Vehicle number reading method, vehicle number reading device, and vehicle number reading program
The vehicle number reading method and device improve accuracy by calculating scores for information in multiple frames and selecting the most reliable data, addressing the reliability issues of existing technologies.
Patent Information
- Application Number
- JP2023074107
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-04-28
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing vehicle number reading technologies using majority voting for frame content identification lack reliability and accuracy in outputting the correct vehicle number.
A method and device that calculate scores for vehicle number information in multiple frames, selecting the most reliable information to output the vehicle number, utilizing a vehicle number reading device with acquisition, reading, calculation, and output units to enhance accuracy.
Enhances the reliability and accuracy of vehicle number reading by selecting the most reliable information from multiple frames, ensuring high-quality output results.
Smart Images

Figure 2024158702000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a vehicle number reading method, a vehicle number reading device, and a vehicle number reading program. [Background technology]
[0002] In recent years, technology has been developed to capture images of a moving vehicle and read the vehicle license plate number of the vehicle. For example, Patent Document 1 discloses a technology that reads the vehicle license plate number from each of a plurality of frames captured continuously in the time axis direction and identifies information, i.e., characters, related to the vehicle license plate number by majority voting. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Patent Publication No. 2021-121892 Summary of the Invention [Problem to be solved by the invention]
[0004] In the above-mentioned Patent Document 1, when there is a difference in the read contents of each frame, the read contents are identified and output by majority voting. However, it cannot be said that the contents identified by majority voting are highly likely to match the contents of the actual vehicle number, and there is room for improvement in the reliability of the output of the read contents.
[0005] In consideration of the above-mentioned problems, an object of the present disclosure is to provide a vehicle number reading method, a vehicle number reading device, and a vehicle number reading program capable of reading vehicle numbers and outputting reading results with high reliability. [Means for solving the problem]
[0006] The vehicle number reading method according to the present disclosure includes: The computer Get the footage, reading first information relating to a vehicle license plate number from a first frame of the video; Calculating a score for each of a plurality of items included in the first information; reading second information relating to the license plate number of the vehicle from a second frame of the video; Calculating a score for each of a plurality of items included in the second information; selecting either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information; The third information composed of the selected information is output as the number of the vehicle.
[0007] The vehicle number reading device according to the present disclosure is An acquisition unit that acquires a video image; a reading unit that reads first information related to a vehicle license plate number from a first frame of the image and reads second information related to the vehicle license plate number from a second frame of the image; A calculation unit that calculates a score for each of a plurality of items included in the first information and calculates a score for each of a plurality of items included in the second information; an output unit that selects either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information, and outputs third information composed of the selected information as the number of the vehicle; Equipped with.
[0008] The vehicle number reading program according to the present disclosure includes: A process of acquiring an image; reading first information relating to a vehicle license plate number from a first frame of the video; A process of calculating a score for each of a plurality of items included in the first information; reading second information relating to the license plate number of the vehicle from a second frame of the video; A process of calculating a score for each of a plurality of items included in the second information; A process of selecting either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information; outputting third information composed of the selected information as the number of the vehicle; to be executed by the computer. Effect of the Invention
[0009] The present disclosure makes it possible to provide a vehicle number reading method, a vehicle number reading device, and a vehicle number reading program capable of outputting highly reliable reading results. [Brief description of the drawings]
[0010] [Figure 1] 1 is a block diagram showing a configuration of a vehicle number reading device according to a first embodiment. [Diagram 2] 4 is a flowchart showing an example of the flow of a vehicle number reading method according to the first embodiment. [Diagram 3] FIG. 11 is a block diagram showing a configuration of a vehicle number reading system according to a second embodiment. [Figure 4] FIG. 11 is a block diagram showing the configuration of a vehicle number reading device according to a second embodiment. [Diagram 5] FIG. 1 is a diagram showing an example of a license plate. [Figure 6] 10 is a flowchart showing an example of the operation of the vehicle number reading device according to the second embodiment. [Figure 7] 10 is a flowchart showing a flow of an example of an identical vehicle determination process. [Figure 8]10 is a flowchart showing a flow of an example of an identical vehicle determination process. [Figure 9] 10 is a flowchart showing a flow of an example of an identical vehicle determination process. [Figure 10] 10 is a flowchart showing a flow of an example of an identical vehicle determination process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0011] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals, and duplicated descriptions will be omitted as necessary for clarity of explanation.
[0012] <Embodiment 1> 1 is a block diagram showing the configuration of a vehicle number reading device according to embodiment 1. The vehicle number reading device 100 includes an acquisition unit 110, a reading unit 120, a calculation unit 130, and an output unit 150.
[0013] The acquisition unit 110 acquires video captured by an imaging device (not shown). The imaging device is a camera that captures images of roads and the like. The video captured by the imaging device is assumed to include a vehicle license plate. The video includes multiple frames captured in succession. In other words, the vehicle license plate is included in multiple frames included in the video. The vehicle is a moving object that is fitted with a license plate and travels on a road, such as a car, a motorcycle, or an electric kick scooter.
[0014] The reading unit 120 reads information related to the vehicle license plate number from each of a plurality of frames included in the video acquired by the acquisition unit 110. The information related to the vehicle license plate number is information written on the license plate shown in the frame. The information related to the vehicle license plate number includes a plurality of items. Specifically, the plurality of items are the local land transport bureau, classification number, business type, and serial number.
[0015] The calculation unit 130 calculates a score for each of a plurality of items included in the information about the number read by the reading unit 120. The score is a numerical representation of the reliability of the read information, and the higher the numerical value, the more accurate the read information is. There are no particular limitations on the method of calculating the score, and it can be calculated using existing technology.
[0016] A vehicle may appear in two or more frames among a plurality of frames included in a video. In this case, the reading unit 120 reads information related to the vehicle's license plate number in each frame in which the vehicle appears. The calculation unit 130 calculates a score for each piece of information related to the vehicle's license plate number read in the frame in which the vehicle appears.
[0017] Hereinafter, one of the frames from which the reading unit 120 reads information related to the vehicle number may be referred to as a "first frame". A frame from which the reading unit 120 reads information related to the vehicle number and which is different from the first frame may be referred to as a "second frame". Information read by the reading unit 120 for the first frame may be referred to as "first information", and information read by the reading unit 120 for the second frame may be referred to as "second information". A vehicle shown in the first frame may be referred to as a "first vehicle", and a vehicle shown in the second frame may be referred to as a "second vehicle". A score calculated by the calculation unit 130 for the first frame may be referred to as a "first score", and a score calculated by the calculation unit 130 for the second frame may be referred to as a "second score".
[0018] The output unit 150 selects either the first information or the second information for each item based on the first score and the second score, and outputs third information consisting of the selected information as the vehicle number. That is, the third information is the one selected from the first information and the second information, whichever has a higher reliability, for each of a plurality of items.
[0019] 2 is a flowchart showing the flow of the vehicle number reading method according to the first embodiment. First, the acquisition unit 110 acquires an image showing a vehicle from a photographing device (step S101). The reading unit 120 reads first information about a first vehicle from one of a plurality of frames included in the image acquired in step S101, i.e., a first frame (step S102). Next, the calculation unit 130 calculates a first score for each of a plurality of items included in the first information (step S103).
[0020] Next, the reading unit 120 reads second information about a second vehicle from a second frame different from the first frame from which the first information was read in step S102 (step S104). Next, the calculation unit 130 calculates a second score for each of a plurality of items included in the second information (step S105). Next, the output unit 150 selects either the first information or the second information for each item based on the first score and the second score, and outputs third information composed of the selected information as the license plate number of the vehicle (step S106).
[0021] The above processing order is merely an example and does not limit the processing order. For example, after reading the first information related to the first vehicle from the first frame, a process may be performed to read the second information related to the second vehicle from a second frame different from the first frame from which the first information was read prior to execution of step S103. Steps S102 and S104 may be executed in parallel. Similarly, steps S103 and S105 may be executed in parallel. The processing order of each step may be interchanged.
[0022] In this way, in the vehicle number reading method according to the first embodiment, a score is calculated for each of a plurality of items included in the read information, and the reading result with a high score in each item, i.e., a reading result with high reliability, is adopted as the third information. Therefore, it is possible to output a reading result with high reliability.
[0023] The vehicle number reading device 100 includes a processor, a memory, and a storage device, which are not shown in the figure. The storage device stores a computer program that implements the processing of the vehicle number reading method according to the present embodiment. The processor then reads the computer program from the storage device into the memory and executes the computer program. As a result, the processor realizes the functions of the acquisition unit 110, the reading unit 120, the calculation unit 130, the determination unit 140, and the output unit 150.
[0024] Alternatively, each component of the vehicle number reading device 100 may be realized by dedicated hardware. Also, a part or all of each component of each device may be realized by a general-purpose or dedicated circuit, processor, etc., or a combination of these. These may be configured by a single chip, or may be configured by multiple chips connected via a bus. A part or all of each component of each device may be realized by a combination of the above-mentioned circuits, etc., and a program. Also, a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field-Programmable Gate Array), quantum processor (quantum computer control chip), etc. can be used as the processor.
[0025] Furthermore, when some or all of the components of the vehicle number reading device 100 are realized by a plurality of information processing devices, circuits, etc., the plurality of information processing devices, circuits, etc. may be centrally arranged or distributed. For example, the information processing devices, circuits, etc. may be realized in a form in which each is connected via a communication network, such as a client-server system or a cloud computing system. Furthermore, the functions of the vehicle number reading device 100 may be provided in a SaaS (Software as a Service) format.
[0026] <Embodiment 2> 3 is a block diagram showing a configuration of a vehicle number reading system 200 according to a second embodiment. The vehicle number reading system 200 is an information system that reads information written on a license plate attached to a vehicle. The vehicle number reading system 200 includes a photographing device 300 and a vehicle number reading device 400. The photographing device 300 and the vehicle number reading device 400 are communicatively connected via a network 500. Here, the network 500 may be a wired communication line, a wireless communication line, or may include the Internet.
[0027] The photographing device 300 is a camera that photographs a vehicle including its license plate. The location where the photographing device 300 is installed is not particularly limited as long as the vehicle can be photographed. The photographing device 300 may be attached to, for example, a utility pole on the side of the road. The photographing device 300 may also be a portable camera such as an in-vehicle camera.
[0028] Next, the configuration of the vehicle number reading device 400 according to the second embodiment will be described with reference to FIG. 4. FIG. 4 is a block diagram showing the configuration of the vehicle number reading device 400 according to the second embodiment. The vehicle number reading device 400 is an example of the vehicle number reading device 100 described above. The vehicle number reading device 400 is an information processing device that performs vehicle number reading processing and the like, and is, for example, a server device realized by a computer. The vehicle number reading device 400 may be redundantly configured with a plurality of servers, and each functional block may be realized by a plurality of computers. The vehicle number reading device 400 may also be a portable device. The vehicle number reading device 400 includes a memory 410, a communication unit 420, a storage unit 430, and a control unit 440.
[0029] The memory 410 is a storage area that temporarily stores the processing contents of the control unit 440, and is, for example, a volatile storage device such as a RAM (Random Access Memory). The communication unit 420 is an interface that communicates with the outside of the vehicle number reading device 400. The storage unit 430 is a storage device that stores a program 431 and the like. The program 431 is a computer program that implements the vehicle number reading process according to this embodiment.
[0030] The control unit 440 includes an acquisition unit 441, a reading unit 442, a calculation unit 443, a determination unit 444, and an output unit 445. The control unit 440 is a control device that controls the operation of the vehicle number reading device 400, and is, for example, a processor such as a CPU. The control unit 440 loads the program 431 from the storage unit 430 into the memory 410 and executes it. As a result, the control unit 440 realizes the functions of the acquisition unit 441, the reading unit 442, the calculation unit 443, the determination unit 444, and the output unit 445.
[0031] The acquisition unit 441 acquires the image by receiving the image transmitted by the image capturing device 300. The reading unit 442 reads information related to the vehicle number from each of a plurality of frames included in the image acquired by the acquisition unit 441. FIG. 5 is a diagram showing an example of a license plate. The license plate 600 shown in FIG. 5 has a land transport bureau 610, a classification number 620, a business type 630, and a serial number 640 written thereon. When the license plate shown in FIG. 5 is captured in a frame, the reading unit 442 reads four items, namely the land transport bureau 610, the classification number 620, the business type 630, and the serial number 640, as information related to the vehicle number. The reading unit 442 reads information related to the vehicle number for each of a plurality of frames included in the image.
[0032] The calculation unit 443 calculates a score for each of a plurality of items included in the information related to the number read by the reading unit 442. When the reading unit 442 reads the information related to the number for a plurality of frames, the calculation unit 443 calculates a score for each of the plurality of frames from which information is read.
[0033] When the information on the number plate is read from a plurality of frames, the determination unit 444 determines whether the vehicles shown in each frame are the same. Specifically, the determination unit 444 extracts two frames from the plurality of frames from which the information on the number plate is read, compares the information on the number plate from the two frames, and determines whether the vehicles shown in the two frames are the same. There is a high possibility that the same vehicle is shown in frames that are taken close to each other among the plurality of frames included in the video. Therefore, when the plurality of frames from which the information on the number plate is read are arranged in order of the time of taking the frames, the determination unit 444 makes a determination on two adjacent frames or two frames selected every other frame. In other words, when the plurality of frames from which the information on the number plate is read are arranged in order of the time of taking the frames, the determination unit 444 makes a determination on the first frame and the second frame, with the frames within two frames before and after the first frame being the second frame.
[0034] Although the method of determining whether the vehicles shown in the first and second frames are the same based on the information on the number has been described, various methods may be used to determine whether the vehicles shown in each frame are the same. For example, based on the characteristics of the vehicles, if the characteristics of the vehicles shown in each frame are similar or identical, it may be determined that the vehicles are the same. As the characteristics of the vehicles, various characteristics that distinguish the appearance of the vehicles, such as the shape, color, and ornaments, may be adopted.
[0035] When the determination unit 444 determines that the first vehicle and the second vehicle are the same vehicle, the output unit 445 compares the first score with the second score for each of the multiple items included in the first information and the second information, and outputs the information with the higher score as the third information for that item.
[0036] Next, an example of the operation of the vehicle number reading device 400 during the number reading process will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the operation of the vehicle number reading device 400 according to the second embodiment. First, the acquisition unit 441 acquires the video by receiving the video transmitted from the photographing device 300 (step S201). The photographing device 300 may transmit the captured video to the vehicle number reading device 400 on a regular or irregular basis. The photographing device 300 may transmit the captured video to the vehicle number reading device 400 in response to a request from the vehicle number reading device 400.
[0037] Next, the reading unit 442 reads information related to the number from each of the multiple frames of the video (step S202). Next, the calculation unit 443 calculates a score for each item of the information read in step S202 (step S203). The control unit 440 repeats steps S202 and S203 until reading of information related to the number for all of the multiple frames included in the video is completed (step S204 No).
[0038] When reading of the information related to the number is completed for all frames (Yes in step S204), the determination unit 444 determines whether the first vehicle and the second vehicle are the same for the first frame and the second frame (step S205). If it is determined that they are the same vehicle (Yes in step S205), the output unit 445 compares the scores for each of the multiple items included in the first information and the second information, and outputs the one with the higher score as the third information for that item (step S206).
[0039] Next, the above-mentioned step S205, i.e., the same vehicle determination process, will be described in more detail with reference to Figures 7 to 10. The determination unit 444 compares the contents of multiple items contained in the first information with the contents of multiple items contained in the second information for each item, and determines whether the first vehicle and the second vehicle are the same vehicle depending on the number of matching items. Figures 7 to 10 are flowcharts showing an example of the operation of the determination unit 444 when performing the same vehicle determination process.
[0040] The determination unit 444 may determine that the first vehicle and the second vehicle are the same vehicle when the contents of the first information and the contents of the second information match in a predetermined number or more of items, as shown in FIG. 7, for example. FIG. 7 shows a case where the number of items is four and the predetermined number is three. In this case, the determination unit 444 first compares the contents of the four items included in the first information with the contents of the four items included in the second information, item by item (step S301). When the contents of three or more items match (step S302 Yes), the determination unit 444 determines that the first vehicle and the second vehicle are the same vehicle (step S303). When the contents of two or less items match (step S302 No), the determination unit 444 determines that the first vehicle and the second vehicle are not the same vehicle (step S304).
[0041] The determination unit 444 may determine that the first vehicle and the second vehicle are the same vehicle when the contents of the most accurately readable item among the multiple items match, for example, as shown in FIG. 8. FIG. 8 shows a case where the serial number 640 shown in FIG. 5 is included in the multiple items. Characters displayed large in the frame are more accurately readable than characters displayed small. Numbers have fewer types of characters and are more accurately readable than hiragana, kanji, and the like. Therefore, the serial number 640 is usually written in large numbers on the license plate, and is more accurately readable than other items. Therefore, in the example shown in FIG. 8, the first vehicle and the second vehicle are determined to be the same vehicle when the serial numbers among the multiple items match. In this case, the determination unit 444 first compares the contents of the multiple items included in the first information with the contents of the multiple items included in the second information for each item (step S401). If the serial numbers match (step S402: Yes), the determination unit 444 determines that the first vehicle and the second vehicle are the same vehicle (step S403). If the serial numbers do not match (step S402: No), the determination unit 444 determines that the first vehicle and the second vehicle are not the same vehicle (step S404).
[0042] The determination unit 444 may determine that the first vehicle and the second vehicle are the same vehicle when the contents of a predetermined number of items including an item that can be read accurately match among the multiple items, as shown in FIG. 9, for example. FIG. 9 shows a case where the multiple items are four items including the classification number 620 shown in FIG. 5. The classification number 620 is written in numbers on the license plate. Therefore, it is more accurately readable than other items written in kanji or hiragana. Therefore, in the example shown in FIG. 8, the first vehicle and the second vehicle are determined to be the same vehicle when the contents of two or more items including the classification number match among the multiple items. In this case, first, the determination unit 444 compares the contents of the multiple items included in the first information with the contents of the multiple items included in the second information for each item (step S501). If the classification numbers match (step S502 Yes), the determination unit 444 determines whether the number of matching items is two or more (step S503). If the number of matching items is two or more (step S503: Yes), the determination unit 444 determines that the first vehicle and the second vehicle are the same vehicle (step S504). If the number of matching items is one or less (step S503: No), the determination unit 444 determines that the first vehicle and the second vehicle are not the same vehicle (step S505).
[0043] The determination unit 444 may determine that the first vehicle and the second vehicle are not the same vehicle when the first score and the second score for the most accurately readable item are equal to or greater than a predetermined value and the content of the item is different between the first information and the second information, as shown in FIG. 10, for example. FIG. 10 shows a case where the serial number 640 shown in FIG. 5 is included in a plurality of items. In this case, the determination unit 444 first compares the content of the plurality of items included in the first information with the content of the plurality of items included in the second information for each item (step S601). If the serial numbers match (step S602 Yes), the determination unit 444 ends the process. If the serial numbers do not match (step S602 No), the determination unit 444 determines whether the first score and the second score for the serial numbers are both equal to or greater than a predetermined value (step S603). If both the first score and the second score for the serial number are equal to or greater than a predetermined value (Yes in step S603), the determination unit 444 determines that the first vehicle and the second vehicle are not the same vehicle (step S604). If at least one of the first score and the second score for the serial number is less than a predetermined value (No in step S603), the determination unit 444 ends the process.
[0044] The same vehicle determination process described above is merely an example, and is not limited to the above. Also, the determination unit 444 may perform the same vehicle determination process by combining the above processes.
[0045] <Other embodiments> In the above embodiment, the present disclosure has been described as a hardware configuration, but is not limited to this. Any process of the present disclosure can be realized by causing a CPU to execute a computer program.
[0046] In the above examples, the program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disk or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.
[0047] The present disclosure is not limited to the above-described embodiment, and may be modified as appropriate without departing from the spirit and scope of the present disclosure. In addition, the present disclosure may be implemented by appropriately combining the respective embodiments.
[0048] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes.
[0049] (Appendix A1) The computer Get the footage, reading first information relating to a vehicle license plate number from a first frame of the video; Calculating a score for each of a plurality of items included in the first information; reading second information relating to the license plate number of the vehicle from a second frame of the video; Calculating a score for each of a plurality of items included in the second information; selecting either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information; outputting third information composed of the selected information as the number of the vehicle; How to read vehicle numbers.
[0050] (Appendix A2) determining whether the vehicles shown in the first frame and the second frame are the same vehicle based on the characteristics of the vehicle shown in the first frame and the characteristics of the vehicle shown in the second frame; If it is determined that the vehicle is the same, the third information composed of the selected information is output as the license plate number of the vehicle. The method for reading vehicle number plates is described in Appendix A1.
[0051] (Appendix A3) comparing the contents of a plurality of items included in the first information with the contents of a plurality of items included in the second information item by item, and when the number of items whose contents match is equal to or exceeds a predetermined number, outputting the third information composed of selected information as the license plate number of the vehicle; A method for reading vehicle number plates as described in Appendix A1 or A2.
[0052] (Appendix A4) When the contents of the most accurately readable item among the plurality of items match, the third information composed of selected information is output as the vehicle number. A vehicle number reading method according to any one of Appendices A1 to A3.
[0053] (Appendix A5) The first information and the second information include, as items, a land transport bureau, a classification number, a business type, and a serial number. 1. A method for reading a vehicle number plate as described in any one of Appendices A1 to A4.
[0054] (Appendix A6) The score represents the reliability of the read information. 1. A method for reading a vehicle number plate as described in any one of Appendices A1 to A4.
[0055] (Appendix A7) determining that the first vehicle and the second vehicle are not the same vehicle when the first score and the second score for the most accurately readable item among the plurality of items are both equal to or greater than a predetermined value and the content of the item contained in the first information differs from the content of the item contained in the second information; A vehicle number reading method according to any one of Appendices A1 to A6.
[0056] (Appendix B1) An acquisition unit that acquires a video image; a reading unit that reads first information related to a vehicle license plate number from a first frame of the image and reads second information related to the vehicle license plate number from a second frame of the image; A calculation unit that calculates a score for each of a plurality of items included in the first information and calculates a score for each of a plurality of items included in the second information; an output unit that selects either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information, and outputs third information composed of the selected information as the number of the vehicle; A vehicle number reading device comprising:
[0057] (Appendix C1) A process of acquiring an image; reading first information relating to a vehicle license plate number from a first frame of the video; A process of calculating a score for each of a plurality of items included in the first information; reading second information relating to the license plate number of the vehicle from a second frame of the video; A process of calculating a score for each of a plurality of items included in the second information; A process of selecting either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information; outputting third information composed of the selected information as the number of the vehicle; A vehicle number reading program that causes a computer to execute the above. [Explanation of symbols]
[0058] 100 Vehicle number reader 110 Acquisition Department 120 Reading unit 130 Calculation section 140 Judgment section 150 Output section 200 Vehicle number reading system 300 Imaging Device 400 Vehicle number reader 410 Memory 420 Communications Department 430 Storage section 431 Programs 440 Control Unit 441 Acquisition Department 442 Reading unit 443 Calculation Department 444 Judgment section 445 Output section 500 Network 600 Number Plate 610 Land Transport Bureau 620 Classification number 630 Business Type 640 Serial Number
Claims
1. The computer Get the footage, reading first information relating to a vehicle license plate number from a first frame of the image; Calculating a score for each of a plurality of items included in the first information; reading second information relating to the license plate number of the vehicle from a second frame of the image; Calculating a score for each of a plurality of items included in the second information; selecting either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information; outputting third information composed of the selected information as the number of the vehicle; How to read vehicle numbers.
2. determining whether the vehicles shown in the first frame and the second frame are the same vehicle based on characteristics of the vehicle shown in each frame; If it is determined that the vehicle is the same, the third information composed of the selected information is output as the license plate number of the vehicle. The vehicle number reading method according to claim 1.
3. the contents of a plurality of items included in the first information are compared with the contents of a plurality of items included in the second information item by item, and when the number of items whose contents match is equal to or greater than a predetermined number, the third information composed of selected information is output as the license plate number of the vehicle. The vehicle number reading method according to claim 1.
4. When the contents of the most accurately readable item among the plurality of items match, the third information composed of selected information is output as the vehicle number. The vehicle number reading method according to claim 1.
5. The first information and the second information include, as items, a land transport bureau, a classification number, a business type, and a serial number. A vehicle number reading method according to any one of claims 1 to 4.
6. The score represents the reliability of the read information.
5. A method for reading a vehicle number plate according to claim 1.
7. When the first score and the second score for the most accurately readable item among the plurality of items are both equal to or greater than a predetermined value, and the content of the item contained in the first information differs from the content of the item contained in the second information, it is determined that the first vehicle and the second vehicle are not the same vehicle. The vehicle number reading method according to claim 1.
8. An acquisition means for acquiring a video; a reading means for reading first information related to a vehicle license plate number from a first frame of the image and for reading second information related to the vehicle license plate number from a second frame of the image; a calculation means for calculating a score for each of a plurality of items included in the first information and a score for each of a plurality of items included in the second information; an output means for selecting either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information, and outputting third information constituted by the selected information as the number of the vehicle; A vehicle number reading device comprising:
9. A process of acquiring an image; reading first information relating to a vehicle license plate number from a first frame of the video; A process of calculating a score for each of a plurality of items included in the first information; reading second information relating to the license plate number of the vehicle from a second frame of the video; A process of calculating a score for each of a plurality of items included in the second information; A process of selecting either the first information or the second information for each item based on a score calculated for each of a plurality of items included in the first information and a score calculated for each of a plurality of items included in the second information; outputting third information composed of the selected information as the number of the vehicle; A vehicle number reading program that causes a computer to execute the above.
Citation Information
Patent Citations
Number plate recognition device, number plate recognition method, and number plate recognition program
JP2021121892A
