CN113607170B - Real-time detection method for deviation behavior of navigation path of air-sea target - Google Patents
Real-time detection method for deviation behavior of navigation path of air-sea target Download PDFInfo
- Publication number
- CN113607170B CN113607170B CN202110877457.0A CN202110877457A CN113607170B CN 113607170 B CN113607170 B CN 113607170B CN 202110877457 A CN202110877457 A CN 202110877457A CN 113607170 B CN113607170 B CN 113607170B
- Authority
- CN
- China
- Prior art keywords
- track
- target
- real
- geohash
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000011897 real-time detection Methods 0.000 title claims abstract description 13
- 230000005856 abnormality Effects 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 32
- 230000002159 abnormal effect Effects 0.000 claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 6
- 238000004088 simulation Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 101000606504 Drosophila melanogaster Tyrosine-protein kinase-like otk Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000036962 time dependent Effects 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
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 real-time detection method for the deviation behavior of the navigation path of the air-sea target is high in calculation efficiency, strong in expandability and simple to realize. The invention is realized by the following technical scheme: according to the principle of set coincidence, calculating the similarity between a target real-time track grid set and a target normal track grid set, and setting the real-time track sequence length of the air-sea target, the GeoHash coding length of the target track point and an abnormal alarm threshold value which participate in calculation; removing repeated codes according to the set code length to obtain a typical track Geohash set participating in calculation; acquiring a real-time track Geohash set, and counting real-time track points corresponding to each set element; according to the target typical track Geohash set and the target real-time track Geohash set, calculating an abnormal index value; and judging that the target has lane departure abnormality according to the set abnormality alarm threshold value, and outputting abnormality alarm gate information.
Description
Technical Field
The invention relates to the field of target state estimation, and aims to realize real-time automatic detection of the deviation of a sea target from a normal course.
Background
With the massive use of the wireless sensor network, the global satellite navigation system and other devices in the aviation and navigation fields, massive air-sea target track data (such as aircraft flight tracks, ship navigation tracks and the like) are generated, the global air-sea target track data is gradually increased at the GB level every day, various targets are mutually mixed and fallen, legal driving targets coexist with illegal moving targets, and huge pressure is brought to air-sea target monitoring. In the maritime field and in the air traffic control field, a route for normal flight is defined for an aerial target, and a route for normal navigation is also defined for a sea target; however, a typical moving track often exists in the task execution process, so that an automatic steering control course is generally adopted at sea, wherein a course keeping system measures the course deviation degree according to positioning information, and the most effective rudder angle and the rudder angle execution time are determined through calculation, so that the ship can return to a set course fastest and most fuel-saving. An aircraft implementing radar guidance may deviate from the expected actual track under the influence of high altitude wind. Whether the hull deviates from the planned course when in the automatic course tracking mode display state is indistinguishable from the ECDIS display interface because the automatic course tracking mode is a display mode that always displays the ship on the planned course, but the actual position of the ship may not be on the course. During flight path inspection, even if the drift is corrected, the aircraft may deviate from the expected course to produce yaw due to variations in air and wind and other factors such as errors in instrumentation and pilot calculations. An uncontrolled change from a normal steady flight state occurs when the flight path deviates too much, i.e., below 1000 feet AFE.
At present, target track deviation behavior identification comprises online real-time and offline non-real-time, and a judging method can be divided into three major categories, namely a method based on statistical mining, a method based on distance and a method based on machine learning. The method based on statistical mining is mainly oriented to offline non-real-time scenes, aims at finding abnormal targets in large-scale data, and the two methods are mainly oriented to online real-time scenes, and focus on real-time judgment and alarm of target abnormal conditions. The distance-based method is mainly used for judging whether the target is abnormal or not by calculating the distance between the real-time characteristic vector of the target and the characteristic vector in the normal mode. The machine learning-based method mainly utilizes models such as decision trees, support vector machines, bayesian networks and the like to automatically learn complex data structures and existing abnormal and normal modes.
The machine learning-based method is a supervised method, a large amount of target track data needs to be collected, abnormal data and normal data need to be marked manually, a training set is constructed to train a model, the learned model has poor interpretation, and even special reasoning hardware needs to be equipped, so that the application scene is limited. The distance-based method is an unsupervised method, and is mainly used for modeling the target feature vector from physical characteristics, a data set is not required to be constructed and training is not required, the principle is clear, the deployment environment is universal, and the method is widely applied in practice. At present, whether the distance method is based on single-dimensional features or combined multi-dimensional features, feature distances are measured based on Hausdorff distances, the distance between a real-time feature and each reference feature needs to be calculated, and time cost is high, so that the efficiency of real-time judgment is seriously affected.
Disclosure of Invention
Aiming at the problem of low calculation efficiency of the current distance-based detection method, the invention provides the real-time detection method for the deviation behavior of the navigation mark, which has high calculation efficiency, strong expandability, simple realization and good interpretability.
In order to achieve the above purpose, the invention provides a real-time detection method for the deviation behavior of a marine target track, which is characterized by comprising the following steps:
initial parameter setting: based on Geohash codes, converting a time track sequence of a target into a Geohash code set for a real-time monitoring scene, calculating the similarity between a target real-time track grid set and a target normal track grid set according to a set coincidence principle, and setting the real-time track sequence length of the target, the Geohash code length of the target track point and an abnormal alarm threshold value of the target participating in calculation according to an actual target track and actual detection requirements when real-time abnormal judgment of an air-sea target navigation path is implemented;
classical trace Geohash set acquisition: modeling a target feature vector based on physical characteristics, coding a target typical track point according to a set GeoHash coding length, and removing repeated codes to obtain a typical track GeoHash set participating in calculation;
real-time track Geohash set acquisition: acquiring a track Geohash set in real time in a cyclic traversal mode, converting a real-time track sequence into the Geohash set according to a set Geohash coding length by a typical track, and counting and recording real-time track points corresponding to elements of each set;
calculating an abnormality index value: according to the target typical track Geohash set and the target real-time track Geohash set, calculating an abnormal index value;
abnormality judgment: judging whether the abnormality index value is smaller than the set threshold value according to the set abnormality alarm threshold value, judging whether the course deviation condition occurs according to the proportion that the observed target track points fall into the typical track peripheral area, judging the target with similarity value exceeding the set threshold value as the course abnormality target, judging that the target has course deviation abnormality, outputting abnormality alarm gate information, otherwise, directly returning and waiting for the input of a new track point.
Compared with the prior art, the invention has the following beneficial effects:
the calculation efficiency is high. The method is based on the Geohash code, and is oriented to a real-time monitoring scene, the time track sequence of the target is converted into a simple Geohash code set, and the similarity between the target real-time track grid set and the target normal track grid set is calculated according to the set coincidence principle, so that the real-time update calculation of the space distance is avoided, the calculation complexity is greatly reduced, and the real-time calculation efficiency is improved.
The realization is simple and the interpretability is good. The invention adopts an unsupervised method based on distance, models the target feature vector from physical characteristics, does not need to construct a data set and train, has clear principle and general deployment environment, and has the characteristics of simple realization, good interpretability and no need of marking data.
And the expandability is strong. The method can be easily expanded to the condition that a plurality of typical tracks exist in the target, and can support the real-time monitoring of application scenes of large-scale air-sea targets in a wide area range by respectively applying the method to each typical track in a circulating traversing mode, so that the method has higher engineering application value.
The method is particularly suitable for monitoring scenes with definite monitoring targets and preset tracks or classical tracks of the targets.
Drawings
FIG. 1 is a schematic diagram of a real-time detection flow of the off-track behavior of the marine target in the air.
FIG. 2 is a schematic diagram of real-time trajectory and typical trajectory of a sea target in a simulation experiment according to the present invention.
FIG. 3 is a graph of the real-time trajectory versus typical trajectory spacing for an air-sea target of the present invention.
Fig. 4 shows the change of the similarity index of the target track of the sea and the air over time.
The invention will be further described with reference to the drawings and examples.
Detailed Description
See fig. 1. According to the invention, the following steps are used:
step 1: initial parameter setting: when the real-time anomaly determination of the air-sea target course is implemented, setting the real-time track sequence length of the air-sea target, the GeoHash coding length of the target track point and the anomaly alarm threshold value which participate in calculation according to the actual target track and the actual detection requirement;
step 2: classical trace Geohash set acquisition: coding a target typical track point according to the set GeoHash coding length, and removing repeated codes to obtain a typical track GeoHash set participating in calculation;
step 3: real-time track Geohash set acquisition: converting the real-time track sequence into a GeoHash set according to the set GeoHash coding length, and counting and recording the real-time track points corresponding to each set element;
step 4: calculating an abnormality index value: according to the target typical track Geohash set and the target real-time track Geohash set, calculating an abnormal index value;
step 5: abnormality judgment: judging whether the abnormality index value is smaller than the set threshold value according to the set abnormality alarm threshold value, and judging whether the course deviation condition occurs according to the proportion of the observed target track points falling into the periphery area of the typical track. And judging the target with the similarity value exceeding the set threshold value as a course abnormal target, judging that the target has course deviation abnormality, outputting abnormality warning gate information, otherwise, directly returning and waiting for the input of a new track point.
When the real-time abnormality determination of the air-sea target course is implemented, the initial parameters to be set include: real-time track sequence length m of air-sea target and GeoHash coding length L of target track point g And an abnormality warning threshold value EL, which can be set according to actual conditions. For example, for the target real-time track sequence length m participating in calculation, the target real-time track sequence length m can be determined by comprehensively considering factors such as a time monitoring window, a target real-time update rate and the like; for the GeoHash coding length, if the average distance of the real-time track of the target, which deviates from the normal track, is less than or equal to 3km, L is equal to g May be set to 5. In particular, for the setting of the abnormality alert threshold EL, it may be performed according to the following heuristic:
for the case where the target real-time trajectory point is completely prohibited from deviating from the normal trajectory specification range, the EL value may be set to 1; for the case of allowing the exception to occur to the target real-time track points, the calculation can be performed according to the proportion of the number of acceptable exception track points to the length m of the target real-time track sequence participating in the calculation. Generally, EL can be set to 0.8, i.e., at most 20% of outliers are allowed to occur, that is, when more than 80% of the locus points fall within the normal locus region, the target is considered to have no abnormality.
In the classical locus GeoHash set acquisition, the set GeoHash coding length L can be used for g Coding the target typical track points, and removing repeated codes to obtain a typical track T participating in calculation typical Corresponding GeoHash code set (T typical )：Wherein (1)>The ith element of the set is encoded for GeoHash. The information such as the air route, the offshore route, the typical route and the like can be preset, and can be summarized and extracted from the historical track data of the target.
GeoHash coding is a kind of geocoding that divides a space into grids, and its core idea is to recursively alternate two earth longitudes and latitudes along the longitude and latitude directions, and convert two-dimensional longitude and latitude coordinates into one-dimensional character strings. In the embodiment, a Z-order space filling curve is adopted to carry out GeoHash encoding on the target track. The main steps of GeoHash coding include binary coding, group coding and Base32 transcoding:
1) Binary encoding: recursively alternating in half along the longitudinal and latitudinal directions. The target longitude falls to the left with 0, falls to the right with 1, the target latitude falls to the upper with 0, and falls to the lower with 1. Since the latitude is 2 times greater than the longitude, the longitude may generally be encoded 1 bit more to keep the latitude and longitude errors as balanced as possible.
2) Group codes: the lowest bit is the 0 th bit, the longitude is put in the even bit and the latitude is put in the odd bit from the low bit, and the longitude and latitude binary codes are coded into a new string.
3) Base32 coding: for simplicity of storage and use, the combined binary codes are converted into Base32 character strings by taking 5 bits as a group, each Base32 character string consists of 0-9,b-z and 32 letters without a, i, l and o, and the length of the character string is the length of the Geohash code of the target track point. It should be noted that, since each Base32 character is represented by 5 binary digits, the number of binary coded bits after the group code must be a multiple of 5.
The length of the GeoHash code determines the accuracy of the trellis, with longer codes being more accurate. The relationship between the GeoHash encoding length and the longitude and latitude binary bit number and the grid precision is shown in table 1.
Table 1 Base32 encodes the corresponding number of longitude and latitude bits and the grid accuracy,
for a target track, a set of Geohash codes can be used to characterize: under the condition of designating the coding length, the GeoHash coding of each track point is obtained, and then the repeated elements are de-duplicated to obtain a GeoHash coding set thereof.
In the calculation of the real-time track point Geohash coding, the target has m track points according to the current moment, and the Geohash coding is carried out on the real-time track of the target. According to the set GeoHash coding length L g Real-time track sequence of target
Conversion to a Geohash code set (T r ) And counting and recording the real-time track point number a corresponding to each set element i
Wherein,for the ith track point of the object, r represents the real-time track identity, < >>And the j-th coding set element, and n is the number of the set elements after conversion.
In the calculation of the abnormal index value, defining a similarity parameter between the real-time track of the target and the typical track of the target, wherein the similarity parameter adopts the following calculation formula:according to this formula, the set (T r ) And a Geohash code set (T typical ) The coincidence index R between the real-time track and the typical track of the target can be calculated s ，
Wherein a is k Is the kth set elementCorresponding track points.
In the abnormality judgment, according to the set abnormality warning threshold value, when the following conditions are established: coincidence index R s＜ EL, judging that the route deviation abnormality occurs in the target, outputting alarm information, otherwise, directly returning to wait for the input of a new track point.
The effect of the invention is further described below in connection with simulation experiments;
see fig. 2-4. In the simulation test, the invention uses the actual measurement track data of a typical aerial target to carry out experimental analysis, and desensitizes the target track data: the real track is offset to be used as a normal track, and the normal track is offset, resampled and the like, so that the real-time track of the target is obtained. The real-time track and the normal track of the target are shown in figure 3, wherein the real-time track update rate of the target is about 2s, and the track point number is about 3300; the normal track update rate is about 5s, and the track point number is 1110 points. As can be seen from fig. 2, there is a serious deviation between the real-time trajectory of the target and the typical trajectory.
Fig. 3 shows the time-dependent change of the distance between the target real-time track point and the classical track. It can further be derived from fig. 3 that the target assumes a state of motion of moving away-then closer-then further away during a period of time.
The invention calculates the similarity index between the target real-time track and the typical track based on the target track deviation behavior real-time detection step, and gives the change condition of the target real-time track and the typical track along with time, as shown in fig. 4. In the simulation experiment, the length m of the target real-time track sequence participating in calculation is set to be 30, and the GeoHash coding length L g Set to 5 and el value set to 0.8. As can be seen from fig. 4, when the real-time track of the target starts to deviate from the typical track, it can be easily determined that the target has an abnormal course according to the set threshold value of 0.8; along with the start of slow regression of the target on the typical track, the similarity index of the target is gradually improved, which indicates that the deviation degree is smaller and is consistent with the distance change trend of the target and the typical track.
In order to verify the calculation efficiency of the method, the method utilizes the data to carry out comparative analysis on the time efficiency of the method and the classical method based on Hausdorff distance in an experimental mode. The experimental configuration used is shown in table 2:
| type(s) | Configuration of |
| Operating system | win7 bit 32 |
| CPU | intel i5-6500@3.2GHz |
| Memory | 4G |
| Development environment | Scilab 6.1 |
| Programming mode | Programming of matrix as main |
To reduce the randomness of statistics, the invention performs 10 experiments and takes the average value as an experiment result. Through experiments, the average time for comprehensively completing real-time abnormality judgment of a target route is 0.26s, and the average time of a classical method based on Hausdorff distance is 1.5s, so that the method has higher calculation efficiency and is about 5.7 times of that of the classical distance method.
The invention is not described in detail in part as being common general knowledge to a person skilled in the art. Those of ordinary skill in the art will appreciate that the foregoing embodiments are provided to aid the reader in understanding the principles of the present invention, and that the scope of the invention is not limited to such specific statements and embodiments. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (6)
1. A real-time detection method for the deviation behavior of a marine target track is characterized by comprising the following steps:
initial parameter setting: based on Geohash codes, converting a time track sequence of a target into a Geohash code set for a real-time monitoring scene; according to the principle of set coincidence, calculating the similarity between a target real-time track grid set and a target normal track grid set, and then setting the real-time track sequence length of the air-sea target, the Geohash coding length of the target track point and an abnormal warning threshold value which participate in calculation according to the actual target track and the actual detection requirement when the real-time abnormal judgment of the air-sea target navigation path is implemented;
classical trace Geohash set acquisition: modeling a target feature vector based on physical characteristics, coding a target typical track point according to a set Geohash coding length, and removing repeated codes to obtain a typical track Geohash set participating in calculation;
real-time track Geohash set acquisition: acquiring a track Geohash set in real time in a cyclic traversal mode, converting a real-time track sequence into the Geohash set according to a set Geohash coding length, and counting and recording real-time track points corresponding to elements of each set;
calculating an abnormality index value: according to the target typical track Geohash set and the target real-time track Geohash set, calculating an abnormal index value;
abnormality judgment: judging whether an abnormality index value is smaller than a set threshold value according to the set abnormality alarm threshold value, judging whether a lane departure abnormality occurs according to the proportion of the observed target track points falling into the surrounding area of the typical track, outputting abnormality alarm gate information, otherwise, directly returning to wait for the input of a new track point;
when the real-time abnormality determination of the air-sea navigation path is implemented, initial parameters to be set include: real-time track sequence length of air-sea target involved in calculationTarget track point Geohash coding Length +.>And an abnormality alert threshold value EL;
in the calculation of real-time track point Geohash codes, the targets are shared according to the current timePerforming Geohash coding on the target real-time track according to the track points, and performing +_on according to the set Geohash coding length>Real-time track sequence of targetConversion to the Geohash coding set +.>And counting and recording the real-time track points corresponding to each set element>Computing Geohash coding set +.>：
Wherein,for the%>Track points->Representing real-time track identity>For the target real-time track sequence length, < > and->Is->Encoding set elements, < >>The number of the elements is the number of the converted set;
in the calculation of the abnormal index value, defining the similarity parameter between the real-time track of the target and the typical track of the target, and utilizing the Geohash coding set of the real-time track of the targetAnd the typical track Geohash coding set +.>Calculating coincidence index between real-time track and typical track of target +.>：
Wherein,is->Personal collection element->Corresponding track points.
2. The real-time detection method for the deviation behavior of the marine target track according to claim 1, wherein the method comprises the following steps: setting the EL value to be 1 for the situation that the real-time track point of the forbidden target deviates from the normal track designated range; for the situation that the exception is allowed to occur to the target real-time track points, the number of the acceptable exception track points accounts for the length of the target real-time track sequence participating in calculationIs calculated by the ratio of (2).
3. The real-time detection method for the deviation behavior of the marine target track according to claim 1, wherein the method comprises the following steps: in the acquisition of a classical locus Geohash set, according to a set Geohash coding lengthCoding the target typical track point, and removing repeated codes to obtain a typical track participating in calculation +.>Corresponding Geohash coding set +.>：
Wherein,coding set +.>Element(s)>Representing a typical track identity.
4. The real-time detection method for the deviation behavior of the marine target track according to claim 1, wherein the method comprises the following steps: dividing the space into the geocoding of grids, recursively alternating the longitude and latitude of the earth along the longitude and latitude directions, converting the two-dimensional longitude and latitude coordinates into one-dimensional character strings, and carrying out Geohash coding on the target track by adopting a Z-order space filling curve.
5. The real-time detection method for the deviation behavior of the marine target track according to claim 1, wherein the method comprises the following steps: geohash coding includes binary coding, group coding, and Base32 transcoding; binary encoding: recursively and alternately halving along the longitude and latitude directions, wherein the target longitude falls to the left interval to be 0, falls to the right interval to be 1, falls to the upper interval to be 0, and falls to the lower interval to be 1; group codes: taking the lowest bit as the 0 th bit, starting from the low bit, placing longitude by an even bit, placing latitude by an odd bit, and coding the longitude and latitude binary code into a new string; base32 coding: for simplicity of storage and use, the combined binary codes are converted into Base32 character strings by taking 5 bits as a group, each Base32 character string consists of 0-9 and b-z which do not contain a, i, l, o and is composed of 32 letters, and the length of the character string is the length of the Geohash code of the target track point.
6. The real-time detection method for the deviation behavior of the marine target track according to claim 1, wherein the method comprises the following steps: and (3) under the condition of designating the coding length, solving the Geohash coding of each track point for the target track, and then performing de-duplication on the repeated elements to obtain a Geohash coding set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110877457.0A CN113607170B (en) | 2021-07-31 | 2021-07-31 | Real-time detection method for deviation behavior of navigation path of air-sea target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110877457.0A CN113607170B (en) | 2021-07-31 | 2021-07-31 | Real-time detection method for deviation behavior of navigation path of air-sea target |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113607170A CN113607170A (en) | 2021-11-05 |
| CN113607170B true CN113607170B (en) | 2023-12-12 |
Family
ID=78306367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110877457.0A Active CN113607170B (en) | 2021-07-31 | 2021-07-31 | Real-time detection method for deviation behavior of navigation path of air-sea target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113607170B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113932816B (en) * | 2021-11-16 | 2023-09-22 | 北京中科海讯数字科技股份有限公司 | Flight path optimization method based on underwater sound data comprehensive situation |
| CN116052482B (en) * | 2023-04-03 | 2023-06-23 | 中航信移动科技有限公司 | Method for early warning of aircraft track yaw, electronic equipment and storage medium |
| CN116300967B (en) * | 2023-05-12 | 2023-08-04 | 威海海洋职业学院 | RFID-based ocean fishing boat track cruising method and system and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017162084A1 (en) * | 2016-03-25 | 2017-09-28 | 阿里巴巴集团控股有限公司 | Method and device for analyzing data similarity |
| CN110471938A (en) * | 2019-06-28 | 2019-11-19 | 安徽四创电子股份有限公司 | A method of Stream Processing and real-time retrieval towards magnanimity track data |
| CN110609881A (en) * | 2019-08-28 | 2019-12-24 | 中山大学 | Vehicle trajectory deviation detection method, system and storage medium |
| CN111209457A (en) * | 2019-12-24 | 2020-05-29 | 中国科学院电子学研究所苏州研究院 | Target typical activity pattern deviation warning method |
| CN112100308A (en) * | 2020-11-02 | 2020-12-18 | 中科星图股份有限公司 | Similarity query method for Beidou space-time trajectory |
-
2021
- 2021-07-31 CN CN202110877457.0A patent/CN113607170B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017162084A1 (en) * | 2016-03-25 | 2017-09-28 | 阿里巴巴集团控股有限公司 | Method and device for analyzing data similarity |
| CN110471938A (en) * | 2019-06-28 | 2019-11-19 | 安徽四创电子股份有限公司 | A method of Stream Processing and real-time retrieval towards magnanimity track data |
| CN110609881A (en) * | 2019-08-28 | 2019-12-24 | 中山大学 | Vehicle trajectory deviation detection method, system and storage medium |
| CN111209457A (en) * | 2019-12-24 | 2020-05-29 | 中国科学院电子学研究所苏州研究院 | Target typical activity pattern deviation warning method |
| CN112100308A (en) * | 2020-11-02 | 2020-12-18 | 中科星图股份有限公司 | Similarity query method for Beidou space-time trajectory |
Non-Patent Citations (4)
| Title |
|---|
| Bidirectional Mapping Trajectory Similarity Measurement Algorithm Based on Geohash Grid;Zhihao Ji;《2021 6th International Symposium on Computer and Information Processing Technology (ISCIPT)》;全文 * |
| 一种目标航路实时异常快速判定方法;张海瀛;《舰船电子工程》;第41卷(第12期);全文 * |
| 基于GeoHash的电磁大数据航迹挖掘;李高云;《电子信息对抗技术》;第35卷(第4期);全文 * |
| 移动轨迹的异常检测及其聚类研究;胡开喜;《中国优秀硕士学位论文全文数据库信息科技辑》(第4期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113607170A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113607170B (en) | Real-time detection method for deviation behavior of navigation path of air-sea target | |
| Liu et al. | Predicting aircraft trajectories: A deep generative convolutional recurrent neural networks approach | |
| CN111159924B (en) | Method and apparatus for predicting drift trajectory | |
| CN107133269A (en) | Frequent location track generation method and device based on mobile target | |
| Zhang et al. | Enhance the AIS data availability by screening and interpolation | |
| CN107340516B (en) | Combined logic fast track starting method based on Doppler velocity | |
| CN110906935B (en) | Unmanned ship path planning method | |
| Naus | Drafting route plan templates for ships on the basis of AIS historical data | |
| CN113516037B (en) | Marine vessel track segment association method, system, storage medium and equipment | |
| CN113283653B (en) | Ship track prediction method based on machine learning and AIS data | |
| CN113887789B (en) | Improved ship track prediction method and device based on cyclic neural network | |
| CN104008403B (en) | A kind of SVM（Vector machine）The multi-targets recognition decision method of pattern | |
| Qin et al. | Trajectory prediction based on long short-term memory network and Kalman filter using hurricanes as an example | |
| Xu et al. | Trajectory clustering for SVR-based Time of Arrival estimation | |
| Dalang et al. | Stochastic optimization of sailing trajectories in an upwind regatta | |
| CN114660561A (en) | AIS and radar track association method and device | |
| CN112556698B (en) | Ship behavior change and abnormality identification method, equipment and medium | |
| CN116502777B (en) | Transformer-based four-dimensional track long-time prediction method and device | |
| Wang et al. | Classification of ship trajectories by using naive Bayesian algorithm | |
| Cheng et al. | A uuv target detection method based on informer | |
| CN116543603A (en) | Flight path completion prediction method and device considering airspace situation and local optimization | |
| CN116258252A (en) | Aircraft track prediction method, storage medium and equipment based on attention mechanism | |
| CN112767445B (en) | Ship target tracking method for video | |
| CN114255616A (en) | Unpowered ship track prediction method, device, equipment and storage medium | |
| Giffard-Roisin et al. | The 2018 climate informatics hackathon: Hurricane intensity forecast |
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 |