CN112395955B - Vehicle-related resident foothold analysis method, device, equipment and medium - Google Patents
Vehicle-related resident foothold analysis method, device, equipment and medium Download PDFInfo
- Publication number
- CN112395955B CN112395955B CN202011164549.6A CN202011164549A CN112395955B CN 112395955 B CN112395955 B CN 112395955B CN 202011164549 A CN202011164549 A CN 202011164549A CN 112395955 B CN112395955 B CN 112395955B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- vehicle passing
- monitoring
- analyzed
- 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 24
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims description 113
- 238000007405 data analysis Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 6
- 230000003203 everyday effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 abstract description 2
- 238000012821 model calculation Methods 0.000 abstract 1
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 206010034701 Peroneal nerve palsy Diseases 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- 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
- G06V2201/08—Detecting or categorising vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the specification discloses a method for analyzing vehicle-related resident falling foot points, and aims to provide a method for studying and judging the vehicle-related resident falling foot points, realize the analysis of the vehicle-related resident falling foot points with point positions accurate to a cell by combining practical application and actual checkpoint license plate identification data, solve the problems of continuous shooting and missed shooting of checkpoint snapshot data, and improve the model calculation rate by utilizing a distributed calculation cluster to realize the data support for the case handling of public security investigation.
Description
Technical Field
The invention relates to the field of road vehicle data analysis, in particular to a method, a device, equipment and a medium for analyzing vehicle-related resident foothold.
Background
With the development of informatization, owners continuously put forward new requirements on platform application, the functions need to be efficient and real-time, and more contents capable of being mined are analyzed through big data. To accommodate these growing changes, vehicle resident foothold analysis is one of the important research directions, but the existing methods have the following problems:
1) in the existing method, only geographical position information and frequency are paid attention to in the process of calculating the resident foothold, and only the simple resident foothold can be obtained, so that the confusion of a living area and a working area is caused;
2) in the existing method, the time length of a vehicle passing through two checkpoints in each group in a specified time period is directly calculated, and all the checkpoints have the same weight, so that the accuracy is insufficient when a resident foothold result is calculated;
3) due to the fact that continuous shooting and wrong license plate recognition exist in the monitoring equipment, the existing method does not conduct targeted processing aiming at the situations, and therefore the resident foothold calculation result generates deviation.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a medium for analyzing vehicle-related resident foothold, which can more accurately analyze the vehicle-related resident foothold by time period division and weight setting according to analysis requirements and monitoring bayonet positions.
In a first aspect, the invention provides a vehicle-related resident foothold analysis method, which comprises the following steps:
step 10, carrying out primary identification on image data of the monitoring bayonet camera equipment to obtain structured vehicle passing data; secondly, carrying out secondary identification on the image data to obtain a vehicle passing picture;
step 20, respectively storing the effective data of the vehicle passing data and the vehicle passing pictures into a data warehouse, and selecting the vehicle passing data and the vehicle passing pictures in a set time period as vehicle passing records according to analysis requirements;
step 30, dividing the vehicle passing record into early vehicle passing data, night vehicle passing data and other vehicle passing data;
step 40, setting weights according to the positions of the monitoring checkpoints, setting the weight of the residential area monitoring checkpoint to be greater than the weight of the non-residential area monitoring checkpoint when calculating the starting point and the ending point, and setting the weight of the business area monitoring checkpoint to be greater than the weight of the non-business area monitoring checkpoint when calculating the working area; respectively setting a starting threshold, an end threshold and a working area threshold;
step 50, taking a monitoring bayonet of a first-time vehicle passing record every day of a vehicle to be analyzed in the morning vehicle passing data as a starting point to obtain a suspected point location result set of the starting point of the vehicle to be analyzed; taking a monitoring bayonet recorded by the last vehicle passing of each day of the vehicle to be analyzed in the night vehicle passing data set as a terminal point to obtain a suspected point location result set of the terminal point of the vehicle to be analyzed; taking the passing time difference value of the vehicle to be analyzed at the current monitoring gate and the next monitoring gate as the staying time of the current monitoring gate, and taking the monitoring gate with the staying time larger than a set value as a suspected point location result set of a working area;
step 60, according to the number of times of the vehicle to be analyzed appearing at the monitoring gate and the weight of the monitoring gate, respectively calculating a weight value of each monitoring gate in the suspected point location result set of the starting point, the suspected point location result set of the end point and the suspected point location result set of the working area, marking the result of which the weight calculation value is greater than the threshold value of the starting point in the suspected point location result set of the starting point as the starting point, marking the result of which the weight calculation value is greater than the threshold value of the end point in the suspected point location result set of the end point as the end point, and marking the result of which the weight calculation value is greater than the threshold value of the working area in the suspected point location result set of the working area as the working area point.
Further, before the step 50, the method further includes:
removing repeated results in the vehicle passing record aiming at the condition of continuous shooting of image data of the monitoring gate; the vehicle passing record meeting the completion condition is completed according to the condition that image data of the monitoring gate is missed or the license plate is wrongly identified; the completion conditions are as follows:
ΔT＜10min&Simlar(plate1,plate2)>0.8&distance(d1,d2)＜1Km
wherein, Δ T ═ Time1-Time2|，Time1Indicating the Time of passage of the current passage record, Time2Indicating the passing time of the vehicle to be analyzed, Simlar (plate)1，plate2) Recording the similarity between the license plate number and the license plate number of the vehicle to be analyzed for the current passing vehicle, distance (d)1，d2) The distance between the current vehicle passing record and the vehicle passing record of the vehicle to be analyzed is recorded.
Further, still include:
and step 70, storing the calculation results in distributed databases Gbase and Hive for data analysis and Web query respectively.
In a second aspect, the present invention provides a car-related resident foothold analysis apparatus, including: the system comprises a data identification module, a data processing module, a data segmentation module, a weight threshold setting module, a suspected point location counting module and a resident foothold analysis module;
the data identification module is used for identifying image data of the camera equipment at the monitoring gate for one time to obtain structured vehicle passing data; secondly, carrying out secondary identification on the image data to obtain a vehicle passing picture;
the data processing module is used for respectively storing the effective data of the vehicle passing data and the vehicle passing pictures into a data warehouse, and selecting the vehicle passing data and the vehicle passing pictures in a set time period as vehicle passing records according to analysis requirements;
the data segmentation module is used for dividing the vehicle passing record into early vehicle passing data, night vehicle passing data and other time vehicle passing data;
the weight threshold setting module is used for setting weight according to the position of the monitoring gate, setting the weight of the residential area monitoring gate to be greater than the weight of the non-residential area monitoring gate when calculating the starting point and the ending point, and setting the weight of the business area monitoring gate to be greater than the weight of the non-business area monitoring gate when calculating the working area; respectively setting a starting threshold, an end threshold and a working area threshold;
the suspected point location statistical module is used for taking a monitoring bayonet of a first vehicle passing record every day of a vehicle to be analyzed in the morning vehicle passing data as a starting point to obtain a suspected point location result set of the starting point of the vehicle to be analyzed; taking a monitoring bayonet recorded by the last vehicle passing of each day of the vehicle to be analyzed in the night vehicle passing data set as a terminal point to obtain a suspected point location result set of the terminal point of the vehicle to be analyzed; taking the passing time difference value of the vehicle to be analyzed at the current monitoring gate and the next monitoring gate as the stay time of the current monitoring gate, and taking the monitoring gate with the stay time larger than a set value as a suspected point location result set of a working area;
the resident foothold analysis module is used for respectively calculating a suspected point location result set of a starting point, a suspected point location result set of a terminal point and a weighted value of each monitoring bayonet in a suspected point location result set of a working area according to the number of times of the vehicle to be analyzed appearing at the monitoring bayonets and the weights of the monitoring bayonets, marking a result of which the weight calculation value in the suspected point location result set of the starting point is greater than the threshold value of the starting point as a starting point location, marking a result of which the weight calculation value in the suspected point location result set of the terminal point is greater than the threshold value of the terminal point as a terminal point location, and marking a result of which the weight calculation value in the suspected point location result set of the working area is greater than the threshold value of the working area as a working area location.
Further, the system also comprises a duplicate removal and completion module;
the duplication elimination and completion module is used for eliminating repeated results in the vehicle passing record aiming at the condition of continuous shooting of image data of the monitoring gate; according to the condition that image data of the monitoring gate is missed or the license plate recognition is wrong, completing the vehicle passing record of the vehicle to be analyzed by the vehicle passing record meeting the completion condition; the completion conditions are as follows:
ΔT＜10min&Simlar(plate1,plate2)>0.8&distance(d1,d2)＜1Km
wherein, Δ T ═ Time1-Time2|，Time1Indicating the Time of passage of the current passage record, Time2Indicating the passing time of the vehicle to be analyzed, Simlar (plate)1，plate2) Recording the similarity between the license plate number and the license plate number of the vehicle to be analyzed for the current passing vehicle, distance (d)1，d2) The distance between the current vehicle passing record and the vehicle passing record of the vehicle to be analyzed is recorded.
Further, still include: a data storage module;
and the data storage module is used for storing the calculation results in distributed databases Gbase and Hive, and is respectively used for data analysis and Web query.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of the first aspect when executing the program.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method of the first aspect.
One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:
1. classifying the monitoring bayonets according to positions based on the traffic data of the monitoring bayonets, setting different weights for different types of point positions, selecting required bayonet data to obtain a starting point and an end point of each day travel of a vehicle to be analyzed and a point with long retention time, and taking the point with the occurrence frequency higher than a set threshold value as a resident foot drop point of the vehicle to be analyzed; fixed resident footfall points are analyzed by emphatically analyzing the passing data in the morning and at night, so that a basis is provided for the study and judgment of public security case handling and case situation;
2. considering that continuous shooting and missed shooting conditions exist in the snapshot data of the monitoring gate, a method for vehicle track completion and multiple vehicle passing record de-weight operation of the same unit in a short time, which is adaptive to the snapshot data conditions, is added;
3. the accurate range of the foot-landing point can be positioned to a cell by fully utilizing the information of the monitoring bayonet, and the result accuracy of the foot-landing point is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
The invention will be further described with reference to the following examples and figures.
FIG. 1 is a flow chart of a method according to one embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an apparatus according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the invention;
FIG. 4 is a schematic structural diagram of a medium according to a fourth embodiment of the present invention;
FIG. 5 is a flowchart illustrating a method according to a fifth embodiment of the present invention.
Detailed Description
Example one
The present embodiment provides a method for analyzing a car-related resident foothold, as shown in fig. 1, including:
step 10, carrying out primary identification on image data of the monitoring bayonet camera equipment to obtain structured vehicle passing data; secondly, carrying out secondary identification on the image data to obtain a vehicle passing picture;
step 20, respectively storing the effective data of the vehicle passing data and the vehicle passing pictures into a data warehouse, and selecting the vehicle passing data and the vehicle passing pictures in a set time period as vehicle passing records according to analysis requirements;
step 30, dividing the vehicle passing record into early vehicle passing data, night vehicle passing data and other vehicle passing data;
step 40, setting weights according to the positions of the monitoring checkpoints, setting the weight of the residential area monitoring checkpoint to be greater than the weight of the non-residential area monitoring checkpoint when calculating the starting point and the ending point, and setting the weight of the business area monitoring checkpoint to be greater than the weight of the non-business area monitoring checkpoint when calculating the working area; respectively setting a starting threshold, an end threshold and a working area threshold;
step 50, taking a monitoring bayonet of a first-time vehicle passing record every day of a vehicle to be analyzed in the morning vehicle passing data as a starting point to obtain a suspected point location result set of the starting point of the vehicle to be analyzed; taking a monitoring bayonet recorded by the last vehicle passing of each day of the vehicle to be analyzed in the night vehicle passing data set as a terminal point to obtain a suspected point location result set of the terminal point of the vehicle to be analyzed; taking the passing time difference value of the vehicle to be analyzed at the current monitoring gate and the next monitoring gate as the stay time of the current monitoring gate, and taking the monitoring gate with the stay time larger than a set value as a suspected point location result set of a working area;
step 60, according to the number of times of the vehicle to be analyzed appearing at the monitoring gate and the weight of the monitoring gate, respectively calculating a weight value of each monitoring gate in the suspected point location result set of the starting point, the suspected point location result set of the end point and the suspected point location result set of the working area, marking the result of which the weight calculation value is greater than the threshold value of the starting point in the suspected point location result set of the starting point as the starting point, marking the result of which the weight calculation value is greater than the threshold value of the end point in the suspected point location result set of the end point as the end point, and marking the result of which the weight calculation value is greater than the threshold value of the working area in the suspected point location result set of the working area as the working area point.
Classifying the monitoring bayonets according to positions based on the traffic data of the monitoring bayonets, setting different weights for point positions of different types, selecting required bayonet data to obtain a starting point and an end point of each day travel of a vehicle to be analyzed and a point with long retention time, and taking the point with the occurrence frequency higher than a set threshold value as a vehicle resident foothold to be analyzed; the fixed resident foothold is analyzed by emphasizing and analyzing the passing data in the morning and at night, so that the basis is provided for the study and judgment of case handling and case situation of the public security, the accurate range of the foothold can be positioned to a cell by fully utilizing the information of the monitoring card port, and the result accuracy of the foothold is improved.
In a possible implementation manner, before the step 50, the method further includes:
removing repeated results in the vehicle passing record aiming at the condition of continuous shooting of image data of the monitoring gate; the vehicle passing record meeting the completion condition is completed according to the condition that image data of the monitoring gate is missed or the license plate is wrongly identified; the completion conditions are as follows:
ΔT＜10min&Simlar(plate1,plate2)>0.8&distance(d1,d2)＜1Km
wherein, Δ T ═ Time1-Time2|，Time1Indicating the Time of passage of the current passage record, Time2Indicating the passing time of the vehicle to be analyzed, Simlar (plate)1，plate2) Recording the similarity between the license plate number and the license plate number of the vehicle to be analyzed for the current passing vehicle, distance (d)1，d2) The distance between the current vehicle passing record and the vehicle passing record of the vehicle to be analyzed is recorded.
The continuous shooting and missed shooting conditions of the snapshot data of the monitoring gate are considered, and a method for vehicle track completion and vehicle passing record de-weight operation of one vehicle and multiple vehicles in the same unit in a short time is added, wherein the vehicle track completion is adaptive to the snapshot data conditions.
In one possible implementation manner, the method further includes:
and step 70, storing the calculation results in distributed databases Gbase and Hive for data analysis and Web query respectively.
Based on the same inventive concept, the application also provides a device corresponding to the method in the first embodiment, which is detailed in the second embodiment.
Example two
In the present embodiment, there is provided an apparatus, as shown in fig. 2, comprising:
the system comprises a data identification module, a data processing module, a data segmentation module, a weight threshold setting module, a suspected point location counting module and a resident foothold analysis module;
the data identification module is used for identifying image data of the camera equipment at the monitoring gate for one time to obtain structured vehicle passing data; secondly, carrying out secondary identification on the image data to obtain a vehicle passing picture;
the data processing module is used for respectively storing the effective data of the vehicle passing data and the vehicle passing pictures into a data warehouse, and selecting the vehicle passing data and the vehicle passing pictures in a set time period as vehicle passing records according to analysis requirements;
the data segmentation module is used for dividing the vehicle passing record into early vehicle passing data, night vehicle passing data and other time vehicle passing data;
the weight threshold setting module is used for setting weight according to the position of the monitoring gate, setting the weight of the residential area monitoring gate to be greater than the weight of the non-residential area monitoring gate when calculating the starting point and the ending point, and setting the weight of the business area monitoring gate to be greater than the weight of the non-business area monitoring gate when calculating the working area; respectively setting a starting threshold, an end threshold and a working area threshold;
the suspected point location statistical module is used for taking a monitoring bayonet of a first vehicle passing record every day of a vehicle to be analyzed in the morning vehicle passing data as a starting point to obtain a suspected point location result set of the starting point of the vehicle to be analyzed; taking a monitoring bayonet recorded by the last vehicle passing of each day of the vehicle to be analyzed in the night vehicle passing data set as a terminal point to obtain a suspected point location result set of the terminal point of the vehicle to be analyzed; taking the passing time difference value of the vehicle to be analyzed at the current monitoring gate and the next monitoring gate as the staying time of the current monitoring gate, and taking the monitoring gate with the staying time larger than a set value as a suspected point location result set of a working area;
the resident foothold analysis module is used for respectively calculating a suspected point location result set of a starting point, a suspected point location result set of a terminal point and a weighted value of each monitoring bayonet in a suspected point location result set of a working area according to the number of times of the vehicle to be analyzed appearing at the monitoring bayonets and the weights of the monitoring bayonets, marking a result of which the weight calculation value in the suspected point location result set of the starting point is greater than the threshold value of the starting point as a starting point location, marking a result of which the weight calculation value in the suspected point location result set of the terminal point is greater than the threshold value of the terminal point as a terminal point location, and marking a result of which the weight calculation value in the suspected point location result set of the working area is greater than the threshold value of the working area as a working area location.
Further, the system also comprises a duplicate removal and completion module;
the duplication elimination and completion module is used for eliminating repeated results in the vehicle passing record aiming at the condition of continuous shooting of image data of the monitoring gate; the vehicle passing record meeting the completion condition is completed according to the condition that image data of the monitoring gate is missed or the license plate is wrongly identified; the completion conditions are as follows:
ΔT＜10min&Simlar(plate1,plate2)>0.8&distance(d1,d2)＜1Km
wherein, Δ T ═ Time1-Time2|，Time1Indicating the Time of passing the vehicle, Time, of the current passing record2Indicating the passing time of the vehicle to be analyzed, Simlar (plate)1，plate2) Recording the similarity between the license plate number and the license plate number of the vehicle to be analyzed for the current passing vehicle, distance (d)1，d2) The distance between the current vehicle passing record and the vehicle passing record of the vehicle to be analyzed is recorded.
Further, still include: a data storage module;
and the data storage module is used for storing the calculation results in distributed databases Gbase and Hive, and is respectively used for data analysis and Web query.
Since the apparatus described in the second embodiment of the present invention is an apparatus used for implementing the method in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and the deformation of the apparatus based on the method described in the first embodiment of the present invention, and thus the details are not described herein again. All the devices adopted in the method of the first embodiment of the present invention belong to the protection scope of the present invention.
Based on the same inventive concept, the application provides an electronic device embodiment corresponding to the first embodiment, which is detailed in the third embodiment.
EXAMPLE III
The embodiment provides an electronic device, as shown in fig. 3, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, any one of the first embodiment modes may be implemented.
Since the electronic device described in this embodiment is a device used for implementing the method in the first embodiment of the present application, based on the method described in the first embodiment of the present application, a specific implementation of the electronic device in this embodiment and various variations thereof can be understood by those skilled in the art, and therefore, how to implement the method in the first embodiment of the present application by the electronic device is not described in detail herein. The equipment used by those skilled in the art to implement the methods in the embodiments of the present application is within the scope of the present application.
Based on the same inventive concept, the application provides a storage medium corresponding to the fourth embodiment, which is described in detail in the fourth embodiment.
Example four
The present embodiment provides a computer-readable storage medium, as shown in fig. 4, on which a computer program is stored, and when the computer program is executed by a processor, any one of the embodiments can be implemented.
EXAMPLE five
The specific practical examples applied to the public security field are as follows:
simulating a service scene: the suspects are hidden at living points or temporary footfall points for a long time, life tracks are researched and judged through the driving tracks of the vehicles of the suspects which are captured, and working areas and living areas of the suspects are judged, so that the suspects can conveniently capture and deploy and control.
The invention provides a module structure for analyzing wading resident foothold, which specifically comprises the following steps:
the method comprises the following steps that 1, data collected by a bayonet device are collected to kafka, and the kafka is read and cleaned by a consumption program;
the module 2 is used for storing historical data by using hive and taking out data of three months to participate in calculation;
and 3, designing a vehicle resident foot-landing point algorithm, and reducing the time for calculating the foot-landing point data of the vehicle by combining distributed calculation.
And the module 4 and the display of a vehicle-related big data platform at the Web end provide various judging tools and vehicle resident foothold query.
As shown in fig. 5, the implementation process of the car-related data analysis in the present practical example specifically includes the following steps:
step 1, collecting data by bayonet equipment, converting video data of images shot by a camera of a road surface monitoring bayonet into vehicle structured data through primary identification, sending the data to kafka, acquiring a passing vehicle picture through secondary identification, and perfecting the characteristic data of the missing part of the passing vehicle picture in the primary identification according to the data of the secondary identification;
step 2, setting consumption group reading kafka data to be synchronized to an offline analysis cluster
Respectively reading data of twice vehicle passing identification topic on kafka, respectively storing the data of twice identification into a data warehouse, cleaning partial data of which the license plate is not identified or is empty, avoiding invalid data, storing historical data by using hive, and reading data in the data warehouse for nearly three months to participate in calculation;
step 3, designing a vehicle resident foot-landing point algorithm, reducing the time for calculating the foot-landing point data of the vehicle by combining distributed calculation, and setting a timing off-line spark task;
1) reading of dataAccording to process identification data in a warehouse, dividing the identification data into early-time vehicle passing data, night-time vehicle passing data and other-time vehicle passing data according to time periods, acquiring first-time and last-time vehicle passing records of a vehicle to be analyzed on the same day as a starting point and an end point (the first-time vehicle passing record is selected from the early-time vehicle passing data only and the last-time vehicle passing record is selected from the night-time vehicle passing data only), wherein the starting point and the end point of the day granularity accord with the work and rest rules of human habitation, and obtaining a suspected point result set D { D } of the starting point and the end point of a person vehicle1,d2...dn}；
2) Determining the suspected resident points as resident foothold (including a starting point and an end point) when the suspected resident points are judged as the suspected points for a plurality of times in the historical data of the vehicle to be analyzed, and counting D { D }1,d2...dnFrequency set C (C) for judging point location historical data as suspected1c2...cnThe starting and ending point result of the vehicle in the station is point diThe number of times of suspected habitats was counted as ciCounting is the threshold of the number of times of the default value, if ci>The Count obtains the suspected foothold and the residential area of the vehicle; according to the average daily point location residence time of the vehicle, when the vehicle resides in the point locations more than three hours and also exceeds a certain frequency, the vehicle is classified into a suspected working area (the point locations are classified before analysis and are divided into point locations close to a residential area and point locations close to a business area, when the residential area and the working area are calculated, the point locations are recorded as the statistical frequency plus 2 when the condition that the point locations meet 1 time, and other common point locations are recorded as the frequency plus 1 only).
3) Aiming at the situation that continuous shooting and missed shooting can cause erroneous judgment of the bayonet snapshot data, a method for adapting the situation of the snapshot data is added into a resident foothold algorithm:
the continuous shooting problem is solved by only reserving one piece of snapshot data within a single-card-mouth minute;
and the missed shooting problem is solved by complementing missed shooting or wrong license plate recognition into tracks of other similar license plates according to the similarity of the license plates, the passing time and the point location distance. The completion condition needs to be satisfied:
ΔT＝|Time1-Time1|
ΔT＜10min&Simlar(plate1,plate2)>0.8&distance(d1,d2)＜1Km
wherein, Δ T ═ Time1-Time2|，Time1Indicating the Time of passage of the current passage record, Time2Indicating the passing time of the vehicle to be analyzed, Simlar (plate)1，plate2) Recording the similarity (plate) between the license plate number and the license plate number of the vehicle to be analyzed for the current passing vehicle1，plate2The license plate numbers of two vehicles respectively, which is obtained by calculating the ratio of the same number of characters at the same position of the two license plates to the length of the license plate number), distance (d)1，d2) For the distance between the current vehicle-passing record and the vehicle-passing record of the vehicle to be analyzed, d1，d2Respectively the longitude and latitude of two vehicles;
finally, the integrity of the vehicle passing data can be perfected through the de-duplication and completion algorithm, and the accurate suspected footfall or residential area can be judged.
Vehicle resident foothold result storage field:
types of foothold:
suspected residential area (starting point judgment)
Suspected residential area (terminal point judgment)
Suspected working area
Step 4, storing the calculated vehicle foothold in a distributed database, wherein Gbase and Hive are selected in the embodiment, and data are stored in the two databases at the same time and are respectively used for data analysis and Web query;
step 5, displaying a result table in the database to a user in a Web form, and providing a plurality of self-defined query functions and threshold configurable functions;
according to the method, a spark calculation frame is adopted to carry out calculation analysis on an offline historical data structure, a large amount of vehicle information, service data and image data in a public security network are combined, the hidden relation between the vehicle and a case event is excavated through service modeling and data analysis, abundant and practical service actual combat application based on the case event is provided, basic data support of a research and judgment tool is provided for a large data platform related to the vehicle, and the requirements of vehicle passing record query and vehicle research and judgment work in the case handling process of a public security department are met. The method carries out ETL on the structured vehicle data, the data are stored in a distributed mode by using Hive and Gbase8aMapp databases, and meanwhile, a multi-dimensional configurable query condition on a large data platform provides a convenient query function.
Calculating each group of bayonets based on the traffic data, classifying the bayonets, setting different calculation rules and weights for different types of point locations, respectively selecting needed bayonet data, dividing traffic data of vehicles to be analyzed passing through all bayonets in a city in a specified time period into a plurality of days of travel with days as granularity (namely finding travel starting points and ending points in one day respectively), counting the starting points, the ending points, the starting points and the ending points of all the travel of the vehicles to be analyzed, and taking the bayonets with the largest occurrence frequency as resident foot-falling points of the vehicles to be analyzed.
In other methods, continuous shooting and missed shooting conditions of the snapshot data of the gate are considered, and a method for vehicle track completion and multiple vehicle passing record duplication removal operation of the same unit in a short time point, which is adapted to the situation of the snapshot data, is added into an algorithm.
Compared with other methods, the method can make full use of the bayonet information to position the accurate range of the pin drop point to the cell, and solves the problem of improving the result accuracy of the pin drop point.
In addition, in the track collision process, the method of the embodiment gives more weight to the tracks in the morning and at night to analyze the fixed resident foothold, thereby providing a basis for the public security to handle cases and study and judge case situations.
Besides analyzing the vehicle passing record, the vehicle big data integral early warning system uses a big data image processing engine to process massive unstructured data such as the bayonet vehicle passing pictures in real time. The system can provide related information clues and data support for work such as public security investigation, case handling, prevention, control and early warning and the like, and can further open the application service of different police types supported by the universal vehicle analysis and early warning function.
Although specific embodiments of the invention have been described above, it will be understood by those skilled in the art that the specific embodiments described are illustrative only and are not limiting upon the scope of the invention, and that equivalent modifications and variations can be made by those skilled in the art without departing from the spirit of the invention, which is to be limited only by the appended claims.
Claims (8)
1. A car-related resident foothold analysis method is characterized by comprising the following steps: the method comprises the following steps:
step 10, carrying out primary identification on image data of the monitoring bayonet camera equipment to obtain structured vehicle passing data; secondly, carrying out secondary identification on the image data to obtain a vehicle passing picture;
step 20, respectively storing the effective data of the vehicle passing data and the vehicle passing pictures into a data warehouse, and selecting the vehicle passing data and the vehicle passing pictures in a set time period as vehicle passing records according to analysis requirements;
step 30, dividing the vehicle passing record into early vehicle passing data, night vehicle passing data and other vehicle passing data;
step 40, setting weights according to the positions of the monitoring checkpoints, setting the weight of the residential area monitoring checkpoint to be greater than the weight of the non-residential area monitoring checkpoint when calculating the starting point and the ending point, and setting the weight of the business area monitoring checkpoint to be greater than the weight of the non-business area monitoring checkpoint when calculating the working area; respectively setting a starting threshold, an end threshold and a working area threshold;
step 50, taking a monitoring bayonet of a first-time vehicle passing record every day of a vehicle to be analyzed in the morning vehicle passing data as a starting point to obtain a suspected point location result set of the starting point of the vehicle to be analyzed; taking a monitoring bayonet recorded by the last vehicle passing of each day of the vehicle to be analyzed in the night vehicle passing data set as a terminal point to obtain a suspected point location result set of the terminal point of the vehicle to be analyzed; taking the passing time difference value of the vehicle to be analyzed at the current monitoring gate and the next monitoring gate as the stay time of the current monitoring gate, and taking the monitoring gate with the stay time larger than a set value as a suspected point location result set of a working area;
step 60, according to the number of times of the vehicle to be analyzed appearing at the monitoring gate and the weight of the monitoring gate, respectively calculating a weight value of each monitoring gate in the suspected point location result set of the starting point, the suspected point location result set of the end point and the suspected point location result set of the working area, marking the result of which the weight calculation value is greater than the threshold value of the starting point in the suspected point location result set of the starting point as the starting point, marking the result of which the weight calculation value is greater than the threshold value of the end point in the suspected point location result set of the end point as the end point, and marking the result of which the weight calculation value is greater than the threshold value of the working area in the suspected point location result set of the working area as the working area point.
2. The method of claim 1, wherein: before the step 50, the method further comprises:
removing repeated results in the vehicle passing record aiming at the condition of continuous shooting of image data of the monitoring gate; the vehicle passing record meeting the completion condition is completed according to the condition that image data of the monitoring gate is missed or the license plate is wrongly identified; the completion condition is as follows:
ΔT＜10min&Simlar(plate1,plate2)>0.8&distance(d1,d2)＜1Km
wherein, Δ T ═ Time1-Time2|，Time1Indicating the Time of passing the vehicle, Time, of the current passing record2Indicating the passing time of the vehicle to be analyzed, Simlar (plate)1，plate2) Recording the similarity between the license plate number and the license plate number of the vehicle to be analyzed for the current passing vehicle, distance (d)1，d2) The distance between the current vehicle passing record and the vehicle passing record of the vehicle to be analyzed is recorded.
3. The method of claim 1, wherein: further comprising:
and step 70, storing the calculation results in distributed databases Gbase and Hive for data analysis and Web query respectively.
4. The utility model provides a wade car resident foothold analytical equipment which characterized in that: the method comprises the following steps: the system comprises a data identification module, a data processing module, a data segmentation module, a weight threshold setting module, a suspected point location counting module and a resident foothold analysis module;
the data identification module is used for identifying image data of the camera equipment at the monitoring gate for one time to obtain structured vehicle passing data; secondly, carrying out secondary identification on the image data to obtain a vehicle passing picture;
the data processing module is used for respectively storing the effective data of the vehicle passing data and the vehicle passing pictures into a data warehouse, and selecting the vehicle passing data and the vehicle passing pictures in a set time period as vehicle passing records according to analysis requirements;
the data segmentation module is used for dividing the vehicle passing record into early vehicle passing data, night vehicle passing data and other time vehicle passing data;
the weight threshold setting module is used for setting weight according to the position of the monitoring gate, setting the weight of the residential area monitoring gate to be greater than the weight of the non-residential area monitoring gate when calculating the starting point and the ending point, and setting the weight of the business area monitoring gate to be greater than the weight of the non-business area monitoring gate when calculating the working area; respectively setting a starting threshold, an end threshold and a working area threshold;
the suspected point location statistical module is used for taking a monitoring bayonet of a first vehicle passing record every day of a vehicle to be analyzed in the morning vehicle passing data as a starting point to obtain a suspected point location result set of the starting point of the vehicle to be analyzed; taking a monitoring bayonet recorded by the last vehicle passing of each day of the vehicle to be analyzed in the night vehicle passing data set as a terminal point to obtain a suspected point location result set of the terminal point of the vehicle to be analyzed; taking the passing time difference value of the vehicle to be analyzed at the current monitoring gate and the next monitoring gate as the stay time of the current monitoring gate, and taking the monitoring gate with the stay time larger than a set value as a suspected point location result set of a working area;
the resident foothold analysis module is used for respectively calculating a suspected point location result set of a starting point, a suspected point location result set of a terminal point and a weighted value of each monitoring bayonet in a suspected point location result set of a working area according to the number of times of the vehicle to be analyzed appearing at the monitoring bayonets and the weights of the monitoring bayonets, marking a result of which the weight calculation value in the suspected point location result set of the starting point is greater than the threshold value of the starting point as a starting point location, marking a result of which the weight calculation value in the suspected point location result set of the terminal point is greater than the threshold value of the terminal point as a terminal point location, and marking a result of which the weight calculation value in the suspected point location result set of the working area is greater than the threshold value of the working area as a working area location.
5. The apparatus of claim 4, wherein: the device also comprises a duplicate removal and completion module;
the duplication elimination and completion module is used for eliminating repeated results in the vehicle passing record aiming at the condition of continuous shooting of image data of the monitoring gate; the vehicle passing record meeting the completion condition is completed according to the condition that image data of the monitoring gate is missed or the license plate is wrongly identified; the completion conditions are as follows:
ΔT＜10min&Simlar(plate1,plate2)>0.8&distance(d1,d2)＜1Km
wherein, Δ T ═ Time1-Time2|，Time1Indicating the Time of passage of the current passage record, Time2Indicating the passing time of the vehicle to be analyzed, Simlar (plate)1，plate2) Recording the similarity between the license plate number and the license plate number of the vehicle to be analyzed for the current passing vehicle, distance (d)1，d2) The distance between the current vehicle passing record and the vehicle passing record of the vehicle to be analyzed is recorded.
6. The apparatus of claim 4, wherein: further comprising: a data storage module;
and the data storage module is used for storing the calculation results in distributed databases Gbase and Hive, and is respectively used for data analysis and Web query.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 3 when executing the program.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011164549.6A CN112395955B (en) | 2020-10-27 | 2020-10-27 | Vehicle-related resident foothold analysis method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011164549.6A CN112395955B (en) | 2020-10-27 | 2020-10-27 | Vehicle-related resident foothold analysis method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112395955A CN112395955A (en) | 2021-02-23 |
| CN112395955B true CN112395955B (en) | 2022-07-12 |
Family
ID=74597204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011164549.6A Active CN112395955B (en) | 2020-10-27 | 2020-10-27 | Vehicle-related resident foothold analysis method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112395955B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114299424A (en) * | 2021-12-17 | 2022-04-08 | 深圳云天励飞技术股份有限公司 | Object classification method, device, electronic device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717790A (en) * | 2018-07-06 | 2018-10-30 | 广州市交通运输研究所 | A kind of vehicle driving analysis method based on bayonet license plate identification data |
| CN108875835A (en) * | 2018-06-26 | 2018-11-23 | 北京旷视科技有限公司 | Object foothold determines method, apparatus, electronic equipment and computer-readable medium |
| CN110851490A (en) * | 2019-10-16 | 2020-02-28 | 青岛海信网络科技股份有限公司 | Vehicle travel common stay point mining method and device based on vehicle passing data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7610146B2 (en) * | 1997-10-22 | 2009-10-27 | Intelligent Technologies International, Inc. | Vehicle position determining system and method |
-
2020
- 2020-10-27 CN CN202011164549.6A patent/CN112395955B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875835A (en) * | 2018-06-26 | 2018-11-23 | 北京旷视科技有限公司 | Object foothold determines method, apparatus, electronic equipment and computer-readable medium |
| CN108717790A (en) * | 2018-07-06 | 2018-10-30 | 广州市交通运输研究所 | A kind of vehicle driving analysis method based on bayonet license plate identification data |
| CN110851490A (en) * | 2019-10-16 | 2020-02-28 | 青岛海信网络科技股份有限公司 | Vehicle travel common stay point mining method and device based on vehicle passing data |
Non-Patent Citations (1)
| Title |
|---|
| 基于车牌识别数据的交通出行特征分析;龚越;《中国优秀博硕士学位论文全文数据库(硕士)工程科技II辑》;20190115;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112395955A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ratcliffe et al. | Aoristic crime analysis | |
| CN109887283B (en) | Road congestion prediction method, system and device based on checkpoint data | |
| TWI425454B (en) | Method, system and computer program product for reconstructing moving path of vehicle | |
| CN110874362A (en) | Data association analysis method and device | |
| CN109615572B (en) | Personnel intimacy degree analysis method and system based on big data | |
| CN107885795B (en) | Data verification method, system and device for card port data | |
| CN101848377B (en) | Device and method for intelligent linkage of multi-video recording device based on cloud computing and mass video searching | |
| CN111930868A (en) | Big data behavior trajectory analysis method based on multi-dimensional data acquisition | |
| CN110738856A (en) | urban traffic jam fine recognition method based on mobile clustering | |
| CN111950470A (en) | A kind of intelligent monitoring method, device, computer equipment and storage medium | |
| CN111949701A (en) | Moving object travel rule analysis method and device based on track similarity | |
| CN114970621A (en) | Method and device for detecting abnormal aggregation event, electronic equipment and storage medium | |
| CN113552656B (en) | Rainfall intensity monitoring method and system based on outdoor image multi-space-time fusion | |
| CN112562315B (en) | Method, terminal and storage medium for acquiring traffic flow information | |
| CN115527364A (en) | Traffic accident tracing method and system based on radar vision data fusion | |
| CN109117771B (en) | System and method for detecting violence events in image based on anchor nodes | |
| CN112395955B (en) | Vehicle-related resident foothold analysis method, device, equipment and medium | |
| CN112686226A (en) | Big data management method and device based on gridding management and electronic equipment | |
| CN111380530A (en) | Navigation Methods and Related Products | |
| CN115187886A (en) | Vehicle violation detection method and device and electronic equipment | |
| CN112364072A (en) | Vehicle-related non-commercial vehicle operation discovery method, device, equipment and medium | |
| CN110738167B (en) | A pedestrian identification method based on multi-domain spatial attribute association analysis | |
| CN112001280A (en) | Real-time online optimization face recognition system and method | |
| CN112182121B (en) | Vehicle-related relationship discovery method, device, equipment and medium | |
| CN113822367B (en) | Regional behavior analysis method, system and medium based on human face |
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 |