CN111931808B - RFID data and image data matching method, main control equipment and system - Google Patents
RFID data and image data matching method, main control equipment and system Download PDFInfo
- Publication number
- CN111931808B CN111931808B CN202010600424.7A CN202010600424A CN111931808B CN 111931808 B CN111931808 B CN 111931808B CN 202010600424 A CN202010600424 A CN 202010600424A CN 111931808 B CN111931808 B CN 111931808B
- Authority
- CN
- China
- Prior art keywords
- image data
- vehicle
- image
- rfid
- buffer area
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000000872 buffer Substances 0.000 claims abstract description 132
- 238000013135 deep learning Methods 0.000 claims abstract description 16
- 230000004044 response Effects 0.000 claims description 16
- 230000005055 memory storage Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 5
- 230000007547 defect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000003491 array Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000003139 buffering effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/12—Replacement control
- G06F12/121—Replacement control using replacement algorithms
- G06F12/123—Replacement control using replacement algorithms with age lists, e.g. queue, most recently used [MRU] list or least recently used [LRU] list
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10009—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves
- G06K7/10297—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves arrangements for handling protocols designed for non-contact record carriers such as RFIDs NFCs, e.g. ISO/IEC 14443 and 18092
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Toxicology (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Security & Cryptography (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a matching method of RFID data and image data of a vehicle, a main control device and a matching system of the RFID data and the image data, wherein the method comprises the following steps: receiving an image sent by an image pickup device, detecting the image by a vehicle based on a deep learning module to obtain a vehicle image, and caching the vehicle image in an image data cache area according to the LRU characteristic rule; when the RFID data of the vehicle is acquired, the target vehicle image matched with the RFID data is read back from the image data buffer area. By implementing the embodiment of the invention, the technical defect that the image data and the RFID data are difficult to match because the acquisition time of the image data and the RFID data cannot be absolutely consistent can be overcome, the image data and the RFID data of the same vehicle can be accurately matched, and more complete and reliable data can be provided for motor vehicle supervision after the image data and the RFID data are matched.
Description
Technical Field
The invention relates to the field of intelligent transportation (Intelligent Transportation System, ITS), in particular to a method for matching RFID data and image data of a vehicle, a main control device and a system for matching RFID data and image data.
Background
With the continuous development of intelligent traffic and intelligent cities, video-based deep learning schemes are gradually applied to urban traffic. The electric bicycle as an urban transportation means has wide spread range and frequent use, so that the safety problem gradually attracts attention, and the electric bicycle is effectively regulated to provide requirements and challenges. The street gate (such as a crossroad, a T-shaped intersection and the like) is taken as a scene, and the track picture and the vehicle information of the motor vehicle (mainly comprising two-wheel electric bicycles, four-wheel automobiles and the like) can be effectively acquired through shooting and identification by the camera device based on a video deep learning scheme; on the basis of the RFID video recognition scheme, RFID data in the license plate of the motor vehicle can be read through the RFID antenna device, and the RFID data contains vehicle information (mainly license plate number information).
In order to supervise a motor vehicle driving in violation, image data shot by an imaging device and RFID data read by an RFID antenna device are required to be matched, and if the motor vehicle breaks rules, the image data and the RFID data of the motor vehicle are required to be acquired to form evidence chain data with higher reliability. However, the image data captured by the image capturing device and the RFID data read by the RFID antenna device cannot be synchronized absolutely in time, and it is difficult to accurately match the image data with the RFID data.
Disclosure of Invention
The embodiment of the invention provides a matching method of RFID data and image data of a vehicle, which can overcome the technical defect that the image data and the RFID data are difficult to match because the acquisition time of the image data and the RFID data cannot be absolutely consistent.
In a first aspect, there is provided a method for matching RFID data with image data of a vehicle, including: receiving an image sent by an image pickup device, detecting the image by a vehicle based on a deep learning module to obtain a vehicle image, and caching the vehicle image in an image data cache area according to an LRU characteristic rule; and when the RFID data of the vehicle is acquired, backtracking and reading the target vehicle image matched with the RFID data from the image data buffer area.
In this embodiment, since the acquiring times of the image data and the RFID data cannot be absolutely identical, and the acquiring times of the image data and the RFID data may be different and cannot be directly matched, the image data with a long processing time is cached in this embodiment, that is, the image sent by the image capturing device is processed by the deep learning module and then stored in the image data cache area. When the RFID data is read through the RFID antenna device, the vehicle image matched with the RFID data is acquired from the image data buffer area. By the embodiment, the image data and the RFID data of the same vehicle can be accurately matched, and after the image data and the RFID data are matched, more complete and reliable data can be provided for motor vehicle supervision
In an alternative embodiment, the image data buffer area includes an N-level image data buffer area, N is a positive integer greater than 1, and the vehicle image is buffered in the image data buffer area according to the LRU characteristic rule, which specifically includes: caching the vehicle image in a first-level image data cache area; if the storage space of the first-level image data buffer area is insufficient, transferring the image data in the first-level image data buffer area to the N-level image data buffer area to the next level in sequence according to the sequence of the storage time, so that the first-level image data buffer area has enough storage space to store the vehicle image.
By implementing the embodiment of the invention, the main control equipment establishes the multi-level image data buffer area, and the latest buffered picture is preferentially acquired during picture backtracking, so that the LRU characteristic is more satisfied, and the picture data reading speed is faster and more accurate.
In an alternative embodiment, when N is 2, the first-level image data buffer area is a memory storage space, and is used for storing the vehicle image in the form of picture data; the secondary image data buffer area is a disk storage space and is used for storing vehicle images in a file form; the read-write response speed is as follows: the first-level image data buffer area is greater than the second-level image data buffer area.
Specifically, since the speed of reading data in the memory storage space is better than the speed of reading data from the disk storage space, and the speed of reading picture data is better than the speed of reading files, the read-write response speed of the first-level image data buffer area is higher than the read-write response speed of the second-level image data buffer area. In general, the hit rate of the RFID data and the recently stored image data is the largest, so that the latest image data is stored in the first-level image data buffer area, which is beneficial to accelerating the matching speed of the backtracking reading.
By implementing the embodiment of the invention, the main control equipment stores the vehicle images in different storage positions in different data modes, so that the corresponding reading and writing speeds of each level of image data buffer areas are ensured, a large enough storage space is ensured, and the vehicle images can be quickly and accurately matched with the target vehicle images during later backtracking.
In an alternative embodiment, when the N is 4, the first-level image data buffer area is a memory storage space, and is used for storing the vehicle image in the form of picture data; the secondary image data buffer area is a disk storage space and is used for storing vehicle images in a file form; the three-level image data buffer area is a memory storage space and is used for storing compressed vehicle images in the form of picture data; the fourth-level image data buffer area is a disk storage space and is used for storing compressed vehicle images in a file form; the read-write response speed is as follows: the first level image data buffer area is larger than the second level image data buffer area, the third level image data buffer area is larger than the fourth level image data buffer area.
By implementing the embodiment of the invention, the main control equipment adopts different image data storage modes in different cache areas, so that the read-write response speeds of the image data cache areas at all levels are different. On one hand, when the main control equipment backtracks and reads the vehicle image, the main control equipment preferentially backtracks and reads the vehicle image from the image data buffer area with the highest read-write response speed, so that the right target vehicle image can be quickly and accurately matched, and on the other hand, the capacity of the buffered image data is ensured to the greatest extent while the backtrack and read speed is ensured.
In an alternative embodiment, the method for retrospectively reading the target vehicle image matched with the RFID data from the image data buffer area specifically includes: and according to the backtracking reading sequence from the first-level image data cache region to the N-level image data cache region, sequentially judging whether the image data in each level of image data cache region are matched with RFID data, if the current image data are matched, stopping backtracking reading, and taking the current image data as a target vehicle image.
Specifically, the main control device backtracks and reads the vehicle images from the image data buffer area according to the sequence from high to low of the read-write response speed, and matches the vehicle images, and when the main control device matches the correct vehicle images, the main control device stops backtracking and reading.
Under normal conditions, the hit rate of the RFID data and the recently stored image data is the largest, namely the probability of successful matching in the first-level image cache area is the largest, so that the main control equipment backtracks and reads the vehicle images from the image data cache area according to the sequence from high to low of the read-write response speed, thereby being beneficial to improving the matching speed and the matching accuracy.
In an alternative embodiment, the RFID data includes license plate information, and whether the image data in each level of image data buffer area is matched with the RFID data is determined in sequence specifically as follows: sequentially reading license plate information obtained by recognizing the image data in each level of image data cache region through a deep learning module; and if the license plate information in the current image data is the same as or similar to the license plate information in the RFID data and exceeds a preset threshold value, determining the current image data as a target vehicle image.
By implementing the embodiment of the invention, the main control equipment can judge whether the matching is correct or not according to the image data and license plate information in the RFID data, so that the matching of the RFID data and the image data is realized.
In an alternative embodiment, the RFID data includes RFID time, where the RFID time is the time when the main control device obtains the RFID data, and sequentially determines whether the image data in each level of image data buffer area is matched with the RFID data, specifically:
according to the RFID time, judging whether the shooting time of the image data in each level of image data buffer area is matched with the RFID time or not in sequence;
if the vehicle is matched with the vehicle, and only one vehicle exists in the current image data, determining that the current image data is a target vehicle image.
By implementing the embodiment of the invention, the main control equipment can directly lock the image data to be matched with the RFID data according to whether the image shooting time and the RFID time are matched or not and when the current image data has one vehicle, the matching time can be further shortened and the matching efficiency can be improved by the mode.
In an alternative embodiment, after retrospectively reading the target vehicle image matched with the RFID data from the image data buffer, the method further includes: and forming evidence chain data of the vehicle according to the target vehicle image and the RFID data.
In the embodiment, after the image data is matched with the RFID data, the data is bound and formed into evidence chain data, so that more complete, reliable and high-reliability data can be provided for motor vehicle supervision.
In a second aspect, a master control device is provided, comprising a processor and a memory, the processor and the memory being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method as described in the first aspect.
In a third aspect, there is provided a system for matching RFID data with image data of a vehicle, the system comprising a master device as described in the second aspect, an image pickup device connected to the master device for capturing an image, an RFID antenna device connected to the master device for reading the RFID data of the vehicle
Drawings
In order to more clearly illustrate the embodiments of the present invention, the drawings that are required for the description of the embodiments will be briefly described below, it being apparent that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the accompanying drawings:
fig. 1 is a schematic view of a scenario of a matching method of RFID data and image data of a vehicle according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a matching method between RFID data and image data of a vehicle according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an N-level image data buffer area according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a method for matching RFID data with image data using multi-level image data caching according to an embodiment of the present invention;
FIG. 5 is a block diagram of a master control device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a matching system of RFID data and image data of a vehicle according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic view of a scenario of a matching method of RFID data and image data according to an embodiment of the present invention. As shown in fig. 1, the traffic situation of the crossroad traffic light is illustrated. The road is provided with a main control device, a camera device and an RFID antenna device, wherein the main control device can communicate and transmit data with the camera device and the RFID antenna device. The device can realize matching of the image data and the RFID data, and provides more complete and reliable data for motor vehicle supervision. Here, the motor vehicle may be an automobile, a two-wheeled electric bicycle, or the like. An RFID tag is required to be mounted on a motor vehicle, and the tag mainly includes license plate information of the motor vehicle, for example, an electric bicycle, and the license plate of the motor vehicle includes the RFID tag.
For ease of understanding and description, the following embodiments are described with respect to electric bicycles as examples, but it should be understood that the present invention is not particularly limited to the type of motor vehicle.
The camera device is used for shooting the electric bicycle and sending the image to the main control equipment when the electric bicycle passes through.
The RFID antenna device is used for reading RFID data of the electric bicycle through an RFID tag on a license plate of the electric bicycle when the electric bicycle runs, and the RFID data is vehicle information (such as license plate number and electric bicycle model number) of the electric bicycle. The RFID antenna device sends RFID data of the electric bicycle to the main control device.
In a preferred embodiment, the RFID antenna device may employ the 900M radio frequency band.
The main control equipment receives the image sent by the camera device, and carries out vehicle detection on the image based on the deep learning module to obtain a vehicle image, wherein the vehicle image can be an image marked with vehicle position information and vehicle information, and the vehicle image is stored in an image data buffer area of the main control equipment according to the LRU characteristic rule after the vehicle image is obtained. When the main control equipment receives RFID data of the electric bicycle, a target vehicle image matched with the RFID data is read back from the image data buffer area.
It should be noted that, the image capturing apparatus and the main control device in the embodiment of the present invention may be two separate devices, or may be a device integrating an image capturing function and a computing function.
Referring to fig. 2, fig. 2 is a schematic diagram of a method for matching RFID data with image data of a vehicle according to an embodiment of the present invention. As shown in fig. 2, the method includes:
s201, the main control equipment receives the image sent by the image pickup device, and obtains a vehicle image after detecting the image based on the deep learning module.
In some embodiments, the image capturing device may continuously capture images and send the images to the main control module, and the main control module performs vehicle detection on the images sent by the image capturing device based on the deep learning module, so as to filter images not including the electric bicycle, obtain vehicle images including the electric bicycle, and in this process, the main control device may complete marking of the vehicle images, for example, marking the position of the electric bicycle, and/or related vehicle information (for example, license plate number).
In other embodiments, the image capturing device is triggered to start capturing image data only when the electric bicycle enters a capturing area or a preset specific area, the captured image includes the electric bicycle, and the vehicle image is obtained by detecting the vehicle based on the deep learning module after the main control device receives the image sent by the image capturing device, where the vehicle image is an image with position labeling information and/or related vehicle information.
S202, the main control equipment caches the vehicle image in the image data cache area according to the LRU characteristic rule.
In general, the hit rate of the RFID data and the recently stored image data is the largest, and the later-stage main control device will preferentially acquire the recently cached image when backtracking to read the image, so when caching the image, the main control device will cache the vehicle image according to the LRU (Least Recently Used) characteristic rule, so that the main control device can read the vehicle image faster later.
In an alternative embodiment, the image data buffer area includes an N-level image data buffer area, N is a positive integer greater than 1, and the vehicle image is buffered in the image data buffer area according to the LRU characteristic rule, which specifically includes: caching the vehicle image in a first-level image data cache area; if the storage space of the first-level image data buffer area is insufficient, transferring the image data in the first-level image data buffer area to the N-level image data buffer area to the next level in sequence according to the sequence of the storage time, so that the first-level image data buffer area has enough storage space to store the vehicle image. The next level of image data buffer area is higher than the present level of image data buffer area by one level, for example, the second level of image data buffer area is the next level of the first level of image data buffer area, the third level of image data buffer area is the next level of the second level of image data buffer area, and so on.
Referring to fig. 3, fig. 3 is a schematic diagram of an N-level image data buffer according to an embodiment of the present invention. As shown in fig. 3, the main control device divides the data buffer into N-level image data buffers. The main control device stores the vehicle picture data in the primary image data buffer according to the LRU characteristic, so that the vehicle image with the latest time is buffered in the primary image data buffer. When the space of the first-level image data buffer area is insufficient, the main control equipment buffers the vehicle image which is the earliest in time and is buffered at the bottommost end of the first-level image data buffer area into the next-level or second-level image data buffer area according to the LUR characteristic, so that the first-level image data buffer area has enough storage space to store the vehicle image. Similarly, the space of the secondary image data buffer area is insufficient, and the main control equipment buffers the vehicle image which is earliest in time and is buffered at the bottommost end of the secondary image data buffer area into the next-level, namely third-level image data buffer area according to the LUR characteristic, so that the secondary image data buffer area has enough storage space to store the vehicle image. The data at the bottom of the image data buffer means the data stored earliest in the image data buffer.
By implementing the embodiment of the invention, the main control equipment establishes the multi-level image data buffer area, and the latest buffered picture is preferentially acquired during picture backtracking, so that the LRU characteristic is more satisfied, and the picture data reading speed is faster and more accurate.
In an alternative embodiment, when N is 2, the first-level image data buffer area is a memory storage space, and is used for storing the vehicle image in the form of picture data; the secondary image data buffer area is a disk storage space and is used for storing vehicle images in a file form; the read-write response speed is as follows: the first-level image data buffer area is larger than the second-level image data buffer area, namely the present-level data buffer area is larger than the next-level image data buffer area.
Specifically, since the speed of reading data in the memory storage space is better than the speed of reading data from the disk storage space, and the speed of reading picture data is better than the speed of reading files, the read-write response speed of the first-level image data buffer area is higher than the read-write response speed of the second-level image data buffer area. In general, the hit rate of the RFID data and the recently stored image data is the largest, so that the latest image data is stored in the first-level image data buffer area, which is beneficial to accelerating the matching speed of the backtracking reading.
In an alternative embodiment, when the N is 3, the first-level image data buffer area is a memory storage space, and is used for storing the vehicle image in the form of picture data; the secondary image data buffer area is a disk storage space and is used for storing vehicle images in a file form; the three-level image data buffer area is a memory storage space and is used for storing compressed vehicle images in the form of picture data; the read-write response speed is as follows: the first level image data buffer area is larger than the second level image data buffer area and larger than the third level image data buffer area.
In an alternative embodiment, when the N is 4, the first-level image data buffer area is a memory storage space, and is used for storing the vehicle image in the form of picture data; the secondary image data buffer area is a disk storage space and is used for storing vehicle images in a file form; the three-level image data buffer area is a memory storage space and is used for storing compressed vehicle images in the form of picture data; the fourth-level image data buffer area is a disk storage space and is used for storing compressed vehicle images in a file form; the read-write response speed is as follows: the first level image data buffer area is larger than the second level image data buffer area, the third level image data buffer area is larger than the fourth level image data buffer area.
By implementing the embodiment of the invention, the main control equipment stores the vehicle images in different storage positions in different data modes, so that the corresponding reading and writing speeds of each level of image data buffer areas are ensured, a large enough storage space is ensured, and the vehicle images can be quickly and accurately matched with the target vehicle images during later backtracking.
In addition, it should be noted that the main control device may divide the N-level image data buffer area into two levels according to various division rules, for example, according to compression and non-compression standards. For another example, the memory storage space and the disk storage space may be divided according to the storage type of the buffer area. It should be understood that the dividing rule of the image data buffer area is not particularly limited in the present invention, and other non-enumerated dividing rules should belong to the protection scope of the present invention.
And S203, when the RFID data of the vehicle is acquired, the main control equipment backtracks and reads the target vehicle image matched with the RFID data from the image data buffer area.
Specifically, when the electric bicycle passes through, the RFID antenna device reads RFID data of the electric bicycle through an RFID tag on a license plate of the electric bicycle, and the RFID data is vehicle information (such as license plate number and electric bicycle model number) of the electric bicycle. The RFID antenna device sends RFID data of the electric bicycle to the main control device.
In an alternative embodiment, according to the backtracking reading sequence from the first-level image data buffer area to the N-level image data buffer area, whether the image data in each level of image data buffer area is matched with the RFID data is sequentially judged, if the current image data is matched, the backtracking reading is stopped, and the current image data is used as the target vehicle image.
Under normal conditions, the hit rate of the RFID data and the recently stored image data is the largest, namely the probability of successful matching in the first-level image cache area is the largest, so that the main control equipment backtracks and reads the vehicle images from the image data cache area according to the sequence from high to low of the read-write response speed, thereby being beneficial to improving the matching speed and the matching accuracy.
Referring to fig. 4, fig. 4 is a schematic diagram of a method for matching RFID data with image data using multi-level image data buffering according to an embodiment of the present invention. As shown in fig. 4, the main control device backtracks from the image data buffer to read the target vehicle image matched with the RFID data, specifically including:
s401, the main control equipment sequentially judges whether the image data in each level of image data buffer area is matched with RFID data according to the backtracking reading sequence from the level one image data buffer area to the level N image data buffer area.
In an alternative embodiment, the RFID data includes license plate information, and whether the image data in each level of image data buffer area is matched with the RFID data is determined in sequence specifically as follows: sequentially reading license plate information obtained by recognizing the image data in each level of image data cache region through a deep learning module; and if the license plate information in the current image data is the same as or similar to the license plate information in the RFID data and exceeds a preset threshold value, determining the current image data as a target vehicle image.
For example, the license plate information of the RFID data is cantonese B0000, the master control device identifies that the license plate information of one image data in the image data buffer is cantonese B0008 based on deep learning, at this time, the similarity between the license plate information in the image data and the license plate information in the RFID data is 80%, and if the preset threshold is 70%, the current image data is determined to be the target vehicle image.
By implementing the embodiment of the invention, the main control equipment can judge whether the matching is correct or not according to the image data and license plate information in the RFID data, so that the matching of the RFID data and the image data is realized.
In an alternative embodiment, the RFID data includes RFID time, where the RFID time is the time when the main control device obtains the RFID data, and sequentially determines whether the image data in each level of image data buffer area is matched with the RFID data, specifically: according to the RFID time, judging whether the shooting time of the image data in each level of image data buffer area is matched with the RFID time or not in sequence; if the vehicle is matched with the vehicle, and only one vehicle exists in the current image data, determining that the current image data is a target vehicle image.
Specifically, the RFID time indicates a time when the RFID antenna device obtains the vehicle information through the RFID tag, and if the capturing time of the current image data read back is within the foregoing time range within a period of time centered on the RFID time, it is determined that the current image data matches the RFID data. At this time, if there is only one vehicle in the current image data, the matching between the current image data and the RFID data can be directly locked, and by the mode, the matching time can be further shortened, and the matching efficiency is improved.
In the case of matching, there are two cases of current image data:
first, only one vehicle is in the current image data; the master device determines the vehicle image as a target vehicle image.
Secondly, a plurality of vehicles exist in the current image data, at the moment, the main control equipment obtains vehicle information of the plurality of vehicles in the image data based on deep learning for the current vehicle image, matches the plurality of vehicle information with RFID data, marks successfully matched vehicles in the image data, and then determines the current vehicle image as a target vehicle image.
If the main control device determines that the image data in the image data buffer area is matched with the RFID data, step S402 is executed; if not, step S403 is performed.
And S402, the main control equipment stops backtracking reading and takes the current image data as a target vehicle image.
In an alternative embodiment, after retrospectively reading the target vehicle image matched with the RFID data from the image data buffer area, the master control device further includes: and forming evidence chain data of the vehicle according to the target vehicle image and the RFID data.
In the embodiment, after the image data is matched with the RFID data, the data is bound and formed into evidence chain data, for example, the data of the vehicle illegal evidence chain is formed, and the data with more complete reliability and high reliability can be provided for the supervision of the motor vehicle through the embodiment.
S403, the master control device determines whether the current time is within a preset backtracking time.
Specifically, the master control equipment can set up the backtracking time in advance, avoids master control equipment to match target vehicle image and always circulate backtracking, can lead to master control backtracking for a long time like this, causes equipment damage.
If the trace-back time is within the preset trace-back time, step S404 is executed;
if the preset backtracking time is exceeded, step S405 is executed.
In step S404, the master device continues backtracking.
In step S405, the master device stops backtracking.
In the embodiment of the invention, the main control equipment receives the image sent by the camera device, acquires a vehicle image after detecting the image by the vehicle based on the deep learning module, and caches the vehicle image in the image data cache area according to the LRU characteristic rule; when the RFID data of the vehicle is acquired, the main control equipment backtracks and reads the target vehicle image matched with the RFID data from the image data buffer area. By adopting the embodiment, the technical defect that the image data and the RFID data are difficult to match because the acquisition time of the image data and the RFID data cannot be absolutely consistent can be overcome.
Referring to fig. 5, fig. 5 is a block diagram of a master control device according to an embodiment of the present invention, where the master control device includes: a processor 501 and a memory 502 storing a computer program, which processor, when executing the computer program stored in the memory, implements the methods and steps of the embodiments of fig. 2 or fig. 4.
In a possible embodiment, the master device may further include: one or more input interfaces 503 and one or more output interfaces 504.
The processor 501, the input interface 503, the output interface 504, and the memory 502 are connected via a bus 505. The memory 502 is used for storing instructions, the processor 501 is used for executing the instructions stored by the memory 502, the input interface 503 is used for receiving data, such as receiving RFID data and image data, and the output interface 704 is used for outputting data, such as data matching results.
Wherein the processor 501 is configured to invoke the program instruction execution: the method and steps of the embodiment of fig. 2 or fig. 4. The method steps of RFID data and image data of the vehicle are related in the embodiment. It should be appreciated that in the disclosed embodiments, the processor 501 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 502 may include read-only memory and random-access memory, as well as read-write programmable non-volatile memory, such as a computer hard disk (e.g., solid state or mechanical hard disk), a U disk, etc., the memory 502 providing instructions and data to the processor 501. A portion of memory 502 may also include non-volatile random access memory. For example, the memory 502 may also store information of the interface type.
In some implementations, the above components of the master control device described in the embodiments of the present disclosure may be used in the methods and steps of the embodiments of fig. 2 or fig. 4, and for brevity, they are not described herein again.
It should be appreciated that in the disclosed embodiments, the processor 501 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 504 may include read-only memory and random-access memory as well as read-write programmable non-volatile memory such as a computer hard disk (e.g., solid state or mechanical hard disk), a U disk, etc., the memory 504 providing instructions and data to the processor 501. A portion of memory 504 may also include non-volatile random access memory. For example, memory 504 may also store information of the interface type.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a matching system of RFID data and image data of a vehicle according to an embodiment of the present invention. As shown in fig. 6, the system includes: a master device 601 as shown in fig. 5; an image pickup device 602 connected to the main control device and configured to pick up an image; an RFID antenna device 603 connected to the master device for reading RFID data of the vehicle.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any such modifications, equivalents, and improvements that fall within the spirit and principles of the present invention are intended to be covered by the following claims.
Claims (8)
1. A method of matching RFID data with image data of a vehicle, comprising:
receiving an image sent by an image pickup device, detecting the image by a vehicle based on a deep learning module to obtain a vehicle image, and caching the vehicle image in an image data cache area according to an LRU characteristic rule;
when RFID data of the vehicle is acquired, backtracking and reading a target vehicle image matched with the RFID data from the image data buffer area;
the image data buffer area comprises an N-level image data buffer area, N is a positive integer greater than 1, and the vehicle image is buffered in the image data buffer area according to the LRU characteristic rule, and the method specifically comprises the following steps: caching the vehicle image in a first-level image data cache area; if the storage space of the first-level image data buffer area is insufficient, sequentially transferring the image data from the first-level image data buffer area to the N-level image data buffer area to the next level according to the sequence of the storage time, so that the first-level image data buffer area has enough storage space to store the vehicle image;
backtracking and reading the target vehicle image matched with the RFID data from the image data cache area, wherein the method specifically comprises the following steps of: and according to the backtracking reading sequence from the first-level image data cache region to the N-level image data cache region, sequentially judging whether the image data in each level of image data cache region is matched with the RFID data in a preset backtracking time, if the current image data is matched, stopping backtracking reading, and taking the current image data as the target vehicle image.
2. The method for matching RFID data with image data of a vehicle according to claim 1, wherein N is 2,
the first-level image data cache area is a memory storage space and is used for storing the vehicle image;
the second-level image data buffer area is a disk storage space and is used for storing the vehicle image;
the read-write response speed is as follows: the first-level image data buffer area is greater than the second-level image data buffer area.
3. The method of matching RFID data with image data of a vehicle according to claim 1, wherein N is 4;
the first-level image data cache area is a memory storage space and is used for storing the vehicle image;
the second-level image data buffer area is a disk storage space and is used for storing the vehicle image;
the three-level image data buffer area is a memory storage space and is used for storing the compressed vehicle image;
the fourth-level image data buffer area is a disk storage space and is used for storing the compressed vehicle image;
the read-write response speed is as follows: the first level image data buffer area is larger than the second level image data buffer area, the third level image data buffer area is larger than the fourth level image data buffer area.
4. The method for matching the RFID data with the image data of the vehicle according to claim 1, wherein the RFID data includes license plate information, and sequentially judges whether the image data in each level of image data buffer area is matched with the RFID data, specifically:
sequentially reading license plate information obtained by recognizing the image data in each level of image data cache region through the deep learning module;
and if the license plate information in the current image data is the same as or similar to the license plate information in the RFID data and exceeds a preset threshold value, determining the current image data as the target vehicle image.
5. The method for matching the RFID data with the image data of the vehicle according to claim 1, wherein the RFID data includes an RFID time, the RFID time is an acquisition time of the RFID data, and whether the image data in each level of the image data buffer area is matched with the RFID data is sequentially determined, specifically:
according to the RFID time, judging whether the shooting time of the image data in each level of image data buffer area is matched with the RFID time or not in sequence;
and if the vehicle is matched with the target vehicle, and only one vehicle exists in the current image data, determining that the current image data is the target vehicle image.
6. The method of matching RFID data with image data of a vehicle according to claim 1, characterized in that after retrospectively reading a target vehicle image matched with the RFID data from the image data buffer, the method further comprises:
and forming evidence chain data of the vehicle according to the target vehicle image and the RFID data.
7. A master control device comprising a processor and a memory storing a computer program, characterized in that the processor, when executing the computer program stored in the memory, implements the steps of the method for matching RFID data with image data of a vehicle according to any one of claims 1-6.
8. A system for matching RFID data with image data of a vehicle, the system comprising:
the master control apparatus of claim 7;
the image pick-up device is connected with the main control equipment and is used for shooting images;
and the RFID antenna device is connected with the main control device and used for reading RFID data of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010600424.7A CN111931808B (en) | 2020-06-28 | 2020-06-28 | RFID data and image data matching method, main control equipment and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010600424.7A CN111931808B (en) | 2020-06-28 | 2020-06-28 | RFID data and image data matching method, main control equipment and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111931808A CN111931808A (en) | 2020-11-13 |
| CN111931808B true CN111931808B (en) | 2024-04-16 |
Family
ID=73316736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010600424.7A Active CN111931808B (en) | 2020-06-28 | 2020-06-28 | RFID data and image data matching method, main control equipment and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931808B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1425985A (en) * | 2001-12-12 | 2003-06-25 | 北京华文世纪科技有限公司 | Image datamation storaging method |
| CN101001311A (en) * | 2006-01-09 | 2007-07-18 | 上海乐金广电电子有限公司 | System providing and editing action effect using video signal and its method |
| CN102855762A (en) * | 2012-09-14 | 2013-01-02 | 广州市远望谷信息技术有限公司 | Method and device for acquiring and verifying data of vehicles entering or exiting from parking lot |
| 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 |
| CN105160884A (en) * | 2015-07-30 | 2015-12-16 | 北京工业大学 | Vehicle identification method and device fusing video monitoring and RFID |
| CN108268018A (en) * | 2018-02-06 | 2018-07-10 | 武汉轻工大学 | A kind of machine-building Workshop Production progress information acquisition system based on RFID |
| CN108875478A (en) * | 2017-08-14 | 2018-11-23 | 北京旷视科技有限公司 | The testimony of a witness unifies checking method, device and system and storage medium |
| CN108959345A (en) * | 2018-04-11 | 2018-12-07 | 北京航星机器制造有限公司 | A kind of method and apparatus that safety check image recording is quickly recalled |
| CN111145369A (en) * | 2019-12-31 | 2020-05-12 | 深圳市金溢科技股份有限公司 | Switch scheduling method, vehicle charging method, industrial personal computer and vehicle charging system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7066388B2 (en) * | 2002-12-18 | 2006-06-27 | Symbol Technologies, Inc. | System and method for verifying RFID reads |
| US10091395B2 (en) * | 2015-12-08 | 2018-10-02 | Ricoh Company, Ltd. | Image forming apparatus, method, and computer-readable recording medium for login and logout management based on multiple user authentication factors |
-
2020
- 2020-06-28 CN CN202010600424.7A patent/CN111931808B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1425985A (en) * | 2001-12-12 | 2003-06-25 | 北京华文世纪科技有限公司 | Image datamation storaging method |
| CN101001311A (en) * | 2006-01-09 | 2007-07-18 | 上海乐金广电电子有限公司 | System providing and editing action effect using video signal and its method |
| CN102855762A (en) * | 2012-09-14 | 2013-01-02 | 广州市远望谷信息技术有限公司 | Method and device for acquiring and verifying data of vehicles entering or exiting from parking lot |
| 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 |
| CN105160884A (en) * | 2015-07-30 | 2015-12-16 | 北京工业大学 | Vehicle identification method and device fusing video monitoring and RFID |
| CN108875478A (en) * | 2017-08-14 | 2018-11-23 | 北京旷视科技有限公司 | The testimony of a witness unifies checking method, device and system and storage medium |
| CN108268018A (en) * | 2018-02-06 | 2018-07-10 | 武汉轻工大学 | A kind of machine-building Workshop Production progress information acquisition system based on RFID |
| CN108959345A (en) * | 2018-04-11 | 2018-12-07 | 北京航星机器制造有限公司 | A kind of method and apparatus that safety check image recording is quickly recalled |
| CN111145369A (en) * | 2019-12-31 | 2020-05-12 | 深圳市金溢科技股份有限公司 | Switch scheduling method, vehicle charging method, industrial personal computer and vehicle charging system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111931808A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11120282B2 (en) | Traffic violation vehicle identification system, server and non-transitory recording medium in which vehicle control program is recorded | |
| US11216676B2 (en) | Information processing system and information processing method | |
| US9842283B2 (en) | Target object detection system and a method for target object detection | |
| CN105355039A (en) | Road condition information processing method and equipment | |
| CN112131935B (en) | Method and device for identifying person carried in motor vehicle compartment and computer equipment | |
| CN110580808B (en) | Information processing method and device, electronic equipment and intelligent traffic system | |
| JP2009175848A (en) | Drive recorder device, drive recording method, program, and recording medium | |
| KR102306789B1 (en) | License Plate Recognition Method and Apparatus for roads | |
| CN111931808B (en) | RFID data and image data matching method, main control equipment and system | |
| CN103106400B (en) | A kind of method for detecting human face and device | |
| JP6244129B2 (en) | OBE | |
| CN116824549B (en) | Target detection method and device based on multi-detection network fusion and vehicle | |
| CN112435479B (en) | Target object violation detection method and device, computer equipment and system | |
| CN111563425B (en) | Traffic incident identification method and electronic equipment | |
| CN114264310A (en) | Positioning and navigation method, device, electronic equipment and computer storage medium | |
| CN111832352A (en) | Non-motor vehicle monitoring method, device and equipment and storage medium | |
| KR101039246B1 (en) | Apparatus and Method for recording event using variable threshold | |
| JP2008065362A (en) | Operation status storing apparatus and threshold value setting method | |
| JP2015075838A (en) | On-vehicle unit | |
| JPH09288795A (en) | Car number reader | |
| KR20150031942A (en) | System for collecting vehicle information and method thereof | |
| KR101350561B1 (en) | Apparatus for storing driving video data in-vehicle system | |
| WO2021176820A1 (en) | Processing device | |
| TWI640960B (en) | Road image processing method and apparatus | |
| JP2024080203A (en) | Forward/reverse travel determination device, forward/reverse travel determination method, and forward/reverse travel determination program |
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 |