Multi-source target fusion judgment method based on offshore monitoring system

Abstract

The invention relates to the technical field of offshore monitoring systems, and discloses a multi-source target fusion judgment method based on an offshore monitoring system, and the method achieves the precise monitoring and recognition of an offshore target through constructing a unified target list and integrating the data of a radar, an AIS (Automatic Identification System), Beidou and other multi-source sensors. The specific implementation comprises the following steps: establishing a multi-source target list, and storing detection target information from different sensors; real-time matching and updating of the target data are realized based on the site ID, the target ID and the target type; and the fusion judgment of the multi-source targets is completed by calculating the fusion degree numerical value between the targets. According to the method, through multi-sensor data fusion, the accuracy and reliability of offshore target monitoring are remarkably improved, the false alarm rate and the omission ratio are effectively reduced, and more perfect technical support is provided for offshore safety monitoring.

Description

Technical Field

[0001] This invention belongs to the technical field of nearshore monitoring systems, and particularly relates to a multi-source target fusion determination method based on nearshore monitoring systems. Background Technology

[0002] Nearshore monitoring systems utilize a network of multiple sensors, including radar, Automatic Identification System (AIS), and GPS / BeiDou, to achieve automatic detection, tracking, and identification of targets across the entire area. However, in practical applications, two major problems exist: First, single-sensor data is prone to interruption or loss due to obstruction, malfunction, or other reasons, resulting in incomplete target information. Second, the system needs to process massive amounts of real-time target data, and the traditional single-sensor independent processing mode suffers from computational redundancy. Therefore, it is urgent to achieve complementarity of target data through multi-source data fusion to improve data quality and reduce system load.

[0003] Current mainstream technologies employ trajectory association algorithms to achieve target fusion. The technical approach involves two key steps: first, time calibration is performed on the spatiotemporal asynchronous data collected by heterogeneous sensors to eliminate clock deviations between systems; then, based on the calibrated trajectory data, matching is determined through location proximity (such as Euclidean distance threshold) and consistency of motion state (speed, heading), and finally, the fusion association relationship of multi-sensor targets is established.

[0004] The existing methods have significant limitations: (1) They rely on short-term trajectory segment analysis. When the recent trajectories of two targets overlap or their motion characteristics are similar (such as ships sailing side by side), they are prone to false associations; (2) The motion state determination is based only on instantaneous speed and heading, without considering the long-term behavior patterns of the target. Low-speed targets will have a higher state misjudgment rate due to sensor noise; (3) They lack comprehensive analysis of the spatiotemporal characteristics of the target's activity range, making it difficult to meet the multi-target discrimination requirements in complex maritime scenarios.

[0005] To address the aforementioned shortcomings, there is an urgent need to propose a multi-source target fusion determination method to improve the accuracy and robustness of multi-source target fusion, thereby solving the technical bottlenecks of existing solutions in areas such as trajectory similarity target differentiation and low-speed target status determination, and providing more reliable data support for nearshore intelligent monitoring systems. Summary of the Invention

[0006] The present invention aims to solve the problem of insufficient accuracy in target fusion judgment in the prior art, and provides a method for comprehensive judgment by combining the similarity of the target's recent flight trajectory, the consistency of its motion state, and the characteristics of its long-term flight trajectory, so as to improve the accuracy of target fusion.

[0007] Specifically, this can be achieved through the following approach: A multi-source target fusion determination method based on a nearshore monitoring system, the method comprising: S1: The near-shore monitoring system constructs a target list, storing each target detected by a multi-sensor network, including radar, Automatic Identification System (AIS), and BeiDou, into the target list; Furthermore, the target source includes one or more of AIS, radar, and BeiDou.

[0008] S2: The nearshore monitoring system receives the measured trajectory point P data of the target, and matches the corresponding target A in the target list according to the station ID, target ID and target type carried by the target, and completes the real-time update of the information of target A; S3: Based on the entire target list, periodically calculate the fusion degree between pairs of targets, and complete the fusion determination based on the fusion degree value.

[0009] Furthermore, in S2, the information of target A is updated in real time, including the update of the standardized sampled short trajectory of target A, the update of the target's motion state, and the update of the compressed trajectory, wherein, The standardized sampling short trajectory refers to a short trajectory sequence composed of predicted trajectory points of the target motion at adjacent standardized sampling times, wherein the length of the short trajectory is set to a fixed value; The target motion state refers to whether the target is currently stationary or in motion; The compressed trajectory refers to storing key points of the target's trajectory during its navigation process, including points of speed change and direction change, so as to compress the target's motion trajectory and make it easier to record a longer navigation time using fewer trajectory points.

[0010] Furthermore, the standardized sampling short trajectory update of target A includes: S2-11: Based on standardized sampling time interval Calculate the data reception time of one frame at the target's measured trajectory point. The most recent standardized sampling time point ; S2-12: Calculate the current frame data reception time of the target's measured trajectory point. T Previous most recent standardized sampling time point ; S2-13: Compare the current standardized sampling time points Standardized sampling time point compared to the previous frame of data reception The interval between them is used to determine the standardized sampling short trajectory update conditions for target A and complete the update.

[0011] Furthermore, in S2-13, the step of determining the standardized sampling short trajectory update conditions for target A based on the interval and completing the update includes: like If so, the current frame data is the latest short trajectory data by default, and there is no need to update the standardized sampled short trajectory; like Then calculate the update time point. The update time point was calculated using linear interpolation. The corresponding trajectory data is added to the short trajectory, keeping the short trajectory length constant, thus completing the standardized sampling short trajectory update for target A.

[0012] Furthermore, the motion state update of target A includes: S2-21: Based on the updated short trajectory, calculate the target's cumulative travel distance and average speed during this period; S2-22: Based on the updated short trajectory, calculate the minimum circumcircle of all trajectory points and obtain the radius of the minimum circumcircle as the size of the target's activity range during this time. S2-23: Set a threshold based on the size of the target's activity range and average speed. If both the size of the target's activity range and average speed are less than the set threshold, the target's motion state is determined to be stationary; otherwise, it is determined to be in motion.

[0013] Furthermore, the compression trajectory update of target A includes: S2-31: Define the list of compressed trajectory points and trajectory sliding window (Initially all are empty), add trajectory point P to the trajectory sliding window. middle, Indicates the first i Key points of the trajectory Indicates the first j A trajectory point P; S2-32: If the trajectory sliding window The number of trajectory points P contained therein is less than or equal to a set threshold. N If the trajectory is not compressed, no trajectory update will be performed; if the trajectory sliding window... The number of trajectory points P contained therein is greater than a set threshold. N Then, based on the motion state of target A, different trajectory key point determination methods are used to find the trajectory sliding window. Trajectory key points in order to reduce The data storage volume is reduced, and the trajectory key points are stored in a compressed trajectory point list. In this process, compressed trajectory updates are implemented.

[0014] Furthermore, in S2-32, the sliding window of the trajectory... The number of trajectory points P contained therein is greater than a set threshold. N Then, based on the motion state of target A, different trajectory key point determination methods are used to find the trajectory sliding window. Among the trajectory key points, the different trajectory key point determination methods specifically include: S2-32-1: If target A is stationary, key points are determined based on the distances between points, including: by starting point As the key point, calculate the second trajectory point. Distance from the starting point d ; By distance d Determine the trajectory point Is it a key point in the trajectory? d< Threshold, then For non-trajectory key points, from Delete ,like d≥ Threshold, then As key points of the trajectory, the points are... Add to In the middle, at the same time from Delete point Based on trajectory key points A new beginning; Based on trajectory key points As a new starting point, calculate the new starting point and the new second trajectory point. The distance between them is used to determine the new second trajectory point using the above-mentioned judgment method. Determine if it is a key point on the trajectory and perform the corresponding operation; Judgment of key points of repeating trajectory until The determination of key points of the trajectory stops when only 2 elements remain. The number of trajectory points P added again exceeds the set threshold. N When target A is stationary, the trajectory key point determination repeats the above operation steps.

[0015] S2-32-2: If target A is in motion, key points are determined by combining heading, speed, and position information, including: calculate Middle starting point To the remaining points Direction value , For natural numbers, represent The number of trajectory points P contained therein; calculate The difference between the direction value from the starting point to the second point and the direction value from the starting point to other points. and the average of all differences ,in, , For natural numbers, represent The number of trajectory points P contained therein; Calculate the sliding window Average speed of targets within range ,in, , Time for each trajectory point; Based on the starting point location and along the direction from the starting point to the ending point, calculate the predicted location at each time point. Calculate the deviation between the predicted position and the measured position. ; like All are less than the set position deviation threshold, and If the value is less than the set heading threshold, no new trajectory key points will be found, and the trajectory will then be determined from the target value. Delete point , For natural numbers, represent The number of trajectory points P contained therein; like All are less than the set position deviation threshold, while If the heading exceeds the set heading threshold, then select... The first trajectory point in the path that exceeds the set heading threshold As key points of the trajectory, the points are... Add to In the middle, at the same time from Delete point , A natural number representing the number of key points on the trajectory; If it exists If the deviation is greater than the set position deviation threshold, for Points greater than the set position deviation threshold Select The first one Points exceeding a set heading threshold are designated as key points on the track; otherwise, a key point is selected. middle The largest point is taken as the key point of the track, and the index of the key point is denoted as . , will point Add to In the middle, at the same time from Delete point , is a natural number representing the number of key points on the trajectory.

[0016] Furthermore, in S3, the periodic calculation of the fusion degree between pairs of targets based on the entire target list specifically includes: S3-1: Calculate the short trajectory overlap between target A and target B in the target list. ; S3-2: Calculate the instantaneous motion consistency parameters between target A and target B in the target list. ; S3-3: Calculate the long-term motion consistency parameters between target A and target B in the target list. ; S3-4: Based on the overlap of short trajectories Instantaneous motion consistency parameters Consistency with long-term exercise The fusion degree between targets is calculated using a weighted summation method. When the degree of integration If the degree of fusion exceeds the set fusion threshold, the two targets are determined to be fused; otherwise, they are determined not to be fused.

[0017] Furthermore, in S3-1, the short trajectory overlap... The specific calculations include: S3-11: Compare the sampling time sequence of short trajectories of two targets. and Then, sampling time point matching is performed to obtain the time point subsequence between the two targets whose sampling time points are closest. And the corresponding sub-trajectories; S3-12: Calculate the time point subsequences respectively T The distance between the corresponding two target trajectory points is used to obtain the distance sequence. The short trajectory overlap is the proportion of points in the distance sequence whose values ​​are less than a set distance threshold to the entire sequence. .

[0018] Furthermore, in S3-2, the instantaneous motion consistency parameter The calculations include: If the two targets have different motion states, then the instantaneous motion consistency parameter =0; If the two targets have the same motion state and are in motion, then calculate the instantaneous motion consistency parameter. The expression is:

[0019] In the formula, and These represent the most recently updated differences in heading and speed between the two targets, respectively. HThis indicates the set heading difference threshold. V Indicates the speed difference threshold; If the two targets have the same motion state and are stationary, then calculate the instantaneous motion consistency parameter. The expression is:

[0020] In the formula, This represents the distance between the most recently updated positions of two targets; D This indicates that a threshold for the distance is set.

[0021] Furthermore, in S3-3, the long-term motion consistency parameter The specific calculations include: Based on the start and end times corresponding to the compression trajectory of target A. The start and end times corresponding to the compression trajectory of target B Calculate the overlap time between the start and end times of the two compression trajectories. ,in, ; The sub-trajectories of two targets within the overlapping time period are obtained using linear interpolation, and the cumulative travel distance of target A's sub-trajectory is calculated. Cumulative travel distance of the target B sub-track ; The ratio of cumulative travel distances is used to measure the long-term motion consistency parameter among targets. The calculation formula is:

[0022] In the formula, w The set distance ratio threshold.

[0023] Furthermore, in S3-4, the weighted summation method is used to calculate the fusion degree between targets. The specific calculation expression is as follows:

[0024] In the formula, Indicates the overlap of short trajectories The weighting percentage Indicates instantaneous motion consistency parameter The weighting percentage Indicating long-term motion consistency The weighting percentage.

[0025] Compared with the prior art, the present invention has the following advantages: 1. Improve the accuracy of target fusion: This invention combines the similarity of the target's recent flight trajectory, the consistency of its motion state, and the characteristics of its long-term flight trajectory to comprehensively judge the similarity of the targets. This solves the problem that existing technologies are prone to misjudgment when the target trajectories are similar or the distance is close, and significantly improves the accuracy of target fusion. 2. Optimize target tracking and identification: By updating the standardized sampled short trajectory and compressed trajectory of the target in real time, and combining it with the determination of motion status, the target can be tracked and identified more accurately, thus improving the overall performance of the nearshore monitoring system.

[0026] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. Attached Figure Description

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 This is a flowchart illustrating a multi-source target fusion determination method based on a nearshore monitoring system. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] In one embodiment, please refer to Figure 1 This paper provides a multi-source target fusion determination method based on a nearshore monitoring system, the method comprising the following steps: Step S1: The nearshore monitoring system constructs a target list, storing each target detected by the multi-sensor network, including radar, AIS, and BeiDou, into the target list; Furthermore, the target source includes one or more of AIS, radar, and BeiDou.

[0031] Step S2: The nearshore monitoring system receives the measured trajectory point P data of the target, matches the corresponding target A in the target list according to the station ID, target ID and target type carried by the target, and completes the real-time update of the information of target A; Furthermore, the information of target A is updated in real time, including updates to the standardized sampled short trajectory of target A, updates to the target's motion state, and updates to the compressed trajectory, wherein... The standardized sampling short trajectory refers to a short trajectory sequence composed of predicted trajectory points of the target motion at adjacent standardized sampling times, wherein the length of the short trajectory is set to a fixed value; The target motion state refers to whether the target is currently stationary or in motion; The compressed trajectory refers to storing key points of the target's trajectory during its navigation process, including points of speed change and direction change, so as to compress the target's motion trajectory and make it easier to record a longer navigation time using fewer trajectory points.

[0032] Furthermore, the standardized sampling short trajectory update, target motion state update, and compressed trajectory update for target A specifically include: The standardized sampling short trajectory update for target A specifically includes: Step S2-11: Based on the standardized sampling time interval Calculate the data reception time of one frame at the target's measured trajectory point. The most recent standardized sampling time point Its calculation expression is:

[0033] In the formula, The function is a standard mathematical function used for rounding up; Step S2-12: Calculate the data reception time of the current frame for the target's measured trajectory point. T Previous most recent standardized sampling time point Its calculation expression is:

[0034] In the formula, The function is a standard mathematical function used for rounding down; Step S2-13: Compare the current standardized sampling time points Standardized sampling time point compared to the previous frame of data reception The interval between them is used to determine the standardized sampling short trajectory update conditions for target A and complete the update. Furthermore, in step S2-13, the step of determining the standardized sampling short trajectory update conditions for target A based on the interval and completing the update includes: like If so, the current frame data is the latest short trajectory data by default, and there is no need to update the standardized sampled short trajectory; like Then calculate the update time point. The update time point was calculated using linear interpolation. The corresponding trajectory data is added to the short trajectory, keeping the short trajectory length constant, thus completing the standardized sampling short trajectory update for target A.

[0035] Furthermore, the requirement to maintain a short trajectory length can be set to a constant threshold as needed during the initial operation of the nearshore monitoring system. M It cannot be changed afterward; The calculation update time point The expression is:

[0036] In the formula, Indicates the first Updates at specific points in time. n It is a natural number representing the total number of update points.

[0037] The motion state update of target A specifically includes: Step S2-21: Based on the updated short trajectory, calculate the target's cumulative travel distance and average speed during this period; Step S2-22: Based on the updated short trajectory, calculate the minimum circumcircle of all trajectory points in the short trajectory, and obtain the minimum circumcircle radius as the size of the target's activity range during this period; Step S2-23: Set a threshold based on the target's activity range size and average speed. If both the target's activity range size and average speed are less than the set threshold, the target's motion state is determined to be stationary; otherwise, it is determined to be in motion.

[0038] The compressed trajectory update of target A specifically includes: Step S2-31: Define the list of compressed trajectory points and trajectory sliding window (Initially all are empty), add trajectory point P to the trajectory sliding window. middle, Indicates the first i Key points of the trajectory Indicates the first j A trajectory point P; Furthermore, the defined compressed trajectory point list and trajectory sliding window Its purpose is to store key points of the target's trajectory during navigation, so as to record a longer navigation time using fewer trajectory points.

[0039] Step S2-32: If the trajectory sliding window The number of trajectory points P contained therein is less than or equal to a set threshold. N If the trajectory is not compressed, no trajectory update will be performed; if the trajectory sliding window... The number of trajectory points P contained therein is greater than a set threshold. N Then, based on the motion state of target A, different trajectory key point determination methods are used to find the trajectory sliding window. Trajectory key points in order to reduce The data storage volume is reduced, and the trajectory key points are stored in a compressed trajectory point list. In this process, compressed trajectory updates are implemented.

[0040] Furthermore, in steps S2-32, the sliding window of the trajectory... The number of trajectory points P contained therein is greater than a set threshold. N Then, based on the motion state of target A, different trajectory key point determination methods are used to find the trajectory sliding window. Among the trajectory key points, the different trajectory key point determination methods specifically include the following: Method 1: If target A is stationary, determine key points based on the distances between points, including: by starting point As the key point, calculate the second trajectory point. Distance from the starting point d ; By distance d Determine the trajectory point Is it a key point in the trajectory? d <threshold, then For non-trajectory key points, from Delete ,like d If ≥ threshold, then As key points of the trajectory, the points are... Add to In the middle, at the same time from Delete point Based on trajectory key points A new beginning; Based on trajectory key points As a new starting point, calculate the new starting point and the new second trajectory point. The distance between them is used to determine the new second trajectory point using the above-mentioned judgment method. Determine if it is a key point on the trajectory and perform the corresponding operation; Judgment of key points of repeating trajectory until The determination of key points of the trajectory stops when only 2 elements remain. The number of trajectory points P added again exceeds the set threshold. N When target A is stationary, the trajectory key point determination repeats the above operation steps.

[0041] Furthermore, in this embodiment, the set threshold is preferably set to 4.

[0042] Method 2: If target A is in motion, determine key points by combining heading, speed, and position information, including: calculate Middle starting point To the remaining points Direction value , For natural numbers, represent The number of trajectory points P contained therein; calculate The difference between the direction value from the starting point to the second point and the direction value from the starting point to other points. and the average of all differences ,in, , For natural numbers, represent The number of trajectory points P contained therein; Calculate the sliding window Average speed of targets within range ,in, , Represents the time of each trajectory point, the first... The time for each trajectory point; Based on the starting point location and along the direction from the starting point to the ending point, calculate the predicted location at each time point. Calculate the deviation between the predicted position and the measured position. ; like All are less than the set position deviation threshold, and If the value is less than the set heading threshold, no new trajectory key points will be found, and the trajectory will then be determined from the target value. Delete point , For natural numbers, represent The number of trajectory points P contained therein; like All are less than the set position deviation threshold, while If the heading exceeds the set heading threshold, then select... The first trajectory point in the path that exceeds the set heading threshold As key points of the trajectory, the points are... Add to In the middle, at the same time from Delete point , A natural number representing the number of key points on the trajectory; If it exists If the deviation is greater than the set position deviation threshold, for Points greater than the set position deviation threshold Select The first one Points exceeding a set heading threshold are designated as key points on the track; otherwise, a key point is selected. middle The largest point is taken as the key point of the track, and the index of the key point is denoted as . , will point Add to In the middle, at the same time from Delete point , is a natural number representing the number of key points on the trajectory.

[0043] Step S3: Based on the entire target list, periodically calculate the fusion degree between pairs of targets, and complete the fusion determination based on the fusion degree value.

[0044] Furthermore, in step S3, the periodic calculation of the fusion degree between pairs of targets based on the entire target list specifically includes: Step S3-1: Calculate the short trajectory overlap between target A and target B in the target list. ; Furthermore, the short trajectory overlap The specific calculations include: Step S3-11: Compare the sampling time sequence of the short trajectories of the two targets. and Then, sampling time point matching is performed to obtain the time point subsequence between the two targets whose sampling time points are closest. And the corresponding sub-trajectories; Furthermore, the sampling time point sequence , and time point subsequence The expression is as follows:

[0045] In the formula, This represents the threshold for the difference between sampling time points. Sampling time point matching is only satisfied when the difference between the sampling time points between two sampling points is minimal and less than this threshold. is a natural number representing the degree of the short trajectory.

[0046] Step S3-12: Calculate the time point subsequences respectively. T The distance between the corresponding two target trajectory points is used to obtain the distance sequence. The short trajectory overlap is the proportion of points in the distance sequence whose values ​​are less than a set distance threshold to the entire sequence. .

[0047] Step S3-2: Calculate the instantaneous motion consistency parameters between target A and target B in the target list. ; Furthermore, the instantaneous motion consistency parameter The calculations include: If the two targets have different motion states, then the instantaneous motion consistency parameter =0; If the two targets have the same motion state and are in motion, then The calculation method includes calculating the difference in the most recently updated headings of the two targets respectively. And speed difference Set heading difference threshold H And speed difference threshold V ,but The expression to be evaluated is, ; If the two targets have the same motion state and are both stationary, then The calculation method includes calculating the distance between the most recently updated positions of the two targets respectively. Set distance threshold D ,but The expression to be evaluated is, .

[0048] Step S3-3: Calculate the long-term motion consistency parameters between target A and target B in the target list. ; Furthermore, the long-term motion consistency is specifically calculated including: Based on the start and end times corresponding to the compression trajectory of target A. The start and end times corresponding to the compression trajectory of target B Calculate the overlap time between the start and end times of the two compression trajectories. ,in, ; The sub-trajectories of two targets within the overlapping time period are obtained using linear interpolation, and the cumulative travel distance of target A's sub-trajectory is calculated. Cumulative travel distance of the target B sub-track ; The ratio of cumulative travel distances is used to measure the long-term motion consistency parameter among targets. The calculation formula is:

[0049] In the formula, w The set distance ratio threshold.

[0050] Step S3-4: Based on the short trajectory overlap Instantaneous motion consistency parameters Consistency with long-term exercise The fusion degree between targets is calculated using a weighted summation method. When the degree of integration If the degree of fusion exceeds the set fusion threshold, the two targets are determined to be fused; otherwise, they are determined not to be fused.

[0051] Furthermore, the weighted summation method is used to calculate the fusion degree between targets. The specific calculation expression is as follows:

[0052] In the formula, Indicates the overlap of short trajectories The weighting percentage Indicates instantaneous motion consistency parameter The weighting percentage Indicating long-term motion consistency The weighting percentage.

[0053] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-source target fusion determination method based on a nearshore monitoring system, characterized in that, The method includes: The nearshore monitoring system constructs a target list, storing each target detected by radar, AIS, and BeiDou multi-sensor network into the target list; The nearshore monitoring system receives the measured trajectory point P data of the target, and matches the corresponding target A in the target list according to the station ID, target ID and target type carried by the target, and completes the real-time update of the information of target A; Based on the entire target list, the fusion degree between each pair of targets is calculated periodically, and the fusion determination is completed based on the fusion degree value.

2. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 1, characterized in that: The information of target A is updated in real time, including updates to the standardized sampled short trajectory of target A, updates to the target's motion state, and updates to the compressed trajectory. The standardized sampling short trajectory refers to a short trajectory sequence composed of predicted trajectory points of the target motion at adjacent standardized sampling times, wherein the length of the short trajectory is set to a fixed value; The target motion state refers to whether the target is currently stationary or in motion; The compressed trajectory refers to storing key points of the target's trajectory during its navigation process, including points of speed change and direction change, so as to compress the target's motion trajectory and make it easier to record a longer navigation time using fewer trajectory points.

3. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 2, characterized in that, The standardized short trajectory update for target A includes: Based on standardized sampling time interval Calculate the data reception time of one frame at the target's measured trajectory point. The most recent standardized sampling time point ; Calculate the current frame data reception time of the target's measured trajectory point. T Previous most recent standardized sampling time point ; Compare the current standardized sampling time points Standardized sampling time point compared to the previous frame of data reception The interval between them is used to determine the standardized sampling short trajectory update conditions for target A and complete the update.

4. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 3, characterized in that, The step of determining the standardized sampling short trajectory update conditions for target A based on the interval and completing the update includes: like If so, the current frame data is the latest short trajectory data by default, and there is no need to update the standardized sampled short trajectory; like Then calculate the update time point. The update time point was calculated using linear interpolation. The corresponding trajectory data is added to the short trajectory, keeping the short trajectory length constant, thus completing the standardized sampling short trajectory update for target A.

5. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 2, characterized in that, The motion state update of target A includes: Based on the updated short trajectory, calculate the target's cumulative travel distance and average speed during this period; Based on the updated short trajectory, calculate the minimum circumcircle of all trajectory points and obtain the radius of the minimum circumcircle as the size of the target's activity range during this time. A threshold is set based on the size of the target's activity range and the average speed. If both the size of the target's activity range and the average speed are less than the set threshold, the target's motion state is determined to be stationary; otherwise, it is determined to be in motion.

6. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 2, characterized in that, The compressed trajectory update for target A includes: Define a list of compressed trajectory points and trajectory sliding window Add trajectory point P to the trajectory slider window. In, among them, and Initially, all are empty. Indicates the first i Key points of the trajectory Indicates the first j A trajectory point P; If the trajectory sliding window The number of trajectory points P contained therein is less than or equal to a set threshold. N In this case, no compressed trajectory update will be performed; If the trajectory sliding window The number of trajectory points P contained therein is greater than the set threshold. N Then, based on the motion state of target A, different trajectory key point determination methods are used to find the trajectory sliding window. Trajectory key points in the middle to reduce The data storage volume is reduced, and the trajectory key points are stored in a compressed trajectory point list. In this process, compressed trajectory updates are implemented.

7. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 6, characterized in that, The different methods for determining trajectory key points specifically include: If target A is stationary, key points are determined based on the distance between points; If target A is in motion, key points are determined by combining heading, speed, and position information.

8. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 7, characterized in that, If target A is stationary, the key point determination is based on the distance between points, including: by starting point As the key point, calculate the second trajectory point. Distance from the starting point d ; By distance d Determine the trajectory point Is it a key point in the trajectory? d <threshold, then For non-trajectory key points, from Delete ,like d If ≥ threshold, then As key points of the trajectory, the points are... Add to In the middle, at the same time from Delete point Based on trajectory key points A new beginning; Based on trajectory key points As a new starting point, calculate the new starting point and the new second trajectory point. The distance between them is used to determine the new second trajectory point using the above-mentioned judgment method. Determine if it is a key point on the trajectory and perform the corresponding operation; Judgment of key points of repeating trajectory until The determination of key points of the trajectory stops when only 2 elements remain. The number of trajectory points P added again exceeds the set threshold. N When target A is stationary, the trajectory key point determination repeats the above operation steps.

9. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 7, characterized in that, If target A is in motion, key point determination is performed by combining heading, speed, and position information, including: calculate Middle starting point To the remaining points Direction value , For natural numbers, represent The number of trajectory points P contained therein; calculate The difference between the direction value from the starting point to the second point and the direction value from the starting point to other points. and the average of all differences ,in, , For natural numbers, represent The number of trajectory points P contained therein; Calculate the sliding window Average speed of targets within range ,in, , For the first j Time for each trajectory point; Based on the starting point location and along the direction from the starting point to the ending point, calculate the predicted location at each time point. Calculate the deviation between the predicted position and the measured position. ; like All are less than the set position deviation threshold, and If the value is less than the set heading threshold, no new trajectory key points will be found, and the trajectory will then be determined from the target value. Delete point , For natural numbers, represent The number of trajectory points P contained therein; like All are less than the set position deviation threshold, while If the heading exceeds the set heading threshold, then select... The first trajectory point in the path that exceeds the set heading threshold As key points of the trajectory, the points are... Add to In the middle, at the same time from Delete point , A natural number representing the number of key points on the trajectory; If it exists If the deviation is greater than the set position deviation threshold, for Points greater than the set position deviation threshold Select The first one Points exceeding a set heading threshold are designated as key points on the track; otherwise, a key point is selected. middle The largest point is taken as the key point of the track, and the index of the key point is denoted as . , will point Add to In the middle, at the same time from Delete point , , is a natural number representing the number of key points on the trajectory.

10. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 1, characterized in that, The calculation of the fusion degree between pairs of targets is performed periodically based on the entire target list, specifically including: Calculate the short trajectory overlap between target A and target B in the target list. ; Calculate the instantaneous motion consistency parameters between target A and target B in the target list. ; Calculate the long-term motion consistency parameters between target A and target B in the target list. ; Based on short trajectory overlap Instantaneous motion consistency parameters Consistency with long-term exercise The fusion degree between targets is calculated using a weighted summation method. When the degree of integration If the degree of fusion exceeds the set fusion threshold, the two targets are determined to be fused; otherwise, they are determined not to be fused.

11. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 10, characterized in that, The short trajectory overlap The specific calculations include: Comparison of sampling time sequence of short trajectories of two targets and Then, sampling time point matching is performed to obtain the time point subsequence between the two targets whose sampling time points are closest. And the corresponding sub-trajectories; Calculate the time point subsequences respectively T The distance between corresponding target trajectory points is used to obtain a distance sequence. The proportion of points in the distance sequence whose values ​​are less than a set distance threshold is counted, which is the short trajectory overlap. .

12. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 10, characterized in that, The instantaneous motion consistency parameter The calculations include: If the two targets have different motion states, then the instantaneous motion consistency parameter =0; If the two targets have the same motion state and are in motion, then calculate the instantaneous motion consistency parameter. The expression is: In the formula, and These represent the most recently updated differences in heading and speed between the two targets, respectively. H This indicates the set heading difference threshold. V Indicates the speed difference threshold; If the two targets have the same motion state and are in a stationary state, then calculate the instantaneous motion consistency parameter. The expression is: In the formula, This represents the distance between the most recently updated positions of two targets; D This indicates that a threshold for the distance is set.

13. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 10, characterized in that, The long-term motion consistency parameter The calculations include: Based on the start and end times corresponding to the compression trajectory of target A. The start and end times corresponding to the compression trajectory of target B Calculate the overlap time between the start and end times of the two compression trajectories. ,in, ; The sub-trajectories of two targets within the overlapping time period are obtained using linear interpolation, and the cumulative travel distance of target A's sub-trajectory is calculated. Cumulative travel distance of the target B sub-track ; The ratio of cumulative travel distances is used to measure the long-term motion consistency parameter among targets. The calculation formula is: In the formula, w The set distance ratio threshold.

14. The multi-source target fusion determination method based on a nearshore monitoring system as described in claim 10, characterized in that, The inter-target fusion degree is calculated using a weighted summation method. The specific calculation expression is as follows: In the formula, Indicates the overlap of short trajectories The weighting percentage Indicates instantaneous motion consistency parameter The weighting percentage Indicating long-term motion consistency The weighting percentage.

Images