CN107609075A - A kind of periodicity surveillance information abnormal data cleaning method - Google Patents
A kind of periodicity surveillance information abnormal data cleaning method Download PDFInfo
- Publication number
- CN107609075A CN107609075A CN201710784137.4A CN201710784137A CN107609075A CN 107609075 A CN107609075 A CN 107609075A CN 201710784137 A CN201710784137 A CN 201710784137A CN 107609075 A CN107609075 A CN 107609075A
- Authority
- CN
- China
- Prior art keywords
- data
- surveillance information
- spot
- information data
- maintenance
- 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
Landscapes
- Closed-Circuit Television Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of surveillance information abnormal data cleaning method, comprise the following steps：Travel through the spot list of all maintenances, to the surveillance information data that this is received, the relation between current reconnaissance data and the spot state change of maintenance is calculated, when surveillance information data fit spot motion state, it is judged as correct data, otherwise regards as data to be cleaned；The spot list of Inspection and maintenance, the transient target of spot list is safeguarded to being added before this, when meeting its motion state without this surveillance information data, the transient target for regarding as adding before is abnormal surveillance information data, is purged；Data to be cleaned are regarded as to this, the transient target to be confirmed as one, add the spot list of maintenance.
Description
Technical field
The present invention relates to the abnormal data that surveillance information data are obtained with the Active Intelligence such as radar, photoelectricity cycle sensor
Cleaning treatment field, abnormal data of the surveillance information particularly obtained in the case of by system environments noise, outside active interference
Cleaning problem, the present invention establish scouting object motion state periodically to scout the information data of acquisition, provide a kind of periodicity
The cleaning method of surveillance information abnormal data.
Background technology
Field is cleaned in mass data, common are the system such as Hadoop platform and MapReduce frameworks processing side at present
Method, but these system processing platforms are all to handle different classes of and industry data with a flexible data structure, because of it
The data characteristicses for considering the versatility of platform and can not being directed to specific industry are applied.
To surveillance information data cleansing field, CFAR detection, detection probability control, unruly-value rejecting, dry presently, there are
A variety of methods such as suppression are disturbed, but these methods are to solve the problems, such as abnormal data in terms of some of principle is scouted, also
Can not solve the abnormal data occurred in scouting before terminal processes.
The present invention combines the mass data record that periodically continued scouting obtains, and gives a kind of based on scouting object motion
The abnormal data cleaning method of state, efficiently solve the data interference problem in subsequent treatment.
The content of the invention
The present invention does not consider the situation of surveillance information industry data feature for available data cleaning treatment framework, proposes one
Kind is based on the abnormal data cleaning method for scouting object motion state, and this method is an indivisible entirety, by following step
Rapid composition.
（1）The spot list of all maintenances is traveled through, to the surveillance information data that this is received, calculates current scouting number
According to the relation between the spot state change of maintenance, when surveillance information data fit spot motion state, sentence
Break as correct data, otherwise regard as data to be cleaned.
（2）The spot list of Inspection and maintenance, the transient target of spot list is safeguarded to being added before this,
When meeting its motion state without this surveillance information data, the transient target for regarding as adding before is abnormal surveillance information number
According to being purged；To the transient target of this new addition, treat that subsequent time period determines whether to remove.
（3）Data to be cleaned are regarded as to this, the transient target to be confirmed as one, add the scouting mesh of maintenance
Mark list.
（4）The judgement whether surveillance information data are met with target state is as follows：
The location variation of preservation 5 periodic motions of target, course variable quantity, velocity variable, acceleration change amount, identical
Time cycle in, above-mentioned 4 variable quantities of target state meet the characteristics of motion for scouting object, including position Sudden Changing Rate
Relevant with speed and acceleration, velocity variable is relevant with acceleration change amount, and course variable quantity is by speed
Variable quantity influences.
Brief description of the drawings
Fig. 1 is surveillance information abnormal data cleaning false code process chart.
Beneficial effect
By the periodicity surveillance information data cleaning method of the present invention, solve by reconnaissance system ambient noise, outside active
The influence of the false surveillance information data interference obtained when interference, the application processing to follow-up surveillance information data provide
Beneficial to help.
Implementation steps
A kind of " periodicity surveillance information abnormal data cleaning method " patent of invention is a system schema, by such as following rapid real
Apply.
The first step：Configuration data cleaning parameterses, including the spot intelligence report cycle, spot velocity variations maximum,
Spot acceleration change maximum.
Second step：The surveillance information data received with this, according to the spot intelligence report cycle, calculate the scouting with safeguarding
Dbjective state changes, including location variation, velocity variable, course variable quantity, acceleration change amount, when velocity variable and
Acceleration change amount is respectively less than the maximum of first step setting, and location variation, course variable quantity are respectively less than computation of Period change
During change amount, it is judged as correct data, otherwise regards as data to be cleaned.
3rd step：To data to be cleaned, new transient target is established, adds the spot list of maintenance.
4th step：The spot list of Inspection and maintenance, the interim mesh of spot list is safeguarded to being added before this
Mark, when this reconnaissance data is in second step detection, during no correct data, the transient target for assert maintenance is by scouting extremely
Information data generation, it is purged.
5th step：The spot list of Inspection and maintenance, to the transient target of this new addition, treat subsequent time period by
Four-step method determines whether to clean the data.
Claims (2)
1. a kind of periodicity surveillance information abnormal data cleaning method, it is characterised in that comprise the following steps：
（1）Travel through the spot list of all maintenances, to the surveillance information data that this is received, calculate current reconnaissance data with
Relation between the spot state change of maintenance, when surveillance information data fit spot motion state, it is judged as
Correct data, otherwise regard as data to be cleaned；
（2）The spot list of Inspection and maintenance, the transient target of spot list is safeguarded to being added before this, when without this
When secondary surveillance information data meet its motion state, the transient target for regarding as adding before is abnormal surveillance information data, is entered
Row is removed；To the transient target of this new addition, treat that subsequent time period determines whether to remove；
（3）Data to be cleaned are regarded as to this, the transient target to be confirmed as one, the spot for adding maintenance arranges
Table.
2. based on claim 1 the（1）The judgement whether described surveillance information data of step meet target state is as follows：
The location variation of preservation 5 periodic motions of target, course variable quantity, velocity variable, acceleration change amount, identical
Time cycle in, above-mentioned 4 variable quantities of target state meet the characteristics of motion for scouting object, including position Sudden Changing Rate
Meet time cycle variation relation with speed and acceleration, velocity variable meets that time cycle change is closed with acceleration change amount
System, course variable quantity meet Time Continuous variation relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710784137.4A CN107609075B (en) | 2017-09-04 | 2017-09-04 | A kind of periodicity surveillance information abnormal data cleaning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710784137.4A CN107609075B (en) | 2017-09-04 | 2017-09-04 | A kind of periodicity surveillance information abnormal data cleaning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107609075A true CN107609075A (en) | 2018-01-19 |
| CN107609075B CN107609075B (en) | 2019-11-01 |
Family
ID=61057298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710784137.4A Active CN107609075B (en) | 2017-09-04 | 2017-09-04 | A kind of periodicity surveillance information abnormal data cleaning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107609075B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102879774A (en) * | 2011-07-11 | 2013-01-16 | 哈尔滨工业大学 | Method and apparatus for synthesizing short flight paths |
| US20130226882A1 (en) * | 2012-02-29 | 2013-08-29 | International Business Machines Corporation | Automatic table cleanup for relational databases |
| CN104280723A (en) * | 2014-10-22 | 2015-01-14 | 四川大学 | Method for processing newly built system track in radar clutter area |
| CN104569964A (en) * | 2015-01-30 | 2015-04-29 | 中国科学院电子学研究所 | Moving target two-dimensional detecting and tracking method for ultra-wideband through-wall radar |
-
2017
- 2017-09-04 CN CN201710784137.4A patent/CN107609075B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102879774A (en) * | 2011-07-11 | 2013-01-16 | 哈尔滨工业大学 | Method and apparatus for synthesizing short flight paths |
| US20130226882A1 (en) * | 2012-02-29 | 2013-08-29 | International Business Machines Corporation | Automatic table cleanup for relational databases |
| CN104280723A (en) * | 2014-10-22 | 2015-01-14 | 四川大学 | Method for processing newly built system track in radar clutter area |
| CN104569964A (en) * | 2015-01-30 | 2015-04-29 | 中国科学院电子学研究所 | Moving target two-dimensional detecting and tracking method for ultra-wideband through-wall radar |
Non-Patent Citations (2)
| Title |
|---|
| 牟之英等: "多平台对多目标无源融合定位方法", 《探测与控制学报》 * |
| 袁德诚等: "杂波环境下雷达新建航迹处理方法分析", 《四川大学学报（自然科学版）》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107609075B (en) | 2019-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Battistelli et al. | A distributed Kalman filter with event-triggered communication and guaranteed stability | |
| WO2020256418A3 (en) | Computing system for implementing virtual sensor by using digital twin, and real-time data collection method using same | |
| Purcaru et al. | Optimal robot path planning using gravitational search algorithm | |
| CN110253572B (en) | Event trigger control method for input saturated multi-single-arm manipulator | |
| CN110111363A (en) | A kind of tracking and equipment based on target detection | |
| Synnaeve et al. | Forward modeling for partial observation strategy games-a starcraft defogger | |
| Zeng et al. | Pixel modeling using histograms based on fuzzy partitions for dynamic background subtraction | |
| Sabaliauskaite et al. | A comprehensive approach, and a case study, for conducting attack detection experiments in cyber–physical systems | |
| Perales Gómez et al. | SafeMan: A unified framework to manage cybersecurity and safety in manufacturing industry | |
| CN107609075A (en) | A kind of periodicity surveillance information abnormal data cleaning method | |
| CN110335466B (en) | Traffic flow prediction method and apparatus | |
| CN107169992A (en) | A kind of traffic video moving target detecting method | |
| CN106257507A (en) | The methods of risk assessment of user behavior and device | |
| CN108961287B (en) | Intelligent shelf triggering method, intelligent shelf system, storage medium and electronic equipment | |
| CN111736593A (en) | Stage mobile robot formation asynchronous control method for preventing uncertain DoS attack | |
| Negi et al. | A LSTM approach to detection of autonomous vehicle hijacking | |
| Han et al. | Multi‐tracking of first order multi‐agent networks via self‐triggered control | |
| CN116384594A (en) | Crop pest early warning method, system, terminal and medium based on big data analysis | |
| Bekhtaoui et al. | Maneuvering target tracking using q-learning based Kalman filter | |
| An et al. | Noise mitigation for multiple target tracking in acoustic wireless sensor networks | |
| CN115147590A (en) | Raise dust reduction method and device, electronic equipment and storage medium | |
| Kim | An Alternative State Estimation Filtering Algorithm for Temporarily Uncertain Continuous Time System. | |
| Yoon et al. | Learning image attacks toward vision guided autonomous vehicles | |
| CN104239557A (en) | Method and device for monitoring promoted accounts | |
| RU2016131908A (en) | METHOD FOR COMPUTATIONAL MODELING OF GAS DYNAMICS OF COMBUSTION |
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 |