CN114063056A - Ship track fusion method, system, medium and equipment - Google Patents
Ship track fusion method, system, medium and equipment Download PDFInfo
- Publication number
- CN114063056A CN114063056A CN202111319617.6A CN202111319617A CN114063056A CN 114063056 A CN114063056 A CN 114063056A CN 202111319617 A CN202111319617 A CN 202111319617A CN 114063056 A CN114063056 A CN 114063056A
- Authority
- CN
- China
- Prior art keywords
- target
- ais
- radar
- value
- fusion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method, a system, a medium and equipment for fusing ship tracks, wherein the method comprises the following steps: the AIS target is subjected to time calibration, the data information detected by each data source is unified to the same reference moment, and the data information of each data source to the target at the same moment is obtained; judging similarity between target tracks by adopting a multi-factor fuzzy judgment algorithm, establishing a fuzzy factor set, determining the weight of the fuzzy factor set, and screening a radar target set which accords with the similarity; performing track association by adopting a Cauchy membership function; calculating gray level correlation values of the AIS target and radar targets in the radar target set according with the acquaintance degree, performing gray level correlation analysis, and judging that the corresponding radar target is the same target as the AIS target when the gray level correlation values are larger than a preset threshold value; and after the radar target associated with the AIS is obtained, fusion calculation is carried out on the tracks of the two targets, and the position and the motion state of the fused target are obtained. The invention can improve the accuracy and stability of target fusion.
Description
Technical Field
The invention relates to the technical field of ship information detection, in particular to a ship track fusion method, a system, a storage medium and computer equipment.
Background
In a VTS (vessel traffic service) ship traffic management system, a ship Automatic Identification System (AIS), a radar and other multi-data sources can be accessed, multiple data sources are provided as ship target related data sources, a single target can generate and obtain a target track through AIS data, meanwhile, a track can be generated through radar tracking in a radar detection range, a carrier can also generate multiple tracks through multiple radar detections in an overlapping area of a radar station, only one target needs to correspond to one track in a VTS comprehensive display center, and therefore, the ship track fusion technology is to determine whether the multiple tracks detected by a sensor, the AIS and the multiple radars are from the same target or not, and the tracks generated by the multi-data sources are fused into one track.
At present, researchers and experts at home and abroad have a great deal of research on the theory and method of association of various tracks. The method mainly comprises the following steps: the fuzzy clustering method, the double wave gate method, the K neighbor domain method, the neural network, the gray level correlation, the fuzzy theory and other methods have different degrees of advantages in different angles, but due to the fact that the external environment is extremely complex, particularly under the conditions that the target is dense and the number of cross maneuvering tracks is large and the like, a single method only considers a certain target situation, cannot be applied to the conditions that the target is complex and variable, and still has a large number of missed and missed tracks.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides a ship track fusion method, which is based on the combination of multi-factor fuzzy judgment and gray correlation degree, and carries out optimization processing on a track correlation algorithm of a fuzzy judgment process according to a target motion state, thereby improving the accuracy and stability of target fusion.
The second purpose of the invention is to provide a ship track fusion system.
A third object of the present invention is to provide a storage medium.
It is a fourth object of the invention to provide a computing device.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a ship track fusion method, which comprises the following steps:
respectively carrying out time calibration processing on the AIS and the radar target, unifying the data information detected by each data source to the same reference time, and obtaining the data information of each data source to the target at the same time;
judging the similarity between target tracks by adopting a multi-factor fuzzy judgment algorithm, establishing a fuzzy factor set, determining the weight of the fuzzy factor set, and screening out a radar target set which accords with the similarity;
performing track association by adopting a Cauchy membership function;
calculating gray level correlation values of the AIS target and the radar targets in the radar target set which accord with the degree of identity, performing gray level correlation analysis, and judging that the corresponding radar target is the same target as the AIS target when the gray level correlation values are larger than a preset correlation threshold value;
and after the radar target associated with the AIS is obtained, fusion calculation is carried out on the tracks of the two targets, and the position and the motion state of the fused target are obtained.
As a preferred technical solution, the time calibration processing is performed on the AIS and the radar target respectively, and the specific steps include:
respectively finding out the sampling time T of the track point from the target track record according to the time calibration time point T1And T2So that T is1And T2Satisfy T1<T<T2Calculating the corresponding position, course and navigational speed values of the target at the time calibration moment by adopting a linear interpolation method;
if the target track record has no sampling time T1And T2So that T is1And T2Satisfy T1<T<T2Then, the sampling time T of the track point is found1So that T is1The absolute value of T is minimum, the position of the target at the synchronous moment is calculated through a uniform linear motion model to obtain a corresponding target position factor value, and the course and the navigational speed use T1Target course and speed values for the trajectory points.
As a preferred technical scheme, before the step of judging the similarity between target tracks by adopting a multi-factor fuzzy judgment algorithm, the method further comprises a step of judging the motion state of the target, and specifically comprises the following steps:
selecting a value after AIS target time calibration, calculating the average speed value of the speed factors of the AIS target in a plurality of sampling time calibration time points, if the average speed value is greater than a preset speed threshold value, judging the AIS target to be a moving target, otherwise, judging the AIS target to be a static target.
As a preferred technical scheme, the determination of the degree of acquaintance is respectively carried out according to the stationary or moving state of the AIS target, and the method specifically comprises the following steps:
when the target is a static target:
judging whether a plurality of targets exist around the AIS, and adjusting a preset distance threshold according to the number of targets of the target set which accord with the degree of identity;
selecting a radar target, calculating the average Euclidean distance between the AIS target and the radar target, adding the radar target into a target set meeting the degree of identity if the average Euclidean distance is smaller than a preset distance threshold, and circularly traversing all the radar targets;
when the target is a moving target:
carrying out multi-factor fuzzy judgment and calculating the average Euclidean distance between the AIS target and the radar target, and if the average Euclidean distance is smaller than a preset distance threshold value, calculating the mean square difference value of the course of the radar target, the average speed of the radar target and the Cauchy membership function value;
judging whether the radar course value is effective or not according to the mean square difference value of the radar target course, adjusting the spread value of the position according to the average speed value of the radar target, carrying out weighted summation on the Cauchy membership function values of the two objective factors to obtain the total membership, carrying out threshold judgment on the weighted summation result, adding the radar target into a target set of AIS targets which accord with the identity when the total membership is greater than a preset distance threshold, and circularly traversing all the radar targets.
As a preferred technical scheme, the method further comprises an Euclidean distance calculation optimization step, and specifically comprises the following steps:
supplementing the target position by using the size of the ship target, and calculating a target position factor;
and setting the points A and B as the positions of the radar target and the AIS target respectively, setting the point C as the intersection point of the AB connecting line and the AIS target, and correcting the distance between the radar target and the AIS target into an AC line segment from an AB line segment.
As a preferred technical scheme, the calculating a gray level correlation value of the AIS target and the radar target in the radar target set conforming to the degree of identity, and performing gray level correlation analysis includes the following specific steps:
respectively carrying out dimension removing operation on the AIS target and the factor values of the position, the course and the speed of the radar target which accords with the mutual identification target set by using an average value method to obtain a dimension-removed numerical value;
calculating the gray level correlation values of the AIS target and the target concentrated radar target, taking the time as a plurality of factors in a gray level correlation model during calculation, taking a plurality of targets as judgment objects to form a calculation matrix, and calculating to obtain the correlation values of longitude, latitude, navigational speed and course at each time;
solving the arithmetic mean value of the time correlation values of longitude, latitude, navigational speed and heading, and carrying out weighted summation;
traversing the targets and the candidate coincidence degree target set targets, obtaining the weighted sum of the gray level correlation values of all radar targets, comparing to obtain the maximum correlation value, carrying out threshold judgment on the maximum correlation value, and judging that the corresponding target and the AIS target are the same target if the maximum correlation value is greater than a preset correlation threshold.
As a preferred technical scheme, after the radar target associated with the AIS is obtained, the two target tracks are subjected to fusion calculation, and the method specifically comprises the following steps:
acquiring the current state information of the AIS target and the radar target, and judging as a static state when the navigational speed of the AIS target is less than a threshold value, or judging as a moving state;
in a static state, the state information of the AIS is used as the state information of the fusion target, and in a moving state, the position information of the fusion target is obtained by a method of carrying out weighted average on the positions of the AIS target and the radar target;
and solving the sum of two target speed vectors by using a vector operation mode, calculating the resultant speed of the target, taking a resultant speed vector value 1/2 as a fusion target speed value, and taking a resultant speed vector direction value as a fusion target course value to obtain the speed and the course of the fusion target so as to obtain a target track fusion state.
In order to achieve the second object, the invention adopts the following technical scheme:
the invention also provides a ship track fusion system, which comprises: the system comprises a time calibration module, a track similarity judgment module, a track association module and a target fusion module;
the time calibration module is used for carrying out time calibration processing on the AIS target, unifying the data information detected by each data source to the same reference time and obtaining the data information of each data source to the target at the same time;
the track similarity judging module is used for judging the similarity between target tracks by adopting a multi-factor fuzzy judging algorithm, establishing a fuzzy factor set, determining the weight of the fuzzy factor set and screening out a radar target set conforming to the similarity;
the flight path correlation module is used for performing flight path correlation by adopting a Cauchy membership function, calculating a gray level correlation value of the AIS target and the radar target in the radar target set which accords with the degree of identity, performing gray level correlation analysis, and judging that the corresponding radar target is the same target as the AIS target when the gray level correlation value is greater than a preset correlation threshold;
and the target fusion module is used for performing fusion calculation on the two target tracks after the radar target associated with the AIS is obtained, so as to obtain the fused target position and motion state.
In order to achieve the third object, the invention adopts the following technical scheme:
a computer-readable storage medium storing a program which, when executed by a processor, implements the above-described ship track fusion method.
In order to achieve the fourth object, the invention adopts the following technical scheme:
a computing device comprises a processor and a memory for storing a program executable by the processor, and when the processor executes the program stored in the memory, the ship track fusion method is realized.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) the method adopts the position average difference to replace multi-factor fuzzy judgment under the condition that the target is static, uses ship target position parameters supplemented by ship size, and adjusts the parameter values of fuzzy association such as judgment spread, judgment threshold value, weight and the like according to the target motion state and the number of peripheral targets, thereby improving the accuracy and stability of target fusion.
Drawings
FIG. 1 is a schematic overall framework flow diagram of the ship track fusion method of the present invention;
FIG. 2 is a schematic flow chart of a specific process of the ship track fusion method of the present invention;
fig. 3 is a schematic diagram of an implementation principle of the ship target position completion of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
As shown in fig. 1 and fig. 2, this embodiment provides a ship track fusion method, which matches tracks of all unfused radar targets based on a single AIS target track, screens out a radar track with the highest matching degree to fuse with the AIS track, and calculates track points to be 10 points, including:
s1: first, time alignment processing is performed on the data, and the state at the same time is used for subsequent calculation of the two determined tracks. N fixed time points with short intervals are selected, and because the moving target with short intervals can approximately move in a uniform linear motion in the short time, the state of each data target at the same time point is calculated by adopting a linear interpolation method.
In this embodiment, since the data sources observe the same target at different times, the data sources need to be time-aligned before subsequent processing. The definition of time calibration is to unify the data information detected by each data source to the same reference time to obtain the data information of each data source to the target at the same time.
S11: calculating time calibration time points, forward decreasing by a fixed value with the current time as a reference, and calculating 10 time calibration time points (T)1、T2、…T10)；
S12: time calibration is carried out on the AIS target, and sampling time T of track points is found out from target track records according to time calibration time points T1And T2So that T is1And T2Satisfy T1<T<T2. And calculating the corresponding position (longitude and latitude), the course and the value X of the speed of the AIS target at the time point of time calibration by adopting a linear interpolation method. If the target track record has no sampling time T1And T2So that T is1And T2Satisfy T1<T<T2Then, the sampling time T of the track point is found1So that T is1The absolute value of T is minimum, and the position of a target at the synchronous moment is calculated through a uniform linear motion model to obtain a corresponding target position (longitude and latitude) factor value; course and speed then uses T1Target course and speed values for the trajectory points. Using the above method, 10 time-calibrated time points, AIS target position (longitude, latitude), heading, and speed values are obtained.
Set time T1<T<T2The ship target is at T1、T2The position information collected at each moment is (X)1，Y1)、(X2，Y2) Then, at the selected time T, the position (X, Y) information of the ship target is:
s13: and time calibration is carried out on the radar target according to an AIS target time calibration method, and four factor values of target positions (longitude, latitude), course and navigational speed corresponding to 10 time calibration time points are obtained.
S2: and taking an AIS target, judging the radar target set, and screening out the radar target set which accords with the degree of identity. Screening a target set which accords with the degree of identity, mainly judging the similarity between target tracks by using a multi-factor fuzzy judgment algorithm, establishing a fuzzy factor set and determining the weight of the fuzzy factor set.
In this embodiment, the multi-factor fuzzy judgment algorithm is only suitable for general target motion situations, but because the external environment is extremely complex, the algorithm performs optimization processing for some special situations: considering that the position, the course and the navigational speed of a radar target show irregular changes due to the error of equipment in a static state, the track identity degree is difficult to judge according to a fuzzy judgment algorithm. Therefore, before the multi-factor fuzzy judgment of the target relation, whether the target is static or not is judged, and if the average speed of the target is smaller than a smaller threshold value, the position average Euclidean distance mode is adopted instead of the multi-factor fuzzy judgment mode under the condition that the target is in the static state.
S21: firstly, an AIS target time-calibrated value is taken, the average speed value of the speed factors in 10 time-calibrated time points of the AIS target is calculated, if the average speed value is greater than a set threshold value, the AIS target is considered to be a moving target, and if not, the AIS target is considered to be a static target;
s22: and judging the acquaintance respectively according to the static or motion state of the AIS target, and dividing the AIS target into two branches.
When the target is a static target:
step 1: whether a plurality of targets exist around the AIS is judged according to the following judgment: in the last fusion calculation period, the number of the screened targets in the target set with the similarity is 0 (the initial calculation is 0); and determining the size of the distance threshold of the two targets according to the number of targets around the targets, wherein when the number of the targets is large, the distance threshold is appropriately reduced, and conversely, the distance threshold is appropriately increased.
Step 2: taking a radar target, calculating the mean Euclidean distance between the AIS target and the radar target, wherein the coordinate is (X)Longitude (G)、YLatitude) And if the average Euclidean distance is smaller than the distance threshold value, adding the radar target into a target set which accords with the degree of identity.
And step 3: repeating the step 2 until all the radar targets are traversed;
when the target is a moving target:
step 1: taking a radar target, calculating the average Euclidean distance between the AIS target and the radar target, wherein the coordinate is (X)Longitude (G)、YLatitude) And judging the average Euclidean distance, and if the average Euclidean distance is smaller than a distance threshold value, performing the next calculation.
Step 2: in order to optimize filtering and eliminate the unstable condition of the radar target, calculating the mean square deviation value of the course in 10 time calibration time points of the radar target, comparing the mean square deviation value with a threshold value, and when the mean square deviation value is larger than the threshold value, considering the course value of the radar to be effective, otherwise, considering the course value of the radar to be invalid. If the radar course is invalid, the course factor is not used to participate in the calculation, and the weighting weight values of other factors are correspondingly adjusted.
And step 3: considering the influence of the speed on the position change of the target, calculating the average value of the navigational speed of the radar target, if the average value is larger than a threshold value, properly amplifying the spread value of the position, and relaxing the judgment condition; if the average value is smaller than the threshold value, properly reducing the spread value of the position, and tightening the judgment condition;
and 4, step 4: and respectively calculating Cauchy membership function values of factors such as two target latitudes, longitudes, headings, navigational speeds and the like. The Cauchy-type distribution is a continuous probability distribution whose probability density function is as follows:
in the formula, xi (eta)k) As a fuzzy factor (latitude, longitude, heading)Or speed) of k time points, ηkRespectively the difference between the kth time point of two target factors (latitude, longitude, course or speed), lambdakThe spread is calculated for the cauchy membership function.
And 5: and carrying out weighted summation on the obtained two objective latitude and longitude, course, speed and other factors Cauchy membership function values to obtain the total membership, wherein the objective position (longitude and latitude) has the highest weight and the second highest speed, and the course weight is the lowest. If the heading factors are not used for calculation in the steps, the weights of the target position (longitude and latitude) and the navigation speed are proportionally recalculated, and then the weights are weighted and summed according to the new weights.
Step 6: and (4) judging a threshold value of the weighted sum result, and adding the radar target into a target set of which the AIS target meets the identification degree if the weighted sum result is larger than the threshold value.
And 7: repeating steps 1 to 6 until all radar targets are traversed.
The AIS ship size influence is considered in relation to the Euclidean distance calculation, algorithm optimization is carried out on the distance calculation, in order to improve fusion accuracy, the ship target size is used for supplementing the target position, and then target position factors are calculated, as shown in FIG. 3, the specific calculation algorithm is as follows:
A. b is the position of the radar target and the AIS target respectively, the AIS target is a rectangle with the length H and the width W, and the point C is the intersection point of the AB connecting line and the AIS target, so that the distance between the radar target and the AIS target is corrected into an AC line segment by the AB line segment, and the length of the AC line segment can be obtained by A, B two-point coordinates and the rectangle value with the length H and the width W in a plane geometric mode.
S3: screening out a target set which accords with the degree of identity, and performing gray level correlation analysis;
s31: and respectively carrying out dimension removing operation on the AIS target and the radar target position (longitude and latitude), the course and the navigational speed which are in line with the identification target set by using an average value method to obtain a dimension-removed numerical value. The average method is specifically as follows, assuming a target longitude (X)1，X2…X10) Then the ith longitude dimension value X is:
solving the latitude, the course and the navigational speed in the same way;
s32: calculating the gray level correlation values of the AIS target and the target set radar target, wherein in the calculation process, the time is taken as a multi-factor K in a gray level correlation model, and the multi-target is taken as an X judgment object to form a calculation matrix so as to obtain the correlation value of the target with the maximum gray level correlation;
gray correlation calculation formula, assuming that the sequence of the target's factors (longitude, latitude, speed, heading, respectively) is XiThe sequence of rows whose candidates match the factors of the identity target set (longitude, latitude, speed, heading, respectively) is Y (x (1), x (2), x (3) … x (n)iWhen the target and the candidate match with the identification target factor, i (1 to 10), the gray correlation value is obtained as follows:
γ is a target correlation value, ρ is a resolution coefficient representing the sensitivity of correlation between X and Y sequences, and is usually an appropriate value within the interval (O, 1).
After 10 moments of longitude, latitude, navigational speed and course factor are solved to obtain a grey correlation value, the arithmetic mean value of longitude, latitude, navigational speed and course is solved, and weighted summation is carried out;
s33: repeat step S32: traversing the target and the candidate object set target which accords with the degree of identity to obtain the gray level correlation value of the radar target;
s34: comparing the obtained gray level correlation values to obtain the maximum gray level correlation value, judging a threshold value, and if the threshold value is greater than the correlation threshold value, judging that the corresponding radar target is the same target as the AIS target;
s4: fusing target tracks: and after the radar target associated with the AIS is obtained, fusion calculation is carried out on the tracks of the two targets, and the position and the motion state of the fused target are obtained.
S41: and acquiring the AIS target and the radar target current state information.
S42: and judging that the motion state of the AIS target is a static state, judging that the navigational speed of the AIS target is less than a threshold value, and judging that the AIS target is in the static state, otherwise, judging that the AIS target is in the motion state.
S43: if the status information is in a static state, the AIS is set to 1, namely, the status information of the AIS is used as the fusion target status information. And if the target is in the motion state, the position information of the fusion target is subjected to weighted average by using the AIS target and the radar target to obtain the position of the fused target. And solving the sum of two target speed vectors by using a vector operation mode, calculating the resultant speed of the target, taking a resultant speed vector value 1/2 as a fusion target speed value, and taking a resultant speed vector direction value as a fusion target course value to obtain the speed and the course of the fusion target so as to obtain a target track fusion state.
Example 2
The embodiment provides a boats and ships track fuses system includes: the system comprises a time calibration module, a track similarity judgment module, a track association module and a target fusion module;
in this embodiment, the time calibration module is configured to perform time calibration processing on the AIS target, unify the data information detected by each data source to the same reference time, and obtain the data information of each data source to the target at the same time;
in this embodiment, the trajectory similarity determination module is configured to determine similarity between target trajectories by using a multi-factor fuzzy determination algorithm, establish a fuzzy factor set, determine weights of the fuzzy factor set, and screen out a radar target set that meets the degree of identity;
in this embodiment, the track association module is configured to perform track association by using a cauchy membership function, calculate a gray level association value of a radar target in a set of AIS targets and radar targets that meet an identity, perform gray level association analysis, and determine that the corresponding radar target is the same target as the AIS target when the gray level association value is greater than a preset association threshold;
in this embodiment, the target fusion module is configured to perform fusion calculation on two target tracks after obtaining the radar target associated with the AIS, so as to obtain a fused target position and a fused motion state.
Example 3
The present embodiment provides a storage medium, which may be a storage medium such as a ROM, a RAM, a magnetic disk, or an optical disk, and the storage medium stores one or more programs, and when the programs are executed by a processor, the ship track fusion method of embodiment 1 is implemented.
Example 4
The embodiment provides a computing device, which may be a desktop computer, a notebook computer, a smart phone, a PDA handheld terminal, a tablet computer, or other terminal devices with a display function, and the computing device includes a processor and a memory, where the memory stores one or more programs, and when the processor executes the programs stored in the memory, the ship track fusion method in embodiment 1 is implemented.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. A ship track fusion method is characterized by comprising the following steps:
respectively carrying out time calibration processing on the AIS and the radar target, unifying the data information detected by each data source to the same reference time, and obtaining the data information of each data source to the target at the same time;
judging the similarity between target tracks by adopting a multi-factor fuzzy judgment algorithm, establishing a fuzzy factor set, determining the weight of the fuzzy factor set, and screening out a radar target set which accords with the similarity;
performing track association by adopting a Cauchy membership function;
calculating gray level correlation values of the AIS target and the radar targets in the radar target set which accord with the degree of identity, performing gray level correlation analysis, and judging that the corresponding radar target is the same target as the AIS target when the gray level correlation values are larger than a preset correlation threshold value;
and after the radar target associated with the AIS is obtained, fusion calculation is carried out on the tracks of the two targets, and the position and the motion state of the fused target are obtained.
2. The ship track fusion method according to claim 1, wherein the AIS and the radar target are respectively subjected to time calibration processing, and the specific steps include:
respectively finding out the sampling time T of the track point from the target track record according to the time calibration time point T1And T2So that T is1And T2Satisfy T1<T<T2Calculating the corresponding position, course and navigational speed values of the target at the time calibration moment by adopting a linear interpolation method;
if the target track record has no sampling time T1And T2So that T is1And T2Satisfy T1<T<T2Then, the sampling time T of the track point is found1So that T is1The absolute value of T is minimum, the position of the target at the synchronous moment is calculated through a uniform linear motion model to obtain a corresponding target position factor value, and the course and the navigational speed use T1Target course and speed values for the trajectory points.
3. The ship track fusion method according to claim 1, wherein before the step of judging the similarity between target tracks by using a multi-factor fuzzy judgment algorithm, the method further comprises a step of judging a target motion state, and specifically comprises:
selecting a value after AIS target time calibration, calculating the average speed value of the speed factors of the AIS target in a plurality of sampling time calibration time points, if the average speed value is greater than a preset speed threshold value, judging the AIS target to be a moving target, otherwise, judging the AIS target to be a static target.
4. The ship track fusion method according to claim 3, wherein the judgment of the degree of acquaintance is performed according to the stationary or moving state of the AIS target, and the specific steps include:
when the target is a static target:
judging whether a plurality of targets exist around the AIS, and adjusting a preset distance threshold according to the number of targets of the target set which accord with the degree of identity;
selecting a radar target, calculating the average Euclidean distance between the AIS target and the radar target, adding the radar target into a target set meeting the degree of identity if the average Euclidean distance is smaller than a preset distance threshold, and circularly traversing all the radar targets;
when the target is a moving target:
carrying out multi-factor fuzzy judgment and calculating the average Euclidean distance between the AIS target and the radar target, and if the average Euclidean distance is smaller than a preset distance threshold value, calculating the mean square difference value of the course of the radar target, the average speed of the radar target and the Cauchy membership function value;
judging whether the radar course value is effective or not according to the mean square difference value of the radar target course, adjusting the spread value of the position according to the average speed value of the radar target, carrying out weighted summation on the Cauchy membership function values of the two objective factors to obtain the total membership, carrying out threshold judgment on the weighted summation result, adding the radar target into a target set of AIS targets which accord with the identity when the total membership is greater than a preset distance threshold, and circularly traversing all the radar targets.
5. The ship track fusion method according to claim 4, further comprising Euclidean distance calculation optimization steps, specifically comprising:
supplementing the target position by using the size of the ship target, and calculating a target position factor;
and setting the points A and B as the positions of the radar target and the AIS target respectively, setting the point C as the intersection point of the AB connecting line and the AIS target, and correcting the distance between the radar target and the AIS target into an AC line segment from an AB line segment.
6. The ship track fusion method according to claim 1, wherein the calculating of the gray level correlation values of the AIS target and the radar targets in the radar target set conforming to the degree of identity and the performing of the gray level correlation analysis comprise the following specific steps:
respectively carrying out dimension removing operation on the AIS target and the factor values of the position, the course and the speed of the radar target which accords with the mutual identification target set by using an average value method to obtain a dimension-removed numerical value;
calculating the gray level correlation values of the AIS target and the target concentrated radar target, taking the time as a plurality of factors in a gray level correlation model during calculation, taking a plurality of targets as judgment objects to form a calculation matrix, and calculating to obtain the correlation values of longitude, latitude, navigational speed and course at each time;
solving the arithmetic mean value of the time correlation values of longitude, latitude, navigational speed and heading, and carrying out weighted summation;
traversing the targets and the candidate coincidence degree target set targets, obtaining the weighted sum of the gray level correlation values of all radar targets, comparing to obtain the maximum correlation value, carrying out threshold judgment on the maximum correlation value, and judging that the corresponding target and the AIS target are the same target if the maximum correlation value is greater than a preset correlation threshold.
7. The ship track fusion method according to claim 1, wherein after the radar target associated with the AIS is obtained, the fusion calculation is performed on the tracks of the two targets, and the method specifically comprises the following steps:
acquiring the current state information of the AIS target and the radar target, and judging as a static state when the navigational speed of the AIS target is less than a threshold value, or judging as a moving state;
in a static state, the state information of the AIS is used as the state information of the fusion target, and in a moving state, the position information of the fusion target is obtained by a method of carrying out weighted average on the positions of the AIS target and the radar target;
and solving the sum of two target speed vectors by using a vector operation mode, calculating the resultant speed of the target, taking a resultant speed vector value 1/2 as a fusion target speed value, and taking a resultant speed vector direction value as a fusion target course value to obtain the speed and the course of the fusion target so as to obtain a target track fusion state.
8. A ship track fusion system, comprising: the system comprises a time calibration module, a track similarity judgment module, a track association module and a target fusion module;
the time calibration module is used for carrying out time calibration processing on the AIS target, unifying the data information detected by each data source to the same reference time and obtaining the data information of each data source to the target at the same time;
the track similarity judging module is used for judging the similarity between target tracks by adopting a multi-factor fuzzy judging algorithm, establishing a fuzzy factor set, determining the weight of the fuzzy factor set and screening out a radar target set conforming to the similarity;
the flight path correlation module is used for performing flight path correlation by adopting a Cauchy membership function, calculating a gray level correlation value of the AIS target and the radar target in the radar target set which accords with the degree of identity, performing gray level correlation analysis, and judging that the corresponding radar target is the same target as the AIS target when the gray level correlation value is greater than a preset correlation threshold;
and the target fusion module is used for performing fusion calculation on the two target tracks after the radar target associated with the AIS is obtained, so as to obtain the fused target position and motion state.
9. A computer-readable storage medium storing a program, wherein the program when executed by a processor implements the ship track fusion method according to any one of claims 1 to 7.
10. A computing device comprising a processor and a memory for storing a program executable by the processor, wherein the processor, when executing the program stored in the memory, implements a method for vessel track fusion according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111319617.6A CN114063056A (en) | 2021-11-09 | 2021-11-09 | Ship track fusion method, system, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111319617.6A CN114063056A (en) | 2021-11-09 | 2021-11-09 | Ship track fusion method, system, medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114063056A true CN114063056A (en) | 2022-02-18 |
Family
ID=80274389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111319617.6A Pending CN114063056A (en) | 2021-11-09 | 2021-11-09 | Ship track fusion method, system, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114063056A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115080903A (en) * | 2022-06-01 | 2022-09-20 | 中国船舶重工集团公司第七0七研究所九江分部 | Offshore multi-target multi-modal matching fusion method based on intelligent optimization algorithm |
| CN115454676A (en) * | 2022-09-26 | 2022-12-09 | 中华人民共和国广东海事局 | Position information fusion method, device, equipment, storage medium and program product |
| CN115525640A (en) * | 2022-11-25 | 2022-12-27 | 三亚海兰寰宇海洋信息科技有限公司 | Target object trajectory processing method, device and equipment |
| CN115577324A (en) * | 2022-12-08 | 2023-01-06 | 亿海蓝（北京）数据技术股份公司 | Data fusion method and system for radar and ship automatic identification system and storage medium |
-
2021
- 2021-11-09 CN CN202111319617.6A patent/CN114063056A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115080903A (en) * | 2022-06-01 | 2022-09-20 | 中国船舶重工集团公司第七0七研究所九江分部 | Offshore multi-target multi-modal matching fusion method based on intelligent optimization algorithm |
| CN115454676A (en) * | 2022-09-26 | 2022-12-09 | 中华人民共和国广东海事局 | Position information fusion method, device, equipment, storage medium and program product |
| CN115454676B (en) * | 2022-09-26 | 2023-12-19 | 中华人民共和国广东海事局 | Position information fusion method, device, equipment, storage medium and program product |
| CN115525640A (en) * | 2022-11-25 | 2022-12-27 | 三亚海兰寰宇海洋信息科技有限公司 | Target object trajectory processing method, device and equipment |
| CN115577324A (en) * | 2022-12-08 | 2023-01-06 | 亿海蓝（北京）数据技术股份公司 | Data fusion method and system for radar and ship automatic identification system and storage medium |
| CN115577324B (en) * | 2022-12-08 | 2023-02-28 | 亿海蓝（北京）数据技术股份公司 | Data fusion method and system for radar and ship automatic identification system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114063056A (en) | Ship track fusion method, system, medium and equipment | |
| CN110232350B (en) | Real-time water surface multi-moving-object detection and tracking method based on online learning | |
| CN107194408B (en) | Target tracking method of mixed block sparse cooperation model | |
| Azami et al. | Classification of GPS satellites using improved back propagation training algorithms | |
| CN110927712B (en) | Tracking method and device | |
| CN105374049B (en) | Multi-corner point tracking method and device based on sparse optical flow method | |
| CN110501671A (en) | A kind of method for tracking target and device based on measurement distribution | |
| US11928813B2 (en) | Method and system for detecting change to structure by using drone | |
| CN113419258B (en) | Positioning abnormality detection method and related equipment thereof | |
| CN114090718B (en) | Bi-LSTM prediction and fuzzy analysis based interrupted track correlation method | |
| CN108549062B (en) | System platform for sea surface search radar and multi-model target tracking method | |
| CN116403139A (en) | Visual tracking and positioning method based on target detection | |
| CN111178261A (en) | Face detection acceleration method based on video coding technology | |
| CN113971688B (en) | Anchor-free multi-target tracking method for enhancing ID re-identification | |
| CN112362042B (en) | Track correlation judgment method based on intelligent ship multi-sensing equipment | |
| Tan | Tclnet: Learning to locate typhoon center using deep neural network | |
| CN116403007B (en) | Remote sensing image change detection method based on target vector | |
| CN117423031A (en) | Target detection and tracking system based on improved YOLOv7 and deep SORT | |
| CN113192110A (en) | Multi-target tracking method, device, equipment and storage medium | |
| CN115220002B (en) | Multi-target data association tracking method and related device for fixed single station | |
| CN111640134B (en) | Face tracking method and device, computer equipment and storage device thereof | |
| CN111242980B (en) | Point target-oriented infrared focal plane blind pixel dynamic detection method | |
| CN114595770A (en) | Long time sequence prediction method for ship track | |
| Peruničić et al. | Vision-based Vehicle Speed Estimation Using the YOLO Detector and RNN | |
| CN113281736B (en) | Radar maneuvering intersection target tracking method based on multi-hypothesis singer model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |