CN109190924B - Video number plate data quality analysis method - Google Patents
Video number plate data quality analysis method Download PDFInfo
- Publication number
- CN109190924B CN109190924B CN201810914240.0A CN201810914240A CN109190924B CN 109190924 B CN109190924 B CN 109190924B CN 201810914240 A CN201810914240 A CN 201810914240A CN 109190924 B CN109190924 B CN 109190924B
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- number plate
- time period
- plate identification
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 34
- 230000002159 abnormal effect Effects 0.000 claims abstract description 39
- 238000007689 inspection Methods 0.000 claims abstract description 6
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010234 longitudinal analysis Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 14
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 abstract 1
- 238000000034 method Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 6
- 238000007619 statistical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a video number plate data quality analysis method, which analyzes the integrity of equipment data acquisition based on the online condition of video number plate identification equipment, further analyzes the data reasonability based on the historical data of the video number plate, the data quality of vehicle inspection equipment and GPS data information, and automatically warns equipment faults; the video license plate data quality analysis method comprises the steps of constructing a data quality detection system of 'data integrity-flow rationality-time rationality', analyzing and detecting data collected by license plate recognition equipment based on the online condition, flow data analysis and time difference analysis conditions of the license plate recognition equipment, judging the abnormal condition of the equipment according to abnormal data and automatically giving an early warning, so that a manager can effectively master the health state of monitoring equipment and timely maintain and manage the abnormal equipment.
Description
Technical Field
The invention relates to a video number plate data quality analysis method.
Background
The 'number plate recognition' utilizes the dynamic video of the vehicle to automatically recognize the number of the vehicle number plate, and is the principle of main collection of equipment such as an electronic police, an intelligent card port and the like. Present number plate identification equipment is widely applied to in the urban traffic management and control, but receives uncertain factors influence such as equipment operating condition, network transmission, road traffic situation, surrounding environment, and number plate identification equipment probably has the data quality problem of gathering, such as data loss, the license plate discernment is unusual, time data drift etc. and data quality problem will directly influence electronic police, intelligent bayonet, ETC, self-service parking detecting system reliability and stability, cause adverse effect for traffic management and control law enforcement etc.. Therefore, for the traffic data quality acquired by the number plate identification equipment, a complete data quality detection method is matched, abnormal data are effectively isolated, and early warning is carried out on the equipment, so that managers can find out maintenance in time.
At present, research aiming at the data quality of number plate recognition equipment mainly focuses on the research of the data accuracy of number plate, for example, patent CN 201510559740.3 proposes a method, device and system for improving the accuracy of license plate recognition, patent CN 201410638356.8 proposes a method for correcting video metadata in a traffic scene, patent CN201610270472.8 proposes an intelligent error method and system for license plate recognition based on license plate rules and space-time accessibility, patent CN 201610160748.7 proposes a method and system for controlling the detection reliability of passing vehicles at a bayonet, and patent CN 201710115608.2 proposes a method for checking the data quality of bayonet equipment based on positioning data. The patents CN 201410638356.8 and CN201610270472.8 are all based on number plate data to analyze vehicle tracks so as to reject abnormal identification information, the patent CN 201610160748.7 obtains threshold values of data quality evaluation indexes such as data quantity and identification rate through statistical analysis of historical detection data, and then judges data quality risks of bayonet equipment, rejects abnormal equipment, and the patent CN 201610160748.7 introduces a multi-source data consistency concept and analyzes data quality based on GPS positioning data.
In summary, although the existing research is directed at the license plate recognition device for the research on the recognition accuracy and the basic research on the data quality, with the development of technologies such as intelligent traffic and artificial intelligence machine learning, the license plate data can be compared in multiple dimensions of time, space, horizontal and vertical directions on the basis of the existing technology and data research, and other multi-source data can be analyzed in an auxiliary manner, so that the data quality analysis and detection of the license plate data can be realized, abnormal devices can be effectively warned, the synchronous detection and management of the device data can be realized, and high-quality data can be provided for traffic control.
Disclosure of Invention
The invention aims to provide a video number plate data quality analysis method, which solves the problems of how to effectively early warn abnormal equipment, realize equipment data synchronous detection management and provide high-quality data for traffic control in the prior art.
The invention provides a video number plate data quality analysis method, which comprises the steps of analyzing the integrity of number plate identification data in an online state of equipment, comparing the flow data with historical flow and flow data collected by a vehicle detector device to detect the reasonability of the flow, and calculating the average time difference to detect the reasonability of data time by analyzing the GPS data of vehicles with vehicle-mounted equipment in a road network, thereby effectively judging abnormal equipment and automatically early warning, providing a support basis for the management of the number plate identification equipment of a traffic control department, and simultaneously providing reliable and accurate data for traffic planning management.
The technical solution of the invention is as follows:
a video number plate data quality analysis method analyzes the integrity of equipment data acquisition based on the online condition of video number plate identification equipment, further analyzes the data rationality based on the historical data of the video number plate, the data quality of vehicle inspection equipment and GPS data information, and automatically warns equipment faults, comprises the following steps,
s1, analyzing the integrity of the data collected by the equipment according to the online condition of the number plate identification equipment;
s2, analyzing and checking the rationality of the data quality according to the flow information of the data collected by the license plate identification equipment;
s3, comparing the GPS data of the vehicle with the positioning equipment with the time information of the data collected by the number plate identification equipment to realize the time rationality analysis of the number plate identification data;
and S4, automatically warning the abnormality of the number plate identification equipment.
Further, in step S1, specifically,
s11, time dimension online rate analysis, wherein the online condition of the equipment in each unit time period is statistically analyzed based on the online state of the number plate identification equipment in the statistical time period, if the online time period ratio is lower than the online rate threshold, the step S4 is carried out, otherwise, the step S12 is carried out;
and S12, analyzing the space dimension online rate, extracting online data of all license plate recognition devices in the road network system, calculating the total online rate of the devices in each unit time period, if the total online rate of the devices is lower than the online threshold of the devices of the system, determining that the license plate recognition system has system faults and automatically warns, and if not, turning to the step S2.
Further, in step S2, specifically,
s21, longitudinal analysis of data flow is achieved through comparison and analysis with equipment historical data, data collected by a unit time period number plate recognition device and historical data of the same time period are compared and analyzed, if the traffic flow in the unit time period exceeds a historical flow threshold interval in the unit time period, the data collected by the equipment in the unit time period is judged to be suspicious abnormal data, the step S22 is carried out, otherwise, the data in the unit time period are considered to be normal, and if all the data in the unit time period in the statistical time period are normal, the step S3 is carried out;
s22, multi-source data flow transverse comparison analysis is achieved through comparison of data quality of the vehicle detector equipment at the arrangement point of the number plate identification equipment.
Further, in step S22, specifically,
s221, extracting data collected by the same-point vehicle detector equipment in the time period to which the suspicious abnormal data belongs, analyzing the quality of the data collected by the vehicle detector equipment, if the data collected by all the equipment in the time period to which the suspicious abnormal data belongs are the suspicious abnormal data, determining that time abnormality possibly exists, and turning to the step S3, otherwise, turning to the next step.
S222, collecting all suspicious abnormal data in the statistical time period, if the ratio of the suspicious abnormal data amount to the total data is larger than the suspicious data proportion threshold, turning to the step S4, otherwise, turning to the step S3.
Further, in step S3, specifically,
s31, extracting GPS data of vehicles with vehicle-mounted positioning devices in the road network, matching the positioning data into the road network, further establishing a device road section association table according to the positions of the number plate identification devices in the road network and road network road section information, and extracting the GPS data in the GPS data range of each number plate identification device;
s32, comparing and analyzing the GPS data in the equipment range with the number plate identification data, extracting the GPS data of the number plate in the data range according to the vehicle number plate information collected by the number plate identification equipment to obtain the average time difference between the two numerical values, if the average time difference in the unit time period is larger than a threshold value, turning to the step S4, and if not, considering that the data collected by the number plate identification equipment is normal.
Further, the average time difference per unit time period between the GPS data and the number plate identification data within the range of the device in step S32, specifically,
in the formula, tGPSTime of data collected for GPS, tALPRThe time value of the number plate identification data is n, and the data volume of the GPS data collected in the range of the number plate identification equipment is n.
Further, in step S32, the average time difference per unit time period is determined based on the GPS data of the vehicles traveling in the unit time
The calculation is carried out, namely:
wherein N is the number of vehicles.
The invention has the beneficial effects that:
a data quality detection system of 'data integrity-flow rationality-time rationality' is constructed, data collected by a number plate recognition device are analyzed and detected based on the online condition, flow data analysis and time difference analysis conditions of the number plate recognition device, abnormal conditions of the device are judged according to the abnormal data, automatic early warning is achieved, a manager can effectively master the health state of the monitoring device, and the abnormal device is maintained and managed in time.
The invention innovatively provides multi-source data analysis, data quality of other equipment at the point location is synchronously analyzed on the basis of the number plate identification and layout point location, and whether the equipment is abnormal or not is judged on the basis of the abnormal data quality condition of all the equipment, so that the accuracy of equipment abnormality judgment and number plate data acquisition traffic flow data is improved.
The invention provides a method for analyzing the time rationality of number plate data based on comparison between GPS data and number plate data of taxies and buses operating vehicles with positioning devices in equipment ranges and analysis based on average time difference.
Drawings
Fig. 1 is a schematic flow chart of a video license plate data quality analysis method according to an embodiment of the present invention.
Fig. 2 is an explanatory diagram of the GPS data range of the number plate identifying device 4 in the embodiment.
Wherein, 1-number plate identification equipment 4; 2-GPS data range.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Examples
According to the video number plate data quality analysis method, a single number plate identification device is used as an object, abnormal data are identified through three aspects of analysis of data integrity, data flow rationality and data time rationality, faults of the number plate identification device are early warned, the quality of the number plate identification data is timely judged, the fault early warning device provides high-quality data for traffic control, and stable operation of a system is guaranteed.
A video number plate data quality analysis method analyzes the integrity of equipment data acquisition based on the online condition of video number plate identification equipment, further analyzes the data rationality based on the historical data of the video number plate, the data quality of vehicle inspection equipment and GPS data information, and automatically warns equipment faults. As shown in fig. 1, the following is specific:
s1, analyzing the integrity of the data collected by the equipment according to the online condition of the number plate identification equipment.
And S11, analyzing the time dimension online rate. And (4) performing statistical analysis on the online condition of the equipment in each unit time period based on the online state of the number plate identification equipment in the statistical time period, if the online time period ratio is lower than an online rate threshold, turning to the step S4, and otherwise, turning to the step S12. Wherein the statistical time period is generally in units of hours or days, and the unit time period is 5min, 10min or 15 min.
And S12, carrying out space dimension online rate analysis. And extracting online data of all the number plate identification devices in the road network system, calculating the total online rate of the devices in each unit time period, if the total online rate of the devices is lower than the online threshold of the system devices, determining that the number plate identification system has system faults and automatically warns, otherwise, turning to the step S2.
In general, the road network system refers to all the number plate identification devices distributed in the same type in the jurisdiction range, and meanwhile, the online conditions of the devices of all manufacturers can be calculated and analyzed according to the number plate identification device manufacturers, and early warning is carried out on the manufacturers with abnormal devices.
And S2, analyzing and checking the reasonability of the data quality according to the flow information of the data acquired by the number plate identification equipment.
And S21, longitudinal analysis of data flow is realized through comparison and analysis with historical data of the equipment.
And comparing and analyzing the data collected by the license plate identification equipment in the unit time period with historical data of the same time period, if the traffic flow in the unit time period exceeds the threshold interval of the historical traffic flow in the unit time period, judging the data collected by the equipment in the unit time period as suspicious abnormal data, and going to the step S22, otherwise, judging that the data in the unit time period are normal, and if all the data in the unit time period in the statistical time period are normal, going to the step S3. The historical flow threshold value of unit time is determined according to the average maximum value and the minimum value of historical data or the 15% bit median and the 85% bit median of the data.
Generally, historical data of weeks and time points are used as calculation units for improving the accuracy of the historical data, wherein the time period of Monday is 7:00-7:15, and the time period of Monday is corresponding to the average value interval of the time period of Monday earlier by 7:00-7:15 in past time.
S22, multi-source data flow transverse comparison analysis is achieved through data quality comparison of the vehicle detector equipment at the arrangement point of the number plate identification equipment.
S221, extracting data collected by the same-point vehicle detector device in the time period to which the suspicious abnormal data belongs, analyzing the quality of data collected by other devices, if the data collected by all the devices in the time period to which the suspicious abnormal data belongs are the suspicious abnormal data, determining that time is abnormal, and turning to the step S3, otherwise, turning to the next step.
In general, an intersection or a road section is provided with not only the number plate recognition and collection device but also a vehicle inspection device, wherein the data quality detection step of the vehicle inspection device is consistent with the step S21, and whether the data is abnormal or not is determined according to the comparison with the historical traffic flow value.
S222, collecting all suspicious abnormal data in the statistical time period, if the ratio of the suspicious abnormal data amount to the total data is larger than the suspicious data proportion threshold, turning to the step S4, otherwise, turning to the step S3.
And S3, comparing the GPS data of the vehicle with the positioning equipment with the time information of the data collected by the number plate identification equipment, and realizing time rationality analysis of the number plate identification data.
S31, GPS data of vehicles with vehicle-mounted positioning devices in the road network are extracted, the positioning data are matched into the road network, a device road section association table is further established according to the positions of the number plate recognition devices in the road network and road network road section information, and GPS data in the GPS data range of each number plate recognition device are extracted.
In general, the vehicle is selected from a taxi, a bus, and other commercial vehicles. Alternatively, the general direction of travel of the vehicle may be determined based on the chronological order of the GPS data, such that the data range is determined by the possible passage of the vehicle. For a crossroad, the number plate identification device at the east entrance can only show the GPS data at the south, the west and the north after the occurrence of the GPS data at the east entrance, thereby excluding the GPS data in the opposite direction of the east entrance, and setting the position which appears within 20-50 meters of the stop line of the east entrance as a data range, thereby extracting effective GPS data.
S32, comparing and analyzing the GPS data in the equipment range with the number plate identification data, extracting the GPS data of the number plate in the data range according to the vehicle number plate information collected by the number plate identification equipment, and obtaining the average time difference between the two values
Namely:
in the formula, tGPSTime of data collected for GPS, tALPRThe time value of the number plate identification data is n, and the data volume of the GPS data collected in the range of the number plate identification equipment is n.
Further, the GPS data of a plurality of vehicles based on the way in the unit time is compared with the average time difference in the unit time period
The calculation is carried out, namely:
in the formula, N is the number of vehicles.
If the average time difference in the unit time period is greater than the threshold value, the process goes to step S4, otherwise, the data collected by the number plate identification device is considered to be normal.
And S4, identifying the abnormality of the equipment and automatically giving an early warning.
The embodiment method can simultaneously carry out real-time detection on the data, and carry out detection analysis on the data integrity, the flow data rationality and the time rationality according to the real-time data volume from the present day to the present.
One specific example of an embodiment is as follows:
and selecting detection data of a certain day, and selecting for 15min in unit time period.
The device data integrity is checked according to step S1:
summarizing the online conditions of 2595 sets of equipment in the road network in each unit time period, calculating the threshold value of the equipment in the online time period of the equipment on the day, and selecting 10 sets of equipment values to perform an example:
and comparing the online rate threshold value (the selected threshold value is 80%) to find that the equipment 3 is abnormal, and carrying out equipment abnormity early warning. And further carrying out statistical analysis on the total online condition of the road network equipment in each unit time period, wherein the total online condition is greater than the total online rate threshold value by 50%, so that system abnormity does not exist.
And (5) detecting the reasonability of the data flow collected by the number plate equipment according to the step S2:
taking the device 4 as an example, the data flow is 311 when the detection date is 7:00-7:15, the average 15% median and the 85% median are selected as the flow threshold interval according to the historical flow, which is [280,320], and the average value is a normal value. In the same way, the data traffic of each time segment of the detection day is compared and analyzed, and abnormal time segments are extracted, which are as follows:
| time period | Flow value | Historical flow threshold interval |
| 2:00-2:15 | 73 | [50,70] |
| 2:15-2:30 | 65 | [25,40] |
The equipment 4 is arranged at an entrance way at the south of the A road, the entrance way is provided with equipment number plate identification equipment (electronic police) 4 and a microwave vehicle detector, the vehicle flow of the microwave vehicle detector 2:00-2:15 and 2:15-2:30 is extracted, the time period is found to be abnormal by comparing with historical vehicle flow data, and the default is that the equipment 4 is normal.
And simultaneously, detecting other equipment to find that the equipment is normal equipment.
The reasonableness of the time collected by the number plate device is detected according to the step S3:
taking the device 4 as an example, the GPS data range is shown in fig. 2 (the intersection a is an intersection, and the number plate recognition device 4 is located at the south entrance). In fig. 2, reference numeral 1 is a number plate recognition device 4; reference numeral 2 is a GPS data range.
Extracting taxi GPS data, extracting GPS data in a data range according to the data time sequence and the position information, and respectively comparing and calculating the taxi number plate with the number plate data time information captured by the equipment 4 according to the taxi number plate to obtain an average time difference, wherein the average time difference is as follows (only some time periods are listed):
| time period | Mean time difference(s) |
| 7:00-7:15 | 38 |
| 7:15-7:30 | 47 |
| 7:30-7:45 | 62 |
| 7:45-8:00 | 109.2 |
The daily average time deviation of 9 sets of equipment is finally obtained as follows:
and comparing with the average time deviation per day threshold (the threshold is 150s), judging that the equipment 6 has equipment abnormality and giving an early warning.
In summary, according to the method of the embodiment, the device abnormality warning is performed on the number plate recognition device 4 and the number plate recognition device 6 according to the detection day data.
Claims (4)
1. A video number plate data quality analysis method is characterized in that: the integrity of the equipment data acquisition is analyzed based on the online condition of the video number plate identification equipment, the reasonability of the data is further analyzed based on the historical data of the video number plate, the data quality of the vehicle inspection equipment and the GPS data information, and the automatic early warning is carried out on the equipment fault, which comprises the following steps,
s1, analyzing the integrity of the data collected by the equipment according to the online condition of the number plate identification equipment; in step S1, specifically, the step,
s11, time dimension online rate analysis, wherein the online condition of the equipment in each unit time period is statistically analyzed based on the online state of the number plate identification equipment in the statistical time period, if the online time period ratio is lower than the online rate threshold, the step S4 is carried out, otherwise, the step S12 is carried out;
s12, carrying out space dimension online rate analysis, extracting online data of all license plate recognition devices in the road network system, calculating the total online rate of the devices in each unit time period, if the total online rate of the devices is lower than the online threshold of the devices of the system, determining that the license plate recognition system has system faults and automatically early warning, and if not, turning to the step S2;
s2, analyzing and checking the rationality of the data quality according to the flow information of the data collected by the license plate identification equipment; in step S2, specifically, the step,
s21, longitudinal analysis of data flow is achieved through comparison and analysis with equipment historical data, data collected by a unit time period number plate recognition device and historical data of the same time period are compared and analyzed, if the traffic flow in the unit time period exceeds a historical flow threshold interval in the unit time period, the data collected by the equipment in the unit time period is judged to be suspicious abnormal data, the step S22 is carried out, otherwise, the data in the unit time period are considered to be normal, and if all the data in the unit time period in the statistical time period are normal, the step S3 is carried out;
s22, multi-source data flow transverse comparison analysis is achieved through comparison of data quality of vehicle detector equipment at the arrangement point of the number plate identification equipment;
s3, comparing the GPS data of the vehicle with the positioning equipment with the time information of the data collected by the number plate identification equipment to realize the time rationality analysis of the number plate identification data; in step S3, specifically, the step,
s31, extracting GPS data of vehicles with vehicle-mounted positioning devices in the road network, matching the positioning data into the road network, further establishing a device road section association table according to the positions of the number plate identification devices in the road network and road network road section information, and extracting the GPS data in the GPS data range of each number plate identification device;
s32, comparing and analyzing the GPS data in the equipment range with the number plate identification data, extracting the GPS data of the number plate in the data range according to the vehicle number plate information collected by the number plate identification equipment to obtain the average time difference between the two numerical values, if the average time difference in the unit time period is larger than a threshold value, turning to the step S4, otherwise, determining that the data collected by the number plate identification equipment is normal;
and S4, automatically warning the abnormality of the number plate identification equipment.
2. The video license plate data quality analysis method of claim 1, characterized in that: in step S22, specifically, the step,
s221, extracting data collected by the same-point vehicle detector equipment in the time period to which the suspicious abnormal data belongs, analyzing the quality of the data collected by the vehicle detector equipment, if the data collected by all the equipment in the time period to which the suspicious abnormal data belongs are the suspicious abnormal data, determining that time abnormality possibly exists, and turning to the step S3, otherwise, turning to the next step;
s222, collecting all suspicious abnormal data in the statistical time period, if the ratio of the suspicious abnormal data amount to the total data is larger than the suspicious data proportion threshold, turning to the step S4, otherwise, turning to the step S3.
3. The video license plate data quality analysis method of claim 1, characterized in that: the average time difference in the unit time period between the GPS data and the number plate identification data within the range of the device in step S32, specifically,
in the formula, tGPSTime of data collected for GPS, tALPRThe time value of the number plate identification data is n, and the data volume of the GPS data collected in the range of the number plate identification equipment is n.
4. The video license plate data quality analysis method of claim 3, characterized in that: in step S32, the average time difference per unit time period is calculated based on GPS data of a plurality of vehicles traveling in the unit time period
The calculation is carried out, namely:
wherein N is the number of vehicles.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810914240.0A CN109190924B (en) | 2018-08-10 | 2018-08-10 | Video number plate data quality analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810914240.0A CN109190924B (en) | 2018-08-10 | 2018-08-10 | Video number plate data quality analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109190924A CN109190924A (en) | 2019-01-11 |
| CN109190924B true CN109190924B (en) | 2021-09-07 |
Family
ID=64921574
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810914240.0A Active CN109190924B (en) | 2018-08-10 | 2018-08-10 | Video number plate data quality analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190924B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110718071B (en) * | 2019-10-25 | 2021-09-03 | 上海眼控科技股份有限公司 | Verification method and device for image acquisition equipment, computer equipment and storage medium |
| CN115376315B (en) * | 2022-08-09 | 2023-10-24 | 北京交通发展研究院 | Multi-level bayonet quality control method for road network emission accounting |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202042051U (en) * | 2011-03-24 | 2011-11-16 | 浙江金之路信息科技有限公司 | Urban traffic intelligent supervision system |
| CN103000028A (en) * | 2011-09-14 | 2013-03-27 | 上海宝康电子控制工程有限公司 | Vehicle registration plate recognition system and method |
| CN105160887A (en) * | 2015-08-26 | 2015-12-16 | 深圳市傲天智能***有限公司 | Vehicle image processing device and image processing method thereof |
| CN106355924A (en) * | 2016-09-06 | 2017-01-25 | 江苏智通交通科技有限公司 | Traffic data quality monitoring system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180025648A1 (en) * | 2010-04-15 | 2018-01-25 | Milan Zlojutro | Vehicle Monitoring & Identification System |
-
2018
- 2018-08-10 CN CN201810914240.0A patent/CN109190924B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202042051U (en) * | 2011-03-24 | 2011-11-16 | 浙江金之路信息科技有限公司 | Urban traffic intelligent supervision system |
| CN103000028A (en) * | 2011-09-14 | 2013-03-27 | 上海宝康电子控制工程有限公司 | Vehicle registration plate recognition system and method |
| CN105160887A (en) * | 2015-08-26 | 2015-12-16 | 深圳市傲天智能***有限公司 | Vehicle image processing device and image processing method thereof |
| CN106355924A (en) * | 2016-09-06 | 2017-01-25 | 江苏智通交通科技有限公司 | Traffic data quality monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109190924A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017157119A1 (en) | Method and device for identifying abnormal behavior of vehicle | |
| CN107798876B (en) | Road traffic abnormal jam judging method based on event | |
| CN102360526B (en) | Real-time monitoring method for road section state of high road | |
| CN105741596B (en) | Electronic police system detects Control for Dependability method and system | |
| CN103077610A (en) | Road trip time estimating method and system | |
| CN108335377B (en) | GIS technology-based automatic check method for road inspection vehicle service | |
| CN110807919A (en) | Urban road network traffic operation situation evaluation method based on vehicle passing data | |
| CN116644373B (en) | Automobile flow data analysis management system based on artificial intelligence | |
| CN110176139A (en) | A kind of congestion in road identification method for visualizing based on DBSCAN+ | |
| CN112053558A (en) | Traffic jam state identification method, device and equipment | |
| CN107424410B (en) | A kind of accident detection method calculated based on route travel time | |
| CN101882374A (en) | System and method for analysis of comprehensive information on vehicle trip distribution | |
| CN104809878A (en) | Method for detecting abnormal condition of urban road traffic by utilizing GPS (Global Positioning System) data of public buses | |
| CN109190924B (en) | Video number plate data quality analysis method | |
| CN106571038A (en) | Method for fully automatically monitoring road | |
| CN113935158B (en) | Traffic detector optimal layout method for multiple points of expressway accident | |
| CN105976610A (en) | Bayonet passing vehicle detection reliability control method and system | |
| CN108629982B (en) | Road section vehicle number estimation method based on travel time distribution rule | |
| CN102426783B (en) | Low flow road traffic incident detection method based on vehicle tracking | |
| CN106910334B (en) | Method and device for predicting road section conditions based on big data | |
| US20220319323A1 (en) | Method for identifying road risk based on networked vehicle-mounted adas | |
| CN102360524B (en) | Automatic detection and confirmation method of dangerous traffic flow characteristics of highway | |
| CN210865032U (en) | Urban waterlogging monitoring and early warning system | |
| CN109272760B (en) | Online detection method for abnormal data value of SCATS system detector | |
| CN114999181A (en) | ETC system data-based highway vehicle speed abnormity identification method |
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 | ||
| CB02 | Change of applicant information |
Address after: 211100 No. 19 Suyuan Avenue, Jiangning Economic and Technological Development Zone, Nanjing City, Jiangsu Province Applicant after: JIANGSU ZHITONG TRANSPORTATION TECHNOLOGY Co.,Ltd. Address before: 210006, Qinhuai District, Jiangsu, Nanjing should be 388 days street, Chenguang 1865 Technology Creative Industry Park E10 building on the third floor Applicant before: JIANGSU ZHITONG TRANSPORTATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Method for analyzing the quality of video license plate data Effective date of registration: 20230621 Granted publication date: 20210907 Pledgee: Jiangsu Zijin Rural Commercial Bank Co.,Ltd. Gulou sub branch Pledgor: JIANGSU ZHITONG TRANSPORTATION TECHNOLOGY Co.,Ltd. Registration number: Y2023320000339 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Granted publication date: 20210907 Pledgee: Jiangsu Zijin Rural Commercial Bank Co.,Ltd. Gulou sub branch Pledgor: JIANGSU ZHITONG TRANSPORTATION TECHNOLOGY Co.,Ltd. Registration number: Y2023320000339 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |