CN105785411A - Abnormal locus detection method based on area division - Google Patents
Abnormal locus detection method based on area division Download PDFInfo
- Publication number
- CN105785411A CN105785411A CN201610102351.2A CN201610102351A CN105785411A CN 105785411 A CN105785411 A CN 105785411A CN 201610102351 A CN201610102351 A CN 201610102351A CN 105785411 A CN105785411 A CN 105785411A
- Authority
- CN
- China
- Prior art keywords
- track
- abnormal
- territory element
- region
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention brings forward an abnormal locus detection method based on area division. The method comprises the following steps: classifying a historical locus of a moving object, and then dividing an area where normal locus data is located; performing area unit expansion processing on the locus after the area division; performing area division and expansion processing on a locus to be detected; querying a locus set of the same initial area unit and the same termination area unit which a normal locus has with the locus to be detected, detecting a support rate of each composition area unit of the locus to be detected in a normal locus set, and the area units with low support rates going into abnormal area unit sets; and comparing a relation between the quantity of the abnormal area unit sets and the quantity of the composition area units of the locus in the normal locus set, determining an abnormal condition of the locus to be detected, and then deciding whether it is necessary to perform further re-division detection on a locus area. According to the invention, the area re-division detection is carried out according to the actual condition of the locus, and thus the detection accuracy and the efficiency are improved.
Description
Technical field
The invention belongs to mobile internet technical field, relate to the use of machine learning algorithm and be analyzed the abnormal conditions of GPS track data in Mobile solution processing, be specifically related to a kind of abnormal track-detecting method divided based on region.
Background technology
In recent years, the development of the technology such as satellite communication, GPS device, RFID, wireless senser, Internet of Things communication, video tracking monitoring and extensive use so that the Mobile solution of all size in global range is all comparatively accurately positioned and effectively follows the tracks of.By these technology, signal receiver can collect the track data of a large amount of mobile subscriber the terminal of location, these data contain very abundant information, and As time goes on, data volume can become more and more huger, complicated, and the mass data of collection further expands in the urgent need to research worker and analyzes flexibly.
According to the DouglasM.Hawkins definition to abnormity point: one is observed a little too much with away from other, to such an extent as to thinks the observation station that another one diverse ways generates.Therefore the purpose of abnormal track detection is to detect the track different from major part track.The abnormality detection of track can be classified according to the historical track that mobile subscriber itself produces, pick out wherein normal track as the standard of detection, namely according to the historical movement path analyzing mobile subscriber oneself, detect the abnormal track different from major part track；Abnormal track detection can also be carried out according to the track that One-male unit user produces, according to analyzing the historical track that user group produces, detect track produced by the single mobile subscriber with user group with different tracks.In the life of reality, two kinds of methods have the scene of each self application, and such as restricted movement user fields such as urban transportation, logistics transportations, the movement locus of mobile subscriber is set in advance mostly, and abnormal track is exactly that mobile subscriber deviate from normal trace set in advance；Air particle clouds motion, animal migrates, the track of the untethered mobile subscribers such as the motion of individual is not then set in advance, normal trace storehouse can be set up according to its historical trajectory data, again by detected track compared with historical track, deviation historical trajectory data arrival is considered as then to a certain degree abnormal track.Use different methods for detection in different scenes in real life, have more practical significance.The abnormal motion majority of mobile subscriber is unexpected, it is possible to can cause huge economic loss, even can threaten the security of the lives and property of people.In order to analyze the active characteristics of mobile subscriber better, hold the activity trend of mobile subscriber and the feature of environment thereof, be necessary for the track data to mobile subscriber and carry out system, effectively analysis and excavate.
How to utilize and analyze these huge and the Mobile solution of complexity data and become a great problem of ongoing research area, be also a big focus of research simultaneously.Having numerous researcher to carry out abnormality detection for the user's GPS track data gathered at present, its method substantially has: Statistics-Based Method, based on the method for distance, density based method and based on the method for the degree of depth.These methods suffer from respective shortcoming and advantage, it is also possible to detect the track that user is abnormal to a certain extent, but these researchs come with some shortcomings.(1) many and assorted data are directly processed, while causing the loss of track characteristic data, also without being guaranteed in the accuracy rate of efficiency and detection；(2) not according to the practical situation of track, make the detection algorithm cannot more efficiently and save time.
Summary of the invention
Given this it is an object of the invention to provide a kind of abnormal track-detecting method divided based on region, its main thought substantially can be divided into four steps: classifies according to the historical trajectory data of target (untethered Mobile solution), summarize the feature of normal trace, then normal trace and track data to be detected are carried out region division process on geographical position, impact due to gps data sample frequency and mobile object translational speed, the track data that division was processed is extended, so make many and the data of complexity become simple and don't lose the feature of necessity；Then travel through territory element set and normal trace territory element set, the abnormal conditions of comparison domain unit of track to be detected, detect the abnormal conditions of track from local feature；Determine whether track is abnormal track according to abnormal area unit set and normal trace set track regions cell-average length, and point out that abnormal sub-trajectory occurs track；Finally, the different characteristic according to track, it is proposed that the detection of the abnormal track that region is subdivided so that detection efficiency is higher, provide the user more efficient, accurately better service with real-time.
The present invention adopts the following technical scheme that a kind of abnormal track-detecting method divided based on region to achieve these goals, it is characterized in that, comprises the following steps:
Step one: the GPS historical trajectory data of user is carried out normal trace data and the classification of abnormal track data, extracts the rail track feature of normal trace data, by carrying out region division on normal trace data position in the ground, obtain track data region.The rail track feature of described extraction normal trace data includes the longitude of track, the latitude of track and timestamp.
Step 2: ready-portioned for step one track data region is carried out track data territory element extension, obtains historical track territory element sequence library.
Step 3: track data to be detected is carried out region and divides acquisition track regions unit sequence tr to be measuredcheck={ g1,g2,...,gn, wherein gnRepresent the territory element that track to be detected is passed, n represents territory element sequence number, finding the unit identical with the initiation region unit of track regions to be measured unit sequence from historical track territory element sequence library is starting point, the unit identical with the termination area unit of track regions to be measured unit sequence is terminal, forms normal trace set TR={tr1,tr2,tr3,...,tri, wherein i is number | TR |, the tr of track in TRiRepresent i-th track.tri={ gi1,gi2,gi3,...,gij, gijRepresent track triThe jth territory element of process.
Step 4: travel through track regions unit sequence tr to be detectedcheckIn each unit lattice track, obtain each cell supporting rate in normal trace set TR, and compared with threshold value, obtain abnormal area unit set A (gi)。
Step 5: according to normal trace set TR and abnormal area unit set A (gi) length relation judge the abnormal conditions of track to be detected.
In order to reduce the energy consumption of detection and reduce the time of detection, present invention additionally comprises the GPS historical trajectory data to user and track data to be detected carries out that region is subdivided and the step of abnormality detection.
Specifically, the extension of described track data territory element includes, and the territory element adjacent with track data region is concluded in track data region, obtains historical track territory element sequence library.
In order to implement the present invention better, track abnormality detection in described step 4 particularly as follows:
S41: traversal trcheckEach compositing area list, with normal trace set TR={tr1,tr2,tr3,...,triIn track tri={ gi1,gi2,gi3,...,gijTerritory element compare, if track triWith trcheckThere is identical territory element, then by track triRecord and deposit into track set Inc (TR, trcheck)。
S42: for each territory element gi of track to be detected, calculate Inc (TR, the tr of each territory elementcheck) tracking quantity proportion function in normal trace set TR,Judge whether this territory element is track tr according to proportion functioncheckIn normal trace point, as Sup (Tr, trcheck) < θ, θ are threshold value, 0≤θ≤1, and this territory element is put into abnormal area unit set A (gi) in, and as Sup (Tr, trcheckThis territory element is put into normal region unit set N (g by) >=θi) in.
In above scheme, the abnormal conditions method of described judgement track to be detected is:
Obtain abnormal area unit set A (gi) after, when the quantity of abnormal area unit | A (gi) | more than one preset valueTime, i.e. abnormal area unit set A (gi) number of elements | A (gi) | time more, this track is abnormal；Otherwise, this track is normal.
To described abnormal area unit set A (gi) carry out abnormal when judging, adopt and calculate exceptional value R (trcheck) mode judge, exceptional valueWherein α is constants, and k is the constant relevant to the meansigma methods of the territory element number of the normal trace each track of set TR.
Then the local of track has been carried out abnormality detection by track data carries out region division process by the present invention, avoiding and whole track causes as elementary cell local anomaly feature probably uncared-for situation in the global property of track, the abnormal sub-trajectory of one track of detection has more meaning in actual applications；Meanwhile, method has carried out the subdivided detection in region according to the practical situation of track, improves Detection accuracy and efficiency.
Track has been carried out region division by the present invention, the input of track Outlier Detection Algorithm is territory element, the process of track raw GPS data point is changed into the process to track territory element, greatly reduces the time complexity of track abnormality detection, so that the detection time is shorter, in hgher efficiency；The abnormal conditions that track is overall can not only be detected by the present invention, also can detect and abnormal sub-trajectory occurs；Furthermore present invention uses multi-level region partitioning method, according to the concrete condition of track initial data, track is carried out more careful division and comprehensively detection, reduce algorithm to the loss of abnormal track and the false drop rate to normal trace.
Accompanying drawing explanation
Above-mentioned and/or the additional aspect of the present invention and advantage, in conjunction with the accompanying drawings below description to embodiment will be apparent from easy to understand, wherein:
Fig. 1 is the overall flow structural representation of the present invention；
Fig. 2 is that track of the present invention carries out region division schematic diagram；
Fig. 3 is that region of the present invention divides detection algorithm flow chart.
Detailed description of the invention
Being described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar implication from start to finish.The embodiment described below with reference to accompanying drawing is illustrative of, and is only used for explaining the present invention, and is not considered as limiting the invention.
As it is shown in figure 1, the invention provides a kind of abnormal track-detecting method divided based on region, including: the GPS historical trajectory data of Mobile solution being classified, extracts feature, the trajectory map that track region carries out region division processes；Then the track data after carrying out region division is carried out territory element extension, make up the sample frequency of GPS track data and move the track characteristic extraction error that object translational speed diversity causes；Track data to be detected is carried out region division and from normal trace sequence library, extracts the track data set TR that initiation region unit with it is identical with termination area unit；Travel through the territory element track of trajectory map to be detected, obtain each territory element supporting rate in normal trace set, and compared with threshold value, obtain abnormal area unit set A (gi)；Judge the abnormal conditions of track to be detected, according to the track in set TR and set A (gi) length | A (gi) | relation judges the abnormal conditions of track to be detected, carries out the track abnormality detection that region divides again.Specifically comprise the following steps that
S1: the GPS historical trajectory data of mobile subscriber is classified, extracts normal trace data track characteristic, the track extracting feature carries out region and divides mapping process.
S2: the track after step S1 is processed carries out track data territory element extension, the track characteristic that the diversity of the sample frequency and mobile object velocity of revising GPS track data causes extracts error, obtains algorithm data input.
S3: track data to be detected carried out region division process and extracts the track data that initiation region unit is identical with termination area unit with it from normal trace sequence library, obtaining normal trace set TR.
S4: travel through the cell track obtained after track regions to be detected divides, obtain each cell supporting rate in normal trace set, and compared with threshold value, obtain abnormal area unit set A (gi)；
S5: judge the abnormal conditions of track to be detected, according to set TR and set A (gi) length relation judge the abnormal conditions of track to be detected.
S6: carry out according to the concrete condition of GPS track data that region is subdivided and abnormality detection.
The present invention is that the GPS track data to mobile terminal collection carry out abnormal detection, is possible not only to the abnormal conditions of whole track are differentiated, and may indicate that abnormal sub-trajectory occurs track；And according to the concrete condition of track, track can being carried out the abnormality detection that region is subdivided, due to the abnormality detection that region is subdivided, efficiency of algorithm obtains a degree of raising, and the detection time is shorter, in hgher efficiency.There is using value in practice more.
The sample of the present invention is the historical track of mobile object, and GPS track historical data is classified, and extracts the longitude of track, latitude and timestamp, pi(longitude, latitude, time), piRepresenting the GPS raw data points of motion track, it is to comprise longitude, latitude and three basic information of timestamp.Then track collection area scope being divided into the territory element specifying size, the scope of each territory element being scanned for, if there is tracing point piSo this territory element is the ingredient of the track after track regions divides, without tracing point piThen this cell is not then the ingredient of track；Track data is carried out GPS track data after region division processes and has become the set Tr=(g being made up of territory elementi)。
Territory element lattice after dividing have been carried out extension process by the present invention, reason due to the sample frequency of gps data, even the same track, region may obtain different territory element set after dividing, carry out cell detection time, may be abnormal track by wherein normal track detection, cause testing result and practical situation not to meet.In order to solve this situation, it is necessary to being extended for track after region is divided, territory element adjacent thereto is also concluded in the unit set of track regions, timestamp is the same.
The abnormal track-detecting method that the present invention divides based on region, extract the normal trace set of identical initiation region unit and termination area unit: the track to be detected according to input, region obtains initiation region unit and the termination area unit of this track after dividing, then from normal trace sequence library to the identical track group of beginning and end, these tracks group form track set TR.Then normal trace set TR={tr is obtained1,tr2,tr3,...,tri, wherein i is number | TR |, the TR of track in TR and track tr to be detectedcheck={ g1,g2,g3,...,giAs the input of detection algorithm.
The abnormal track-detecting method that the present invention divides based on region, track abnormality detection stage etch:
S41: to trcheck={ g1,g2,g3,...,giCarry out abnormal conditions detection time, travel through trcheckEach compositing area cell, with normal trace set TR={tr1,tr2,tr3,...,triIn track tri={ gi1,gi2,gi3,...,gijTerritory element compare, travel through trcheckIn each territory element, TR={tr1,tr2,tr3,...,triWhether there is track triWith trcheckThere is identical territory element.If there is such track tri, then by track triDeposit into track set Inc (TR, trcheck) in, wherein Namely the quantity of each later territory element of trajectory map to be detected track identical with track regions unit in normal trace set is calculated.Track set Inc (TR, trcheck) weigh track tr to be detectedcheckTerritory element g with normal trace set TR (identical initiation region unit and termination area unit)iSituation about overlapping.
S42: for each compositing area unit g of track to be detectediThere are corresponding set Inc (TR, a trcheck), calculate Inc (TR, the tr of each territory elementcheck) tracking quantity | Inc (TR, trcheck) | the proportion accounted in normal trace set TR, define a threshold θ (0≤θ≤1) according to practical situation simultaneously and judge the effect that track is abnormal of proportion.Proportion functionJust can determine whether whether this territory element is track tr according to proportion functioncheckIn normal trace point, as Sup (Tr, trcheck) < this territory element is put into abnormal area unit set A (g by θi) in, and as Sup (Tr, trcheckThis territory element is deposited into normal region unit set N (g by) >=θi) in, this territory element is the normal segments of track.Namely when the territory element of track obtain the support of more track time be considered as the normal part of track, but the less part obtaining normal trace support is considered as unusual part, after whole piece track has all detected, it is possible to obtain abnormal area unit set A (gi) and normal region unit set N (gi), wherein i is A (gi) in the number of territory element set | A (gi)|。
The abnormal track-detecting method that the present invention divides based on region, it is judged that the abnormal conditions method of track to be detected is:
S51: obtain abnormal area unit set A (gi) after, the detection of the abnormal conditions of track is converted to the abnormal area element number problem to the territory element forming path, when the quantity of abnormal area unit | A (gi) | more than one preset valueTime,Value be usually track to be detected composition territory element quantity 1/2, i.e. abnormal area unit set A (gi) number of elements | A (gi) | time more, this track is abnormal；Otherwise, this track is normal.
S52: exceptional value determining type is as follows:Wherein α is constants, and k is the constant relevant to the meansigma methods of the territory element number of the set each track of TR.The judgement of track abnormal conditions is not only needed to detect the number of abnormal area unit | A (gi) |, also have the average length of the track of normal trace set, so more conform to the situation of reality, it is to avoid erroneous judgement.Average length according further to the track of normal trace set can also avoid following a kind of special situation, and the accuracy of the detection being is higher.
The present invention further optimizes detection algorithm, when GPS track carries out region division mapping, the length of side of territory element is changeless, also just says that the size of territory element is constant, the type that the size of territory element is according to gps data determines, very big deviation will not occur the result of detection.But when territory element is less, the territory element opposed area unit larger amt of composition track wants many, and the place of territory element is comprehended and causes more energy consumption and time loss by detection algorithm, can be also higher to the performance requirement of system.The present invention proposes a kind of based on the subdivided detection method in region according to the practical situation of track, reduces the energy consumption of detection and reduces the time of detection.The basic thought of method is first by bigger territory element, track to be detected, so can just can detecting track obvious for some off-notes when territory element is bigger, it is made without the process that territory element is less, the territory element of the track of composition increases, the amount of calculation that the algorithm of abnormality detection needs increases, and the requirement of time is also increased by the increase of amount of calculation accordingly, if online detection, then will result in ageing bad effect.The subdivided abnormal track detection algorithm in region that the present invention adopts will reduce the power consumption of system to a certain extent and make the ageing of detection be improved to some extent.
nullThe data volume dropping on same territory element owing to dropping on the tracing point in identical strip path curve is different，Sample frequency is fixing，Speed is then various，The distance different (distance=speed/frequency) that mobile object moves can be caused，Namely the distance between object trajectory data point is moved different，So the present invention uses the territory element track to carrying out after the division of region to be extended，First the traversal all of data point of track，Obtain the trajectory map sequence at the cell of area planar map，Then in order to reduce error，The adjacent area unit of the territory element that tracing point is fallen into (include itself one have nine) is also required to give a basic numerical value (being denoted as the territory element of 1 in Fig. 2)，The track preventing path identical produces bigger diversity，Testing result is made to there is bigger deviation with practical situation，Track abnormal conditions are judged by accident.Fig. 2 grey area unit is the territory element that track data point falls into, and its value is the quantitative value of the data point falling into this territory element, uses g in figureiRepresent；The value of its neighbours' territory element is 1；The value of other territory elements is 0.Track can be expressed as tr=(g1,g2,...,g11) wherein also include neighbours' territory element of territory element sequence.
Fig. 3 is the flow chart of invention algorithm, first the input of algorithm is the historical trajectory data of mobile object and track data to be detected, two class data carries out region division respectively and extension obtains the territory element sequence tr of historical track territory element sequence library TR and track to be detectedcheck={ g1,g2,...,gn}；Then by TR and trcheck={ g1,g2,...,gnCalculate trcheckIn the proportion function Sup value of each territory element, it is judged that Sup and the magnitude relationship of threshold value, if the Sup value of territory element is less than threshold value, then corresponding territory element is deposited into abnormal area unit set A (gi) in until travel through whole trcheck；Then A (g is comparedi) the average area unit number of track, to judge that whether track to be detected abnormal, and may indicate that abnormal sub-trajectory occurs in the territory element number gathered and TR；Concrete condition finally according to track to be detected decides whether track is carried out the track abnormality detection that region divides again.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: these embodiments can being carried out multiple change, amendment, replacement and modification when without departing from principles of the invention and objective, the scope of the present invention is limited by claim and equivalent thereof.
Claims (7)
1. the abnormal track-detecting method divided based on region, is characterized in that, comprise the following steps:
Step one: the GPS historical trajectory data of user is classified, extracts the rail track feature of normal trace data, by carrying out region division on normal trace data position in the ground, obtains track data region；
Step 2: ready-portioned for step one track data region is carried out track data territory element extension, obtains historical track territory element sequence library；
Step 3: track data to be detected is carried out region and divides acquisition track regions unit sequence tr to be measuredcheck={ g1,g2,...,gn, wherein gnRepresent the territory element that track to be detected is passed, n represents territory element sequence number, finding the unit identical with the initiation region unit of track regions to be measured unit sequence from historical track territory element sequence library is starting point, the unit identical with the termination area unit of track regions to be measured unit sequence is terminal, forms normal trace set TR={tr1,tr2,tr3,...,tri, wherein i is number | TR |, the tr of track in TRiRepresent i-th track, tri={ gi1,gi2,gi3,...,gij, gijRepresent track triThe jth territory element of process；
Step 4: travel through track regions unit sequence tr to be detectedcheckIn each unit lattice track, obtain each cell supporting rate in normal trace set TR, and compared with threshold value, obtain abnormal area unit set A (gi)；
Step 5: according to normal trace set TR and abnormal area unit set A (gi) length relation judge the abnormal conditions of track to be detected.
2. a kind of abnormal track-detecting method divided based on region according to claim 1, is characterized in that: also include the GPS historical trajectory data to user and track data to be detected carries out that region is subdivided and the step of abnormality detection.
3. a kind of abnormal track-detecting method divided based on region according to claim 1 or claim 2, is characterized in that: the rail track feature of described extraction normal trace data includes the longitude of track, the latitude of track and timestamp.
4. a kind of abnormal track-detecting method divided based on region according to claim 1 or claim 2, it is characterized in that: the extension of described track data territory element includes, the territory element adjacent with track data region is concluded in track data region, obtains historical track territory element sequence library.
5. according to claim 1 or claim 2 a kind of based on region divide abnormal track-detecting method, it is characterized in that: track abnormality detection in described step 4 particularly as follows:
S41: traversal trcheckEach compositing area unit, with normal trace set TR={tr1,tr2,tr3,...,triIn track tri={ gi1,gi2,gi3,...,gijTerritory element compare, if track triWith trcheckThere is identical territory element, then by track triRecord and deposit into track set Inc (TR, trcheck)；
S42: for each territory element g of track to be detectedi, calculate Inc (TR, the tr of each territory elementcheck) tracking quantity proportion function in normal trace set TR,Judge whether this territory element is track tr according to proportion functioncheckIn normal trace point, as Sup (Tr, trcheck) < θ, θ are threshold value, 0≤θ≤1, and this territory element is put into abnormal area unit set A (gi) in, and as Sup (Tr, trcheckThis territory element is put into normal region unit set N (g by) >=θi) in.
6. a kind of abnormal track-detecting method divided based on region according to claim 1 or claim 2, is characterized in that: the abnormal conditions method of described judgement track to be detected is:
Obtain abnormal area unit set A (gi) after, when the quantity of abnormal area unit | A (gi) | more than one preset valueTime, i.e. abnormal area unit set A (gi) number of elements | A (gi) | time more, this track is abnormal；Otherwise, this track is normal.
7. according to claim 6 a kind of based on region divide abnormal track-detecting method, it is characterized in that: to described abnormal area unit set A (gi) carry out abnormal when judging, adopt and calculate exceptional value R (trcheck) mode judge, exceptional valueWherein α is constants, and k is the constant relevant to the meansigma methods of the territory element number of the normal trace each track of set TR.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610102351.2A CN105785411B (en) | 2016-02-24 | 2016-02-24 | A kind of abnormal track-detecting method based on region division |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610102351.2A CN105785411B (en) | 2016-02-24 | 2016-02-24 | A kind of abnormal track-detecting method based on region division |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105785411A true CN105785411A (en) | 2016-07-20 |
| CN105785411B CN105785411B (en) | 2018-10-12 |
Family
ID=56402913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610102351.2A Active CN105785411B (en) | 2016-02-24 | 2016-02-24 | A kind of abnormal track-detecting method based on region division |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105785411B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106643734A (en) * | 2016-12-30 | 2017-05-10 | 中国科学院电子学研究所 | Grading processing method for space-time track data |
| CN108092840A (en) * | 2016-11-23 | 2018-05-29 | ***通信集团广东有限公司 | Network rate segment processing method and device |
| CN108804539A (en) * | 2018-05-08 | 2018-11-13 | 山西大学 | A kind of track method for detecting abnormality under time and space double-visual angle |
| CN109034181A (en) * | 2018-06-05 | 2018-12-18 | 广州杰赛科技股份有限公司 | The classification method and device of motion track, equipment, storage medium |
| CN109218985A (en) * | 2018-08-08 | 2019-01-15 | 上海中交水运设计研究有限公司 | A kind of shipping work abnormal behavior detection method and system based on Pattern similarity |
| CN109726737A (en) * | 2018-11-27 | 2019-05-07 | 武汉极意网络科技有限公司 | Trajectory-based anomaly detection method and device |
| CN110634264A (en) * | 2018-06-22 | 2019-12-31 | 镇江雅迅软件有限责任公司 | Children prevent system of wandering away based on indoor positioning technique |
| CN111474565A (en) * | 2020-05-20 | 2020-07-31 | 上海评驾科技有限公司 | Method for judging illegal plugging condition of road transport vehicle satellite positioning system terminal |
| CN111563137A (en) * | 2020-04-28 | 2020-08-21 | 厦门市美亚柏科信息股份有限公司 | Analysis method and system for coincident track |
| CN111699512A (en) * | 2018-04-13 | 2020-09-22 | 上海趋视信息科技有限公司 | Abnormal scene detection system and method |
| CN111798971A (en) * | 2020-07-15 | 2020-10-20 | 智博云信息科技(广州)有限公司 | Medical information data processing method, system, electronic device and medium |
| CN111862586A (en) * | 2019-12-11 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining abnormal road section of road area and storage medium |
| CN111882873A (en) * | 2020-07-22 | 2020-11-03 | 平安国际智慧城市科技股份有限公司 | Track anomaly detection method, device, equipment and medium |
| CN114639216A (en) * | 2022-02-18 | 2022-06-17 | 国政通科技有限公司 | Specific personnel track area analysis early warning system and method |
| CN114822040A (en) * | 2022-06-23 | 2022-07-29 | 南京城建隧桥智慧管理有限公司 | Good neighbor set construction method for assisting mobile node position anomaly detection |
| CN115936561A (en) * | 2022-11-18 | 2023-04-07 | 广州云达供应链管理有限公司 | Logistics vehicle track operation abnormity monitoring method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011025662A2 (en) * | 2009-08-31 | 2011-03-03 | Behavioral Recognition Systems, Inc. | Detecting anomalous trajectories in a video surveillance system |
| CN104700434A (en) * | 2015-03-27 | 2015-06-10 | 北京交通大学 | Crowd movement track anomaly detection method for complicated structuring scenes |
-
2016
- 2016-02-24 CN CN201610102351.2A patent/CN105785411B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011025662A2 (en) * | 2009-08-31 | 2011-03-03 | Behavioral Recognition Systems, Inc. | Detecting anomalous trajectories in a video surveillance system |
| CN104700434A (en) * | 2015-03-27 | 2015-06-10 | 北京交通大学 | Crowd movement track anomaly detection method for complicated structuring scenes |
Non-Patent Citations (4)
| Title |
|---|
| DAQING ZHANG ET AL.: "iBAT: Detecting Anomalous Taxi Trajectories from GPS Traces", 《PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON UBIQUITOUS COMPUTING》 * |
| 任杰 等: "基于划分检测模型的终端区异常轨迹检测方法", 《航空计算技术》 * |
| 刘鹏 等: "基于条件随机场与区域划分的异常行为检测", 《通信技术》 * |
| 陈刚 等: "基于划分的高效异常轨迹检测", 《计算机工程与应用》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108092840A (en) * | 2016-11-23 | 2018-05-29 | ***通信集团广东有限公司 | Network rate segment processing method and device |
| CN108092840B (en) * | 2016-11-23 | 2021-08-31 | ***通信集团广东有限公司 | Network rate segmentation processing method and device |
| CN106643734B (en) * | 2016-12-30 | 2019-01-11 | 中国科学院电子学研究所 | The hierarchical processing method of space-time trajectory data |
| CN106643734A (en) * | 2016-12-30 | 2017-05-10 | 中国科学院电子学研究所 | Grading processing method for space-time track data |
| CN111699512B (en) * | 2018-04-13 | 2023-11-03 | 上海趋视信息科技有限公司 | Abnormal scene detection system and method |
| US11842542B2 (en) | 2018-04-13 | 2023-12-12 | Shanghai Truthvision Information Technology Co., Ltd. | System and method for abnormal scene detection |
| CN111699512A (en) * | 2018-04-13 | 2020-09-22 | 上海趋视信息科技有限公司 | Abnormal scene detection system and method |
| CN108804539A (en) * | 2018-05-08 | 2018-11-13 | 山西大学 | A kind of track method for detecting abnormality under time and space double-visual angle |
| CN108804539B (en) * | 2018-05-08 | 2022-03-18 | 山西大学 | Track anomaly detection method under time and space double view angles |
| CN109034181A (en) * | 2018-06-05 | 2018-12-18 | 广州杰赛科技股份有限公司 | The classification method and device of motion track, equipment, storage medium |
| CN110634264A (en) * | 2018-06-22 | 2019-12-31 | 镇江雅迅软件有限责任公司 | Children prevent system of wandering away based on indoor positioning technique |
| CN109218985A (en) * | 2018-08-08 | 2019-01-15 | 上海中交水运设计研究有限公司 | A kind of shipping work abnormal behavior detection method and system based on Pattern similarity |
| CN109218985B (en) * | 2018-08-08 | 2020-09-22 | 上海中交水运设计研究有限公司 | Ship operation behavior abnormity detection method and system based on pattern similarity |
| CN109726737A (en) * | 2018-11-27 | 2019-05-07 | 武汉极意网络科技有限公司 | Trajectory-based anomaly detection method and device |
| CN111862586A (en) * | 2019-12-11 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining abnormal road section of road area and storage medium |
| CN111862586B (en) * | 2019-12-11 | 2021-10-15 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining abnormal road section of road area and storage medium |
| CN111563137B (en) * | 2020-04-28 | 2022-05-17 | 厦门市美亚柏科信息股份有限公司 | Analysis method and system for coincident track |
| CN111563137A (en) * | 2020-04-28 | 2020-08-21 | 厦门市美亚柏科信息股份有限公司 | Analysis method and system for coincident track |
| CN111474565A (en) * | 2020-05-20 | 2020-07-31 | 上海评驾科技有限公司 | Method for judging illegal plugging condition of road transport vehicle satellite positioning system terminal |
| CN111798971A (en) * | 2020-07-15 | 2020-10-20 | 智博云信息科技(广州)有限公司 | Medical information data processing method, system, electronic device and medium |
| CN111882873A (en) * | 2020-07-22 | 2020-11-03 | 平安国际智慧城市科技股份有限公司 | Track anomaly detection method, device, equipment and medium |
| CN111882873B (en) * | 2020-07-22 | 2022-01-28 | 平安国际智慧城市科技股份有限公司 | Track anomaly detection method, device, equipment and medium |
| CN114639216A (en) * | 2022-02-18 | 2022-06-17 | 国政通科技有限公司 | Specific personnel track area analysis early warning system and method |
| CN114822040A (en) * | 2022-06-23 | 2022-07-29 | 南京城建隧桥智慧管理有限公司 | Good neighbor set construction method for assisting mobile node position anomaly detection |
| CN114822040B (en) * | 2022-06-23 | 2022-11-11 | 南京城建隧桥智慧管理有限公司 | Good neighbor set construction method for assisting mobile node position anomaly detection |
| CN115936561A (en) * | 2022-11-18 | 2023-04-07 | 广州云达供应链管理有限公司 | Logistics vehicle track operation abnormity monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105785411B (en) | 2018-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105785411A (en) | Abnormal locus detection method based on area division | |
| CN111623722B (en) | Multi-sensor-based slope deformation three-dimensional monitoring system and method | |
| CN105138779B (en) | Vehicle GPS space-time track big data method for optimizing and system | |
| CN110400332A (en) | A kind of target detection tracking method, device and computer equipment | |
| CN103324937B (en) | The method and apparatus of label target | |
| CN103810717B (en) | A kind of human body behavioral value method and device | |
| US20150170514A1 (en) | Systems and Methods for Detecting Road Congestion and Incidents in Real Time | |
| CN101827002B (en) | Concept drift detection method of data flow classification | |
| CN109615862A (en) | Road vehicle movement of traffic state parameter dynamic acquisition method and device | |
| CN109684384B (en) | Trajectory data space-time density analysis system and analysis method thereof | |
| CN108664841A (en) | A kind of sound state object recognition methods and device based on laser point cloud | |
| CN110427807A (en) | A kind of temporal events motion detection method | |
| CN109996175B (en) | Indoor positioning system and method | |
| CN103473540B (en) | The modeling of intelligent transportation system track of vehicle increment type and online method for detecting abnormality | |
| CN107507417A (en) | A kind of smartway partitioning method and device based on microwave radar echo-signal | |
| CN103985257A (en) | Intelligent traffic video analysis method | |
| CN101304479B (en) | Method and apparatus for detecting motion in video sequence | |
| CN114372503A (en) | Cluster vehicle motion trail prediction method | |
| CN102129559A (en) | SAR (Synthetic Aperture Radar) image object detection method based on Primal Sketch algorithm | |
| Veni et al. | Video-Based Detection, Counting and Classification of Vehicles Using OpenCV | |
| Pinelli et al. | Robust bus-stop identification and denoising methodology | |
| KR102616571B1 (en) | System and method for providing road traffic information based on image analysis using artificial intelligence | |
| CN117517868A (en) | Lightning stroke fault matching method and system based on distributed measurement data | |
| KR102682309B1 (en) | System and Method for Estimating Microscopic Traffic Parameters from UAV Video using Multiple Object Tracking of Deep Learning-based | |
| CN113899948B (en) | System and method for quickly extracting electromagnetic spectrum target characteristic data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |