CN107063259A - A kind of Data Association and electronic equipment - Google Patents
A kind of Data Association and electronic equipment Download PDFInfo
- Publication number
- CN107063259A CN107063259A CN201710135102.8A CN201710135102A CN107063259A CN 107063259 A CN107063259 A CN 107063259A CN 201710135102 A CN201710135102 A CN 201710135102A CN 107063259 A CN107063259 A CN 107063259A
- Authority
- CN
- China
- Prior art keywords
- track
- flight
- data
- historical
- determining whether
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 claims description 77
- 238000005070 sampling Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000009825 accumulation Methods 0.000 claims description 6
- 230000001953 sensory effect Effects 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims 1
- 241001269238 Data Species 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 37
- 230000000694 effects Effects 0.000 description 13
- 239000011159 matrix material Substances 0.000 description 10
- 239000011295 pitch Substances 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000000737 periodic effect Effects 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- CLOMYZFHNHFSIQ-UHFFFAOYSA-N clonixin Chemical compound CC1=C(Cl)C=CC=C1NC1=NC=CC=C1C(O)=O CLOMYZFHNHFSIQ-UHFFFAOYSA-N 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a kind of Data Association and electronic equipment, including：The N group sensing datas that the M sensor collection being arranged on the flight equipment obtains the flight track for being used to characterize the flight equipment are obtained, M is the integer more than or equal to 2, and N is the integer more than zero；The N groups sensing data is divided into shared data and identity data, wherein, the shared data are the data that the M sensor can be gathered, and the identity data is for the data for the type for characterizing the M sensor；The shared data and the identity data are utilized respectively, the flight track is associated with the flight path in flight path storehouse, wherein, the flight path storehouse includes at least one flight track of at least one flight equipment., there is the technical problem under-utilized to identity information for solving track association of the prior art in the technical scheme provided by the present invention.
Description
Technical Field
The present invention relates to the field of electronic technologies, and in particular, to a track association method and an electronic device.
Background
With the rapid development of computers, data fusion has been rapidly developed and widely applied to military and civil fields such as target tracking, situation assessment and the like. In recent years, in order to solve the problem of combined explosion of data association, various national scholars propose a tracking method based on a random finite set, and get great attention of the tracking world, but because the tracking method is difficult to implement in engineering at present, a tracking algorithm based on track association is still the focus of current research.
The correctness of the effect of the track association method is the premise and guarantee of the correctness of data fusion. The main methods comprise weighted statistical distance test method, modified weighted statistical distance test method, nearest neighbor method, classical distribution method, likelihood ratio detection method, maximum likelihood and other algorithms, and the algorithms are established based on radar data, and the types of data collected by the radar are single, so that the algorithms are mainly associated by using common information and cannot be associated by using identity information of multi-source information.
Therefore, the technical problem of insufficient utilization of identity information exists in track association in the prior art.
Disclosure of Invention
The embodiment of the invention provides a track association method and electronic equipment, which are used for solving the technical problem of insufficient utilization of identity information in track association in the prior art, realizing the hierarchical implementation of the track association by utilizing the identity information and common information of multi-source information and achieving the technical effect of improving the utilization rate of the identity information.
The embodiment of the invention provides a track association method, which is applied to electronic equipment, wherein the electronic equipment can be communicated with flight equipment, and the method comprises the following steps:
acquiring M sensors arranged on the flight equipment, acquiring N groups of sensing data for representing the flight path of the flight equipment, wherein M is an integer greater than or equal to 2, and N is an integer greater than zero;
dividing the N groups of sensing data into common data and identity data, wherein the common data is data which can be collected by the M sensors, and the identity data is data used for representing the types of the M sensors;
and respectively associating the flight path with a path in a path library by using the common data and the identity data, wherein the path library comprises at least one flight path of at least one flight device.
Optionally, the dividing the N groups of sensing data into common data and identity data includes:
acquiring a time tag of each group of sensing data in the N groups of sensing data, and acquiring N time tags in total;
determining whether the N groups of sensing data are continuous sensing data based on the N time tags;
and if the N groups of sensing data are continuous sensing data, dividing the N groups of sensing data into common data and identity data.
Optionally, the associating the flight path with a path in a path library by respectively using the common data and the identity data includes:
determining whether a first historical track matched with the flight track exists in the track library based on the identity data;
and if not, determining whether the first historical track matched with the flight track exists in the track library or not based on the common data.
Optionally, the determining whether there is a first historical track matching the flight track in the track library based on the identity data includes:
acquiring a first time label corresponding to the identity data and a second time label corresponding to the track in the track library;
determining whether the first time tag is earlier than a latest time tag in time in the second time tags;
if not, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data.
Optionally, if the first historical track matching the flight track does not exist in the track library, determining whether the first historical track matching the flight track exists in the track library based on the common data includes:
acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library;
determining a candidate historical track from the track library based on the altitude difference, the azimuth difference and the distance difference, wherein the altitude difference between the candidate historical track and the flight track is smaller than an altitude wave gate, the azimuth difference between the candidate historical track and the flight track is smaller than an azimuth wave gate, and the distance difference between the candidate historical track and the flight track is smaller than a distance wave gate;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks.
Optionally, the obtaining of the height difference, the azimuth difference, and the distance difference between the flight path and each flight path in the flight path library includes:
determining whether the flight path is associated with a second historical path in the path library at a time prior to a current time;
if so, determining whether the association between the flight path and the second historical path is valid;
and if the flight path is invalid, acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library.
Optionally, the determining whether the first historical track matching the flight track exists in the candidate historical tracks includes:
extrapolating the flight tracks and each flight track to the current moment by using a least square method;
calculating the vector difference between the flight tracks and each flight track, and obtaining a module of the at least one vector difference;
acquiring a first total error mean value of the flight tracks and a second total error mean value of each flight track to obtain at least one second total error mean value;
obtaining a statistical correlation distance between the flight path and each flight path based on the model of the at least one vector difference, the first total error mean value and the at least one second total error mean value;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks based on the statistical correlation distance.
Optionally, after determining whether the N sets of sensing data are consecutive sensing data based on the N time tags, the method further includes:
if the N groups of sensing data are discontinuous sensing data, determining whether the N groups of sensing data contain identity data;
if yes, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data;
if not, determining whether the first historical flight path matched with the flight path exists in the flight path library or not based on the N groups of sensing data.
Optionally, if not, determining whether the first historical track matched with the flight track exists in the track library based on the N sets of sensing data includes:
determining whether the N sets of sensing data are sparse;
and if the sparsity exists, determining whether the first historical track matched with the flight track exists in the track library or not based on the N groups of sensing data.
Optionally, the determining whether the N groups of sensing data have sparsity includes:
determining whether the time difference of the time labels of two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset time difference; or
Determining whether the difference value of the space angles in two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset space angle difference; or
And determining whether the dimensionalities of two adjacent groups of sensing data in the N groups of data are consistent or whether the dimensionalities after coordinate conversion are consistent.
Optionally, after determining whether the first historical track matching the flight track exists in the track library based on the common data if the first historical track matching the flight track does not exist, the method further includes:
determining whether an association conflict exists for the flight path; wherein the association conflict is that the flight device associates different historical tracks at different time periods;
and if the association conflict exists, adjusting the association result of the flight path to obtain a new association result.
Optionally, if there is a correlation conflict, adjusting the correlation result of the flight path to obtain a new correlation result, including:
determining whether the current track number of the first historical track is the same as the historical track number of a third historical track associated at a time between the current times;
if the difference is positive, acquiring the association times of the flight path and the third history path;
and if the association times are more than 1, adjusting the association track of the flight track from the first history track to the third history track.
Optionally, if there is a correlation conflict, adjusting the correlation result of the flight path to obtain a new correlation result, including:
determining the period of data acquisition of the M sensors and the sampling interval between the period of data acquisition of the M sensors and the sampling period corresponding to the first historical track;
determining whether the first historical track is successfully associated in the period of data acquisition of the M sensors;
if the association is successful, determining whether the association quality sequence of the first historical track in the sampling interval is an increasing sequence; the correlation quality sequence is accumulation of correct correlation results in the correlation results of the first historical flight path;
and if the sequence is an increasing sequence, associating the flight path with the first historical path.
On the other hand, an embodiment of the present invention further provides an electronic device, which can communicate with a flight device, and includes:
the first acquisition unit is used for acquiring M sensors arranged on the flight equipment, acquiring N groups of sensing data used for representing the flight path of the flight equipment, wherein M is an integer larger than or equal to 2, and N is an integer larger than zero;
the first dividing unit is used for dividing the N groups of sensing data into common data and identity data, wherein the common data are data which can be collected by the M sensors, and the identity data are data used for representing the types of the M sensors;
and the first association unit is used for associating the flight path with the flight path in a path library by respectively utilizing the common data and the identity data, wherein the path library comprises at least one flight path of at least one flight device.
Optionally, the first dividing unit is configured to:
acquiring a time tag of each group of sensing data in the N groups of sensing data, and acquiring N time tags in total;
determining whether the N groups of sensing data are continuous sensing data based on the N time tags;
and if the N groups of sensing data are continuous sensing data, dividing the N groups of sensing data into common data and identity data.
Optionally, the first associating unit is configured to:
determining whether a first historical track matched with the flight track exists in the track library based on the identity data;
and if not, determining whether the first historical track matched with the flight track exists in the track library or not based on the common data.
Optionally, the first associating unit is configured to:
acquiring a first time label corresponding to the identity data and a second time label corresponding to the track in the track library;
determining whether the first time tag is earlier than a latest time tag in time in the second time tags;
if not, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data.
Optionally, the first associating unit is configured to:
acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library;
determining a candidate historical track from the track library based on the altitude difference, the azimuth difference and the distance difference, wherein the altitude difference between the candidate historical track and the flight track is smaller than an altitude wave gate, the azimuth difference between the candidate historical track and the flight track is smaller than an azimuth wave gate, and the distance difference between the candidate historical track and the flight track is smaller than a distance wave gate;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks.
Optionally, the first associating unit is configured to:
determining whether the flight path is associated with a second historical path in the path library at a time prior to a current time;
if so, determining whether the association between the flight path and the second historical path is valid;
and if the flight path is invalid, acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library.
Optionally, the first associating unit is configured to:
extrapolating the flight tracks and each flight track to the current moment by using a least square method;
calculating the vector difference between the flight tracks and each flight track, and obtaining a module of the at least one vector difference;
acquiring a first total error mean value of the flight tracks and a second total error mean value of each flight track to obtain at least one second total error mean value;
obtaining a statistical correlation distance between the flight path and each flight path based on the model of the at least one vector difference, the first total error mean value and the at least one second total error mean value;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks based on the statistical correlation distance.
Optionally, after determining whether the N sets of sensing data are continuous sensing data based on the N time tags, the electronic device further includes:
a first determining unit, configured to determine whether the N groups of sensing data include identity data if the N groups of sensing data are discontinuous sensing data;
a second determining unit, configured to determine, based on the identity data, whether a first historical track matching the flight track exists in the track library if the first historical track exists;
and if not, determining whether the first historical flight path matched with the flight path exists in the flight path library or not based on the N groups of sensing data.
Optionally, the third determining unit is configured to:
determining whether the N sets of sensing data are sparse;
and if the sparsity exists, determining whether the first historical track matched with the flight track exists in the track library or not based on the N groups of sensing data.
Optionally, the third determining unit is configured to:
determining whether the time difference of the time labels of two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset time difference; or
Determining whether the difference value of the space angles in two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset space angle difference; or
And determining whether the dimensionalities of two adjacent groups of sensing data in the N groups of data are consistent or whether the dimensionalities after coordinate conversion are consistent.
Optionally, after determining whether the first historical track matching the flight track exists in the track library based on the common data if the first historical track matching the flight track does not exist, the electronic device further includes:
a fourth determining unit, configured to determine whether there is an association conflict in the flight path; wherein the association conflict is that the flight device associates different historical tracks at different time periods;
and the first adjusting unit is used for adjusting the correlation result of the flight path to acquire a new correlation result if the correlation conflict exists.
Optionally, the first adjusting unit is configured to:
determining whether the current track number of the first historical track is the same as the historical track number of a third historical track associated at a time between the current times;
if the difference is positive, acquiring the association times of the flight path and the third history path;
and if the association times are more than 1, adjusting the association track of the flight track from the first history track to the third history track.
Optionally, the first adjusting unit is configured to:
determining the period of data acquisition of the M sensors and the sampling interval between the period of data acquisition of the M sensors and the sampling period corresponding to the first historical track;
determining whether the first historical track is successfully associated in the period of data acquisition of the M sensors;
if the association is successful, determining whether the association quality sequence of the first historical track in the sampling interval is an increasing sequence; the correlation quality sequence is accumulation of correct correlation results in the correlation results of the first historical flight path;
and if the sequence is an increasing sequence, associating the flight path with the first historical path.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
according to the technical scheme, M sensors arranged on the flight equipment are acquired to acquire N groups of sensing data used for representing the flight path of the flight equipment, wherein M is an integer larger than or equal to 2, and N is an integer larger than zero; dividing the N groups of sensing data into common data and identity data, wherein the common data is data which can be collected by the M sensors, and the identity data is data used for representing the types of the M sensors; and respectively associating the flight path with a path in a path library by using the common data and the identity data, wherein the path library comprises at least one flight path technical scheme of at least one flight device. The method comprises the steps of classifying acquired sensing data, dividing the sensing data into common data and identity data, and then performing track association by respectively using the common data and the identity data, so that the technical problem that the identity information is not fully utilized in the track association in the prior art is effectively solved, and further the technical effects of realizing the track association by using the identity information and the common information of multi-source information in a hierarchical manner and improving the utilization rate of the identity information are achieved.
Secondly, according to the technical scheme of the embodiment of the invention, if the N groups of sensing data are discontinuous sensing data, whether the N groups of sensing data contain identity data is determined; if yes, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data; and if not, determining whether the first historical track matched with the flight track exists in the track library or not based on the N groups of sensing data, namely processing discrete point tracks by using identity data and common data under the condition that the sensing data are determined to be discontinuous sensing data, and further achieving the technical effect of improving the correlation accuracy.
Thirdly, according to the technical scheme in the embodiment of the invention, whether the flight path has association conflict or not is determined; wherein the association conflict is that the flight device associates different historical tracks at different time periods; and if the association conflict exists, adjusting the association result of the flight path to obtain a new association result, namely determining whether the association has the conflict or not after the flight path association is completed by utilizing the common data and the identity data, and if the association has the conflict, adjusting the associated object to further achieve the technical effect of improving the association accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments will be briefly introduced, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 is a flowchart of a specific implementation of a track association method according to an embodiment of the present invention;
fig. 2 is a flowchart of a specific implementation of performing track association by using common data in a track association method according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating processing of discontinuous sensing data in a track association method according to an embodiment of the present invention;
FIG. 4 is a flowchart of a first implementation of association conflict resolution provided by an embodiment of the present invention;
FIG. 5 is a flowchart of a second implementation of association conflict resolution provided by an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a track association method and electronic equipment, which are used for solving the technical problem of insufficient utilization of identity information in track association in the prior art, realizing the hierarchical implementation of the track association by utilizing the identity information and common information of multi-source information and achieving the technical effect of improving the identity utilization rate.
In order to solve the technical problems, the technical scheme in the embodiment of the invention has the following general idea:
acquiring M sensors arranged on the flight equipment, acquiring N groups of sensing data for representing the flight path of the flight equipment, wherein M is an integer greater than or equal to 2, and N is an integer greater than zero;
dividing the N groups of sensing data into common data and identity data, wherein the common data is data which can be collected by the M sensors, and the identity data is data used for representing the types of the M sensors;
and respectively associating the flight path with a path in a path library by using the common data and the identity data, wherein the path library comprises at least one flight path of at least one flight device.
According to the technical scheme, N groups of sensing data used for representing the flight path of the flight equipment are acquired by acquiring M sensors arranged on the flight equipment, wherein M is an integer larger than or equal to 2, and N is an integer larger than zero; dividing the N groups of sensing data into common data and identity data, wherein the common data is data which can be collected by the M sensors, and the identity data is data used for representing the types of the M sensors; and respectively associating the flight path with a path in a path library by using the common data and the identity data, wherein the path library comprises at least one flight path technical scheme of at least one flight device. The method comprises the steps of classifying acquired sensing data, dividing the sensing data into common data and identity data, and then performing track association by respectively using the common data and the identity data, so that the technical problem that the identity information is not fully utilized in the track association in the prior art is effectively solved, and further the technical effects of realizing the track association by using the identity information and the common information of multi-source information in a hierarchical manner and improving the utilization rate of the identity information are achieved.
In order to better understand the technical solutions, the technical solutions of the present invention are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present invention are detailed descriptions of the technical solutions of the present invention, and are not limitations of the technical solutions of the present invention, and the technical features in the embodiments and examples of the present invention may be combined with each other without conflict.
First aspect
Referring to fig. 1, a method for associating a flight path provided in an embodiment of the present invention is applied to an electronic device, where the electronic device can communicate with a flight device, and the method includes:
s101: acquiring M sensors arranged on the flight equipment, acquiring N groups of sensing data for representing the flight path of the flight equipment, wherein M is an integer greater than or equal to 2, and N is an integer greater than zero;
s102: dividing the N groups of sensing data into common data and identity data, wherein the common data is data which can be collected by the M sensors, and the identity data is data used for representing the types of the M sensors;
s103: and respectively associating the flight path with a path in a path library by using the common data and the identity data, wherein the path library comprises at least one flight path of at least one flight device.
In the embodiment of the present invention, step S101 is first executed: acquiring M sensors arranged on the flight equipment, and acquiring N groups of sensing data for representing the flight path of the flight equipment, wherein M is an integer larger than or equal to 2, and N is an integer larger than zero.
In the embodiment of the present invention, the electronic device may be a device independent from the flight device or a device integrated in the flight device, and is not particularly limited herein. The flying device may be specifically an airplane, a missile or other tracking target, which is not illustrated here.
In the embodiment of the present invention, the flight device may be provided with a plurality of sensors of different types, different working systems, and different data rates, such as ADS-B, data chain, IRST, ESM, and the like, and after the flight device takes off, the electronic device acquires heterogeneous asynchronous data acquired by various sensors on the flight device, such as: location data, static data, identity data, etc., or other sensory data, to name but a few. In the specific implementation process, theIs shown at tiData collected by the sensors at all times.
After acquiring N sets of sensing data, step S102 is executed: and dividing the N groups of sensing data into common data and identity data, wherein the common data is data which can be collected by the M sensors, and the identity data is data used for representing the types of the M sensors.
In the embodiment of the present invention, as to the specific implementation process of step S102, the following steps are specifically included:
acquiring a time tag of each group of sensing data in the N groups of sensing data, and acquiring N time tags in total;
determining whether the N groups of sensing data are continuous sensing data based on the N time tags;
and if the N groups of sensing data are continuous sensing data, dividing the N groups of sensing data into common data and identity data.
In the embodiment of the present invention, when the tracking target is in different states, for example: in the stealth state or the visible state, the sensing data acquired by the sensor may be continuous or discontinuous, and therefore, in the embodiment of the present invention, in order to improve the accuracy of association, different processing flows are respectively adopted for the continuous data and the discontinuous data, and therefore, when acquiring N sets of sensing data, it is first determined whether the N sets of sensing data are continuous data.
In a specific implementation process, time tags corresponding to N groups of sensing data, that is, corresponding times when the N groups of sensing data are acquired, are first obtained, as shown in table 1 below.
TABLE 1
| Collected data numbering | Time tag |
| 1 | 2016.12.5.16:02 |
| 2 | 2016.12.5.16:03 |
| 3 | 2016.12.5.16:05 |
| … | … |
| N | 2016.12.5.17:01 |
After the time tags corresponding to the N groups of sensing data are obtained, whether the time interval between the time tags corresponding to the two adjacent groups of sensing data exceeds a preset time interval or not is determined, and if the time interval exceeds the preset time interval, the N groups of sensing data are determined to be discrete data.
In the embodiment of the present invention, the preset time interval may be specifically 1 hour, 2 hours, 3 hours, or other preset time intervals, and one of ordinary skill in the art may set the preset time interval according to actual needs, which is not specifically limited in the embodiment of the present invention.
In a specific implementation process, a preset time interval is 1 hour as an example, N groups of sensing data are time tags of the data in table one as an example, a time interval between a first group of sensing data and a second group of sensing data is 2 minutes and is smaller than the preset time interval, a time interval between the second group of sensing data and a third group of sensing data is 2 minutes and is smaller than the preset time interval, so that time intervals between every two adjacent groups of sensing data are sequentially calculated, and if the time intervals are smaller than the preset time interval, the N groups of sensing data are determined to be continuous sensing data.
In the embodiment of the present invention, when it is determined that N groups of sensing data are continuous sensing data, the N groups of sensing data are divided into common data and identity data according to characteristics of the sensing data, where the common data is data that each sensor can acquire, for example: information such as information source number, track number, longitude, latitude, altitude, navigation speed, course, distance and azimuth of track point; identity data is in particular data for characterizing the identity of a sensor, such as: the 24-bit address code of the ADS-B established track, the batch number of the data chain established track, the ship call number of the AIS established track, and the like are not illustrated.
In the embodiment of the present invention, after classifying the N groups of received sensing data, the classified data is used to perform track association, that is, step S103 is executed: and respectively associating the flight path with a path in a path library by using the common data and the identity data, wherein the path library comprises at least one flight path of at least one flight device.
In the embodiment of the present invention, as to the specific implementation process of step S103, the following steps are specifically included:
the first step is as follows: determining whether a first historical track matched with the flight track exists in the track library based on the identity data;
the second step is as follows: and if not, determining whether the first historical track matched with the flight track exists in the track library or not based on the common data.
In the embodiment of the present invention, as to the specific implementation process of the first step, the following steps are specifically included:
acquiring a first time label corresponding to the identity data and a second time label corresponding to the track in the track library;
determining whether the first time tag is earlier than a latest time tag in time in the second time tags;
if not, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data.
In the embodiment of the invention, the track library also becomes a historical track library, namely, under the same scene, the set of all target tracks is formed, wherein each track is composed of a track number, common data and identity data, and under the condition that all the target tracks are continuous, the track library has the characteristics that the track number is unique, track information is updated along with the operation of the scene, and the track is composed of the latest multi-period correlation results.
In the specific implementation process, firstly, time tags corresponding to the identity data are obtained, the track in the track library takes the track with the track number of 1 and 2 as an example, and the corresponding time tags are respectively: 2016.12.5.15:50, 2016.12.5.15:53, wherein the latest time tag of the time tags corresponding to the two tracks is 2016.12.5.15:53, and then determining whether the time tag corresponding to the identity information is earlier than the latest time tag 2016.12.5.15:53, if: the time label corresponding to the identity data is 2016.12.5.15:35, and if the time label is earlier than the latest time label, the identity data is ignored, i.e. no track association is made with the identity data.
And if the time tag corresponding to the identity data is later than the latest time tag, matching the identity data with the identity data corresponding to the flight path in the flight path library, specifically, determining that a first historical flight path matched with the flight path exists in the flight path library if the identity data acquired by the sensor is a 24-bit address code and the flight path with the 24-bit address code exists in the flight path library, and sequentially determining the storage positions of the flight path in the flight path library so as to update the subsequent processing result at the position.
In the embodiment of the present invention, as to the specific implementation process of the second step, the following steps are specifically included:
acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library;
determining a candidate historical track from the track library based on the altitude difference, the azimuth difference and the distance difference, wherein the altitude difference between the candidate historical track and the flight track is smaller than an altitude wave gate, the azimuth difference between the candidate historical track and the flight track is smaller than an azimuth wave gate, and the distance difference between the candidate historical track and the flight track is smaller than a distance wave gate;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks.
In the embodiment of the invention, for the steps: the specific implementation process of obtaining the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library comprises the following steps:
determining whether the flight path is associated with a second historical path in the path library at a time prior to a current time;
if so, determining whether the association between the flight path and the second historical path is valid;
and if the flight path is invalid, acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library.
In an embodiment of the present invention, a time before the current time of flight path is first determined, such as: at current time instant 2016.12.5.15:50, it is determined whether the tracking target corresponding to the flight path is associated with a flight path in the flight path library before current time instant 2016.12.5.15:50, such as: the tracked target was associated with a second historical track in the track library before the current time 2016.12.5.15: 50. The track with track number 2 is associated.
In a specific implementation process, the second historical track takes a track with a track number of 2 as an example, and if the flight track is associated with the track number of 2, whether the association between the flight track and the track with the track number of 3 is valid is further determined. In the embodiment of the present invention, it is determined whether the association between the flight path and the second historical path is valid by determining whether the flight path has a batch break phenomenon, specifically, the following steps are performed: and (3) receiving the sensing data collected by the sensor between 10s and 20s, and receiving no sensing data collected by the sensor between 20s and 30s, even 50 s, determining that the flight path has a batch interruption phenomenon, wherein the situation indicates that the tracking target has great pulsation, namely the flight path needs to be correlated again, and if the batch interruption phenomenon does not occur, determining that the associated flight path of the flight path is the second historical flight path.
In the embodiment of the invention, if the association between the flight path and the second historical path is determined to be invalid, the height difference, the azimuth difference and the distance difference between the flight path and each path in the path library are obtained.
In the embodiment of the present invention, 2 groups of N groups of sensing data are taken as an example, and the acquired sensing data includes height, azimuth and distance, such as: at t1The data collected at a time is denoted as t1(3000 m, 45 degrees, 200 m); at t2The data collected at a time is denoted as t2(4000 meters, 45 degrees and 300 meters), the historical tracks in the track library are 2, the sensing data corresponding to each historical track is 2 groups as an example, specifically, the historical track with the track number of 1 is at t1Track point data corresponding to the moment (3500 m, 40 degrees, 180 m); at t2Track point data corresponding to the moment (3800 m, 45 degrees, 220 m); historical track t with track number 21Track point data (5100 m, 45 degrees and 300 m) corresponding to the time; at t2Corresponding track point data (3400 m, 45 degrees and 180 m) at the moment, and at the moment, calculating the flight track and the historical track at t1Time t and2height difference, azimuth difference and distance difference corresponding to the time.
In the embodiment of the present invention, after obtaining the altitude difference, the azimuth difference, and the distance difference between the flight path and the flight path in the flight path library, the candidate historical flight path is determined based on the altitude difference, the azimuth difference, and the distance difference, which are specifically as follows:
in the specific implementation process, the preset height difference is 2000 m, the preset azimuth difference is 15 degrees, and the preset distance difference is 50 m, for example. Flight path and historical path with path number 1 at t1Time t and2and the corresponding height difference at each moment is 500 meters and 800 meters, the height difference is smaller than the preset height difference, the azimuth difference is 5 degrees and 0 degrees, the azimuth difference is smaller than the preset azimuth difference, the distance difference is 20 meters and 20 meters, and the distance difference is smaller than the preset distance difference.
Flight path and historical path with path number 2 at t1Time t and2the height difference corresponding to the time is 2100 and 400, the azimuth difference is 0 and 0 degrees, the distance difference is 100 and 20 meters, wherein, at t1And the corresponding height difference at the moment is larger than the preset height difference of 2000 m, and under the condition, the historical track with the track number of 2 is determined to be the non-candidate historical track.
In the embodiment of the present invention, after determining the candidate historical track, the following steps are performed: determining whether the first historical track matched with the flight track exists in the candidate historical tracks.
In the embodiment of the present invention, referring to fig. 2, a specific implementation process for the above steps specifically includes the following steps:
s201: extrapolating the flight tracks and each flight track to the current moment by using a least square method;
s202: calculating the vector difference between the flight tracks and each flight track, and obtaining a module of the at least one vector difference;
s203: acquiring a first total error mean value of the flight tracks and a second total error mean value of each flight track to obtain at least one second total error mean value;
s204: obtaining a statistical correlation distance between the flight path and each flight path based on the model of the at least one vector difference, the first total error mean value and the at least one second total error mean value;
s205: determining whether the first historical track matched with the flight track exists in the candidate historical tracks based on the statistical correlation distance.
In the embodiment of the invention, by taking the track with the track number of 1 in the track library as an example, firstly, a difference vector between the flight track and the track with the track number of 1 is calculated, namely, a vector difference between data acquired at corresponding moments of the flight track and the track with the track number of 1 is calculated, and then, a model DeltaR of the difference vector is calculated.
Further, calculating the total error mean value of the flight path and the flight path with the path number of 1, specifically, the total error mean value TotalMeasError of the flight path is the position error plus the speed error of the flight path and the extrapolation time; and the total error mean value TotalTrackError of the flight track with the flight track number of 1 is the position error plus the speed error of the flight track with the flight track number of 1, and the extrapolated time is the time difference between the time label corresponding to the flight track and the time label corresponding to the flight track with the flight track number of 1.
After the average of the total errors of the flight path and the path with the path number 1 is determined, the statistical correlation distance between the flight path and the path with the path number 1 is calculated, specifically, CorrDis ═ DeltaR-totalmeasror-totaltractor.
Further, whether a first historical track matched with the flight track exists in the historical candidate tracks or not is determined according to the relation between the statistical correlation distance and the preset correlation distance.
In the specific implementation process, the preset correlation distance is corcgate sigma, and corcgate is a set value, such as: 280 m, and the sigma is max { MeasRSS, TrackRSS }, wherein MeasRSS is the error mean value of flight tracks, and TrackRSS is the error mean value of tracks with the track number of 1.
The specific calculation process of the error mean value of the flight path and the error mean value of the flight path with the flight path number of 1 is as follows:
hypothesis track covariance matrixThe tracking covariance matrix is a 6-by-6 matrix, specifically a covariance matrix formed by relations among distances, distance change rates, orientations, orientation change rates, pitches and pitch change rates, wherein initial values of elements in the tracking covariance matrix are all 1, and the tracking covariance matrix is continuously updated with the addition of new tracking points, and then the updating process is specifically described as follows.
Firstly, calculating a track covariance matrix, recording the track covariance matrix as a Sigma factor, recording tracking distance error Sigma factor, azimuth error Sigma factor and pitch error Sigma factor as SigmaRng, SigmaAz and SigmaEl respectively, and respectively showing the corresponding calculation formulas as the following formulas (1) to (3):
wherein,
rngrand: distance uncertainty in meters; azrand:orientation uncertainty in degrees; SElRand: pitch uncertainty in degrees; rngsynoise: distance system noise in meters; AzSysNoise: azimuth system noise in degrees; ElMultiPth: pitching multipath coefficient, dimensionless; MlPth: the sum of the multipath coefficients, dimensionless; ElBeamwidth: the pitch width of the sensor beam in degrees; diffchannleselop: the height difference slope of the sensor is dimensionless and generally takes a value of 1.2; k is a radical of1,k2,k3Distance resolution squared, azimuth resolution squared and pitch resolution squared, respectively. The above parameters are performance parameters of the sensor or may be calculated from the performance parameters of the sensor.
The parameters in the flight path covariance are calculated as follows:
the values of other elements are all zero, CovVel is a coefficient for updating covariance, and the value of CovVel is generally between 1 and 2.
Wherein,
SumRng1＝SumRng1+SigmaRng SumRng2＝SumRng2+SigmaRng*t
SumRng3＝SumRng3+SigmaRng*t*t SumAz1＝SumAz1+SigmaAz；
SumAz2＝SumAz2+SigmaAz*t SumAz3＝SumAz3+SigmaAz*t*t；
SumEl1＝SumEl1+SigmaEl SumEl2＝SumEl2+SigmaEl*t；
SumEl3＝SumEl3+SigmaEl*t*3
DenomAz＝SumAz1*SumAz3-SumAzi2*SumAz2
DenomElev＝SumEl1*SumEl3-SumEl2*SumEl2；
DenomRng＝SumRng1*SumRng3-SumRng2*SumRng2
in the above formula, the initial values of SumRng1, SumAz1 and SumEl1 are all 1, t is the time difference between the flight path and the flight path with the flight path number of 1, and the flight path covariance matrix is obtained through the above calculation. Meanwhile, SumRng1, SumRng2, SumRng3, SumAz1, SumAz2, SumAz3, SumEl1, SumEl2 and SumEl3 are updated into the corresponding data items of the flight path.
And a second step of calculating a track error mean (RSS) of the flight track. The calculation formula of the track error mean value RSS is as follows:
wherein,
TrackError1＝cov00+cov11+cov22
TrackError2 and TrackError3 are the second and third eigenvalues of the covariance matrix, respectively.
The calculation process of the error mean RSS of the flight path with the flight path number of 1 is the same as the flight path error mean RSS of the flight path, and will not be described herein again. After calculating the average RSS of the flight path error of the flight path and the flight path with the flight path number of 1, the Sigma factor can be determined.
In the embodiment of the invention, under the condition that the N groups of sensing data are continuous data and the correlation is carried out through the identity data and the common data, the first historical track correlated with the flight track does not exist, and a new track is added into the track library to obtain an updated track library.
Further, in an embodiment of the present invention, after determining whether the N groups of sensing data are consecutive sensing data based on the N time tags, please refer to fig. 3, where the method further includes:
s301: if the N groups of sensing data are discontinuous sensing data, determining whether the N groups of sensing data contain identity data;
s302: if yes, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data;
s303: if not, determining whether the first historical flight path matched with the flight path exists in the flight path library or not based on the N groups of sensing data.
In a specific implementation process, whether identity data exists in the N groups of sensing data is judged, if the identity data exists, the flight track is matched with the flight track in the track library by using the identity data, and the specific steps are as follows: the identity data collected by the sensor is a 24-bit address code, and if the flight path with the 24-bit address code exists in the flight path library, the first historical flight path matched with the flight path exists in the flight path library.
If the first historical flight path matched with the flight path does not exist in the flight path library, determining whether the first historical flight path matched with the flight path exists in the flight path library by using N groups of sensing data, wherein the specific implementation process of the step specifically comprises the following steps:
determining whether the N sets of sensing data are sparse;
and if the sparsity exists, determining whether the first historical track matched with the flight track exists in the track library or not based on the N groups of sensing data.
In the embodiment of the invention, for the steps: the specific implementation process for determining whether the N groups of sensing data have sparsity specifically includes the following steps:
determining whether the time difference of the time labels of two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset time difference; or
Determining whether the difference value of the space angles in two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset space angle difference; or
And determining whether the dimensionalities of two adjacent groups of sensing data in the N groups of data are consistent or whether the dimensionalities after coordinate conversion are consistent.
In a specific implementation process, the judgment of the sparsity of the N groups of data can be performed from any dimension of time, space and information dimensions or a combination of multiple dimensions, and the judgment of the sparsity is explained from three aspects of time, space and information dimensions. Suppose that Representing data at adjacent time instants.
First, time angle. Assuming a given time thresholdTimeIf the information satisfies | ti-ti+1|＜TimeN-1, that is, the time difference between any two adjacent sets of sensing data is smaller than the preset time difference, the two adjacent sets of sensing data Info (t) are considered to bei) And Info (t)i+1) Are sparse in time.
In the embodiment of the present invention, the preset time difference may be specifically 1s, 2s or 3s, or another preset time difference, and a person skilled in the art may set the preset time difference according to actual situations, which is not specifically limited in the embodiment of the present invention.
Second, spatial angle. In the embodiment of the present invention, the spatial angles mainly include: azimuth, elevation, pitch, etc., given a set of spatial thresholdsSpace＝{1，2，…，nH, and Info (t)i) And Info (t)i+1) If there is no missing information, then for angles in the spatial angle, such as: any one of azimuth, elevation or pitch angleThen Info (t)i) And Info (t)i+1) Is sparse in k-angle in space; if forAre all provided withIf true, then Info (t)i) And Info (t)i+1) Are sparse in spatial terms.
And thirdly, information dimension angle. If the information dimensions of adjacent time are not consistent or after coordinate conversion, the Info (t) is indicatedi) Or Info (t)i+1) If there is a missing of the neighbor information, the neighbor data is sparse by default.
The inconsistent information dimensions mean that the coordinate systems of the sensing data are different, such as: the radar point trace may be distance, azimuth and elevation in an aircraft coordinate system, while the point trace of ADS-B is longitude, latitude and altitude in a terrestrial coordinate system, and the two coordinate systems are mutually convertible, if the two coordinate systems are converted, the information dimensionality is still inconsistent, such as: let tiThe time information includes longitude, latitude, altitude, speed, heading, etc., and at ti+1And if only the altitude, the navigational speed and the heading are available at the moment, the sensing data is sparse in the information dimension.
In the embodiment of the invention, when N groups of sensing data have sparsity, N groups of sensing data are clustered and classified, and the clustering method can be specifically a division method, a hierarchy method, a density algorithm, a graph theory clustering method or other algorithms, which is not exemplified herein; the classification method may be a decision tree, bayes, an artificial neural network, or another classification method, and a person skilled in the art may select the classification method according to actual needs, which is not specifically limited in the embodiment of the present invention.
In the embodiment of the present invention, after N groups of sensing data are processed by clustering and classifying, it is determined whether the number of the acquired N groups of sensing data exceeds a preset number, and when the number exceeds the preset number, N groups of data, that is, common data, are passed, for example: and (4) correlating the position data and correlating the flight path.
Through the technical scheme provided by the embodiment of the invention, when the N groups of sensing data are discontinuous data, a processing flow aiming at the discontinuous data is provided, so that the technical effect of improving the correlation accuracy is achieved.
In the course of associating the flight path, because an association conflict may occur due to the uncertainty of the common data, the target distribution, and the like, in this embodiment of the present invention, in order to avoid the existence of the association conflict, further, in this embodiment of the present invention, after determining whether the first historical flight path matching the flight path exists in the flight path library based on the common data if the association conflict does not exist, the method further includes:
determining whether an association conflict exists for the flight path; wherein the association conflict is that the flight device associates different historical tracks at different time periods;
and if the association conflict exists, adjusting the association result of the flight path to obtain a new association result.
In the embodiment of the present invention, after associating the flight paths, it is further necessary to determine whether there is a conflict in the tracked target, that is, determine that the flight devices associate different historical paths at different time periods, for example: and the tracking target is associated with the track number of 1 in the upper track library in the first data acquisition period, and is associated with the track number of 2 in the upper track library in the second data acquisition period, and at the moment, the flight track is determined to have association conflict.
When the flight path has the association conflict, the association result of the flight path needs to be adjusted, in the embodiment of the invention, the steps are as follows: if the association conflict exists, the association result of the flight path is adjusted, and a specific implementation process of obtaining a new association result includes, but is not limited to, the following two implementation manners, which are described in detail below.
A first implementation, please refer to fig. 4, which includes the following steps:
s401: determining whether the current track number of the first historical track is the same as the historical track number of a third historical track associated at a time between the current times;
s402: if the difference is positive, acquiring the association times of the flight path and the third history path;
s403: and if the association times are more than 1, adjusting the association track of the flight track from the first history track to the third history track.
In the concrete implementation process, firstly, the track number n of a first historical track is obtainedkA track number m of a third history track associated with the flight track at a time between the current times, and then n is judgedkAnd if the number of times of association between the flight path and the third history path is not the same as that of m, acquiring the number of times of association between the flight path and the third history path.
And if the association times are more than 1, adjusting the associated flight path of the flight path into a third history flight path.
If the association times is equal to 1, judging whether the first history track and the third history track have identity data specifically, such as: if the first historical track has the identity data and the third historical track does not have the identity data, determining that the associated track of the flight track is the first historical track; if the first historical track does not have the identity data and the third historical track has the identity data, adjusting the associated track of the flight track into the third historical track; and if the first historical track does not have the identity data, and the third historical track does not have the identity data, the correlation result is not output for the moment.
The second implementation, please refer to fig. 5, includes the following steps:
s501: determining the period of data acquisition of the M sensors and the sampling interval between the period of data acquisition of the M sensors and the sampling period corresponding to the first historical track;
s502: determining whether the first historical track is successfully associated in the period of data acquisition of the M sensors;
s503: if the association is successful, determining whether the association quality sequence of the first historical track in the sampling interval is an increasing sequence; the correlation quality sequence is accumulation of correct correlation results in the correlation results of the first historical flight path;
s504: and if the sequence is an increasing sequence, associating the flight path with the first historical path.
In a specific implementation process, a period of data acquisition by the sensor is determined, such as 10s, 20s, or 30s, or other data acquisition periods, which can be set by a person of ordinary skill in the art according to actual needs and is not specifically limited in the embodiment of the present invention. And the data acquisition period of the sensor and the period of the flight path in the flight path library, such as: 11s, 22s or 32s, in which case the periodic interval between them is 1s, 2s or3 s.
In the embodiment of the present invention, it is first determined whether the first historical track associated with the flight track is successfully associated with the periodic content of the data collected by the sensor, and if the association is successful, the association quality sequence of the first historical track in the periodic interval is continuously determined, such as: the association is successful in the first period interval, the association is successful in the second period interval and the association is successful in the third period, and the association is successful in each period interval, which indicates that the association quality sequence is an incremental association quality sequence, specifically, for the first historical track, the association is successful for 5 times, and the association quality may be 0.95; if the 6 th association is also successful, then the association quality may be 0.98; however, if the association conflict occurs at the 6 th time, the association quality may be 0.85, and thus, whether the association conflict occurs or not can be deduced from the trend of the change of the association quality.
In the embodiment of the invention, when the associated quality sequence is the incremental quality sequence, the associated flight path of the flight path is determined to be the first historical flight path.
Second aspect of the invention
Based on the same inventive concept of the first aspect, please refer to fig. 6, an embodiment of the present invention further provides an electronic device, where the electronic device is capable of communicating with a flight device, and the electronic device includes:
a first obtaining unit 601, configured to obtain N sets of sensing data acquired by M sensors arranged on the flight device and used for representing a flight path of the flight device, where M is an integer greater than or equal to 2, and N is an integer greater than zero;
a first dividing unit 602, configured to divide the N groups of sensing data into common data and identity data, where the common data is data that can be acquired by all the M sensors, and the identity data is data used to characterize types of the M sensors;
a first associating unit 603, configured to associate the flight path with a flight path in a path library by using the common data and the identity data, respectively, where the path library includes at least one flight path of at least one flight device.
Optionally, the first dividing unit 602 is configured to:
acquiring a time tag of each group of sensing data in the N groups of sensing data, and acquiring N time tags in total;
determining whether the N groups of sensing data are continuous sensing data based on the N time tags;
and if the N groups of sensing data are continuous sensing data, dividing the N groups of sensing data into common data and identity data.
Optionally, the first associating unit 603 is configured to:
determining whether a first historical track matched with the flight track exists in the track library based on the identity data;
and if not, determining whether the first historical track matched with the flight track exists in the track library or not based on the common data.
Optionally, the first associating unit 603 is configured to:
acquiring a first time label corresponding to the identity data and a second time label corresponding to the track in the track library;
determining whether the first time tag is earlier than a latest time tag in time in the second time tags;
if not, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data.
Optionally, the first associating unit 603 is configured to:
acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library;
determining a candidate historical track from the track library based on the altitude difference, the azimuth difference and the distance difference, wherein the altitude difference between the candidate historical track and the flight track is smaller than an altitude wave gate, the azimuth difference between the candidate historical track and the flight track is smaller than an azimuth wave gate, and the distance difference between the candidate historical track and the flight track is smaller than a distance wave gate;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks.
Optionally, the first associating unit 603 is configured to:
determining whether the flight path is associated with a second historical path in the path library at a time prior to a current time;
if so, determining whether the association between the flight path and the second historical path is valid;
and if the flight path is invalid, acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library.
Optionally, the first associating unit 603 is configured to:
extrapolating the flight tracks and each flight track to the current moment by using a least square method;
calculating the vector difference between the flight tracks and each flight track, and obtaining a module of the at least one vector difference;
acquiring a first total error mean value of the flight tracks and a second total error mean value of each flight track to obtain at least one second total error mean value;
obtaining a statistical correlation distance between the flight path and each flight path based on the model of the at least one vector difference, the first total error mean value and the at least one second total error mean value;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks based on the statistical correlation distance.
Optionally, after determining whether the N sets of sensing data are continuous sensing data based on the N time tags, the electronic device further includes:
a first determining unit, configured to determine whether the N groups of sensing data include identity data if the N groups of sensing data are discontinuous sensing data;
a second determining unit, configured to determine, based on the identity data, whether a first historical track matching the flight track exists in the track library if the first historical track exists;
and if not, determining whether the first historical flight path matched with the flight path exists in the flight path library or not based on the N groups of sensing data.
Optionally, the third determining unit is configured to:
determining whether the N sets of sensing data are sparse;
and if the sparsity exists, determining whether the first historical track matched with the flight track exists in the track library or not based on the N groups of sensing data.
Optionally, the third determining unit is configured to:
determining whether the time difference of the time labels of two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset time difference; or
Determining whether the difference value of the space angles in two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset space angle difference; or
And determining whether the dimensionalities of two adjacent groups of sensing data in the N groups of data are consistent or whether the dimensionalities after coordinate conversion are consistent.
Optionally, after determining whether the first historical track matching the flight track exists in the track library based on the common data if the first historical track matching the flight track does not exist, the electronic device further includes:
a fourth determining unit, configured to determine whether there is an association conflict in the flight path; wherein the association conflict is that the flight device associates different historical tracks at different time periods;
and the first adjusting unit is used for adjusting the correlation result of the flight path to acquire a new correlation result if the correlation conflict exists.
Optionally, the first adjusting unit is configured to:
determining whether the current track number of the first historical track is the same as the historical track number of a third historical track associated at a time between the current times;
if the difference is positive, acquiring the association times of the flight path and the third history path;
and if the association times are more than 1, adjusting the association track of the flight track from the first history track to the third history track.
Optionally, the first adjusting unit is configured to:
determining the period of data acquisition of the M sensors and the sampling interval between the period of data acquisition of the M sensors and the sampling period corresponding to the first historical track;
determining whether the first historical track is successfully associated in the period of data acquisition of the M sensors;
if the association is successful, determining whether the association quality sequence of the first historical track in the sampling interval is an increasing sequence; the correlation quality sequence is accumulation of correct correlation results in the correlation results of the first historical flight path;
and if the sequence is an increasing sequence, associating the flight path with the first historical path.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
according to the technical scheme, M sensors arranged on the flight equipment are acquired to acquire N groups of sensing data used for representing the flight path of the flight equipment, wherein M is an integer larger than or equal to 2, and N is an integer larger than zero; dividing the N groups of sensing data into common data and identity data, wherein the common data is data which can be collected by the M sensors, and the identity data is data used for representing the types of the M sensors; and respectively associating the flight path with a path in a path library by using the common data and the identity data, wherein the path library comprises at least one flight path technical scheme of at least one flight device. The method comprises the steps of classifying acquired sensing data, dividing the sensing data into common data and identity data, and then performing track association by respectively using the common data and the identity data, so that the technical problem that the identity information is not fully utilized in the track association in the prior art is effectively solved, and further the technical effects of realizing the track association by using the identity information and the common information of multi-source information in a hierarchical manner and improving the utilization rate of the identity information are achieved.
Secondly, according to the technical scheme of the embodiment of the invention, if the N groups of sensing data are discontinuous sensing data, whether the N groups of sensing data contain identity data is determined; if yes, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data; and if not, determining whether the first historical track matched with the flight track exists in the track library or not based on the N groups of sensing data, namely processing discrete point tracks by using identity data and common data under the condition that the sensing data are determined to be discontinuous sensing data, and further achieving the technical effect of improving the correlation accuracy.
Thirdly, according to the technical scheme in the embodiment of the invention, whether the flight path has association conflict or not is determined; wherein the association conflict is that the flight device associates different historical tracks at different time periods; and if the association conflict exists, adjusting the association result of the flight path to obtain a new association result, namely determining whether the association has the conflict or not after the flight path association is completed by utilizing the common data and the identity data, and if the association has the conflict, adjusting the associated object to further achieve the technical effect of improving the association accuracy.
The above embodiments are only used to describe the technical solutions of the present application in detail, but the above embodiments are only used to help understanding the method and the core idea of the present invention, and should not be construed as limiting the present invention. Those skilled in the art should also appreciate that they can easily conceive of various changes and substitutions within the technical scope of the present disclosure.
Claims (26)
1. A flight path association method is applied to an electronic device, the electronic device can communicate with a flight device, and the flight path association method is characterized by comprising the following steps:
acquiring M sensors arranged on the flight equipment, acquiring N groups of sensing data for representing the flight path of the flight equipment, wherein M is an integer greater than or equal to 2, and N is an integer greater than zero;
dividing the N groups of sensing data into common data and identity data, wherein the common data is data which can be collected by the M sensors, and the identity data is data used for representing the types of the M sensors;
and respectively associating the flight path with a path in a path library by using the common data and the identity data, wherein the path library comprises at least one flight path of at least one flight device.
2. The method of claim 1, wherein said separating said N sets of sensory data into common data and identity data comprises:
acquiring a time tag of each group of sensing data in the N groups of sensing data, and acquiring N time tags in total;
determining whether the N groups of sensing data are continuous sensing data based on the N time tags;
and if the N groups of sensing data are continuous sensing data, dividing the N groups of sensing data into common data and identity data.
3. The method of claim 2, wherein said associating said flight path with a path in a path library using said common data and said identity data, respectively, comprises:
determining whether a first historical track matched with the flight track exists in the track library based on the identity data;
and if not, determining whether the first historical track matched with the flight track exists in the track library or not based on the common data.
4. The method of claim 3, wherein said determining whether a first historical track exists in the track library that matches the flight track based on the identity data comprises:
acquiring a first time label corresponding to the identity data and a second time label corresponding to the track in the track library;
determining whether the first time tag is earlier than a latest time tag in time in the second time tags;
if not, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data.
5. The method of claim 3, wherein determining whether the first historical track matching the flight track exists in the track library based on the common data if not, comprises:
acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library;
determining a candidate historical track from the track library based on the altitude difference, the azimuth difference and the distance difference, wherein the altitude difference between the candidate historical track and the flight track is smaller than an altitude wave gate, the azimuth difference between the candidate historical track and the flight track is smaller than an azimuth wave gate, and the distance difference between the candidate historical track and the flight track is smaller than a distance wave gate;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks.
6. The method of claim 5, wherein obtaining the altitude difference, azimuth difference and distance difference between the flight path and each flight path in the flight path library comprises:
determining whether the flight path is associated with a second historical path in the path library at a time prior to a current time;
if so, determining whether the association between the flight path and the second historical path is valid;
and if the flight path is invalid, acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library.
7. The method of claim 5, wherein said determining whether the first historical track matching the flight track exists in the candidate historical tracks comprises:
extrapolating the flight tracks and each flight track to the current moment by using a least square method;
calculating the vector difference between the flight tracks and each flight track, and obtaining a module of the at least one vector difference;
acquiring a first total error mean value of the flight tracks and a second total error mean value of each flight track to obtain at least one second total error mean value;
obtaining a statistical correlation distance between the flight path and each flight path based on the model of the at least one vector difference, the first total error mean value and the at least one second total error mean value;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks based on the statistical correlation distance.
8. The method of claim 2, wherein after said determining whether said N sets of sensory data are consecutive sensory data based on said N time tags, the method further comprises:
if the N groups of sensing data are discontinuous sensing data, determining whether the N groups of sensing data contain identity data;
if yes, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data;
if not, determining whether the first historical flight path matched with the flight path exists in the flight path library or not based on the N groups of sensing data.
9. The method of claim 8, wherein said determining if there is a first historical track in the track library that matches the flight track based on the N sets of sensed data, if not, comprises:
determining whether the N sets of sensing data are sparse;
and if the sparsity exists, determining whether the first historical track matched with the flight track exists in the track library or not based on the N groups of sensing data.
10. The method of claim 9, wherein said determining whether said N sets of sensed data are sparse comprises:
determining whether the time difference of the time labels of two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset time difference; or
Determining whether the difference value of the space angles in two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset space angle difference; or
And determining whether the dimensionalities of two adjacent groups of sensing data in the N groups of data are consistent or whether the dimensionalities after coordinate conversion are consistent.
11. The method of claim 3, wherein after determining whether the first historical track matching the flight track exists in the track library based on the common data if not, the method further comprises:
determining whether an association conflict exists for the flight path; wherein the association conflict is that the flight device associates different historical tracks at different time periods;
and if the association conflict exists, adjusting the association result of the flight path to obtain a new association result.
12. The method of claim 11, wherein adjusting the correlation result of the flight path to obtain a new correlation result if there is a correlation conflict comprises:
determining whether the current track number of the first historical track is the same as the historical track number of a third historical track associated at a time between the current times;
if the difference is positive, acquiring the association times of the flight path and the third history path;
and if the association times are more than 1, adjusting the association track of the flight track from the first history track to the third history track.
13. The method of claim 11, wherein adjusting the correlation result of the flight path to obtain a new correlation result if there is a correlation conflict comprises:
determining the period of data acquisition of the M sensors and the sampling interval between the period of data acquisition of the M sensors and the sampling period corresponding to the first historical track;
determining whether the first historical track is successfully associated in the period of data acquisition of the M sensors;
if the association is successful, determining whether the association quality sequence of the first historical track in the sampling interval is an increasing sequence; the correlation quality sequence is accumulation of correct correlation results in the correlation results of the first historical flight path;
and if the sequence is an increasing sequence, associating the flight path with the first historical path.
14. An electronic device capable of communicating with an in-flight device, comprising:
the first acquisition unit is used for acquiring M sensors arranged on the flight equipment, acquiring N groups of sensing data used for representing the flight path of the flight equipment, wherein M is an integer larger than or equal to 2, and N is an integer larger than zero;
the first dividing unit is used for dividing the N groups of sensing data into common data and identity data, wherein the common data are data which can be collected by the M sensors, and the identity data are data used for representing the types of the M sensors;
and the first association unit is used for associating the flight path with the flight path in a path library by respectively utilizing the common data and the identity data, wherein the path library comprises at least one flight path of at least one flight device.
15. The electronic device of claim 14, wherein the first partitioning unit is to:
acquiring a time tag of each group of sensing data in the N groups of sensing data, and acquiring N time tags in total;
determining whether the N groups of sensing data are continuous sensing data based on the N time tags;
and if the N groups of sensing data are continuous sensing data, dividing the N groups of sensing data into common data and identity data.
16. The electronic device of claim 15, wherein the first associating unit is to:
determining whether a first historical track matched with the flight track exists in the track library based on the identity data;
and if not, determining whether the first historical track matched with the flight track exists in the track library or not based on the common data.
17. The electronic device of claim 16, wherein the first associating unit is to:
acquiring a first time label corresponding to the identity data and a second time label corresponding to the track in the track library;
determining whether the first time tag is earlier than a latest time tag in time in the second time tags;
if not, determining whether a first historical track matched with the flight track exists in the track library or not based on the identity data.
18. The electronic device of claim 17, wherein the first associating unit is to:
acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library;
determining a candidate historical track from the track library based on the altitude difference, the azimuth difference and the distance difference, wherein the altitude difference between the candidate historical track and the flight track is smaller than an altitude wave gate, the azimuth difference between the candidate historical track and the flight track is smaller than an azimuth wave gate, and the distance difference between the candidate historical track and the flight track is smaller than a distance wave gate;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks.
19. The electronic device of claim 18, wherein the first associating unit is to:
determining whether the flight path is associated with a second historical path in the path library at a time prior to a current time;
if so, determining whether the association between the flight path and the second historical path is valid;
and if the flight path is invalid, acquiring the height difference, the azimuth difference and the distance difference between the flight path and each flight path in the flight path library.
20. The electronic device of claim 19, wherein the first associating unit is to:
extrapolating the flight tracks and each flight track to the current moment by using a least square method;
calculating the vector difference between the flight tracks and each flight track, and obtaining a module of the at least one vector difference;
acquiring a first total error mean value of the flight tracks and a second total error mean value of each flight track to obtain at least one second total error mean value;
obtaining a statistical correlation distance between the flight path and each flight path based on the model of the at least one vector difference, the first total error mean value and the at least one second total error mean value;
determining whether the first historical track matched with the flight track exists in the candidate historical tracks based on the statistical correlation distance.
21. The electronic device of claim 15, wherein after said determining whether the N sets of sensory data are consecutive sensory data based on the N time tags, the electronic device further comprises:
a first determining unit, configured to determine whether the N groups of sensing data include identity data if the N groups of sensing data are discontinuous sensing data;
a second determining unit, configured to determine, based on the identity data, whether a first historical track matching the flight track exists in the track library if the first historical track exists;
and if not, determining whether the first historical flight path matched with the flight path exists in the flight path library or not based on the N groups of sensing data.
22. The electronic device of claim 21, wherein the third determination unit is to:
determining whether the N sets of sensing data are sparse;
and if the sparsity exists, determining whether the first historical track matched with the flight track exists in the track library or not based on the N groups of sensing data.
23. The electronic device of claim 22, wherein the third determination unit is to:
determining whether the time difference of the time labels of two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset time difference; or
Determining whether the difference value of the space angles in two adjacent groups of sensing data in the N groups of sensing data is smaller than a preset space angle difference; or
And determining whether the dimensionalities of two adjacent groups of sensing data in the N groups of data are consistent or whether the dimensionalities after coordinate conversion are consistent.
24. The electronic device of claim 15, wherein after determining whether the first historical track matching the flight track exists in the track library based on the common data if not, the electronic device further comprises:
a fourth determining unit, configured to determine whether there is an association conflict in the flight path; wherein the association conflict is that the flight device associates different historical tracks at different time periods;
and the first adjusting unit is used for adjusting the correlation result of the flight path to acquire a new correlation result if the correlation conflict exists.
25. The electronic device of claim 24, wherein the first adjustment unit is to:
determining whether the current track number of the first historical track is the same as the historical track number of a third historical track associated at a time between the current times;
if the difference is positive, acquiring the association times of the flight path and the third history path;
and if the association times are more than 1, adjusting the association track of the flight track from the first history track to the third history track.
26. The electronic device of claim 24, wherein the first adjustment unit is to:
determining the period of data acquisition of the M sensors and the sampling interval between the period of data acquisition of the M sensors and the sampling period corresponding to the first historical track;
determining whether the first historical track is successfully associated in the period of data acquisition of the M sensors;
if the association is successful, determining whether the association quality sequence of the first historical track in the sampling interval is an increasing sequence; the correlation quality sequence is accumulation of correct correlation results in the correlation results of the first historical flight path;
and if the sequence is an increasing sequence, associating the flight path with the first historical path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710135102.8A CN107063259B (en) | 2017-03-08 | 2017-03-08 | Track association method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710135102.8A CN107063259B (en) | 2017-03-08 | 2017-03-08 | Track association method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107063259A true CN107063259A (en) | 2017-08-18 |
| CN107063259B CN107063259B (en) | 2020-06-09 |
Family
ID=59622143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710135102.8A Active CN107063259B (en) | 2017-03-08 | 2017-03-08 | Track association method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107063259B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107463967A (en) * | 2017-08-25 | 2017-12-12 | 中国人民解放军海军航空工程学院 | Multi-source track association machine learning system |
| CN108513644A (en) * | 2017-12-18 | 2018-09-07 | 深圳市大疆创新科技有限公司 | Unmanned plane barrier-avoiding method and unmanned plane |
| CN109444899A (en) * | 2018-09-20 | 2019-03-08 | 杭州电子科技大学 | A kind of Data Association based on pure angle information |
| CN109656271A (en) * | 2018-12-27 | 2019-04-19 | 杭州电子科技大学 | A kind of soft correlating method of track based on data correlation thought |
| CN109696172A (en) * | 2019-01-17 | 2019-04-30 | 福瑞泰克智能系统有限公司 | A kind of multisensor flight path fusion method, device and vehicle |
| CN110321401A (en) * | 2019-07-09 | 2019-10-11 | 中国人民解放军海军航空大学 | Space-time data is associated with deep learning method |
| CN110781949A (en) * | 2019-10-23 | 2020-02-11 | 福建汉特云智能科技有限公司 | Asynchronous serial multi-sensor-based flight path data fusion method and storage medium |
| CN111965634A (en) * | 2020-08-28 | 2020-11-20 | 北京国遥新天地信息技术有限公司 | Air traffic control non-relevant monitoring track data synthesis method |
| CN112180338A (en) * | 2020-06-10 | 2021-01-05 | 四川九洲电器集团有限责任公司 | Holographic digital array radar target quantity estimation method and system |
| CN113673787A (en) * | 2021-09-10 | 2021-11-19 | 中国舰船研究设计中心 | Unmanned cluster multi-domain detection data track association and prediction method |
| CN114994633A (en) * | 2022-08-04 | 2022-09-02 | 四川九洲空管科技有限责任公司 | Method for secondary radar point track correlation processing |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101655561A (en) * | 2009-09-14 | 2010-02-24 | 南京莱斯信息技术股份有限公司 | Federated Kalman filtering-based method for fusing multilateration data and radar data |
| US20140022107A1 (en) * | 2012-07-17 | 2014-01-23 | Electronics And Telecommunications Research Institute | Method and apparatus for managing tracking information using unique id in vessel traffic system |
| CN103575279A (en) * | 2013-11-04 | 2014-02-12 | 成都金本华科技股份有限公司 | Flight path correlating method and system based on fuzzy information |
| CN103886196A (en) * | 2014-03-14 | 2014-06-25 | 中国电子科技集团公司第二十八研究所 | Track associating method resistant to big system errors |
| CN104656070A (en) * | 2015-03-19 | 2015-05-27 | 哈尔滨工业大学 | Method for eliminating false target under radar networking |
| CN104749576A (en) * | 2015-04-08 | 2015-07-01 | 四川九洲空管科技有限责任公司 | Multi-radar track association and fusion method |
| CN104808197A (en) * | 2015-05-06 | 2015-07-29 | 四川九洲空管科技有限责任公司 | Multi-surveillance-source flying target parallel track processing method |
| CN104931960A (en) * | 2015-05-25 | 2015-09-23 | 中国电子科技集团公司第十研究所 | Trend message and radar target state information whole-track data correlation method |
| CN106017475A (en) * | 2016-07-04 | 2016-10-12 | 四川九洲电器集团有限责任公司 | Flight path updating method and flight path updating device |
| CN106323272A (en) * | 2016-08-23 | 2017-01-11 | 四川九洲电器集团有限责任公司 | Method and electronic equipment for acquiring starting track of flight path |
| CN106371091A (en) * | 2016-08-24 | 2017-02-01 | 四川九洲空管科技有限责任公司 | ADS-B and secondary surveillance radar monitoring information data integration method and device |
-
2017
- 2017-03-08 CN CN201710135102.8A patent/CN107063259B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101655561A (en) * | 2009-09-14 | 2010-02-24 | 南京莱斯信息技术股份有限公司 | Federated Kalman filtering-based method for fusing multilateration data and radar data |
| US20140022107A1 (en) * | 2012-07-17 | 2014-01-23 | Electronics And Telecommunications Research Institute | Method and apparatus for managing tracking information using unique id in vessel traffic system |
| CN103575279A (en) * | 2013-11-04 | 2014-02-12 | 成都金本华科技股份有限公司 | Flight path correlating method and system based on fuzzy information |
| CN103886196A (en) * | 2014-03-14 | 2014-06-25 | 中国电子科技集团公司第二十八研究所 | Track associating method resistant to big system errors |
| CN104656070A (en) * | 2015-03-19 | 2015-05-27 | 哈尔滨工业大学 | Method for eliminating false target under radar networking |
| CN104749576A (en) * | 2015-04-08 | 2015-07-01 | 四川九洲空管科技有限责任公司 | Multi-radar track association and fusion method |
| CN104808197A (en) * | 2015-05-06 | 2015-07-29 | 四川九洲空管科技有限责任公司 | Multi-surveillance-source flying target parallel track processing method |
| CN104931960A (en) * | 2015-05-25 | 2015-09-23 | 中国电子科技集团公司第十研究所 | Trend message and radar target state information whole-track data correlation method |
| CN106017475A (en) * | 2016-07-04 | 2016-10-12 | 四川九洲电器集团有限责任公司 | Flight path updating method and flight path updating device |
| CN106323272A (en) * | 2016-08-23 | 2017-01-11 | 四川九洲电器集团有限责任公司 | Method and electronic equipment for acquiring starting track of flight path |
| CN106371091A (en) * | 2016-08-24 | 2017-02-01 | 四川九洲空管科技有限责任公司 | ADS-B and secondary surveillance radar monitoring information data integration method and device |
Non-Patent Citations (5)
| Title |
|---|
| ZHU LI-LI 等: "FGAs-Based Data Association Algorithm for Multi-sensor Multi-target Tracking", 《CHINESE JOURNAL OF AERONAUTICS》 * |
| 何桂萍: "ADS-B与雷达组合监视数据融合方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 兰旭辉等: "一种改进的多源异类航迹关联方法", 《空军雷达学院学报》 * |
| 周新宇: "基于多源信息不确定性的可能性融合方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 毛艺帆等: "基于空天信息的异类传感器模糊航迹关联算法", 《空军工程大学学报(自然科学版)》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107463967A (en) * | 2017-08-25 | 2017-12-12 | 中国人民解放军海军航空工程学院 | Multi-source track association machine learning system |
| CN108513644A (en) * | 2017-12-18 | 2018-09-07 | 深圳市大疆创新科技有限公司 | Unmanned plane barrier-avoiding method and unmanned plane |
| CN109444899A (en) * | 2018-09-20 | 2019-03-08 | 杭州电子科技大学 | A kind of Data Association based on pure angle information |
| CN109656271B (en) * | 2018-12-27 | 2021-11-02 | 杭州电子科技大学 | Track soft association method based on data association idea |
| CN109656271A (en) * | 2018-12-27 | 2019-04-19 | 杭州电子科技大学 | A kind of soft correlating method of track based on data correlation thought |
| CN109696172A (en) * | 2019-01-17 | 2019-04-30 | 福瑞泰克智能系统有限公司 | A kind of multisensor flight path fusion method, device and vehicle |
| CN110321401A (en) * | 2019-07-09 | 2019-10-11 | 中国人民解放军海军航空大学 | Space-time data is associated with deep learning method |
| CN110321401B (en) * | 2019-07-09 | 2023-05-26 | 中国人民解放军海军航空大学 | Space-time data correlation deep learning method |
| CN110781949A (en) * | 2019-10-23 | 2020-02-11 | 福建汉特云智能科技有限公司 | Asynchronous serial multi-sensor-based flight path data fusion method and storage medium |
| CN112180338A (en) * | 2020-06-10 | 2021-01-05 | 四川九洲电器集团有限责任公司 | Holographic digital array radar target quantity estimation method and system |
| CN112180338B (en) * | 2020-06-10 | 2022-03-01 | 四川九洲电器集团有限责任公司 | Holographic digital array radar target quantity estimation method and system |
| CN111965634A (en) * | 2020-08-28 | 2020-11-20 | 北京国遥新天地信息技术有限公司 | Air traffic control non-relevant monitoring track data synthesis method |
| CN113673787A (en) * | 2021-09-10 | 2021-11-19 | 中国舰船研究设计中心 | Unmanned cluster multi-domain detection data track association and prediction method |
| CN113673787B (en) * | 2021-09-10 | 2023-09-26 | 中国舰船研究设计中心 | Unmanned cluster multi-domain detection data track association and prediction method |
| CN114994633A (en) * | 2022-08-04 | 2022-09-02 | 四川九洲空管科技有限责任公司 | Method for secondary radar point track correlation processing |
| CN114994633B (en) * | 2022-08-04 | 2022-11-08 | 四川九洲空管科技有限责任公司 | Method for secondary radar point track correlation processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107063259B (en) | 2020-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107063259B (en) | Track association method and electronic equipment | |
| CN103336863B (en) | The flight intent recognition methods of flight path observed data of flying based on radar | |
| CN103116688A (en) | Multi-source abnormal sensor target track correlation method for airborne avionic system | |
| CN106934324A (en) | Based on the radar data correlating methods for simplifying many hypothesis algorithms | |
| CN112466103B (en) | Aircraft flight threat evolution early warning method, device, equipment and storage medium | |
| CN110598730A (en) | Flight path association algorithm based on decision tree | |
| CN106323272B (en) | A kind of method and electronic equipment obtaining track initiation track | |
| CN107832778A (en) | A kind of same target recognition methods based on spatial synthesis similarity | |
| CN111126504A (en) | Multi-source incomplete information fusion image target classification method | |
| Spiliopoulos et al. | Knowledge extraction from maritime spatiotemporal data: An evaluation of clustering algorithms on Big Data | |
| CN112116019A (en) | Multi-sensor Vine Copula heterogeneous information decision fusion method | |
| Baumann et al. | Timing of the solar wind propagation delay between L1 and Earth based on machine learning | |
| CN116071667A (en) | Method and system for detecting abnormal aircraft targets in specified area based on historical data | |
| CN117725448A (en) | Cluster analysis method for meteorological navigation signal characteristics | |
| Park et al. | Fi-Vi: Large-area indoor localization scheme combining ML/DL-based wireless fingerprinting and visual positioning | |
| Olofsson et al. | Sea ice tracking with a spatially indexed labeled multi-Bernoulli filter | |
| Goswami et al. | Convective cloud detection and tracking from series of infrared images | |
| Chatterjee et al. | Sparse group lasso for regression on land climate variables | |
| Hall et al. | Analog sky condition forecasting based on a k-nn algorithm | |
| KR101468560B1 (en) | A method of detecting outlier pulses of radar signal based on mahalanobis distance | |
| Wu et al. | Real-time Ship Track Association: a Benchmark and a Network-Based Method | |
| CN106127182B (en) | The two passive sensor multi-jamming sources based on inclination angle are positioned to terrible point methods | |
| CN113095448B (en) | Method for realizing heterogeneous multi-scale track link | |
| Popp et al. | m-best SD assignment algorithm with application to multitarget tracking | |
| Nithya et al. | Multi Small Object Detection and Prioritized Tracking for Navy Operations using Deep Learning Techniques |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |