CN112230253A - Track characteristic anomaly detection method based on public slice subsequence - Google Patents

Track characteristic anomaly detection method based on public slice subsequence Download PDF

Info

Publication number
CN112230253A
CN112230253A CN202011094683.3A CN202011094683A CN112230253A CN 112230253 A CN112230253 A CN 112230253A CN 202011094683 A CN202011094683 A CN 202011094683A CN 112230253 A CN112230253 A CN 112230253A
Authority
CN
China
Prior art keywords
track
tracks
common
slice
difference
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
Application number
CN202011094683.3A
Other languages
Chinese (zh)
Other versions
CN112230253B (en
Inventor
牛新征
刘鹏飞
何玲
郑云红
刘翔宇
杨胜瀚
匡洁良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Electronic Science and Technology of China
Original Assignee
University of Electronic Science and Technology of China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Electronic Science and Technology of China filed Critical University of Electronic Science and Technology of China
Priority to CN202011094683.3A priority Critical patent/CN112230253B/en
Publication of CN112230253A publication Critical patent/CN112230253A/en
Application granted granted Critical
Publication of CN112230253B publication Critical patent/CN112230253B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • 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
    • G01S19/393—Trajectory determination or predictive tracking, e.g. Kalman filtering
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Algebra (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Automation & Control Theory (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the technical field of information technology processing, and provides a track characteristic anomaly detection method based on a common slice subsequence. The problem that the abnormal track is easily mistaken as the normal track under the condition that only the public part is considered in the traditional method is solved. The main scheme includes that the difference D' of the non-public part between the two tracks is calculated, the difference of the non-public part of the two tracks is judged to be smaller than a difference judgment threshold value, and the ratio of the longest public part to the whole track exceeds the threshold value, so that the characteristics of the two tracks are similar; and judging that the ratio of the number of other tracks with similar characteristics to the current track in the track set to the number of all tracks in the track set exceeds a threshold value, representing that the current track is a characteristic normal track, and if not, representing that the characteristic is an abnormal track.

Description

Track characteristic anomaly detection method based on public slice subsequence
Technical Field
The invention relates to the technical field of information technology processing, and provides a track characteristic anomaly detection method based on a common slice subsequence.
Background
With the rapid development of various GPS devices and wireless communication technologies, a large amount of moving object trajectory data is generated and collected. Such as mobile users, vehicles, animals, and hurricanes. Analysis of this data can help researchers obtain a host of valuable information, such as hotspots, patterns of interest, location predictions, and other relevant implications. Therefore, there is an increasing interest in track pattern mining, where Track Outlier Detection (TOD) is one of the hottest research topics.
As is well known, outliers refer to data objects that are significantly different or inconsistent with the remaining data set. This is a very rare pattern that may indicate an abnormal event. Therefore, outlier detection is an important data analysis task. Track outliers (also called outlier tracks) are tracks that have large differences from most other tracks over a time interval based on some similarity evaluation mechanism. TOD falls into the category of spatio-temporal outlier detection because the trajectory has spatio-temporal features. The detection results may help identify suspicious activity, moving objects, and thus may be used in many applications such as bad weather forecasting, security monitoring, and intelligent transportation and scientific research. Such as Chen et al. One tropical cyclonic system or hurricane proposed in the literature may be considered an abnormal activity of atmospheric systems. In addition, the detection and removal of the track outliers have important significance for improving the efficiency of the track similarity clustering algorithm.
The existing anomaly detection technologies include four types, namely, classification-based detection technologies, history similarity-based detection technologies, distance-based detection technologies, and meshing-based detection technologies. However, in most of the existing anomaly detection technologies, only the part with the similar track is considered in the process of measuring the track similarity, but the influence of the part with the different track on the similarity measurement between the two tracks is not considered, the feature extraction is insufficient, and the accuracy of anomaly detection is reduced, so that an anomaly detection algorithm for synthesizing the part with the similar track and the part with the different track is urgently needed to be researched.
Disclosure of Invention
The invention aims to solve the problem that in the prior art, only two similar tracks are considered, and no dissimilar track is considered, so that an abnormal track with higher similarity cannot be checked, if the slice codes in the two track directions are 90% identical, but one slice code has a larger difference and is obviously an abnormal track, the abnormal track can be judged to be a normal track by only considering the similar track, and the abnormal track can be missed for detection. The method and the device have the advantages that the influence of the track non-public partial sequence on the similarity measurement of the two tracks is added, and the detection precision is improved.
The invention does not solve the technical problems and adopts the following technical scheme:
the track characteristic anomaly detection method based on the common slice subsequence comprises the following steps:
step 1: connecting two adjacent points on each track by using line segments, wherein each line segment is a track segment, and each track consists of a series of track segments;
step 2: drawing N rays with an origin as a starting point in a plane rectangular coordinate system, evenly dividing a plane into N small planes, numbering each plane, sequentially taking integers from 1 to N, calculating the slope of each track section, wherein the number of the plane where the slope is positioned is the direction code of the track section;
and step 3: if the difference of the direction values of two adjacent track sections of a certain point exceeds a threshold value, the point is an inflection point, the inflection points in the track are sequentially connected by line segments, the line segment at the moment is a track slice, the track slice reforms the track, and the average value x of the track sections between the two inflection points of the slice is calculatednmThe remainder carry of the average value is used as track slice direction code, and the track slice direction code forms track slice direction code sequence Xn，
Xn＝[xn1，xn2，xn3，……，xnm]
Wherein xnmWhere n represents the track number, m represents the track slice number, XnWherein n represents the number of the track;
and 4, step 4: after the track slicing is finished, finding out the longest public subsequence Z of the slice direction coding sequence between any two tracks:
Z＝[z1，z2，z3，……，zk]
the track is sliced into a sequence XnElement z through the longest common subsequencekFor delimiters, the track slice direction is coded by a sequence XnElement z cut to contain no longest common subsequencekNon-common partial sequence string X ofnzkThe non-common part set of each track formed by the non-common part sequence strings is the non-common part of two tracks:
D＝{Xnz1，Xnz2，……Xnzk}
wherein XnzkRepresenting a non-common partial sequence string with subscript meaning, n representing the track number, XnzkElement z representing the longest common subsequence in the nth tracek-1And zkThe track slice direction coding sequence;
and 5: calculating the difference D' of the non-public part between the two tracks, and judging that the difference of the non-public part of the two tracks is smaller than a difference judgment threshold value and the ratio of the longest public part to the whole track exceeds the threshold value, so that the characteristics of the two tracks are similar;
step 6: and judging that the ratio of the number of other tracks with similar characteristics to the current track in the track set to the number of all tracks in the track set exceeds a threshold value, representing that the current track is a characteristic normal track, and otherwise, representing that the current track is a characteristic abnormal track.
And 7: calculating the distance before the track through the track sheet in the longest common part;
and 8: if the distance between the two tracks is smaller than the threshold value, the two tracks are adjacent, if the ratio of the number of the tracks adjacent to the current track to the number of all the tracks in the track set exceeds the threshold value, the current track is represented as a normal track, and if not, the current track is represented as a distance abnormal track.
In the above technical solution, the obtaining of the difference D' of the non-common part in the step 5 includes the following steps:
taking two track non-common parts of the two tracks to be respectively recorded as:
track A: DA ═ XAz1，XAz2，……XAzk}；
And a track B: DB ═ XBz1，XBz2，……XBzk}；
The track slice direction coding sequence of track a and track B indicates:
XAzkthe track slice direction code sequence of (a) is recorded as: [ x'A1，x′A2，…，x′Am]；
XBzkThe track slice direction code sequence of (a) is recorded as: [ x'B1，x′B2，…，x′Bn]；
When m-n is equal to 0, accumulating and summing to obtain non-common partial sequence string XAzkAnd a non-common partial sequence string XBzkLocal difference value r ofzk：
Figure BDA0002721903040000031
When m-n is less than 0, accumulating and summing to obtain a local difference value rzk：
rzK＝rzk' + n-m n-m denotes XBzkThe number of the track slice direction coding sequence entries exceeds XAzkThe number of terms of the track slice direction coding sequence of (1), the excess is directly recorded as the difference, and each more term r is r +1,
Figure BDA0002721903040000041
when m-n is more than 0, accumulating and summing to obtain a local difference value rzk：
rzk＝rzk′+m-n
Figure BDA0002721903040000042
Not publicPartial difference D' ═ r (r)z1+rz2+…rzk)/k。
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
the track anomaly detection method has wide application prospect and research value in various fields such as traffic management, safety monitoring, criminal investigation and the like. Judging the congestion condition of the current road according to the abnormal track mode of the vehicle if the traffic dispatching of the vehicle is needed, and carrying out ordered command and guidance on the vehicle; the safety monitoring needs to continuously perform abnormity detection on the track data, and an alarm or a corresponding decision is made at the initial stage of the abnormal condition, so that the potential safety hazard is eliminated in time; in addition, the method has good application prospect in the aspects of detecting the abnormal track of the taxi, such as detour behavior in the running process of the taxi, and partial road section congestion caused by unexpected traffic accidents or temporary road blockade.
In the case where only the common portion is considered in the conventional method, the abnormal trajectory may be easily mistaken as the normal trajectory.
Drawings
Fig. 1 is a schematic view of a track slice.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the detailed description and specific examples, while indicating the preferred embodiment of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The track characteristic anomaly detection method based on the common slice subsequence comprises the following steps:
step 1: connecting two adjacent points on each track by using line segments, wherein each line segment is a track segment, and each track consists of a series of track segments;
step 2: drawing N rays with an origin as a starting point in a plane rectangular coordinate system, evenly dividing a plane into N small planes, numbering each plane, sequentially taking integers from 1 to N, calculating the slope of each track section, wherein the number of the plane where the slope is positioned is the direction code of the track section;
and step 3: if the difference of the direction values of two adjacent track sections of a certain point exceeds a threshold value, the point is an inflection point, the inflection points in the track are sequentially connected by line segments, the line segment at the moment is a track slice, the track slice reforms the track, and the average value x of the track sections between the two inflection points of the slice is calculatednmThe remainder carry of the average value is used as track slice direction code, and the track slice direction code forms track slice direction code sequence Xn，
Xn＝[xn1，xn2，xn3，……，xnm]
Wherein xnmWhere n represents the track number, m represents the track slice number, XnWherein n represents the number of the track;
and 4, step 4: after the track slicing is finished, finding out the longest public subsequence Z of the slice direction coding sequence between any two tracks:
Z＝[z1，z2，z3，……，zk]
the track is sliced into a sequence XnElement z through the longest common subsequencekFor delimiters, the track slice direction is coded by a sequence XnElement z cut to contain no longest common subsequencekNon-common partial sequence string X ofnzkThe non-common part set of each track formed by the non-common part sequence strings is the non-common part of two tracks:
D＝{Xnz1，Xnz2，……Xnzk}
wherein XnzkRepresenting a non-common partial sequence string with subscript meaning, n representing the track number, XnzkElement z representing the longest common subsequence in the nth tracek-1And zkThe track slice direction coding sequence;
and 5: calculating the difference D' of the non-public part between the two tracks, and judging that the difference of the non-public part of the two tracks is smaller than a specified value and the ratio of the longest public part to the whole track exceeds a threshold value, so that the characteristics of the two tracks are similar;
step 6: and judging that the ratio of the number of other tracks with similar characteristics to the current track in the track set to the number of all tracks in the track set exceeds a threshold value, representing that the current track is a characteristic normal track, and if not, representing that the characteristic is an abnormal track.
And 7: calculating the distance before the track through the track sheet in the longest common part;
and 8: if the distance between the two tracks is smaller than the threshold value, the two tracks are adjacent, if the ratio of the number of the tracks adjacent to the current track to the number of all the tracks in the track set exceeds the threshold value, the current track is represented as a normal track, and if not, the current track is represented as a distance abnormal track.
In the above technical solution, the obtaining of the difference D' of the non-common part in the step 5 includes the following steps:
taking two track non-common parts of the two tracks to be respectively recorded as:
track A: dA＝{XAz1，XAz2，……XAzk}；
And a track B: dB＝{XBz1，XBz2，……XBzk}；
The track slice direction coding sequence of track a and track B indicates:
XAzkthe track slice direction code sequence of (a) is recorded as: [ x'A1，x′A2，…，x′Am]；
XBzkThe track slice direction code sequence of (a) is recorded as: [ x'B1，x′B2，…，x′Bn]；
When m-n is equal to 0, accumulating and summing to obtain non-common partial sequence string XAzkAnd a non-common partial sequence string XBzkLocal difference value r ofzk：
Figure BDA0002721903040000071
When m-n is less than 0, accumulating and summing to obtain a local difference value rzk：
rzk＝rzk' + n-m n-m denotes XBzkThe number of the track slice direction coding sequence entries exceeds XAzkThe number of entries of the track slice direction coding sequence of (1), the excess is directly recorded as the difference, and r is added to each entryzk＝rzk+1，
Figure BDA0002721903040000072
When m-n is more than 0, accumulating and summing to obtain a local difference value rzk：
rzk＝rzk′+m-n
Figure BDA0002721903040000073
The difference of the non-common part D ═ (r)z1+rz2+…rzk)/k。
Example 1
Track slice direction coding sequence of 3 tracks as in fig. 1:
X1＝[3，2，1，13，16，2，12，7]
X2＝[3，2，1，14，15，2，14，7]
X3＝[3，2，1，3，6，2，6，7]
the common parts of the three tracks are shown as the bold part in the figure, namely the common part of the tracks is in the sequence of
And Z is [3, 2, 1, 2, 7], and three tracks correspond to two non-common parts. Since the ratio of the number of slices in the common part of the three tracks to the number of slices in the whole track is the same, the abnormal track cannot be accurately detected by simply considering the common part of the track, and therefore, the difference of the non-common part of the track needs to be considered.
Calculating the difference value of the non-public part (setting the difference threshold t to be 2 and the difference discrimination threshold to be 1):
(1)X1and X2First common partial difference value calculation:
Figure BDA0002721903040000081
local difference value of
Figure BDA0002721903040000082
And is
Figure BDA0002721903040000083
Is 0.
Since |13-14| < ═ 2, this time
Figure BDA0002721903040000084
Equal to 0;
and because |16-152, so at this time
Figure BDA0002721903040000085
Namely, it is
Figure BDA0002721903040000086
(2)X1And X2Second common partial difference value calculation:
Figure BDA0002721903040000087
is provided with
Figure BDA0002721903040000088
Can obtain X1And X2Difference value between non-common parts
Figure BDA0002721903040000089
(3)X1And X3First common partial difference value calculation:
Figure BDA00027219030400000810
local difference value of
Figure BDA00027219030400000811
And is
Figure BDA00027219030400000812
Is 0.
Since |13-2| > | 2, this time
Figure BDA00027219030400000813
Equal to 1;
since |16-6| < ═ 2, this time
Figure BDA00027219030400000814
Namely, it is
Figure BDA00027219030400000815
(that is to say
Figure BDA00027219030400000816
Accumulation)
(2)X1And X3Second common partial difference value calculation:
Figure BDA00027219030400000817
is provided with
Figure BDA00027219030400000818
Can obtain X1And X3Difference value between non-common parts
Figure BDA00027219030400000819
As a result: due to X1And X2The difference between D' is 0.5 and r < discrimination threshold (equal to 1), so we will be X1And X2The characteristics are considered similar;
due to X1And X3The difference between D' ═ 1.5 and r > 1, so we convert X1And X3The features are regarded as different, so X can be distinguished3Is characterized by X1And X2。

Claims (3)

1. The track characteristic anomaly detection method based on the common slice subsequence is characterized by comprising the following steps of:
step 1: connecting two adjacent points on each track by using line segments, wherein each line segment is a track segment, and each track consists of a series of track segments;
step 2: drawing N rays with an origin as a starting point in a plane rectangular coordinate system, evenly dividing a plane into N small planes, numbering each plane, sequentially taking integers from 1 to N, calculating the slope of each track section, wherein the number of the plane where the slope is positioned is the direction code of the track section;
and step 3: if the difference of the direction values of two adjacent track sections of a certain point exceeds a threshold value, the point is an inflection point, the inflection points in the track are sequentially connected by line segments, the line segment at the moment is a track slice, the track slice reforms the track, and the average value x of the track sections between the two inflection points of the slice is calculatednmThe remainder carry of the average value is used as track slice direction code, and the track slice direction code forms track slice direction code sequence Xn，
Xn＝[xn1，xn2，xn3，……，xnm]
Wherein xnmWhere n represents the track number, m represents the track slice number, XnWherein n represents the number of the track;
and 4, step 4: after the track slicing is finished, finding out the longest public subsequence Z of the slice direction coding sequence between any two tracks:
Z＝[z1，z2，z3，……，zk]，
will and will track the slice direction coding sequence XnElement z through the longest common subsequencekFor delimiters, the track slice direction is coded by a sequence XnElement z cut to contain no longest common subsequencekNon-common partial sequence string X ofnzkThe non-common part set of each track formed by the non-common part sequence strings is the non-common part of two tracks:
D＝{Xnz1，Xnz2，……Xnzk}
wherein XnzkRepresenting a non-common partial sequence string with subscript meaning, n representing the track number, XnzkElement z representing the longest common subsequence in the nth tracek-1And zkThe track slice direction coding sequence;
and 5: calculating the difference D' of the non-public part between the two tracks, and judging that the difference of the non-public part of the two tracks is smaller than a difference judgment threshold value and the ratio of the longest public part to the whole track exceeds the threshold value, so that the characteristics of the two tracks are similar;
step 6: and judging that the ratio of the number of other tracks with similar characteristics to the current track in the track set to the number of all tracks in the track set exceeds a threshold value, representing that the current track is a characteristic normal track, and if not, representing that the characteristic is an abnormal track.
2. A common slice subsequence-based track feature anomaly detection method according to claim 1, further comprising the steps of:
and 7: calculating the distance before the track through the track sheet in the longest common part;
and 8: if the distance between the two tracks is smaller than the threshold value, the two tracks are adjacent, if the ratio of the number of the tracks adjacent to the current track to the number of all the tracks in the track set exceeds the threshold value, the current track is represented as a normal track, and if not, the current track is represented as a distance abnormal track.
3. A common slice subsequence-based track feature anomaly detection method according to claim 1, wherein the obtaining of the difference D of the non-common parts in step 5 comprises the steps of:
taking two track non-common parts of the two tracks to be respectively recorded as:
track A: dA＝{XAz1，XAz2，……XAzk}；
And a track B: dB＝{XBz1，XBz2，……XBzk}；
The track slice direction coding sequence of track a and track B indicates:
XAzkthe track slice direction code sequence of (a) is recorded as: [ x'A1，x′A2，…，x′Am]；
XBzkThe track slice direction code sequence of (a) is recorded as: [ x'B1，x′B2，…，x′Bn]；
When m-n is equal to 0, accumulating and summing to obtain non-common partial sequence string XAzkAnd a non-common partial sequence string XBzkLocal difference value r ofzk：
Figure FDA0002721903030000021
When m-n is less than 0, accumulating and summing to obtain a local difference value rzk：
rzK＝rzk+ n-m n-m represents XBzkThe number of the track slice direction coding sequence entries exceeds XAzkThe number of terms of the track slice direction coding sequence of (1), the excess is directly recorded as the difference, and each more term r is r +1,
Figure FDA0002721903030000031
when m-n is more than 0, accumulating and summing to obtain a local difference value rzk：
rzk＝rzk+m-n
Figure FDA0002721903030000032
The difference of the non-common part D ═ rz1+rz2+…rzk)/k。
CN202011094683.3A 2020-10-13 2020-10-13 Track characteristic anomaly detection method based on public slice subsequence Active CN112230253B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011094683.3A CN112230253B (en) 2020-10-13 2020-10-13 Track characteristic anomaly detection method based on public slice subsequence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011094683.3A CN112230253B (en) 2020-10-13 2020-10-13 Track characteristic anomaly detection method based on public slice subsequence

Publications (2)

Publication Number Publication Date
CN112230253A true CN112230253A (en) 2021-01-15
CN112230253B CN112230253B (en) 2021-07-09

Family

ID=74112615

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011094683.3A Active CN112230253B (en) 2020-10-13 2020-10-13 Track characteristic anomaly detection method based on public slice subsequence

Country Status (1)

Country Link
CN (1) CN112230253B (en)

Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101872418A (en) * 2010-05-28 2010-10-27 电子科技大学 Detection method based on group environment abnormal behavior
US20120170802A1 (en) * 2010-12-30 2012-07-05 Pelco Inc. (Clovis, CA) Scene activity analysis using statistical and semantic features learnt from object trajectory data
CN103605362A (en) * 2013-09-11 2014-02-26 天津工业大学 Learning and anomaly detection method based on multi-feature motion modes of vehicle traces
KR20140132140A (en) * 2013-05-07 2014-11-17 성균관대학교산학협력단 Method and apparatus for video surveillance based on detecting abnormal behavior using extraction of trajectories from crowd in images
CN104657746A (en) * 2015-01-29 2015-05-27 电子科技大学 Anomaly detection method based on vehicle trajectory similarity
US9396399B1 (en) * 2008-09-18 2016-07-19 Grandeye, Ltd. Unusual event detection in wide-angle video (based on moving object trajectories)
CN106294485A (en) * 2015-06-05 2017-01-04 华为技术有限公司 Determine the method and device in notable place
CN106383868A (en) * 2016-09-05 2017-02-08 电子科技大学 Road network-based spatio-temporal trajectory clustering method
JP2017097479A (en) * 2015-11-19 2017-06-01 日立建機株式会社 Abnormality detection device for self-location estimation device, and vehicle
CN106922176A (en) * 2014-12-10 2017-07-04 哈曼国际工业有限公司 Lane detection
CN107944475A (en) * 2017-11-09 2018-04-20 安徽师范大学 Track outlier detection method based on public burst subsequence
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
CN110069585A (en) * 2017-12-05 2019-07-30 腾讯科技（深圳）有限公司 Treating method and apparatus, storage medium and the electronic device of track point data
CN110175633A (en) * 2019-04-29 2019-08-27 杭州电子科技大学 A kind of fishing boat track method for detecting abnormality based on Beidou satellite transmission data
CN110490264A (en) * 2019-08-23 2019-11-22 中国民航大学 Multidimensional distance cluster method for detecting abnormality and system based on time series
CN111046968A (en) * 2019-12-20 2020-04-21 电子科技大学 Road network track clustering analysis method based on improved DPC algorithm
CN111242521A (en) * 2020-04-24 2020-06-05 中国人民解放军国防科技大学 Track anomaly detection method and system
CN111328403A (en) * 2018-10-16 2020-06-23 华为技术有限公司 Improved trajectory matching based on quality indicators allowed using weighted confidence values

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170161563A1 (en) * 2008-09-18 2017-06-08 Grandeye, Ltd. Unusual Event Detection in Wide-Angle Video (Based on Moving Object Trajectories)
US9396399B1 (en) * 2008-09-18 2016-07-19 Grandeye, Ltd. Unusual event detection in wide-angle video (based on moving object trajectories)
CN101872418A (en) * 2010-05-28 2010-10-27 电子科技大学 Detection method based on group environment abnormal behavior
US20120170802A1 (en) * 2010-12-30 2012-07-05 Pelco Inc. (Clovis, CA) Scene activity analysis using statistical and semantic features learnt from object trajectory data
KR20140132140A (en) * 2013-05-07 2014-11-17 성균관대학교산학협력단 Method and apparatus for video surveillance based on detecting abnormal behavior using extraction of trajectories from crowd in images
CN103605362A (en) * 2013-09-11 2014-02-26 天津工业大学 Learning and anomaly detection method based on multi-feature motion modes of vehicle traces
CN106922176A (en) * 2014-12-10 2017-07-04 哈曼国际工业有限公司 Lane detection
CN104657746A (en) * 2015-01-29 2015-05-27 电子科技大学 Anomaly detection method based on vehicle trajectory similarity
CN106294485A (en) * 2015-06-05 2017-01-04 华为技术有限公司 Determine the method and device in notable place
JP2017097479A (en) * 2015-11-19 2017-06-01 日立建機株式会社 Abnormality detection device for self-location estimation device, and vehicle
CN106383868A (en) * 2016-09-05 2017-02-08 电子科技大学 Road network-based spatio-temporal trajectory clustering method
CN107944475A (en) * 2017-11-09 2018-04-20 安徽师范大学 Track outlier detection method based on public burst subsequence
CN110069585A (en) * 2017-12-05 2019-07-30 腾讯科技（深圳）有限公司 Treating method and apparatus, storage medium and the electronic device of track point data
CN111328403A (en) * 2018-10-16 2020-06-23 华为技术有限公司 Improved trajectory matching based on quality indicators allowed using weighted confidence values
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
CN110175633A (en) * 2019-04-29 2019-08-27 杭州电子科技大学 A kind of fishing boat track method for detecting abnormality based on Beidou satellite transmission data
CN110490264A (en) * 2019-08-23 2019-11-22 中国民航大学 Multidimensional distance cluster method for detecting abnormality and system based on time series
CN111046968A (en) * 2019-12-20 2020-04-21 电子科技大学 Road network track clustering analysis method based on improved DPC algorithm
CN111242521A (en) * 2020-04-24 2020-06-05 中国人民解放军国防科技大学 Track anomaly detection method and system

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
X. NIU, T. CHEN, C. Q. WU, J. NIU AND Y. LI,: "Label-Based Trajectory Clustering in Complex Road Networks", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 *
X. ZHAO, Y. RAO, J. CAI AND W. MA: "Abnormal Trajectory Detection Based on a Sparse Subgraph", 《IEEE ACCESS》 *
牛新征: "基于时空轨迹的热点区域提取", 《电子科技大学学报》 *
韩昭蓉: "基于自适应阈值的船舶轨迹异常点检测算法", 《计算机与现代化》 *

Also Published As

Publication number Publication date
CN112230253B (en) 2021-07-09

Similar Documents

Publication Publication Date Title
CN108668233B (en) Building entrance detection method and system
CN104821082B (en) Short-time traffic flow prediction method based on integrated evaluation
CN111949896B (en) Track abnormality detection method based on track big data
CN111612038B (en) Abnormal user detection method and device, storage medium and electronic equipment
CN112464439A (en) Three-layer data mining-based power system fault type analysis method and device
CN111401218A (en) Smart city monitoring method and system
CN117436005B (en) Abnormal data processing method in automatic ambient air monitoring process
CN111524350A (en) Method, system, terminal device and medium for detecting abnormal driving condition of vehicle and road cooperation
CN112949735A (en) Liquid hazardous chemical substance volatile concentration abnormity discovery method based on outlier data mining
CN112230253B (en) Track characteristic anomaly detection method based on public slice subsequence
Cui et al. Data-based windstorm type identification algorithm and extreme wind speed prediction
CN113870620B (en) Ship identification method for simultaneously opening multiple AIS devices
CN115186762A (en) Engine abnormity detection method and system based on DTW-KNN algorithm
CN115482489A (en) Improved YOLOv 3-based power distribution room pedestrian detection and trajectory tracking method and system
CN114925731B (en) Method for detecting abnormal value of monitoring data of flexible inclinometer
CN107944475B (en) Track outlier detection method based on public fragment subsequence
CN117076788A (en) Personnel foothold point location analysis method and system based on multidimensional sensing data
CN116257651A (en) Intelligent monitoring system for abnormal sound of through channel cab apron
CN115062708A (en) Abnormal node detection method based on track deviation point embedding and depth clustering
CN113625686A (en) Safety baseline checking system and method based on industrial control protocol
Cui et al. Data-based wind disaster climate identification algorithm and extreme wind speed prediction
CN112906709A (en) Information fusion algorithm based on OPD-S
Elnekave et al. Discovering regular groups of mobile objects using incremental clustering
CN111681429A (en) Method and system for identifying fragile road section in severe weather based on GPS data
CN117854279B (en) Road condition prediction method and system based on edge calculation

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