CN111461124A - Large data-based shielded license plate recognition method and device and storage medium - Google Patents
Large data-based shielded license plate recognition method and device and storage medium Download PDFInfo
- Publication number
- CN111461124A CN111461124A CN202010136530.4A CN202010136530A CN111461124A CN 111461124 A CN111461124 A CN 111461124A CN 202010136530 A CN202010136530 A CN 202010136530A CN 111461124 A CN111461124 A CN 111461124A
- Authority
- CN
- China
- Prior art keywords
- license plate
- electronic equipment
- special
- database
- vehicle
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 11
- 238000005065 mining Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 5
- 230000003203 everyday effect Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 5
- 230000000903 blocking effect Effects 0.000 description 4
- 230000002354 daily effect Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Abstract
The invention relates to the technical field of license plate recognition and big data, in particular to a method, equipment and a storage medium for recognizing a shielded license plate based on big data; the identification method comprises the following steps: replacing the shielded characters or the missing characters with special symbols to generate a special license plate; based on a special license plate space-time database and a wireless electronic device detection database, respectively extracting the moving tracks of a special license plate vehicle and the wireless electronic device based on time sequence: judging the association relationship between the special license plate and the wireless electronic equipment; and excavating a normal license plate associated with the ID of the electronic equipment from the association relation database of the electronic equipment and the license plate. The method, the equipment and the storage medium for identifying the shielded license plate based on the big data do not increase extra investment, fully utilize the existing social big data resources and identify the real license plate number of the shielded license plate; and manual participation and vehicle management database support are not required, so that the application cost is lower.
Description
Technical Field
The invention relates to the technical field of license plate recognition and big data, in particular to a method, equipment and a storage medium for recognizing a shielded license plate based on big data.
Background
With the improvement of living standard of people, vehicles on roads are more and more, and in order to avoid congestion, a number-limiting road-going measure is implemented in many cities. In order to avoid traffic control measures and traffic electronic eyes, some car owners start to shield license plates or forge license plates, which causes great obstacles to traffic order and vehicle management. The covering of the license plate means that a driver of the vehicle covers part or all of the license plate area by using a certain object, so that a traffic police or an electronic eye cannot identify the real license plate of the vehicle, and the purpose that illegal or illegal behaviors are not punished is achieved.
The traffic management department usually searches vehicles with the blocked license plates on site in a manual card setting mode, and the mode is like a sea fishing needle, consumes a large amount of manpower and material resources and has low efficiency. With the development and popularization of electronic eye and license plate recognition technology, it is possible to quickly recognize a vehicle with a blocked license plate, however, unless the process of blocking the license plate and the real license plate before blocking are shot, the method still cannot determine the real number of the blocked license plate, and thus it is difficult to recognize the owner of the vehicle and penalize the owner.
Zhangwuli (1) provides a method and a device for recognizing a blocked license plate, which comprises the steps of firstly carrying out primary license plate recognition on a license plate candidate region, outputting a primary recognition result comprising primary recognition characters and confidence degrees corresponding to the primary recognition characters, then judging according to the primary recognition result, carrying out deep learning recognition on the license plate candidate region meeting preset blocking conditions, and obtaining the number of characters and position information of the characters obtained by the deep learning recognition; and finally, determining the position of the shielding character in the license plate according to the primary recognition character, the confidence corresponding to the primary recognition character, the number of the characters and the position information of the characters, replacing the shielding character with a special symbol in the primary recognition result, and outputting a final recognition result. The method has the following defects: and recognizing a malicious license plate shielding event, replacing shielded characters with special characters to generate a license plate recognition result, but not recognizing a real license plate of the shielded license plate.
Yangyinghouse [ 2 ] provides a real-time detection method for detecting whether a vehicle is brand-free and the license plate is blocked. The method comprises the following steps: (1) performing license plate recognition and vehicle detection on a single frame; (2) associating the license plate recognized by each frame with the license plate recognized by the previous frame, and outputting a license plate track chain after comprehensive recognition; (3) associating the same vehicle with multiple frames, removing the false detection target, and outputting a vehicle track chain when the vehicle runs out of the picture; (4) analyzing the comprehensive recognition result of the license plate track chain, judging whether the character is shielded or not and giving out the shielded character position; (5) and matching the license plate track chain with the vehicle track chain, and judging that the vehicle is not a license plate when the vehicle track chain which is not matched with the license plate is not a license plate. The method has the following defects: the method can effectively and automatically detect the license plate missing or license plate shielding event, but cannot identify the real license plate of the license plate missing or shielded.
Beam army et al [ 3 ] propose a method and system for discriminating the vehicles with the occluded license plate in an auxiliary manner. The system comprises an electronic eye end system and a background server. Wherein, electronic eye end system includes: the device comprises an electronic eye, a local storage unit, a shielding identification module and a data sending module; the background server comprises: the system comprises a background data receiving module, a background storage unit, a feature extraction and identification unit, a database processing unit and a vehicle information database. The vehicle information database includes information such as vehicle color, model number, license plate symbol, etc. According to the method, after the license plate-free or license plate shielding event is automatically detected, the event and the captured vehicle picture are uploaded, and the computer vision technology is adopted to compare with the vehicle image and the characteristics in the database at the background, so that the vehicles with the same vehicle color, model and other characteristics are filtered. The method has the following defects: the number of vehicles with the same color and model is large, so that on one hand, the workload of later-stage investigation is increased; on the other hand, due to lack of evidence of fact, it is also easy to cause "out of the way" or "wrong way".
With the development of mobile internet and internet of things technology, wireless electronic devices (such as mobile phones, smart speakers, smart watches, hand rings, vehicle-mounted WIFI, electronic license plates, and the like) are rapidly merging into the lives of people and becoming life necessities carried by vehicle drivers. The global ID or MAC address of the wireless electronic equipment, and the time and the position of the wireless electronic equipment at that time can be extracted by analyzing the received mobile equipment data message through the wireless base stations such as the WIFI router, the RFID card reader and the Bluetooth base station.
Wanhualin et al [ 4 ] propose a moving target correlation method based on space-time trajectory matching, through excavating the bayonet license plate identification data and wireless electronic device detection data of the given time quantum, withdraw vehicle and wireless electronic device position set or activity orbit based on time sequence every day, through calculating the vehicle orbit and the public orbit point of the place of daily residence of the wireless electronic device orbit, associate vehicle license plate with electronic device, and produce the associated data records such as license plate, electronic device ID, place of daily residence.
Therefore, in order to solve the above problems, it is urgently needed to invent a new method, device and storage medium for identifying a blocking license plate based on big data.
Disclosure of Invention
The invention aims to: provided are a method and equipment for identifying a shielded license plate based on big data and a storage medium.
The invention provides the following scheme:
a shielded license plate identification method based on big data comprises the following steps:
analyzing the vehicle monitoring video stream, identifying the events of the shielded license plate and the license plate-free event, and replacing the shielded characters or the missing characters with special symbols to generate a special license plate;
importing and cleaning data in a given time period to obtain a special license plate space-time database and a wireless electronic equipment detection database;
based on a special license plate space-time database and a wireless electronic device detection database, respectively extracting the moving tracks of a special license plate vehicle and the wireless electronic device based on time sequence:
calculating the track matching degree or similarity between the special license plate vehicle and the wireless electronic equipment, and judging the association relation between the special license plate vehicle and the wireless electronic equipment;
and mining a normal license plate associated with the ID of the electronic equipment from an association relation database of the electronic equipment and the license plate according to the global ID of the electronic equipment associated with the special license plate.
The method comprises the steps of respectively extracting the moving tracks of the special license plate vehicle and the wireless electronic equipment based on the time sequence based on a special license plate space-time database and a wireless electronic equipment detection database, and specifically comprises the following steps:
extracting the track of the license plate in a given time period for any special license plate in a special license plate space-time database;
for any electronic device global ID in the wireless electronic device detection database, the track of the electronic device in a given time period is extracted.
Calculating the track matching degree or similarity between the special license plate vehicle and the wireless electronic equipment, and judging the association relation between the special license plate vehicle and the wireless electronic equipment, wherein the steps are as follows:
respectively extracting special license plate track T from a special license plate space-time database S1 and a wireless electronic equipment detection database S2AWith the electronic device trajectory TBCalculating TAAnd TBThe number p of the public track points;
if p is>q(q>0, predefined threshold), a special license plate is associatediAnd an electronic device global ID.
The method comprises the following steps of mining a normal license plate related to an electronic equipment ID from an association relation database of the electronic equipment and the license plate according to the electronic equipment global ID related to the special license plate, wherein the steps are as follows:
generating a database S3 with the ID of the electronic equipment as a primary key word by using the generated database of the association relationship between the license plate and the electronic equipment;
traversing a database S3, and associating data records of any electronic equipment with the license plate;
and if the global ID of the electronic equipment is the same as the associated electronic equipment of the special license plate, the associated license plate is the real license plate of the shielded license plate.
And generating a vehicle license plate and electronic equipment association relation database based on a moving target association method based on space-time trajectory matching.
The method for associating the moving target based on space-time trajectory matching comprises the following steps of generating an association relation database of a license plate and electronic equipment, and specifically comprises the following steps:
importing and cleaning checkpoint license plate identification data and wireless electronic equipment detection data in a given time period;
extracting a position set or a motion track of the vehicle and the wireless electronic equipment based on a time sequence every day according to the license plate identification data of the vehicle and the detection data of the wireless electronic equipment:
respectively calculating host positions of the vehicle and the wireless electronic equipment according to the extracted position sets or activity tracks of the vehicle and the wireless electronic equipment;
calculating public track points of the vehicle track and the wireless electronic equipment track according to the extracted position sets or the extracted activity tracks of the vehicle and the wireless electronic equipment to obtain a maximum same track point set in sequence of time;
and associating the license plate of the vehicle with the wireless electronic equipment according to the calculated maximum same track point set and the host positions of the vehicle and the wireless electronic equipment, and generating a data record.
The license plate is identified by utilizing a license plate identification algorithm, characters, letters or numbers which cannot be identified are marked as special symbols, and license plate identification results which are not license plates or completely shielded are all special symbols.
Importing and cleaning data in a given time period to obtain a special license plate space-time database and a wireless electronic equipment detection database, which specifically comprises the following steps:
importing a special license plate space-time database:
and importing the wireless electronic equipment detection database.
An electronic device comprising a memory and a processor; the memory is used for storing a computer program; the processor executes the computer program in the memory to realize the occlusion vehicle license plate recognition method based on the big data.
A computer-readable storage medium, storing a computer program which, when executed by a processor, is adapted to implement the big-data based occluded license plate recognition method.
The invention has the following beneficial effects:
the invention discloses a method, equipment and a storage medium for identifying a shielded license plate based on big data, wherein the identification method comprises the following steps: analyzing the vehicle monitoring video stream, identifying the events of the shielded license plate and the license plate-free event, and replacing the shielded characters or the missing characters with special symbols to generate a special license plate; importing and cleaning data in a given time period to obtain a special license plate space-time database and a wireless electronic equipment detection database; based on a special license plate space-time database and a wireless electronic device detection database, respectively extracting the moving tracks of a special license plate vehicle and the wireless electronic device based on time sequence: calculating the track matching degree or similarity between the special license plate vehicle and the wireless electronic equipment, and judging the association relation between the special license plate vehicle and the wireless electronic equipment; according to the electronic equipment global ID associated with the special license plate, excavating a normal license plate associated with the electronic equipment ID from an association relation database of the electronic equipment and the license plate; without adding extra investment, existing social big data resources are fully utilized, the incidence relation between the shielded license plate and the wireless electronic equipment is identified from blank data such as a license plate without the license plate or the shielded license plate, the ID of the wireless electronic equipment and the like, and then the real license plate number of the shielded license plate is identified; and manual participation and vehicle management database support are not required, so that the application cost is lower.
Drawings
FIG. 1 is a flow chart of a big data-based occluded license plate recognition method of the present invention.
Fig. 2 is a block diagram of an electronic device according to the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Referring to fig. 1, a method for identifying a blocked license plate based on big data includes the following steps:
analyzing the vehicle monitoring video stream, identifying the events of the shielded license plate and the license plate-free event, and replacing the shielded characters or the missing characters with special symbols to generate a special license plate;
importing and cleaning data in a given time period to obtain a special license plate space-time database and a wireless electronic equipment detection database;
based on a special license plate space-time database and a wireless electronic device detection database, respectively extracting the moving tracks of a special license plate vehicle and the wireless electronic device based on time sequence:
calculating the track matching degree or similarity between the special license plate vehicle and the wireless electronic equipment, and judging the association relation between the special license plate vehicle and the wireless electronic equipment;
and mining a normal license plate associated with the ID of the electronic equipment from an association relation database of the electronic equipment and the license plate according to the global ID of the electronic equipment associated with the special license plate.
The method comprises the steps of respectively extracting the moving tracks of the special license plate vehicle and the wireless electronic equipment based on the time sequence based on a special license plate space-time database and a wireless electronic equipment detection database, and specifically comprises the following steps:
extracting the track of the license plate in a given time period for any special license plate in a special license plate space-time database;
for any electronic device global ID in the wireless electronic device detection database, the track of the electronic device in a given time period is extracted.
Calculating the track matching degree or similarity between the special license plate vehicle and the wireless electronic equipment, and judging the association relation between the special license plate vehicle and the wireless electronic equipment, wherein the steps are as follows:
respectively extracting special license plate track T from a special license plate space-time database S1 and a wireless electronic equipment detection database S2AWith the electronic device trajectory TBCalculating TAAnd TBThe number p of the public track points;
if p is>q(q>0, predefined threshold), a special license plate is associatediAnd an electronic device global ID.
The method comprises the following steps of mining a normal license plate related to an electronic equipment ID from an association relation database of the electronic equipment and the license plate according to the electronic equipment global ID related to the special license plate, wherein the steps are as follows:
generating a database S3 with the ID of the electronic equipment as a primary key word by using the generated database of the association relationship between the license plate and the electronic equipment;
traversing a database S3, and associating data records of any electronic equipment with the license plate;
and if the global ID of the electronic equipment is the same as the associated electronic equipment of the special license plate, the associated license plate is the real license plate of the shielded license plate.
And generating a vehicle license plate and electronic equipment association relation database based on a moving target association method based on space-time trajectory matching.
The method for associating the moving target based on space-time trajectory matching comprises the following steps of generating an association relation database of a license plate and electronic equipment, and specifically comprises the following steps:
importing and cleaning checkpoint license plate identification data and wireless electronic equipment detection data in a given time period;
extracting a position set or a motion track of the vehicle and the wireless electronic equipment based on a time sequence every day according to the license plate identification data of the vehicle and the detection data of the wireless electronic equipment:
respectively calculating host positions of the vehicle and the wireless electronic equipment according to the extracted position sets or activity tracks of the vehicle and the wireless electronic equipment;
calculating public track points of the vehicle track and the wireless electronic equipment track according to the extracted position sets or the extracted activity tracks of the vehicle and the wireless electronic equipment to obtain a maximum same track point set in sequence of time;
and associating the license plate of the vehicle with the wireless electronic equipment according to the calculated maximum same track point set and the host positions of the vehicle and the wireless electronic equipment, and generating a data record.
The license plate is identified by utilizing a license plate identification algorithm, characters, letters or numbers which cannot be identified are marked as special symbols, and license plate identification results which are not license plates or completely shielded are all special symbols.
Importing and cleaning data in a given time period to obtain a special license plate space-time database and a wireless electronic equipment detection database, which specifically comprises the following steps:
importing a special license plate space-time database:
and importing the wireless electronic equipment detection database.
An electronic device comprising a memory and a processor; the memory is used for storing a computer program; the processor executes the computer program in the memory to realize the occlusion vehicle license plate recognition method based on the big data.
A computer-readable storage medium, storing a computer program which, when executed by a processor, is adapted to implement the big-data based occluded license plate recognition method.
Referring to fig. 2, an electronic device includes a memory 1 and a processor 2; the memory is used for storing a computer program; the processor executes the computer program in the memory to realize the occlusion vehicle license plate recognition method based on the big data.
A computer-readable storage medium, storing a computer program which, when executed by a processor, is adapted to implement the big-data based occluded license plate recognition method.
In the embodiment, the identification method, the equipment and the storage medium for the shielded license plate based on the big data comprises the following steps: analyzing the vehicle monitoring video stream, identifying the events of the shielded license plate and the license plate-free event, and replacing the shielded characters or the missing characters with special symbols to generate a special license plate; importing and cleaning data in a given time period to obtain a special license plate space-time database and a wireless electronic equipment detection database; based on a special license plate space-time database and a wireless electronic device detection database, respectively extracting the moving tracks of a special license plate vehicle and the wireless electronic device based on time sequence: calculating the track matching degree or similarity between the special license plate vehicle and the wireless electronic equipment, and judging the association relation between the special license plate vehicle and the wireless electronic equipment; according to the electronic equipment global ID associated with the special license plate, excavating a normal license plate associated with the electronic equipment ID from an association relation database of the electronic equipment and the license plate; without adding extra investment, existing social big data resources are fully utilized, the incidence relation between the shielded license plate and the wireless electronic equipment is identified from blank data such as a license plate without the license plate or the shielded license plate, the ID of the wireless electronic equipment and the like, and then the real license plate number of the shielded license plate is identified; and manual participation and vehicle management database support are not required, so that the application cost is lower.
The method for identifying the shielded license plate based on the big data in the embodiment comprises the following specific processes:
detecting the events of the blocked license plate and the non-license plate based on patent methods [ 1 ] or [ 2 ], and replacing blocked characters or missing characters with "+". If the number of the star points in the license plate number is more than 3, marking the license plate as a special license plate;
importing and cleaning space-time data of the license plate and the wireless electronic equipment in the last 1 day:
2.1 importing a special license plate time-space database: s1 { (plate)i,timei,loci(longitude,latitude)),i∈N}
2.2 importing a wireless electronic device (WIFI or Bluetooth) detection database: s2 { (MAC)j,timej,locj(longitude,latitude)),j∈N})
3, based on the space-time databases S1 and S2, respectively, the activity tracks (based on time sequence) of the special license plate vehicle and the line electronic equipment in the 1 day are extracted:
3.1 for any particular license plate in set S1iBased on the plateiSpace-time data to generate license plateiIn the activity track of the 1 day, the data format may be (plate)i，(timestart,locstart)，(time1,loc1)，(time2,loc2)，...，(timeend,locend))；
3.2 Global Address MAC for any electronic device in set S2jExtracting the MAC daily trace data, data format (MAC)j，(timestart,locstart)，(time1,loc1)，(time2,loc2)，...，(timeend,locend))；
3.3, extracting the daily activity track data of the equipment by using the global ID of other uniquely-identified electronic equipment by using the same method;
4, judging the incidence relation between the special license plate and the electronic equipment according to the track matching degree or the similarity:
4.1 calculating vehicle plateiTrack of
With electronic equipment MACjTrack of
Number of common track points:
4.1.1 sequential traversal of TAFor TAEach of which
(0<i<m)；
4.1.2 if TBIn existence of
(0<j<n) are such that
Second and
rice, then
And
is TAAnd TBThe same trace points of (A) are marked as
k represents the k +1 th identical track point; otherwise j is j +1, returning to the step 4.1.1;
4.1.3 traversing trajectory TAAnd track TBObtaining the maximum same track point set with time as the sequence,
4.1.4 computing the set TmaxThe number of middle elements is marked as p (p ∈ N);
4.2 if p>q(q>0, predefined threshold), then the license plate can be judgediWith electronic equipment MACjIs related;
5, importing a database of the association relationship between the license plate and the electronic device generated in the patent [ 4 ], and generating a data record set S3 with the electronic device MAC as a main key, wherein S3 { (MAC)k,platek),k∈N}；
5.2 traverse the set S3, for each record (MAC) in the set S3k,platek),k∈N；
5.3 if MACk＝MACjThen platekFor shielding license plateiThe real license plate.
If with MACkThe number of the associated license plates is more than 1: the comparison can be carried out by combining the structural characteristics (brand, model, vehicle money, vehicle color and the like) of the vehicle; for a partially shielded license plate, the plate can be comparediAnd platekA character string; further improve the real license plate recognitionThe accuracy of (2).
The embodiment of the invention discloses a method for identifying the real license plate of an unlicensed or shielded license plate, which comprises the following steps: the method comprises the steps of firstly detecting a license plate-free or shielding event through a computer vision method, excavating an incidence relation between a license plate-free or shielding event and a global ID of electronic equipment by combining a vehicle positioning technology and an electronic equipment positioning/track matching technology, and further identifying a real license plate of the license plate-free or shielding event based on the incidence relation between the overall ID of the mobile electronic equipment and the license plate excavated in the patent [ 4 ]. In real life, as the intentional license plate shielding or license plate detaching is illegal, the probability of no license plate or license plate shielding on a road is very low, that is, the probability of more than two recognition results appearing at the same place at the same time is very low, so that the license plate marked by special characters can be treated as a special license plate. Even if the special license plate vehicles appear in a plurality of places at the same time, the physical positions of the special license plate vehicles at the moment can be judged according to the license plate positions, the vehicle speed and the road planning at the previous moment, so that the special license plate moving track is generated.
In the method for identifying a license plate covered based on big data in the embodiment, the background data is as follows:
when the motor vehicle passes through a crossing of a gate or a camera, a license plate recognition algorithm is used for recognizing the license plate, and characters, letters or numbers which cannot be recognized are marked as special symbols (such as 'a'). The recognition result of the license plate without the license plate or completely shielded is ". times.. may be" jing F "for the recognition result of the license plate partially shielded.
Database of vehicle activity information with or without license plates (license plates containing "+" characters): including the license plate, time (in the format of yyyy-MM-dd hh: MM: ss), location loc,;
wireless electronic device scanning database:
1) WIFI equipment: MAC address, time of time, location loc.;
2) bluetooth equipment: MAC address, date, time of time, location loc.;
3) an RFID device: TID, date, time, location loc.;
here, the location loc is a longitude and latitude data pair (longitude, latitude) obtained by a positioning system such as GPS and beidou.
When the difference between the two feature acquisition times | time1-time2|<α(α>0) Time can be considered1And time2The time is the same; when the distance between the two feature collection points is distance (loc)1,loc2)<β(β>0) Then, it can be considered as loc1And loc2The locations are the same.
The technical problem to be solved by the big data-based shielded license plate recognition method in the embodiment is as follows: recognizing a license plate shielding event, and identifying the characters of the shielded license plate by using specific characters to generate a special license plate; extracting positions and tracks of global IDs (identity) of the special license plate and the electronic equipment within a period of time before and after the appearance of the shielded license plate, and excavating an association relation between the special license plate and certain electronic equipment; and further analyzing and excavating the real license plate of the shielded license plate according to the global I D of the electronic equipment and the electronic equipment/license plate association database.
For simplicity of explanation, the method embodiments are described as a series of acts or combinations, but those skilled in the art will appreciate that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently with other steps in accordance with the embodiments of the invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A shielded license plate recognition method based on big data is characterized by comprising the following steps:
analyzing the vehicle monitoring video stream, identifying the events of the shielded license plate and the license plate-free event, and replacing the shielded characters or the missing characters with special symbols to generate a special license plate;
importing and cleaning data in a given time period to obtain a special license plate space-time database and a wireless electronic equipment detection database;
based on a special license plate space-time database and a wireless electronic device detection database, respectively extracting the moving tracks of a special license plate vehicle and the wireless electronic device based on time sequence:
calculating the track matching degree or similarity between the special license plate vehicle and the wireless electronic equipment, and judging the association relation between the special license plate vehicle and the wireless electronic equipment;
and mining a normal license plate associated with the ID of the electronic equipment from an association relation database of the electronic equipment and the license plate according to the global ID of the electronic equipment associated with the special license plate.
2. The shielded license plate recognition method based on big data as claimed in claim 1, wherein the step of extracting the time-sequence-based motion tracks of the special license plate vehicle and the wireless electronic device based on the special license plate space-time database and the wireless electronic device detection database respectively comprises:
extracting the track of the license plate in a given time period for any special license plate in a special license plate space-time database;
for any electronic device global ID in the wireless electronic device detection database, the track of the electronic device in a given time period is extracted.
3. The shielded license plate recognition method based on big data of claim 2, wherein the step of calculating the track matching degree or similarity between the special license plate vehicle and the wireless electronic device and judging the association relationship between the special license plate vehicle and the wireless electronic device specifically comprises:
respectively extracting special license plate track T from a special license plate space-time database S1 and a wireless electronic equipment detection database S2AWith the electronic device trajectory TBCalculating TAAnd TBThe number p of the public track points;
if p is>q(q>0, predefined threshold), a special license plate is associatediAnd an electronic device global ID.
4. The shielded license plate recognition method based on big data as claimed in claim 3, wherein the step of mining the normal license plate associated with the electronic device ID from the association relation database of the electronic device and the license plate according to the electronic device global ID associated with the special license plate is specifically as follows:
generating a database S3 with the ID of the electronic equipment as a primary key word by using the generated database of the association relationship between the license plate and the electronic equipment;
traversing a database S3, and associating data records of any electronic equipment with the license plate;
and if the global ID of the electronic equipment is the same as the associated electronic equipment of the special license plate, the associated license plate is the real license plate of the shielded license plate.
5. The blocked license plate recognition method based on big data of claim 4, wherein a license plate and electronic device association relation database is generated based on a moving target association method of spatiotemporal trajectory matching.
6. The shielded license plate recognition method based on big data of claim 5, wherein the step of generating a database of association relationship between the license plate and the electronic device based on a moving target association method of spatiotemporal trajectory matching specifically comprises:
importing and cleaning checkpoint license plate identification data and wireless electronic equipment detection data in a given time period;
extracting a position set or a motion track of the vehicle and the wireless electronic equipment based on a time sequence every day according to the license plate identification data of the vehicle and the detection data of the wireless electronic equipment:
respectively calculating host positions of the vehicle and the wireless electronic equipment according to the extracted position sets or activity tracks of the vehicle and the wireless electronic equipment;
calculating public track points of the vehicle track and the wireless electronic equipment track according to the extracted position sets or the extracted activity tracks of the vehicle and the wireless electronic equipment to obtain a maximum same track point set in sequence of time;
and associating the license plate of the vehicle with the wireless electronic equipment according to the calculated maximum same track point set and the host positions of the vehicle and the wireless electronic equipment, and generating a data record.
7. The occlusion vehicle plate recognition method based on big data as claimed in claim 6,
the license plate is identified by utilizing a license plate identification algorithm, characters, letters or numbers which cannot be identified are marked as special symbols, and license plate identification results which are not license plates or completely shielded are all special symbols.
8. The shielded license plate recognition method based on big data as claimed in claim 7, wherein the step of importing and cleaning data of a given time period to obtain a special license plate space-time database and a wireless electronic device detection database specifically comprises:
importing a special license plate space-time database:
and importing the wireless electronic equipment detection database.
9. An electronic device, characterized in that: comprising a memory and a processor; the memory is used for storing a computer program; the processor executes a computer program in the memory to implement the big-data based occluded license plate recognition method of any of claims 1-8.
10. A computer-readable storage medium characterized by: a computer program is stored which, when being executed by a processor, is adapted to carry out the big-data based occluded license plate recognition method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136530.4A CN111461124A (en) | 2020-03-02 | 2020-03-02 | Large data-based shielded license plate recognition method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136530.4A CN111461124A (en) | 2020-03-02 | 2020-03-02 | Large data-based shielded license plate recognition method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111461124A true CN111461124A (en) | 2020-07-28 |
Family
ID=71682432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010136530.4A Pending CN111461124A (en) | 2020-03-02 | 2020-03-02 | Large data-based shielded license plate recognition method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461124A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052094A (en) * | 2021-03-30 | 2021-06-29 | 北京卓视智通科技有限责任公司 | Method and device for determining original shielding license plate and electronic equipment |
| CN113723316A (en) * | 2021-09-01 | 2021-11-30 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308605A (en) * | 2008-05-23 | 2008-11-19 | 陈汇鑫 | Method implementing traffic dynamic management by vehicle information recognition |
| CN102737506A (en) * | 2011-07-01 | 2012-10-17 | 山东佳信自动化有限公司 | Method for immediately collecting information of driving vehicle |
| CN103021184A (en) * | 2012-12-26 | 2013-04-03 | 江苏大学 | Method and system for assistant distinguishing of vehicles with license plates covered |
| CN104200669A (en) * | 2014-08-18 | 2014-12-10 | 华南理工大学 | Fake-licensed car recognition method and system based on Hadoop |
| CN108305466A (en) * | 2018-03-13 | 2018-07-20 | 北京智芯原动科技有限公司 | Roadside Parking detection method and device based on vehicle characteristics analysis |
| CN110335473A (en) * | 2019-08-14 | 2019-10-15 | 中国联合网络通信集团有限公司 | Block the personal identification method and system of license plate vehicle |
| CN110674236A (en) * | 2019-09-23 | 2020-01-10 | 浙江省北大信息技术高等研究院 | Moving target association method, device and equipment based on space-time trajectory matching and storage medium |
-
2020
- 2020-03-02 CN CN202010136530.4A patent/CN111461124A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308605A (en) * | 2008-05-23 | 2008-11-19 | 陈汇鑫 | Method implementing traffic dynamic management by vehicle information recognition |
| CN102737506A (en) * | 2011-07-01 | 2012-10-17 | 山东佳信自动化有限公司 | Method for immediately collecting information of driving vehicle |
| CN103021184A (en) * | 2012-12-26 | 2013-04-03 | 江苏大学 | Method and system for assistant distinguishing of vehicles with license plates covered |
| CN104200669A (en) * | 2014-08-18 | 2014-12-10 | 华南理工大学 | Fake-licensed car recognition method and system based on Hadoop |
| CN108305466A (en) * | 2018-03-13 | 2018-07-20 | 北京智芯原动科技有限公司 | Roadside Parking detection method and device based on vehicle characteristics analysis |
| CN110335473A (en) * | 2019-08-14 | 2019-10-15 | 中国联合网络通信集团有限公司 | Block the personal identification method and system of license plate vehicle |
| CN110674236A (en) * | 2019-09-23 | 2020-01-10 | 浙江省北大信息技术高等研究院 | Moving target association method, device and equipment based on space-time trajectory matching and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052094A (en) * | 2021-03-30 | 2021-06-29 | 北京卓视智通科技有限责任公司 | Method and device for determining original shielding license plate and electronic equipment |
| CN113723316A (en) * | 2021-09-01 | 2021-11-30 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN113723316B (en) * | 2021-09-01 | 2024-04-16 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019153193A1 (en) | Taxi operation monitoring method, device, storage medium, and system | |
| CN106384513B (en) | A kind of fake-licensed car capture system and method based on intelligent transportation | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| CN110674236A (en) | Moving target association method, device and equipment based on space-time trajectory matching and storage medium | |
| US11734783B2 (en) | System and method for detecting on-street parking violations | |
| CN103699677B (en) | A kind of criminal's whereabouts mapping system and method based on face recognition technology | |
| CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
| CN104766479A (en) | Automobile identity recognition method and device based on ultrahigh frequency radio frequency and video image dual-recognition matching | |
| CN111353369B (en) | Application method and system of urban road side parking high-level video in auxiliary criminal investigation | |
| CN108986472A (en) | One kind turns around vehicle monitoring method and device | |
| CN105046966A (en) | System and method for automatically detecting illegal parking behaviors in drop-off areas | |
| CN106529401A (en) | Vehicle anti-tracking method, vehicle anti-tracking device and vehicle anti-tracking system | |
| CN105448105A (en) | Patrol police vehicle-based monitoring system | |
| US20230073717A1 (en) | Systems And Methods For Electronic Surveillance | |
| CN105528626A (en) | RFID (Radio Frequency Identification) reader and camera integrated machine and application thereof | |
| CN111369797A (en) | Vehicle monitoring method, electronic fence construction method, electronic fence and device | |
| CN111444798A (en) | Method and device for identifying driving behavior of electric bicycle and computer equipment | |
| CN111461124A (en) | Large data-based shielded license plate recognition method and device and storage medium | |
| CN114067270B (en) | Vehicle tracking method and device, computer equipment and storage medium | |
| CN112380892B (en) | Image recognition method, device, equipment and medium | |
| CN114898297A (en) | Non-motor vehicle illegal behavior determination method based on target detection and target tracking | |
| CN111078973A (en) | Fake-licensed vehicle identification method and equipment based on big data and storage medium | |
| CN112836683A (en) | License plate recognition method, device, equipment and medium for portable camera equipment | |
| CN106327876B (en) | A kind of fake-licensed car capture system and method based on automobile data recorder | |
| CN113901946A (en) | Abnormal behavior detection method and device, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |
|
| RJ01 | Rejection of invention patent application after publication |