CN114494327A - Method, device and equipment for processing flight path of target object - Google Patents
Method, device and equipment for processing flight path of target object Download PDFInfo
- Publication number
- CN114494327A CN114494327A CN202210060144.0A CN202210060144A CN114494327A CN 114494327 A CN114494327 A CN 114494327A CN 202210060144 A CN202210060144 A CN 202210060144A CN 114494327 A CN114494327 A CN 114494327A
- Authority
- CN
- China
- Prior art keywords
- track point
- track
- point set
- value
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
Abstract
The invention provides a method, a device and equipment for processing a flight path of a target object, wherein the method comprises the following steps: acquiring a track point set of a track of a target object; filtering the track point set to obtain a first track point set, wherein the first track point set comprises data information of each track point; determining the motion state of each track point according to the data information of each track point in the first track point set; and compressing the first track point set according to the motion state to obtain a second track point set. The scheme of the invention can improve the track compression ratio of the target object and simultaneously can ensure that the track is not distorted.
Description
Technical Field
The invention relates to the technical field of ship track processing, in particular to a method, a device and equipment for processing a track of a target object.
Background
For the offshore radar target, the target update time is between 2 and 3 seconds, while the update time of the AIS target is indefinite, and after the fusion processing, the update period of the fusion target is generally between 3 and 10 seconds. The redundancy of the track information is large for targets in different motion states, such as parked or fixed position targets, and the redundancy of the track is large for targets sailing in a specific course. If the original track is visualized and the track characteristic is identified, the pressure on the front-end and back-end algorithms of the web is large. The traditional track compression algorithm is difficult to balance in the aspects of fidelity (retention of track characteristics) and compression rate; how to improve the compression ratio and reduce the loss of the track characteristics is a main technical problem to be solved by the invention.
Disclosure of Invention
The invention aims to provide a method, a device and equipment for processing a track of a target object, so as to improve the track compression rate and reduce the loss of track characteristic values.
In order to solve the technical problems, the technical scheme of the invention is as follows:
the embodiment of the invention provides a flight path processing method of a target object, which comprises the following steps:
acquiring a track point set of a track of a target object;
filtering the track point set to obtain a first track point set, wherein the first track point set comprises data information of each track point;
determining the motion state of each track point according to the data information of each track point in the first track point set;
and compressing the first track point set according to the motion state to obtain a second track point set.
Optionally, the filtering the trace point set to obtain a first trace point set, including:
obtaining a predicted position value of the track point at the time t according to the position estimation value of the track point at the time t-1 in the track point set, the speed measurement value and the course measurement value of the track point at the time t, wherein t is greater than or equal to 1, and the position estimation value of the initial track point is the position measurement value when t is equal to 1;
obtaining a position estimation value of the track point at the t moment according to the position prediction value of the track point at the t moment and the position measurement value of the track point at the t moment;
and acquiring the first track point set according to the estimation value.
Optionally, obtaining a predicted position value of the track point at the time t according to the speed measurement value and the course measurement value of the track point at the time t in the track point set and the position estimation value of the track point at the time t-1, including:
according to formula x "i＝x'i-1+vi*sin(ci)*(ti-ti-1)/cos(yi) And y "i＝y'i-1+vi*cos(ci)*(ti-ti-1) Obtaining a position predicted value of the track point at the time t;
according to a formula x'i＝x”i+α*(xi-x”i) And y'i＝y”i+α*(yi-y”i) Obtaining a position estimation value of a track point at the time t;
wherein i is less than or equal to t, t is greater than or equal to 1, and alpha is a Kalman coefficient and x'iAs an estimate of the longitude of the locus point, yi'Latitude estimate, x', for a trace point "iAs longitude predictors of the trace points, yi"is the latitude predicted value of the track point; v. ofiAs velocity measurements of the trace points, ciThe course measurement value of the track point is obtained.
Optionally, determining the motion state of each trace point according to the data information of each trace point in the first trace point set, including:
acquiring a subset of the first track point set within a preset time period;
obtaining the characteristic vector of the track point according to the data information of each track point in the subset;
and determining the motion state of the track point at the time t in the first track point set according to the characteristic vector.
Optionally, the data information includes at least one of:
position information of the track points;
measuring course of the track points;
velocity measurements of the trace points; time stamp of the trace point;
the feature vector includes at least one of:
measuring the speed of the track point at the time t;
the track overlap ratio.
Optionally, compressing the first trace point set according to the motion state to obtain a second trace point set, including:
when each track point is in a static state, performing first snapshot compression on the first track point set according to a first preset time interval to obtain a first compressed track point set;
and clustering the first compressed track point set, and performing second snapshot compression according to a second preset time interval to obtain a second track point set.
Optionally, compressing the first trace point set according to the motion state to obtain a second trace point set, including:
when each track point is in a motion state, performing sliding window type compression on the first track point set for the first time according to the linearity of a first sliding track section of the first track point set to obtain a first compressed track point set, wherein the first sliding track section is a track section formed by the track points in the first track point set within a first preset time period;
performing sliding window type filtering processing on the first compressed track point set to obtain a second filtered track point set;
and according to the linearity of a second sliding track section of the second filtering track point set, performing second sliding window type compression on the second filtering track point set to obtain a second track point set, wherein the second sliding track section is in a second preset time period, and track sections formed by track points in the second filtering track point set are obtained.
The embodiment of the invention also provides a device for processing the target track, which comprises:
the acquisition module is used for acquiring a track point set of a track of a target object;
the processing module is used for filtering the track point set to obtain a first-stage track point set, and the first track point set comprises data information of each track point; determining the motion state of each track point according to the data information of each track point in the first track point set; and compressing the first track point set according to the motion state to obtain a second track point set.
Embodiments of the present invention also provide a computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the corresponding operation of the method.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method as described above.
The scheme of the invention at least comprises the following beneficial effects:
according to the scheme, the track point set is filtered, so that the purpose of noise filtering of track point position information is achieved, and a first track point set is obtained, wherein the first track point set comprises data information of each track point; determining the motion state of each track point according to the data information of each track point in the first track point set; and compressing the first track point set according to the motion state to obtain a second track point set, and compressing the track point set by combining the motion state of the track points in the track point set, so that the compression efficiency is improved, and meanwhile, the data distortion of the track points can be avoided.
Drawings
FIG. 1 is a flowchart of a method for processing a flight path of a target object according to an embodiment of the present invention;
FIG. 2 is a flowchart of an implementation of a method for processing a flight path of a target object according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of a track processing apparatus for a target object according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention provides a method for processing a flight path of a target object, where the method includes:
and 14, compressing the first track point set according to the motion state to obtain a second track point set.
In this embodiment, the acquired track point set of the target object track is an original track point set, and the original track point set includes original data information of each track point; filtering the original track point set to obtain a first track point set, wherein the first track point set comprises filtered data information of each track point after filtering; the original data information and the filtered data information comprise timestamps, longitudes, latitudes, speeds and headings of track points; in this embodiment, a kalman filtering algorithm may be used to perform point-by-point filtering processing on each trace point in the trace point set, that is, to process data information of the trace point, so as to eliminate trace point noise, and implement initial filtering processing on the trace point, so as to perform subsequent compression processing; preferably, before the point-by-point filtering processing, the method further includes cleaning data information of the track points, where the cleaning includes, but is not limited to, processing of invalid data and abnormal data, so as to ensure accuracy of subsequent point-by-point filtering processing;
the original set of trace points may be denoted as P ═ P (P)1，p2，p3，…，pn) WhereinTrace point pi＝(ti，xi，yi，vi，ci)，tiRepresenting points of track piTime stamp of xiRepresenting points of track piLongitude measurement of, yiRepresenting points of track piMeasured value of latitude, viRepresenting points of track piA measured value of velocity of ciRepresenting points of track piI and n are positive integers, i is less than or equal to n; the data information of each original track point in the original track point set is filtered, each first track point and the first track point set corresponding to the data information after filtering are obtained, the motion state of each first track point is judged according to the data information after filtering, the first track point set is compressed in different modes according to different motion states of each first track point, the redundancy of the data information of the track points in the first track point set is reduced, the target track is compressed to a greater degree, and the compression efficiency is further improved.
In an optional embodiment of the present invention, the step 12 may include:
step 121, obtaining a predicted position value of the track point at the time t according to the position estimation value of the track point at the time t-1 in the track point set, the speed measurement value and the course measurement value of the track point at the time t, wherein t is greater than or equal to 1, and the position estimation value of the initial track point is the position measurement value when t is equal to 1;
step 122, obtaining a position estimation value of the track point at the time t according to the position prediction value of the track point at the time t and the position measurement value of the track point at the time t;
and step 123, acquiring the first track point set according to the estimation value.
In this embodiment, the position measurement may be position information of the target measured by a related instrument, the position measurement value includes a longitude and latitude measurement value of the trace point, the position estimation value includes a longitude and latitude estimation value of the trace point, and the position prediction value includes a longitude and latitude prediction value of the trace point; the position estimation value of the track point at the initial moment in the track point set is the position measurement value of the track point, filtering the trace points in the trace point set according to the initial time, according to the position estimation value of the trace point at the initial time, namely the position measurement value, and the speed measurement value of the next moment track point of the initial moment track point, obtaining the position prediction value of the next moment track point, and obtaining the position estimation value of the next moment track point according to the position prediction value and the position measurement value of the next moment track point, processing the track points in the initial track point set by the method point by point to obtain the position estimation value of each first track point corresponding to each initial track point after processing, and a first track point set is formed so as to achieve the purpose of filtering noise of position information of each track point in the initial track point set.
In an optional embodiment of the present invention, the step 122 may include:
step 1221, according to formula x "i＝x'i-1+vi*sin(ci)*(ti-ti-1)/cos(yi) And y "i＝y'i-1+vi*cos(ci)*(ti-ti-1) Obtaining a position predicted value of the track point at the time t;
according to formula x'i＝x”i+α*(xi-x”i) And y'i＝y”i+α*(yi-y”i) Obtaining a position estimation value of a track point at the time t;
wherein i is less than or equal to t, t is greater than or equal to 1, and alpha is a Kalman coefficient, x'iIs a longitude estimate of the track point, y'iAs latitude estimates of the locus points, x "iIs the longitude predicted value of the track point, y "iThe latitude predicted value of the track point is taken; v. ofiAs velocity measurements of the trace points, ciThe course measurement value of the track point is obtained; in this embodiment, the larger the noise of the initial trace point is, the larger the kalman coefficient needs to be, so as to achieve a better denoising effect, and preferably, the initial setting value of the kalman coefficient may be 0.8.
In an optional embodiment of the present invention, step 13 may include:
step 131, obtaining a sliding track unit formed by track points in the first track point set within a preset time period;
step 132, obtaining a feature vector of the track point according to the data information of each track point in the sliding track unit;
and step 133, determining the motion state of the track point at the time t in the first track point set according to the feature vector.
In this embodiment, the preset time period may be set according to an empirical value, and a value range of the preset time period is 1 to 2 minutes, and further, the data information includes at least one of the following items: position information of the tracing points, namely longitude and latitude of the tracing points; measuring course of the track points; velocity measurements of the trace points; time stamp of the trace point; the feature vector includes at least one of: measuring the speed of the track point at the time t; a track overlap rate; the average speed value of the track points at the time t; the speed measurement is derived from the position information, and the current speed measurement value represents the average speed of the previous time period;
by means of machine learning, feature vectors are formed by the current speed, the average speed, the track overlapping rate and the like of historical track points, a decision tree model is trained, decision tree models corresponding to the track points in different states are obtained, feature vectors formed by data of the track points in the current sliding track unit are input into the trained decision tree model, and the motion state of the track points in the sliding track unit is judged; preferably, the track overlapping rate can be calculated by the following formula:
wherein x isi，yiRespectively representing longitude estimation value and latitude estimation value, x, of ith track point in N track points of current sliding track unitmax，xmin，ymax，yminRespectively representing the maximum of the middle track points of the current sliding track unitA major longitude estimate, a minimum longitude estimate, a maximum latitude estimate, and a minimum latitude estimate.
In an optional embodiment of the present invention, in step 14, when each track point is in a static state, the method may include:
step 14-01, when each track point is in a static state, performing first snapshot compression on the first track point set according to a first preset time interval to obtain a first compressed track point set;
and 14-02, clustering the first compressed track point set, and performing second snapshot compression according to a second preset time interval to obtain a second track point set.
In this embodiment, the first preset time interval and the second preset time interval may be set according to the size of a system storage space and a requirement of a compression rate, and the higher the compression rate is, the larger the first preset time interval and the second preset time interval are; performing first snapshot compression on the first track point set according to a first preset time interval, for example, when the first preset time interval can be set to 15 minutes, that is, in the first track point set, a static track point is reserved every 15 minutes, and the reserved track points form a first compressed track point set so as to reduce the redundancy of the track point set;
performing clustering processing on the first compressed track point set, preferably, performing clustering analysis by adopting a DBSCAN algorithm, and performing second snapshot compression on the clustered first compressed track point set according to the second preset time interval, wherein the second snapshot compression is performed on the first-stage compressed track points on the basis of the first snapshot compression, and a set value of the second preset time interval is greater than a set value of the first preset time interval; and performing secondary compression on the clustered first compressed track point set, so that historical track points slightly far away from the track point at the current moment can obtain a higher compression rate, and the redundancy of the track point set is further reduced.
In an optional embodiment of the present invention, in step 14, when each track point is in a motion state, the method may include:
14-11, when each track point is in a motion state, performing sliding window type compression on a first track point set for the first time according to a first linearity of a first sliding track section of the first track point set to obtain a first compressed track point set, wherein the first sliding track section is a track section formed by the track points in the first track point set within a first preset time period;
14-12, performing sliding window type filtering processing on the first compressed track point set to obtain a second filtered track point set;
and 14-13, performing second sliding window type compression on the second filtering track point set according to the second linearity of the second sliding track section of the second filtering track point set to obtain a second track point set, wherein the second sliding track section is a track section formed by track points in the second filtering track point set in a second preset time period.
In this embodiment, the steps 14-11, 14-12 and 14-13 are processing steps for compressing the trace points in the motion state, and are not based on the steps 14-01 and 14-02;
when each track point is in a motion state, performing sliding window type compression on the first track point set for the first time according to the first linearity of the first sliding track section of the first track point set; when the first linearity meets a first preset linearity threshold value, determining that track points in the first sliding track section meet a linear relation, and performing sliding window type track compression on the first track point set by taking the first sliding track section as a step length to obtain a first compressed track point set;
when the first linearity does not meet a first preset linearity threshold value, determining that track points in the first sliding track section do not meet a linear relation, keeping track points with the maximum deviation track section in the first sliding track section as key track points, discarding track points between the initial track points and the key track points, reconstructing the sliding track section, wherein the end point of the sliding track section is the key track points, and performing sliding window type track compression on the first track point set according to the sliding track section as a step length at the moment to obtain a first compressed track point set;
the first compressed track point set is subjected to sliding window type filtering treatment, preferably, the current track point can be judged to be a jump point by the current time track point in the first compressed track point set and the previous time track point thereof and the subsequent time track point thereof when the included angle formed between the three track points is smaller than a preset included angle threshold value, the preset included angle threshold value can be set according to the actual condition or experience value of the current track point, if the preset included angle threshold value is set to be 60 degrees, for example, whether the current track point O is the jump point or not is judged, AO is a vector formed by the previous time track point A and the current track point O, BO is a vector formed by the subsequent time track point B and the current track point O, when the included angle AOB is smaller than the preset included angle threshold value, the current track point O is the jump point and the jump point is discarded, and other compressed track points in the first compressed track point set are sequentially judged, obtaining a second filtering track point set;
it is right the second filters track point set and carries out the compression of sliding window formula for the second time, with the step of the compression of sliding window formula for the first time is the same, because of the compression of sliding window formula for the second time is in go on the basis of the compression of sliding window formula for the first time, admittedly the setting value of the predetermined linearity threshold value of second should be greater than the setting value of the first predetermined linearity.
In an alternative embodiment of the present invention, the linearity of the sliding track segment can be calculated by the following formula:
The method is described below by using a specific example, as shown in fig. 2, the specific flow is as follows:
step 21, pre-filtering the original data: when a new track point comes in, cleaning is firstly carried out, and the method comprises the following steps: processing invalid data and abnormal data, and performing Kalman filtering processing point by point to obtain a position predicted value and a position estimated value of a track point, wherein the position predicted value comprises: predicting the longitude and latitude values of the track points; the position estimation values include: and predicting and estimating the position information of the target by the longitude and latitude estimation values of the track points so as to achieve the purpose of filtering the noise of the position information.
Step 22, identifying the motion state:
step 221, processing is performed based on the minimum track unit of 1 to 2 minutes (default 1.5 minutes), and track point data of the current minimum track unit is collected in a time dimension sliding window mode, wherein the track point data mainly comprises the position, speed, course and timestamp information of each track point.
Step 222, performing stationary target recognition on the minimum trajectory unit by means of machine learning. And (2) forming a feature vector by using the current speed, the average speed, the track overlapping rate and the like of the target, training a decision tree model, and automatically judging whether the generated model is static or not according to the current feature vector of the target, wherein the calculation formula of the track overlapping degree is as follows:
step 23, compressing the target track point may include the following steps:
step 23a, performing first-stage compression on the static target: compression is performed on a time scale. An appropriate time interval may be selected based on the size of the storage space and the compression ratio requirements, with the larger the value, the higher the compression ratio. For example, setting for 15 minutes, a track point is reserved for a static target every 15 minutes;
step 24a, performing clustering analysis on the first-stage compressed track points in the static state by adopting a DBSCAN density clustering algorithm, and performing secondary compression on the clustered points;
step 23b, performing first-stage compression on the target in the motion state: and performing sliding window type track compression by taking the minimum track unit as a step length, constructing a straight line by using head and tail points of the current track section, and calculating the linearity of the track section. : if the current track section meets the linearity requirement, namely the linearity is smaller than a preset linearity threshold value, the track length is increased by one step length, if the current track section does not meet the linearity requirement, the maximum deviation point is reserved as a key point, a point between the initial point and the key point is discarded, and the initial point of the sliding window is updated to be the current key point.
And 24b, performing secondary filtering treatment on the primary compressed motion state target: carry out the second grade to the track point of the motion state after the one-level compression and filter, carry out the size and the predetermined contained angle threshold value contrast of the contained angle that forms between the adjacent three track point, if be less than predetermined contained angle threshold value, then judge the middle track point in the adjacent three track point and be the jump point, then filter this jump point, and is further, adopt the mode of sliding window, judge whether other track points are the jump point, further smooth orbit.
And step 25b, compressing the motion state target track after the second-stage filtering in a linear discrimination mode. The pre-set linearity threshold used for the second stage compression is greater than the first stage compression. Because the second-stage compression threshold is larger, in order to achieve the optimal fitting error, a least square algorithm can be added, and key points are fitted.
According to the embodiment of the invention, the motion state of the track points and the linearity of the track section formed by the track points are combined, the first-stage compression and the second-stage compression are sequentially carried out on the track points, the basic principle of data compression is met under the condition of large data storage, the track compression ratio can be improved, and the authenticity of track point data is ensured.
As shown in fig. 3, an embodiment of the present invention further provides a device 30 for processing a target track, where the device 30 includes:
the acquisition module 31 is configured to acquire a track point set of a track of a target object;
the processing module 32 is configured to filter the trace point set to obtain a first-stage trace point set, where the first trace point set includes data information of each trace point; determining the motion state of each track point according to the data information of each track point in the first track point set; and compressing the first track point set according to the motion state to obtain a second track point set.
Optionally, the processing module 32 is configured to filter the trace point set to obtain a first trace point set, and includes:
obtaining a predicted position value of the track point at the time t according to the position estimation value of the track point at the time t-1 in the track point set, the speed measurement value and the course measurement value of the track point at the time t, wherein t is greater than or equal to 1, and the position estimation value of the initial track point is the position measurement value when t is equal to 1;
obtaining a position estimation value of the track point at the t moment according to the position prediction value of the track point at the t moment and the position measurement value of the track point at the t moment;
and acquiring the first track point set according to the estimation value.
Optionally, the processing module 32 obtains the predicted position value of the track point at the t moment according to the speed measurement value and the course measurement value of the track point at the t moment in the track point set and the position estimation value of the track point at the t-1 moment, and includes:
according to formula x "i＝x'i-1+vi*sin(ci)*(ti-ti-1)/cos(yi) And y "i＝y'i-1+vi*cos(ci)*(ti-ti-1) Obtaining a position predicted value of the track point at the time t;
according to a formula x'i＝x”i+α*(xi-x”i) And y'i＝y”i+α*(yi-y”i) Obtaining a position estimation value of a track point at the time t;
wherein i is less than or equal to t, t is greater than or equal to 1, and alpha is a Kalman coefficient and x'iIs a longitude estimate of the track point, y'iAs latitude estimates of the locus points, x "iIs the longitude predicted value of the track point, y "iThe latitude predicted value of the track point is taken; v. ofiAs velocity measurements of the trace points, ciIs a trackA heading measurement of a point.
Optionally, the determining, by the processing module 32, the motion state of each trace point according to the data information of each trace point in the first trace point set includes:
acquiring a subset of the first track point set within a preset time period;
obtaining the characteristic vector of the track point according to the data information of each track point in the subset;
and determining the motion state of the track point at the time t in the first track point set according to the characteristic vector.
Optionally, the data information includes at least one of:
position information of the track points;
measuring course of the track points;
velocity measurements of the trace points; time stamping of the track points;
the feature vector includes at least one of:
measuring the speed of the track point at the time t;
the track overlap ratio.
Optionally, the processing module 32, according to the motion state, compresses the first trace point set to obtain a second trace point set, and includes:
when each track point is in a static state, performing first snapshot compression on the first track point set according to a first preset time interval to obtain a first compressed track point set;
and clustering the first compressed track point set, and performing second snapshot compression according to a second preset time interval to obtain a second track point set.
Optionally, the processing module 32, according to the motion state, compresses the first trace point set to obtain a second trace point set, and includes:
when each track point is in a motion state, performing sliding window type compression on the first track point set for the first time according to the linearity of a first sliding track section of the first track point set to obtain a first compressed track point set, wherein the first sliding track section is a track section formed by the track points in the first track point set within a first preset time period;
performing sliding window type filtering processing on the first compressed track point set to obtain a second filtered track point set;
and according to the linearity of a second sliding track section of the second filtering track point set, performing second sliding window type compression on the second filtering track point set to obtain a second track point set, wherein the second sliding track section is in a second preset time period, and track sections formed by track points in the second filtering track point set are obtained.
It should be noted that the apparatus is an apparatus corresponding to the above-mentioned track processing method, and all implementation manners in the above-mentioned method embodiment are applicable to the embodiment of the apparatus, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computing device, comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the above method embodiment are applicable to this embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method as described above. All the implementation manners in the above method embodiment are applicable to this embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
Furthermore, it is to be noted that in the device and method of the invention, it is obvious that the individual components or steps can be decomposed and/or recombined. These decompositions and/or recombinations are to be regarded as equivalents of the present invention. Also, the steps of performing the series of processes described above may naturally be performed chronologically in the order described, but need not necessarily be performed chronologically, and some steps may be performed in parallel or independently of each other. It will be understood by those skilled in the art that all or any of the steps or elements of the method and apparatus of the present invention may be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or any combination thereof, which can be implemented by those skilled in the art using their basic programming skills after reading the description of the present invention.
Thus, the objects of the invention may also be achieved by running a program or a set of programs on any computing device. The computing device may be a general purpose device as is well known. The object of the invention is thus also achieved solely by providing a program product comprising program code for implementing the method or the apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is to be understood that the storage medium may be any known storage medium or any storage medium developed in the future. It is further noted that in the apparatus and method of the present invention, it is apparent that each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be regarded as equivalents of the present invention. Also, the steps of executing the series of processes described above may naturally be executed chronologically in the order described, but need not necessarily be executed chronologically. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A method for processing a trajectory of a target object, the method comprising:
acquiring a track point set of a track of a target object;
filtering the track point set to obtain a first track point set, wherein the first track point set comprises data information of each track point;
determining the motion state of each track point according to the data information of each track point in the first track point set;
and compressing the first track point set according to the motion state to obtain a second track point set.
2. The track processing method of the target object according to claim 1, wherein the step of filtering the track point set to obtain a first track point set comprises:
obtaining a predicted position value of the track point at the time t according to the position estimation value of the track point at the time t-1 in the track point set, the speed measurement value and the course measurement value of the track point at the time t, wherein t is greater than or equal to 1, and the position estimation value of the initial track point is the position measurement value when t is equal to 1;
obtaining a position estimation value of the track point at the t moment according to the position prediction value of the track point at the t moment and the position measurement value of the track point at the t moment;
and acquiring the first track point set according to the estimation value.
3. The track processing method of the target object according to claim 2, wherein obtaining the predicted position value of the track point at the time t according to the speed measurement value and the course measurement value of the track point at the time t in the track point set and the position estimation value of the track point at the time t-1 comprises:
according to the formula x ″)i＝x'i-1+vi*sin(ci)*(ti-ti-1)/cos(yi) And
y″i＝y'i-1+vi*cos(ci)·(ti-ti-1) Obtaining a position predicted value of the track point at the time t;
according to a formula x'i＝x″i+α*(xi-x″i) And y'i＝y″i+α*(yi-y″i) Obtaining a position estimation value of a track point at the time t;
wherein i is less than or equal to t, t is greater than or equal to 1, and alpha is a Kalman coefficient and x'iIs a longitude estimate of the track point, y'iIs an estimate of the latitude of the locus, x ″)iIs the longitude predicted value, y ″, of the track pointiThe latitude predicted value of the track point is taken; v. ofiAs velocity measurements of the trace points, ciThe course measurement value of the track point is obtained.
4. The track processing method of the target object according to claim 1, wherein determining the motion state of each track point according to the data information of each track point in the first track point set includes:
acquiring a subset of the first track point set within a preset time period;
obtaining the characteristic vector of the track point according to the data information of each track point in the subset;
and determining the motion state of the track point at the time t in the first track point set according to the characteristic vector.
5. The method of claim 4, wherein the data information comprises at least one of:
position information of the track points;
measuring course of the track points;
velocity measurements of the trace points; time stamp of the trace point;
the feature vector includes at least one of:
measuring the speed of the track point at the time t;
the track overlap ratio.
6. The track processing method of the target object according to claim 1, wherein the compressing the first track point set according to the motion state to obtain a second track point set comprises:
when each track point is in a static state, performing first snapshot compression on the first track point set according to a first preset time interval to obtain a first compressed track point set;
and clustering the first compressed track point set, and performing second snapshot compression according to a second preset time interval to obtain a second track point set.
7. The target track processing method according to claim 1, wherein the compressing the first track point set according to the motion state to obtain a second track point set comprises:
when each track point is in a motion state, performing sliding window type compression on the first track point set for the first time according to the linearity of a first sliding track section of the first track point set to obtain a first compressed track point set, wherein the first sliding track section is a track section formed by the track points in the first track point set within a first preset time period;
performing sliding window type filtering processing on the first compressed track point set to obtain a second filtered track point set;
according to the linearity of the second sliding track section of the second filtering track point set, the second filtering track point set is subjected to sliding window type compression for the second time, a second track point set is obtained, the second sliding track section is in a second preset time period, and the track section formed by the track points in the second filtering track point set is obtained.
8. An apparatus for processing a target track, the apparatus comprising:
the acquisition module is used for acquiring a track point set of a track of a target object;
the processing module is used for filtering the track point set to obtain a first-stage track point set, and the first track point set comprises data information of each track point; determining the motion state of each track point according to the data information of each track point in the first track point set; and compressing the first track point set according to the motion state to obtain a second track point set.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction which causes the processor to execute the corresponding operation of the method according to any one of claims 1-7.
10. A computer-readable storage medium having stored thereon instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210060144.0A CN114494327A (en) | 2022-01-19 | 2022-01-19 | Method, device and equipment for processing flight path of target object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210060144.0A CN114494327A (en) | 2022-01-19 | 2022-01-19 | Method, device and equipment for processing flight path of target object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114494327A true CN114494327A (en) | 2022-05-13 |
Family
ID=81472426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210060144.0A Pending CN114494327A (en) | 2022-01-19 | 2022-01-19 | Method, device and equipment for processing flight path of target object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494327A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116188519A (en) * | 2023-02-07 | 2023-05-30 | 中国人民解放军海军航空大学 | Ship target motion state estimation method and system based on video satellite |
| CN117831014A (en) * | 2024-03-04 | 2024-04-05 | 山西阳光三极科技股份有限公司 | Carriage transportation state monitoring method based on railway freight train |
-
2022
- 2022-01-19 CN CN202210060144.0A patent/CN114494327A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116188519A (en) * | 2023-02-07 | 2023-05-30 | 中国人民解放军海军航空大学 | Ship target motion state estimation method and system based on video satellite |
| CN116188519B (en) * | 2023-02-07 | 2023-10-03 | 中国人民解放军海军航空大学 | Ship target motion state estimation method and system based on video satellite |
| CN117831014A (en) * | 2024-03-04 | 2024-04-05 | 山西阳光三极科技股份有限公司 | Carriage transportation state monitoring method based on railway freight train |
| CN117831014B (en) * | 2024-03-04 | 2024-05-14 | 山西阳光三极科技股份有限公司 | Carriage transportation state monitoring method based on railway freight train |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114494327A (en) | Method, device and equipment for processing flight path of target object | |
| CN112883819A (en) | Multi-target tracking method, device, system and computer readable storage medium | |
| US20170007137A1 (en) | Method of estimating blood pressure based on image | |
| CN113065474B (en) | Behavior recognition method and device and computer equipment | |
| CN110059761A (en) | A kind of human body behavior prediction method and device | |
| US20160171341A1 (en) | Apparatus and method for detecting object in image, and apparatus and method for computer-aided diagnosis | |
| CN111832492A (en) | Method and device for distinguishing static traffic abnormality, computer equipment and storage medium | |
| CN107918688B (en) | Scene model dynamic estimation method, data analysis method and device and electronic equipment | |
| CN116704441A (en) | Abnormal behavior detection method and device for community personnel and related equipment | |
| CN108960286A (en) | A kind of target following localization method and device | |
| Meynard et al. | An efficient forecasting approach to reduce boundary effects in real-time time-frequency analysis | |
| CN110222734B (en) | Bayesian network learning method, intelligent device and storage device | |
| CN113869526A (en) | Data processing model performance improving method and device, storage medium and electronic equipment | |
| CN113269104A (en) | Group abnormal behavior identification method, system, storage medium and equipment | |
| CN113160279A (en) | Method and device for detecting abnormal behaviors of pedestrians in subway environment | |
| CN111784750A (en) | Method, device and equipment for tracking moving object in video image and storage medium | |
| CN116952277A (en) | Potential position estimation method and system based on artificial intelligence and behavior characteristics | |
| CN108520237B (en) | Risk behavior identification method | |
| CN103093481A (en) | Moving object detection method under static background based on watershed segmentation | |
| CN110657807A (en) | Indoor positioning displacement measurement method for detecting discontinuity based on wavelet transformation | |
| CN110738149A (en) | Target tracking method, terminal and storage medium | |
| Wu et al. | In situ evaluation of tracking algorithms using time reversed chains | |
| EP3499513A1 (en) | Determining whether a hypothesis concerning a signal is true | |
| CN114757855A (en) | Method, device, equipment and storage medium for correcting action data | |
| CN116776137A (en) | Data processing method and electronic equipment |
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 |