CN107480647B - Method for detecting abnormal behaviors in real time based on inductive consistency abnormality detection - Google Patents
Method for detecting abnormal behaviors in real time based on inductive consistency abnormality detection Download PDFInfo
- Publication number
- CN107480647B CN107480647B CN201710726270.4A CN201710726270A CN107480647B CN 107480647 B CN107480647 B CN 107480647B CN 201710726270 A CN201710726270 A CN 201710726270A CN 107480647 B CN107480647 B CN 107480647B
- Authority
- CN
- China
- Prior art keywords
- track
- distance
- updating
- data set
- sub
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Radar Systems Or Details Thereof (AREA)
- Organic Low-Molecular-Weight Compounds And Preparation Thereof (AREA)
Abstract
The invention discloses an abnormal behavior real-time detection method based on inductive consistency abnormality detection. The method can fully consider the position, speed and movement direction information of the target, adopts the idea of inductive consistency abnormal detection, can realize real-time detection of abnormal behaviors of the target under the condition of greatly reducing the calculated amount, and specifically comprises the following steps of 1, defining related variables; step 2, initializing; step 3, carrying out real-time anomaly detection on each sub track in the test track; step 4, after each sub track in the current test track is detected abnormally, updating the training track data set; step 5, updating the multi-factor directional Hausdorff distance matrix; and 6, carrying out real-time anomaly detection on the next test track. The method has the advantages of simple parameter setting, high accuracy, real-time detection, easy realization of engineering and wide application prospect in the field of early warning and monitoring.
Description
Technical Field
The invention relates to an anomaly detection technology in data mining and a high-level fusion technology in information fusion, belonging to the field of pattern recognition and intelligent information processing.
Background
With the continuous perfection of the information fusion theory and the wide application of the information fusion technology, the information processing system can automatically or semi-automatically complete the detection, tracking, track association and attribute judgment of the target through the fusion process of a detection level, a position level and an attribute level, and form a continuous and stable target track. With the increasing of the types and the quantity of the targets and the increasing of the performance of the early warning monitoring system, more and more target information data are formed and stored in various early warning monitoring systems. How to let a computer automatically find the abnormal behavior of a target is a very important research content in intelligent intelligence processing. A large number of scholars at home and abroad carry out a great deal of research on the real-time abnormality detection problem of the target, and the main method comprises a learning stage and an abnormality detection stage. The learning stage includes a statistical model-based method, a neural network-based method, a clustering-based method, and the like, and the abnormality detection stage includes a statistical test-based method, a distance-based method, and the like. However, the methods generally have the problems of complex parameter setting, inaccurate statistical model, ineffective control of false alarm rate, poor online learning effect and the like. The abnormal behavior sequential detection method based on the multi-factor inconsistency measurement can fully utilize the position, speed and motion direction information of a target, and realize real-time abnormal detection of the abnormal behavior of the target in an online learning and sequential abnormal detection mode, but all historical track data need to be recalculated during each abnormal detection, so that the problem of large calculation amount exists.
Disclosure of Invention
The invention provides an abnormal behavior real-time detection method based on inductive consistency abnormal detection, which not only can fully consider the position, the speed and the motion direction information of a target, but also adopts the idea of inductive consistency abnormal detection, and can realize the real-time detection of the abnormal behavior of the target under the condition of greatly reducing the calculated amount. The method specifically comprises the following steps:
1) an anomaly threshold;
2) the number of neighbors to consider k;
3) training track data set (TR)1,…,TRlWherein the compressed track number set is { TR }1,…,TRr}, checking the track data set to be { TRr+1,…,TRl};
4) Multifactor oriented Hausdorff distance matrix M, each element M of matrixi,jI 1, …, l-r, j 1, …, k denotes the track TR in the test track data setiI-r +1, …, l to the compressed track data set { TR }1,…,TRrA multi-factor directional Hausdorff distance between jth and near tracks;
5) an empty priority sequence Q;
6) test track TRl+1Continuously updated track point x1,…,xL。
7) Variable for exception indicationWherein j 1, …, L-1 corresponding to the sub-trackThe category of the result of the calculation is,corresponding track { x1∪x2∪…∪xL}=TRl+1Calculating the obtained category;
TRgG-1, …, r, a multifactorial directional Hausdorff distance mgG-1, …, assigning an initial value of zero to r, and calculating a multi-factor directional Hausdorff distance matrix Mi,1,…,Mi,kIs defined as
Step 3, for the test track TRl+1={x1∪x2∪…∪xLSub track in { x }1∪…∪xj1, …, L repeats the following anomaly detection process:
1) for track TR in the inspection track data setiI-r +1, …, l as a measure of inconsistencyiUpdating is carried out;
2) definition of m according to the multi-factor directional Hausdorff distancegUpdating the value of (1);
3) updating the elements in Q;
4) extracting current k distance values from QFor the current test sub track { x1∪…∪xj} disparity measure αl+1Updating the value of (1);
5) calculating pl+1Taking values;
6) p is to bel+1Judging a threshold value, and detecting and updating the abnormal condition of the current test sample;
step 4, when testing the track TRl+1Each sub track { x }1∪…∪xjWhen the abnormality detection is completed for all the j-1, …, an abnormality indication variable is output, and TR is setl+1Add to training track dataset TR1,…,TRlIn the method, the training track data set is updated to be { TR }1,…,TRl+1Where the inspection track data set is updated to { TR }r+1,…,TRl+1};
Step 5, updating the multi-factor directional Hausdorff distance matrix M as follows;
step 6, the updated training track set { TR1,…,TRl+1The updated multi-factor directional Hausdorff distance matrix M is used as a new input variable for the test track TRl+1And (6) carrying out abnormity detection.
The invention has the beneficial effects that: the method for detecting the abnormal behaviors based on the inductive consistency abnormity detection not only comprehensively considers the position, the speed and the course information of the target and can detect the abnormal behaviors of the target in real time, but also adopts the idea of inductive consistency abnormity detection, has the advantages of simple parameter setting, high accuracy and real-time detection, and can realize the real-time detection of the abnormal behaviors of the target in the early warning monitoring field under the condition of greatly reducing the calculated amount.
Drawings
FIG. 1 is an overall flow chart of the method for detecting abnormal behavior in real time based on inductive consistency abnormality detection according to the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
1) an anomaly threshold;
2) the number of neighbors to consider k;
3) training track data set (TR)1,…,TRlWherein the compressed track number set is { TR }1,…,TRr}, checking the track data set to be { TRr+1,…,TRl};
4) Multifactor oriented Hausdorff distance matrix M, each element M of matrixi,jI 1, …, l-r, j 1, …, k denotes the track TR in the test track data setiI-r +1, …, l to the compressed track data set { TR }1,…,TRrA multi-factor directional Hausdorff distance between jth and near tracks;
5) an empty priority sequence Q;
6) test track TRl+1Continuously updated track point x1,…,xL;
7) Variable for exception indicationWherein j 1, …, L-1 corresponding to the sub-trackThe category of the result of the calculation is,corresponding track { x1∪x2∪…∪xL}=TRl+1Calculating the obtained category;
step 2, initialization: for current test sub-trackTR into compressed track data setgG-1, …, r, a multifactorial directional Hausdorff distance mgG-1, …, assigning an initial value of zero to r, and calculating a multi-factor directional Hausdorff distance matrix Mi,1,…,Mi,kIs defined asMulti-factor orientationThe Hausdorff distance is specifically defined as follows:
1) considering the position characteristics, the speed characteristics and the heading characteristics of the two targets, the multi-factor distance between the two target points a and b is defined as:
mfdist(a,b)=wd·dist(a,b)+wv·dist(va,vb)+wθ·dist(θa,θb) (1)
wherein v isa,vbRepresenting the velocity, θ, of points a and ba,θbIndicating the course of points a and b, dist (a, b) indicating the Euclidean distance of the position features between points a and b, dist (v)a,vb) Euclidean distance, dist (θ) representing a velocity characteristic between points a and ba,θb) Euclidean distance, w, representing course characteristics between points a and bdWeight factor, w, representing a position featurevWeight factor, w, representing a velocity characteristicθRepresenting a weight factor of the heading characteristic, wherein the value of the weight factor depends on an application scene of the multi-factor distance;
2) target track TR based on multifactor distance mfdist (a, b) between two target pointsATo target track TRBThe multifactor oriented Hausdorff distance of (a) is defined as:
TRAand TRBTwo target tracks are provided;
step 3, for the test track TRl+1={x1∪x2∪…∪xLSub track in { x }1∪…∪xj1, …, L repeats the following anomaly detection process:
1) for track TR in the inspection track data setiI-r +1, …, l as a measure of inconsistencyiUpdating:
αi=vi-r(3)
2) definition of m according to the multi-factor directional Hausdorff distancegUpdating the value of (a):
wherein m isgG-1, …, r representing the current test sub-trackTR into compressed track data setgG-1, …, r, a multifactorial directional Hausdorff distance;
3) updating the elements within Q: if the number of elements in Q is less than the number k of neighbors, then the current m is determinedgInserting the value into Q, if there are k distance values in Q, and the current mgIf the distance value is less than the maximum distance value in Q, deleting the maximum distance value in Q and adding the current mgInserting values into Q;
4) extracting current k distance values from QPerforming summation calculation to the current test sub track { x1∪…∪xj} disparity measure αl+1Updating the value of (a):
5) calculating pl+1Taking values:
|{i=r+1,…,l+1:αi≥αl+1denotes the set { i ═ r +1, …, l +1: αi≥αl+1The number of elements in the page;
6) p is to bel+1And (3) judging a threshold value, and detecting and updating the abnormal condition of the current test sample:
if p isl+1<,
If not, then,
wherein the content of the first and second substances,representing the current sub-track { x1∪…∪xjJ is 1, …, and the detection result of L is abnormal behavior,representing the current sub-track { x1∪…∪xj1, …, and the detection result of L is normal behavior;
step 4, when testing the track TRl+1Each sub track { x }1∪…∪xjWhen the abnormality detection is completed for all the j-1, …, an abnormality indication variable is output, and TR is setl+1Add to training track dataset TR1,…,TRlIn the method, the training track data set is updated to be { TR }1,…,TRl+1Where the inspection track data set is updated to { TR }r+1,…,TRl+1};
Step 5, updating the multi-factor directional Hausdorff distance matrix M as follows: distance vector (m) to be output1,…,ml) Added to M as the last row;
step 6, the updated training track set { TR1,…,TRl+1The updated multi-factor directional Hausdorff distance matrix M is used as a new input variable for the test track TRl+2And (6) carrying out abnormity detection.
Claims (4)
1. A real-time detection method for abnormal behaviors based on inductive consistency abnormality detection is characterized by comprising the following steps:
step 1, defining related variables:
1) an anomaly threshold;
2) the number of neighbors to consider k;
3) training track data set (TR)1,…,TRnWherein the compressed track number set is { TR }1,…,TRr}, checking the track data set to be { TRr+1,…,TRn};
4) Multifactor oriented Hausdorff distance matrix M, each element M of matrixi,jI 1, …, n-r, j 1, …, k denotes the track TR in the test track data setiI-r +1, …, n to the compressed track data set TR1,…,TRrA multi-factor directional Hausdorff distance between jth and near tracks;
5) an empty priority sequence Q;
6) test track TRn+1Continuously updated track point x1,…,xL;
7) Variable for exception indicationWhereinj 1, …, L-1 corresponding to the sub-trackThe category of the result of the calculation is,corresponding trackCalculating the obtained category;
step 2, initialization: for the current test sub-trackTR into compressed track data setgG-1, …, r, a multifactorial directional Hausdorff distance mgG-1, …, assigning an initial value of zero to r, and calculating a multi-factor directional Hausdorff distance matrix Mi,1,…,Mi,kIs defined as
Step 3, for the test track TRn+1={x1∪x2∪…∪xLSub track in { x }1∪…∪xj1, …, L repeats the following anomaly detection process:
1) for track TR in the inspection track data setiI-r +1, …, n as a measure of inconsistencyiUpdating is carried out;
2) definition of m according to the multi-factor directional Hausdorff distancegUpdating the value of (1);
3) updating the elements in Q;
4) extracting current k distance values from QFor the current test sub track { x1∪…∪xj} disparity measure αl+1Updating the value of (1);
5) calculating pn+1Taking values;
6) p is to ben+1Judging a threshold value, and detecting and updating the abnormal condition of the current test sample;
step 4, when testing the track TRn+1Each sub track { x }1∪…∪xjWhen the abnormality detection is completed for all the j-1, …, an abnormality indication variable is output, and TR is setn+1Add to training track dataset TR1,…,TRnIn the method, the training track data set is updated to be { TR }1,…,TRn+1Where the inspection track data set is updated to { TR }r+1,…,TRn+1};
Step 5, updating the multi-factor directional Hausdorff distance matrix M as follows;
step 6, the updated training track set { TR1,…,TRn+1The updated multi-factor directional Hausdorff distance matrix M is used as a new input variable for the test track TRn+2And (6) carrying out abnormity detection.
2. The method for detecting abnormal behaviors based on inductive consistency abnormality detection according to claim 1, wherein the specific definition of the multi-factor directional Hausdorff distance in step 2 is as follows:
1) considering the position characteristics, the speed characteristics and the heading characteristics of the two targets, the multi-factor distance between the two target points a and b is defined as:
mfdist(a,b)=wd·dist(a,b)+wv·dist(va,vb)+wθ·dist(θa,θb)
wherein v isa,vbRepresenting the velocity, θ, of points a and ba,θbIndicating the course of points a and b, dist (a, b) indicating the Euclidean distance of the position features between points a and b, dist (v)a,vb) Euclidean distance, dist (θ) representing a velocity characteristic between points a and ba,θb) Euclidean distance, w, representing course characteristics between points a and bdWeight factor, w, representing a position featurevWeight factor, w, representing a velocity characteristicθRepresenting a weight factor of the heading characteristic, wherein the value of the weight factor depends on an application scene of the multi-factor distance;
2) target track TR based on multifactor distance mfdist (a, b) between two target pointsATo target track TRBThe multifactor oriented Hausdorff distance of (a) is defined as:
TRAand TRBTwo target tracks.
3. The method for detecting abnormal behaviors based on inductive consistency abnormality detection according to claim 1, wherein the step 3 is specifically as follows:
for test track TRl+1={x1∪x2∪…∪xLSub track in { x }1∪…∪xj1, …, L repeats the following anomaly detection process:
1) for track TR in the inspection track data setiI-r +1, …, n as a measure of inconsistencyiUpdating:
αi=vi-r
2) definition of m according to the multi-factor directional Hausdorff distancegUpdating the value of (a):
wherein m isgG-1, …, r representing the current test sub-trackTR into compressed track data setgG-1, …, r, a multifactorial directional Hausdorff distance;
3) updating the elements within Q: if the number of elements in Q is less than the number k of neighbors, then the current m is determinedgInserting the value into Q, if there are k distance values in Q, and the current mgIf the distance value is less than the maximum distance value in Q, deleting the maximum distance value in Q and adding the current mgInserting values into Q;
4) extracting current k distance values from QPerforming summation calculation to the current test sub track { x1∪…∪xj} disparity measure αn+1Updating the value of (a):
5) calculating pn+1Taking values:
|{i=r+1,…,n+1:αi≥αn+1denotes the set { i ═ r +1, …, n +1: α } -i≥αn+1The number of elements in the page;
6) p is to ben+1And (3) judging a threshold value, and detecting and updating the abnormal condition of the current test sample:
if p isn+1<,
If not, then,
4. The method for detecting abnormal behavior in real time based on inductive consistency abnormality detection according to claim 1, wherein the step 5 is specifically as follows:
the multi-factor directional Hausdorff distance matrix M is updated as follows: distance vector (m) to be output1,…,mn) Added to M as the last line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710726270.4A CN107480647B (en) | 2017-08-22 | 2017-08-22 | Method for detecting abnormal behaviors in real time based on inductive consistency abnormality detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710726270.4A CN107480647B (en) | 2017-08-22 | 2017-08-22 | Method for detecting abnormal behaviors in real time based on inductive consistency abnormality detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107480647A CN107480647A (en) | 2017-12-15 |
CN107480647B true CN107480647B (en) | 2020-11-03 |
Family
ID=60602185
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710726270.4A Active CN107480647B (en) | 2017-08-22 | 2017-08-22 | Method for detecting abnormal behaviors in real time based on inductive consistency abnormality detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107480647B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108256285A (en) * | 2018-01-09 | 2018-07-06 | 上海交通大学 | Flight path exception detecting method and system based on density peaks fast search |
CN115356013B (en) * | 2022-08-15 | 2023-04-18 | 桂林师范高等专科学校 | Reflow soldering temperature curve abnormity detection method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6104834A (en) * | 1996-08-01 | 2000-08-15 | Ricoh Company Limited | Matching CCITT compressed document images |
CN104986347A (en) * | 2015-06-03 | 2015-10-21 | 中国民航大学 | Real-time detection method for civil aircraft airline pilot operation errors |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105894014B (en) * | 2016-03-29 | 2020-03-10 | 中国人民解放军海军航空大学 | Abnormal behavior sequential detection method based on multi-factor inconsistency measurement |
-
2017
- 2017-08-22 CN CN201710726270.4A patent/CN107480647B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6104834A (en) * | 1996-08-01 | 2000-08-15 | Ricoh Company Limited | Matching CCITT compressed document images |
CN104986347A (en) * | 2015-06-03 | 2015-10-21 | 中国民航大学 | Real-time detection method for civil aircraft airline pilot operation errors |
Non-Patent Citations (1)
Title |
---|
基于多维航迹特征的异常行为检测方法;潘新龙,王海鹏,何友,熊伟,周伟;《航空学报》;20170430;第38卷(第4期);第254-263页 * |
Also Published As
Publication number | Publication date |
---|---|
CN107480647A (en) | 2017-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106572493B (en) | Rejecting outliers method and system in LTE network | |
CN105279365B (en) | For the method for the sample for learning abnormality detection | |
CN103473540B (en) | The modeling of intelligent transportation system track of vehicle increment type and online method for detecting abnormality | |
JP7298494B2 (en) | Learning device, learning method, learning program, determination device, determination method, and determination program | |
CN104317681A (en) | Behavioral abnormality automatic detection method and behavioral abnormality automatic detection system aiming at computer system | |
CN104715154B (en) | Core K average Data Associations based on KMDL criterion criterions | |
CN105894014B (en) | Abnormal behavior sequential detection method based on multi-factor inconsistency measurement | |
CN114090718B (en) | Bi-LSTM prediction and fuzzy analysis based interrupted track correlation method | |
CN107480647B (en) | Method for detecting abnormal behaviors in real time based on inductive consistency abnormality detection | |
CN105678417A (en) | Prediction method and device for tunnel face water inflow of construction tunnel | |
CN102257448A (en) | Robust filtering and prediction using switching models for machine condition monitoring | |
CN112766301A (en) | Similarity judgment method for indicator diagram of oil extraction machine | |
CN114997296A (en) | Unsupervised track anomaly detection method and unsupervised track anomaly detection system based on GRU-VAE model | |
CN114863170A (en) | Deep learning-based new energy vehicle battery spontaneous combustion early warning method and device | |
Wang et al. | Three‐stage feature selection approach for deep learning‐based RUL prediction methods | |
CN112882898B (en) | Anomaly detection method, system, device and medium based on big data log analysis | |
CN115063337A (en) | Intelligent maintenance decision-making method and device for buried pipeline | |
CN111209942B (en) | Multi-mode sensing abnormality monitoring method for foot robot | |
Li et al. | Structural health monitoring data anomaly detection by transformer enhanced densely connected neural networks | |
CN106203526B (en) | Goal behavior mode online classification method based on multidimensional characteristic | |
CN112836719A (en) | Indicator diagram similarity detection method fusing two classifications and three groups | |
Flotzinger et al. | Building inspection toolkit: Unified evaluation and strong baselines for damage recognition | |
CN117034808A (en) | Natural gas pipe network pressure estimation method based on graph attention network | |
Xin et al. | Research on Remote Sensing Image Target Detection Algorithm Based on YOLOv5 | |
WO2020183781A1 (en) | Abnormality diagnosis device |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200930 Address after: 264001 Research and Academic Department, 188 Erma Road, Zhifu District, Yantai City, Shandong Province Applicant after: NAVAL AERONAUTICAL University Address before: 264001 Yantai City, Zhifu Province, No. two road, No. 188, Department of research, Applicant before: NAVAL AERONAUTICAL AND ASTRONAUTICAL University PLA |
|
GR01 | Patent grant | ||
GR01 | Patent grant |