CN107798334A - A kind of matching process and device of vehicle electron identifying data and video identification data - Google Patents
A kind of matching process and device of vehicle electron identifying data and video identification data Download PDFInfo
- Publication number
- CN107798334A CN107798334A CN201710743924.4A CN201710743924A CN107798334A CN 107798334 A CN107798334 A CN 107798334A CN 201710743924 A CN201710743924 A CN 201710743924A CN 107798334 A CN107798334 A CN 107798334A
- Authority
- CN
- China
- Prior art keywords
- matrix
- matching
- data
- vehicle
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides the matching process of a kind of vehicle electron identifying data and video identification data, comprise the following steps：1) video data in time period t 1 to t2 is obtained, forms the fisrt feature matrix of vehicle characteristics；2) rf data of the vehicle electron identifying in time period t 1 to t2 is obtained, forms the second characteristic matrix of vehicle characteristics；3) similarity per a line with every a line in second characteristic matrix in fisrt feature matrix is calculated；4) similarity for obtaining upper step forms matching matrix；5) matching and non-matching video data and rf data are found by matching matrix.The method of the invention is implemented simply, to use in server end, can also be used in resource-constrained collection terminal, there is very much versatility.The vehicle characteristics that video and radio frequency can be provided all consider as matching factor, have used for reference the theory of probability, calculate the matching degree of video and rf data, using the maximum data of matching degree in data set to as matching result.
Description
Technical field
The invention belongs to RFID REIDs and candid camera field of license plate recognition, more particularly, to one kind
The matching process and device of vehicle electron identifying data and video identification data.
Background technology
1. vehicle electron identifying：" electronic license plate " is commonly called as, the information such as the number-plate number are stored in RF tag, can be certainly
The identification and monitoring of vehicle are completed dynamicly, non-contact, not parking, are to be handed over based on Internet of Things passive radio frequency identification (RFID) in wisdom
The extension in logical field.
2. biradical matching：Video data and RFID data are matched, is the basis for identifying vacation/fake license plate vehicle.Its general principle
It is：
RFID REIDs, traffic video camera license plate recognition technology are used simultaneously, and iron car is installed on vehicle
Board and vehicle electron identifying (vehicle-related information or unique identifier are stored with the internal memory of electronic mark), when vehicle passes through
When, electronic mark information is read by radio-frequency identification reader/writer, the iron number-plate number is identified by video camera, and different information is carried out
Intersect and compare.
The meaning of this method is the accuracy for improving vehicle identification, and because electronic license plate is relative to physics car plate tool
There is the characteristics of not being forged, the current of the illegal vehicles such as problem car, fake-licensed car can be reduced in theory, improve the peace of road traffic
Quan Xing.
In technology practical application, due to that may have more in the identification range of radio frequency identification or in the range of video identification
Car exist, so the matching object of matching algorithm be usually multi-to-multi, it is necessary to two set (video data set and radio frequencies
Data acquisition system) in the range of matched.
Preposition constraints is needed in current various algorithms, it is unified, it is necessary to car if desired for radio frequency and video coverage
Positioned and tested the speed；Implementation and use environment of these constraints all to system propose exacting terms.
The content of the invention
In view of this, the present invention is directed to propose the matching algorithm of a kind of vehicle electron identifying data and video identification data,
Implement simply, to use in server end, can also be used in resource-constrained collection terminal, there is very much versatility.
To reach above-mentioned purpose, the technical proposal of the invention is realized in this way：
A kind of matching process of vehicle electron identifying data and video identification data, comprises the following steps：
1) video data in time period t 1 to t2 is obtained, extracts information of vehicles, forms the fisrt feature square of vehicle characteristics
Gust, every a line in fisrt feature matrix is all fully described the feature of a car；
2) rf data of the vehicle electron identifying in time period t 1 to t2 is obtained, forms the second feature square of vehicle characteristics
Gust, every a line in second characteristic matrix is all fully described the feature of a car；
3) similarity per a line with every a line in second characteristic matrix in fisrt feature matrix is calculated；
4) using the car plate identified in video data as line index, the car plate that rf data identifies is column index, will be upper
Walk obtained similarity and form matching matrix；
5) matching and non-matching video data and rf data are found by matching matrix.
Preferably, in step 3, by the feature of a car of every a line in fisrt feature matrix and second characteristic matrix
The character string of description vehicle is formed, then calculates similarity of the similarity of two character strings as vehicle.
Preferably, in step 3, using each feature of a vehicle as a character string, calculate in fisrt feature matrix
Per a line, the similarity of character string of each feature corresponding with every a line in second characteristic matrix, weight is set to each feature,
It is weighted, obtains the similarity of vehicle.
Preferably, in steps of 5, specifically comprise the following steps：
51) obtain matching the maximum in matrix；
52) video data identification car plate and vehicle electron identifying car plate according to corresponding to maximum, find corresponding feature
Data, using this data to as matching result；
53) in matrix is matched, row and column corresponding to maximum in matching matrix is eliminated, i.e., matching matrix dropped
Tie up, the matrix after dimensionality reduction turns into new matching matrix；
54) judge whether new matching matrix is empty；If so, then terminate to exit；If otherwise jump to step 55；
55) judge whether the maximum of new matching matrix is more than similarity lower limit L, be if it is transferred to step 52；It is no
Then, it is transferred to step 56；
56) license board information that output matching matrix intermediate value is less than corresponding to similarity lower limit L is investigated as emphasis.
A kind of coalignment of vehicle electron identifying data and video identification data, including：
Fisrt feature acquiring unit, the video data in time period t 1 to t2 is obtained, extract information of vehicles, it is special to form vehicle
The fisrt feature matrix of sign, every a line in fisrt feature matrix are all fully described the feature of a car；
Second feature acquiring unit, the rf data of the vehicle electron identifying in time period t 1 to t2 is obtained, form vehicle
The second characteristic matrix of feature, every a line in second characteristic matrix are all fully described the feature of a car；
Similarity calculated, calculate similar per a line to second characteristic matrix per a line in fisrt feature matrix
Degree；
Match matrix construction unit, using the car plate identified in video data as line index, car that rf data identifies
Board is column index, and the similarity that upper step is obtained forms matching matrix；
As a result output unit, matching and non-matching video data and rf data are found by matching matrix.
Preferably, similarity calculated, by a car of every a line in fisrt feature matrix and second characteristic matrix
Feature form the character string of description vehicle, then calculate similarity of the similarity as vehicle of two character strings.
Preferably, similarity calculated, using each feature of a vehicle as a character string, fisrt feature square is calculated
The similarity of character string of every a line each feature corresponding with every a line in second characteristic matrix, sets to each feature and weighs in battle array
Weight, is weighted, obtains the similarity of vehicle.
Preferably, as a result the course of work of output unit is as follows：
S1) obtain matching the maximum in matrix；
S2) video data identification car plate and vehicle electron identifying car plate according to corresponding to maximum, find corresponding feature
Data, using this data to as matching result；
S3) in matrix is matched, row and column corresponding to maximum in matching matrix is eliminated, i.e., matching matrix dropped
Tie up, the matrix after dimensionality reduction turns into new matching matrix；
S4) judge whether new matching matrix is empty；If so, then terminate to exit；If otherwise jump to step S5；
S5) judge whether the maximum of new matching matrix is more than similarity lower limit L, be if it is transferred to step 52；It is no
Then, it is transferred to step S6；
S6) license board information that output matching matrix intermediate value is less than corresponding to similarity lower limit L is investigated as emphasis.
Relative to prior art, method and device of the present invention is respectively provided with following advantage：
(1) it is different from traditional matching algorithm and only matches car plate, but the vehicle characteristics that video and radio frequency can be provided
All consider as matching factor；
(2) it is different from that traditional algorithm can only provide two Data Matchings or unmatched direct result, this algorithm are borrowed
Reflected the theory of probability, calculated the matching degree of video and rf data, using the maximum data of matching degree in data set to as
With result, solving video data itself also has mismatch problem caused by recognition correct rate；
(3) the data result feature of associate(d) matrix, matching matrix is formed, dimension-reduction treatment is gradually carried out in deterministic process,
With the more efficient of calculating is spent, more accurately；
(4) for different characteristic, weights are given, avoiding inessential feature influences the problem of whole matching is spent.
Brief description of the drawings
The accompanying drawing for forming the part of the present invention is used for providing a further understanding of the present invention, schematic reality of the invention
Apply example and its illustrate to be used to explain the present invention, do not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the gradual reduction process schematic diagram that matrix is matched described in the embodiment of the present invention.
Embodiment
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
Describe the present invention in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
The matching process of a kind of vehicle electron identifying data of the embodiment of the present invention and video identification data, including following step
Suddenly：
1st, within the period (t2-t1), video data provides the first data matrix V (n*k) of vehicle characteristics, wherein
ViPlateNo is vehicle i license board information, and ViFi is vehicle i a certain characteristic information (such as vehicle color)；
| V1PlateNo | V1F1 | V1F2 | V1F3 | …… | V1Fk |
| V2PlateNo | V2F1 | V2F2 | V2F3 | …… | V2Fk |
| V3PlateNo | V3F1 | V3F2 | V3F3 | …… | V3Fk |
| …… | …… | …… | …… | …… | …… |
| VnPlateNo | VnF1 | VnF2 | VnF3 | …… | VnFk |
2nd, within the same period (t2-t1), vehicle electron identifying provides the second data matrix R of vehicle characteristics
(m*k), wherein RiPlateNo is vehicle i license board information, and RiFi is vehicle i a certain characteristic information (such as vehicle color)
| R1PlateNo | R1F1 | R1F2 | R1F3 | …… | R1Fk |
| R2PlateNo | R2F1 | R2F2 | R2F3 | …… | R2Fk |
| R3PlateNo | R3F1 | R3F2 | R3F3 | …… | R3Fk |
| …… | …… | …… | …… | …… | …… |
| RmPlateNo | RnF1 | RnF2 | RnF3 | …… | RnFk |
3rd, every a line in two matrixes is all fully described the feature of a car, according to feature calculation matrix V and matrix R
In per a line similarity, calculate similarity various algorithms, such as each feature can be utilized to can be rated as character string, calculate each spy
The similarity of character string of sign.Processing can also be weighted to each feature, to protrude different characteristic for whole identification feature
Importance.
Or the vehicle characteristics for collecting the rfid vehicle characteristics collected and video identification are abstracted as description vehicle
Character string statement, then calculate similarity of the similarity of two sentences as vehicle.
Such as：What rfid was collected is " white, Cherry, capital KA1234, kart, in May, 2010 production, 3 tracks ",
The automobile that video provides is characterized as " white, Cherry, capital KA1234, kart, 3 tracks, speed 60km/h ", then calculate two
The similarity of car, the calculating " white that in the May, 2010 for being capital KA1234 in the license plate numbers of 3 lanes produces is reformed into
Cherry's board kart " with " in the 1 white Cherry that the travel speed that the license plate numbers of 3 lanes are capital KA1234 is 60km/h
The similarity of two character strings of bat kart ".
4th, using the car plate that video identification goes out as line index, the car plate that electronic mark identifies is column index, obtains matching square
Battle array M,
5th, the video data and rf data of matching are found by matching matrix M：
A) matching matrix M maximum Pmax, that is, the video and rf data that similarity is maximum are found.
B) video identification car plate and vehicle electron identifying car plate according to corresponding to maximum, find in V and R and count accordingly
According to using this data to as matching result.Such as the capital A12345 in Fig. 1.
C) in matrix is matched, row and column corresponding to Pmax is eliminated, i.e., dimensionality reduction is carried out to matrix, the matrix after dimensionality reduction into
For new matrix M.Such as Fig. 1 .a) to Fig. 1 .c) shown in process.
Repeat a)~c), until Pmax be less than the similarity lower limit L of setting either M turn into empty matrix or M only remain 1 row or
1 column data.Illustrate that video data and rf data similarity are low less than L, remaining data are all nonmatched datas；M is empty square
All Data Matchings that can be matched of battle array explanation are completed.Non-matched data can be used as the doubtful board illegal vehicle data emphasis that relates to close
Note.If Tianjin KL1514 in Fig. 1 is probably the vehicle of not installing electronic mark.
The development of subsequent technology, the quantity for the characteristic value that rfid and video can provide is more and more, and matching result is more next
It is more accurate, in theory when the quantity of characteristic value is sufficiently large, it can accurately match each car.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
God any modification, equivalent substitution and improvements made etc., should be included in the scope of the protection with principle.
Claims (8)
1. the matching process of a kind of vehicle electron identifying data and video identification data, it is characterised in that comprise the following steps：
1) video data in time period t 1 to t2 is obtained, extracts information of vehicles, forms the fisrt feature matrix of vehicle characteristics, the
Every a line in one eigenmatrix is all fully described the feature of a car；
2) rf data of the vehicle electron identifying in time period t 1 to t2 is obtained, forms the second characteristic matrix of vehicle characteristics,
Every a line in second characteristic matrix is all fully described the feature of a car；
3) similarity per a line with every a line in second characteristic matrix in fisrt feature matrix is calculated；
4) using the car plate identified in video data as line index, the car plate that rf data identifies is column index, and upper step is obtained
The similarity arrived forms matching matrix；
5) matching and non-matching video data and rf data are found by matching matrix.
2. the matching process of vehicle electron identifying data according to claim 1 and video identification data, it is characterised in that：
In step 3, the feature of a car of every a line in fisrt feature matrix and second characteristic matrix is formed into description vehicle
Character string, then calculate similarity of the similarity of two character strings as vehicle.
3. the matching process of vehicle electron identifying data according to claim 1 and video identification data, it is characterised in that：
In step 3, using each feature of a vehicle as a character string, calculate in fisrt feature matrix per a line and second feature
The similarity of character string of each feature corresponding to every a line, sets weight to each feature, is weighted, obtains in matrix
The similarity of vehicle.
4. the matching process of vehicle electron identifying data according to claim 1 and video identification data, it is characterised in that：
In steps of 5, specifically comprise the following steps：
51) obtain matching the maximum in matrix；
52) video data identification car plate and vehicle electron identifying car plate according to corresponding to maximum, find corresponding characteristic,
Using this data to as matching result；
53) in matrix is matched, row and column corresponding to maximum in matching matrix is eliminated, i.e., dimensionality reduction is carried out to matching matrix,
Matrix after dimensionality reduction turns into new matching matrix；
54) judge whether new matching matrix is empty；If so, then terminate to exit；If otherwise jump to step 55；
55) judge whether the maximum of new matching matrix is more than similarity lower limit L, be if it is transferred to step 52；Otherwise, adjust
To step 56；
56) license board information that output matching matrix intermediate value is less than corresponding to similarity lower limit L is investigated as emphasis.
A kind of 5. coalignment of vehicle electron identifying data and video identification data, it is characterised in that including：
Fisrt feature acquiring unit, the video data in time period t 1 to t2 is obtained, extract information of vehicles, form vehicle characteristics
Fisrt feature matrix, every a line in fisrt feature matrix are all fully described the feature of a car；
Second feature acquiring unit, the rf data of the vehicle electron identifying in time period t 1 to t2 is obtained, form vehicle characteristics
Second characteristic matrix, every a line in second characteristic matrix is all fully described the feature of a car；
Similarity calculated, calculate the similarity per a line with every a line in second characteristic matrix in fisrt feature matrix；
Matrix construction unit is matched, using the car plate identified in video data as line index, the car plate that rf data identifies is
Column index, the similarity that upper step is obtained form matching matrix；
As a result output unit, matching and non-matching video data and rf data are found by matching matrix.
6. the coalignment of vehicle electron identifying data according to claim 5 and video identification data, it is characterised in that：
Similarity calculated, the feature of a car of every a line in fisrt feature matrix and second characteristic matrix is formed into description car
Character string, then calculate similarity of the similarity as vehicle of two character strings.
7. the coalignment of vehicle electron identifying data according to claim 5 and video identification data, it is characterised in that：
Similarity calculated, using each feature of a vehicle as a character string, calculate in fisrt feature matrix per a line with the
The similarity of character string of each feature corresponding to every a line, sets weight to each feature, is weighted meter in two eigenmatrixes
Calculate, obtain the similarity of vehicle.
8. the coalignment of vehicle electron identifying data according to claim 5 and video identification data, it is characterised in that：
As a result the course of work of output unit is as follows：
S1) obtain matching the maximum in matrix；
S2) video data identification car plate and vehicle electron identifying car plate according to corresponding to maximum, find corresponding characteristic,
Using this data to as matching result；
S3) in matrix is matched, row and column corresponding to maximum in matching matrix is eliminated, i.e., dimensionality reduction is carried out to matching matrix,
Matrix after dimensionality reduction turns into new matching matrix；
S4) judge whether new matching matrix is empty；If so, then terminate to exit；If otherwise jump to step S5；
S5) judge whether the maximum of new matching matrix is more than similarity lower limit L, be if it is transferred to step 52；Otherwise, adjust
To step S6；
S6) license board information that output matching matrix intermediate value is less than corresponding to similarity lower limit L is investigated as emphasis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710743924.4A CN107798334B (en) | 2017-08-25 | 2017-08-25 | Method and device for matching automobile electronic identification data and video identification data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710743924.4A CN107798334B (en) | 2017-08-25 | 2017-08-25 | Method and device for matching automobile electronic identification data and video identification data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107798334A true CN107798334A (en) | 2018-03-13 |
| CN107798334B CN107798334B (en) | 2021-06-11 |
Family
ID=61531647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710743924.4A Active CN107798334B (en) | 2017-08-25 | 2017-08-25 | Method and device for matching automobile electronic identification data and video identification data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107798334B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596119A (en) * | 2018-04-28 | 2018-09-28 | 江苏本能科技有限公司 | Radio frequency identification and video identification matching process and system, equipment, storage medium |
| CN109358989A (en) * | 2018-12-25 | 2019-02-19 | 四川效率源信息安全技术股份有限公司 | A method of the multiple mysql-innodb database of carving based on graph theory |
| CN109580522A (en) * | 2018-11-20 | 2019-04-05 | 北京计算机技术及应用研究所 | A kind of automobile exhaust pollutant monitoring method merging vehicle electron identifying and video |
| CN111325054A (en) * | 2018-12-14 | 2020-06-23 | 航天信息股份有限公司 | Method and device for determining cloned vehicle and computing equipment |
| CN112435479A (en) * | 2020-11-09 | 2021-03-02 | 浙江大华技术股份有限公司 | Target object violation detection method and device, computer equipment and system |
| CN112562347A (en) * | 2020-11-30 | 2021-03-26 | 高新兴智联科技有限公司 | Matching algorithm for electronic identification radio frequency data and video data of motor vehicle |
| CN115359397A (en) * | 2022-08-17 | 2022-11-18 | 北京博宏科元信息科技有限公司 | Radio frequency video fusion data management method and device and computer equipment |
| CN115359665A (en) * | 2022-08-17 | 2022-11-18 | 北京博宏科元信息科技有限公司 | Multichannel violation vehicle recording method and device based on radio frequency video all-in-one machine |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130201316A1 (en) * | 2012-01-09 | 2013-08-08 | May Patents Ltd. | System and method for server based control |
| CN103745600A (en) * | 2014-01-28 | 2014-04-23 | 陈昊 | Realizing method for comparing radiofrequency identification and license plate identification |
| CN103778787A (en) * | 2014-02-19 | 2014-05-07 | 陈昊 | Automobile artificial and informal license plate identification logical judgment method |
| CN103927881A (en) * | 2014-05-05 | 2014-07-16 | 陈昊 | Radio frequency and video double-base recognition and comparison integrated machine |
| CN104077570A (en) * | 2014-06-25 | 2014-10-01 | 北京计算机技术及应用研究所 | Method and system for fusing radio frequency identification and vehicle license plate recognition |
| CN104766479A (en) * | 2015-01-27 | 2015-07-08 | 公安部交通管理科学研究所 | Automobile identity recognition method and device based on ultrahigh frequency radio frequency and video image dual-recognition matching |
| CN205827664U (en) * | 2016-07-18 | 2016-12-21 | 武汉万集信息技术有限公司 | A kind of vehicle restricted driving supervisory systems based on RFID, laser and video |
| CN106875697A (en) * | 2017-04-20 | 2017-06-20 | 江苏本能科技有限公司 | Radio frequency identification and video identification comparison method and system |
-
2017
- 2017-08-25 CN CN201710743924.4A patent/CN107798334B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130201316A1 (en) * | 2012-01-09 | 2013-08-08 | May Patents Ltd. | System and method for server based control |
| CN103745600A (en) * | 2014-01-28 | 2014-04-23 | 陈昊 | Realizing method for comparing radiofrequency identification and license plate identification |
| CN103778787A (en) * | 2014-02-19 | 2014-05-07 | 陈昊 | Automobile artificial and informal license plate identification logical judgment method |
| CN103927881A (en) * | 2014-05-05 | 2014-07-16 | 陈昊 | Radio frequency and video double-base recognition and comparison integrated machine |
| CN104077570A (en) * | 2014-06-25 | 2014-10-01 | 北京计算机技术及应用研究所 | Method and system for fusing radio frequency identification and vehicle license plate recognition |
| CN104766479A (en) * | 2015-01-27 | 2015-07-08 | 公安部交通管理科学研究所 | Automobile identity recognition method and device based on ultrahigh frequency radio frequency and video image dual-recognition matching |
| CN205827664U (en) * | 2016-07-18 | 2016-12-21 | 武汉万集信息技术有限公司 | A kind of vehicle restricted driving supervisory systems based on RFID, laser and video |
| CN106875697A (en) * | 2017-04-20 | 2017-06-20 | 江苏本能科技有限公司 | Radio frequency identification and video identification comparison method and system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596119A (en) * | 2018-04-28 | 2018-09-28 | 江苏本能科技有限公司 | Radio frequency identification and video identification matching process and system, equipment, storage medium |
| CN109580522A (en) * | 2018-11-20 | 2019-04-05 | 北京计算机技术及应用研究所 | A kind of automobile exhaust pollutant monitoring method merging vehicle electron identifying and video |
| CN111325054A (en) * | 2018-12-14 | 2020-06-23 | 航天信息股份有限公司 | Method and device for determining cloned vehicle and computing equipment |
| CN111325054B (en) * | 2018-12-14 | 2023-05-23 | 航天信息股份有限公司 | Method and device for determining cloned vehicles and computing equipment |
| CN109358989A (en) * | 2018-12-25 | 2019-02-19 | 四川效率源信息安全技术股份有限公司 | A method of the multiple mysql-innodb database of carving based on graph theory |
| CN109358989B (en) * | 2018-12-25 | 2021-08-03 | 四川效率源信息安全技术股份有限公司 | Graph theory-based method for replicating mysql-inodb database by carving |
| CN112435479A (en) * | 2020-11-09 | 2021-03-02 | 浙江大华技术股份有限公司 | Target object violation detection method and device, computer equipment and system |
| CN112562347A (en) * | 2020-11-30 | 2021-03-26 | 高新兴智联科技有限公司 | Matching algorithm for electronic identification radio frequency data and video data of motor vehicle |
| CN115359397A (en) * | 2022-08-17 | 2022-11-18 | 北京博宏科元信息科技有限公司 | Radio frequency video fusion data management method and device and computer equipment |
| CN115359665A (en) * | 2022-08-17 | 2022-11-18 | 北京博宏科元信息科技有限公司 | Multichannel violation vehicle recording method and device based on radio frequency video all-in-one machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107798334B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107798334A (en) | A kind of matching process and device of vehicle electron identifying data and video identification data | |
| US20130132166A1 (en) | Smart toll network for improving performance of vehicle identification systems | |
| CN102693299B (en) | System and method for parallel video copy detection | |
| CN109299644A (en) | A kind of vehicle target detection method based on the full convolutional network in region | |
| CN110689043A (en) | Vehicle fine granularity identification method and device based on multiple attention mechanism | |
| CN105528595A (en) | Method for identifying and positioning power transmission line insulators in unmanned aerial vehicle aerial images | |
| CN102831403B (en) | A kind of recognition methods based on fingerprint feature point | |
| CN112163574A (en) | ETC interference signal transmitter identification method and system based on deep residual error network | |
| CN105931253A (en) | Image segmentation method combined with semi-supervised learning | |
| CN102541954A (en) | Method and system for searching trademarks | |
| CN107506368A (en) | The determination method and device of one species case suspected vehicles | |
| CN112613344B (en) | Vehicle track occupation detection method, device, computer equipment and readable storage medium | |
| CN108510396A (en) | It insures method, apparatus, computer equipment and the storage medium of verification | |
| CN104573699A (en) | Trypetid identification method based on medium field intensity magnetic resonance dissection imaging | |
| CN105335689A (en) | Character recognition method and apparatus | |
| CN104268553A (en) | SAR image target recognition method based on kernel fuzzy Foley-Sammon transformation | |
| CN103136546A (en) | Multi-dimension authentication method and authentication device of on-line signature | |
| CN114219507A (en) | Qualification auditing method and device for traditional Chinese medicine supplier, electronic equipment and storage medium | |
| CN108229273A (en) | Multilayer neural network model training, the method and apparatus of roadway characteristic identification | |
| CN116343237A (en) | Bill identification method based on deep learning and knowledge graph | |
| Soleimani et al. | Fast and efficient minutia‐based palmprint matching | |
| Liu et al. | A novel SVM network using HOG feature for prohibition traffic sign recognition | |
| Kumar et al. | FPR using machine learning with multi‐feature method | |
| Tong et al. | Object detection for panoramic images based on MS‐RPN structure in traffic road scenes | |
| CN116977834A (en) | Method for identifying internal and external images distributed under open condition |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 401, building 12, East Airport Business Park, 80 Huanhe North Road, Tianjin Binhai New Area pilot free trade zone (Airport Economic Zone) Patentee after: Gaoxing Zhilian Technology Co.,Ltd. Address before: 300308 Tianjin Binhai New Area Airport Economic Zone Dongqidao No.2 ZTE Industrial Base Patentee before: ZTE INTELLIGENT IOT TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 401, building 12, East Airport Business Park, 80 Huanhe North Road, Tianjin Binhai New Area pilot free trade zone (Airport Economic Zone) Patentee after: Zte Intelligent Iot Technology Co.,Ltd. Address before: Room 401, building 12, East Airport Business Park, 80 Huanhe North Road, Tianjin Binhai New Area pilot free trade zone (Airport Economic Zone) Patentee before: Gaoxing Zhilian Technology Co.,Ltd. |