coordinate system, is the y-axis grid position in the global coordinate system, is the grid echo intensity data, is the jth echo distance of the mth side angle at the kth moment, is the jth echo intensity at the mth side angle at the kth moment, where k, m, and j are natural numbers. is the echo clustering data, Indicates echo Map to raster .

[0189] Optionally, the processing module 22 is further configured to:

[0190] Obtaining element occupancy probability data based on the grid clustering data at the plurality of moments;

[0191] performing binarization processing on the element occupation probability data to obtain binarized element occupation probability data;

[0192] Performing screening processing on the element occupation probability data after the binarization processing to obtain a plurality of screened raster clustering data;

[0193] The plurality of filtered grid cluster data are merged to obtain radar echo processing data.

[0194] Optionally, obtaining element occupancy probability data based on the grid clustering data at the multiple moments includes:

[0195] according to:

[0196] ,

[0197] Get element occupancy probability data;

[0198] in, is the probability data of each element in the grid cluster from time 0 to k, is the probability data of each element in the grid cluster from 0 to k-1 time, is the maximum echo intensity, η1 is the probability of non-occupancy, is the x-axis grid position in the global coordinate system from time 0 to k, is the y-axis grid position in the global coordinate system from time 0 to k, is the grid clustering data from time 0 to k-1.

[0199] It should be noted that this device is a device corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0200] like Figure 3As shown, an embodiment of the present invention further provides a computing device 30, including a processor 31, a memory 32, and a program or instruction stored in the memory 32 and executable on the processor 31. When the program or instruction is executed by the processor 31, each process of the above-mentioned unmanned boat navigation radar echo processing method embodiment is implemented, and the same technical effect is achieved. To avoid repetition, it is not described here. It should be noted that the computing device in the embodiment of the present invention includes the above-mentioned mobile electronic device and non-mobile electronic device.

[0201] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0202] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0203] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0204] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0205] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0206] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for causing a computer device (such as a personal computer, server, or network device) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0207] In addition, it should be pointed out that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but they do not necessarily need to be performed in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it can be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in hardware, firmware, software or a combination thereof in any computing device (including a processor, storage medium, etc.) or a network of computing devices. This can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0208] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the purpose of the present invention can also be achieved simply by providing a program product containing program code for implementing the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but do not necessarily need to be performed in chronological order. Certain steps can be performed in parallel or independently of each other.

[0209] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for processing echoes of an unmanned boat navigation radar, characterized in that: include: Obtain the drone navigation radar echo set at multiple times; performing clustering processing on the unmanned boat navigation radar echo sets at the multiple moments to obtain a line segment set; Determining echo clustering data at multiple moments according to the line segment set; Mapping the echo clustering data at the multiple moments into a grid map to obtain grid clustering data at the multiple moments; Obtaining element occupancy probability data based on the grid clustering data at the plurality of moments; performing binarization processing on the element occupation probability data to obtain binarized element occupation probability data; Performing screening processing on the element occupation probability data after the binarization processing to obtain a plurality of screened raster clustering data; Merging the plurality of filtered grid cluster data to obtain radar echo processing data; The element occupancy probability data is obtained based on the grid clustering data at the multiple moments, including: according to: ， Get element occupancy probability data; in, From 0 to k The probability data of each element in the grid cluster at the moment, 0 to k -1 time grid clustering of each element occupies the probability data, is the maximum echo intensity, η 1 is the probability of non-occupancy, which is a predefined constant. From 0 to k In the global coordinate system at the moment x Axis grid positions, From 0 to k In the global coordinate system at the moment y Axis grid positions, From 0 to k -1 moment grid clustering data, For the k Raster clustering data at time, is the grid echo intensity data.

2. The unmanned boat navigation radar echo processing method according to claim 1, characterized in that: Clustering is performed on the unmanned boat navigation radar echo sets at the multiple moments to obtain a line segment set, including: Analyzing and processing the navigation radar echo sets of the unmanned boat at the multiple moments to obtain navigation radar echo sequences of multiple side angles; The navigation radar echo sequences of the multiple side angles are traversed and processed according to preset conditions to obtain multiple single echo information; The plurality of single echo information are merged to obtain a line segment set.

3. The unmanned boat navigation radar echo processing method according to claim 1, characterized in that: Determining echo clustering data at multiple moments according to the line segment set includes: Determining a plurality of line segment data of a plurality of side angles according to the line segment set; determining a plurality of distance maximum values ​​according to the plurality of line segment data of the plurality of side angles; Determining the overlap of multiple distance intervals according to the multiple distance maximum values; Echo clustering data at multiple moments are determined according to the overlap degrees of the multiple distance intervals.

4. The unmanned boat navigation radar echo processing method according to claim 1, characterized in that: Mapping the echo clustering data at the multiple moments into a grid map to obtain grid clustering data at the multiple moments includes: Performing coordinate conversion processing on the echo clustering data at the multiple moments to obtain global coordinate position data of the unmanned boat; Mapping the global coordinate position data of the unmanned boat into a grid map to obtain grid data; determining echo intensity data according to the grid data; Grid clustering data at multiple moments are determined according to the grid data and the echo intensity data.

5. The unmanned boat navigation radar echo processing method according to claim 4, characterized in that: Determining grid clustering data at multiple moments according to the grid data and the echo intensity data, including: according to: ， Determine raster clustering data at multiple moments; in, For the k Raster clustering data at time, In the global coordinate system x Axis grid positions, In the global coordinate system y Axis grid positions, is the grid echo intensity data, For the k Moment m The first side angle j Echo distance, For the k Moment m The first side angle j The echo strength, k 、 m 、 j is a natural number, is the echo clustering data, Indicates echo Map to raster .

6. An unmanned boat navigation radar echo processing device, characterized in that: include: The acquisition module is used to obtain the echo sets of the unmanned boat navigation radar at multiple times; A processing module is configured to cluster the echo sets of the unmanned boat navigation radar at the multiple moments to obtain a line segment set; determine echo clustering data at the multiple moments based on the line segment set; map the echo clustering data at the multiple moments to a grid map to obtain grid clustering data at the multiple moments; obtain element occupancy probability data based on the grid clustering data at the multiple moments; and perform binarization processing on the element occupancy probability data to obtain binarized element occupancy probability data; Performing screening processing on the element occupation probability data after the binarization processing to obtain a plurality of screened raster clustering data; Merging the plurality of filtered grid cluster data to obtain radar echo processing data; The element occupancy probability data is obtained based on the grid clustering data at the multiple moments, including: according to: ， Get element occupancy probability data; in, From 0 to k The probability data of each element in the grid cluster at the moment, 0 to k -1 time grid clustering of each element occupies the probability data, is the maximum echo intensity, η 1 is the probability of non-occupancy, which is a predefined constant. From 0 to k In the global coordinate system at the moment x Axis grid positions, From 0 to k In the global coordinate system at the moment y Axis grid positions, From 0 to k -1 moment grid clustering data, For the k Raster clustering data at time, is the grid echo intensity data.

7. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 5 is performed.

8. A computer-readable storage medium, characterized in that The device stores instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 5.

Images