Processing device, processing method, and program

Abstract

The present invention provides a processing device (10) having: a first collation unit (14) for carrying out a first collation process for collating license plate information on an exiting vehicle and license plate information on an entering vehicle with each other; a first identification unit (15) for identifying an entering vehicle that is the same vehicle as the exiting vehicle on the basis of the result of the first collation process, when both the result of the first collation process and the reliability of the license plate information satisfy a criterion; a second collation unit (16) for carrying out a second collation process for collating supplemental information on the exiting vehicle and supplemental information on the entering vehicle with each other when at least one of the result of the first collation process and the reliability of the license plate information does not satisfy the criterion; and a second identification unit (17) for identifying the entering vehicle that is the same vehicle as the exiting vehicle on the basis of the result of the first collation process and the result of the second collation process, when at least one of the result of the first collation process and the reliability of the license plate information does not satisfy the criterion.

Description

[Technical field]

[0001] The present invention relates to a processing device, a processing method, and a program. [Background technology]

[0002] Techniques related to the present invention are disclosed in Patent Documents 1 to 3.

[0003] Patent document 1 discloses a technology that performs vehicle matching processing based on the vehicle's license plate information and vehicle characteristic information (vehicle name, vehicle model, model, color, etc.), and performs settlement processing for parking lots, toll roads, etc. based on the matching results.

[0004] Patent Document 2 discloses a parking lot management system that performs vehicle verification processing based on the vehicle number data and facial data of the passengers, and determines parking fees based on the verification results.

[0005] Patent Document 3 discloses a technology for detecting the target vehicle from within an image by performing a vehicle matching process based on the results of a license plate analysis, an analysis of the vehicle type and color, an analysis of the passengers' faces, and an analysis of the number of passengers. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] International Publication No. 2021 / 075278 [Patent Document 2] JP 2006-338479 A [Patent Document 3] Patent Publication No. 2020-191509 Summary of the Invention [Problem to be solved by the invention]

[0007] In toll roads, parking lots, and the like, it is necessary to identify the correspondence between entering and exiting vehicles. "Identifying the correspondence" means identifying an exiting vehicle that is the same as an entering vehicle. For example, there is known technology that identifies the correspondence between entering and exiting vehicles using license plate information. However, the accuracy of reading license plate information is not 100%. When only license plate information is used, there is a problem that if the license plate information cannot be read correctly, the correct correspondence between entering and exiting vehicles cannot be identified.

[0008] As disclosed in Patent Documents 1 to 3, the above problems can be alleviated by using the technology of matching using the characteristics of the vehicle and the characteristics of the passengers in addition to the license plate information. However, as the amount of data used for matching increases, a new problem arises in that the processing load on the computer increases.

[0009] The present invention aims to provide a technology that can accurately identify the correspondence between entering and exiting vehicles while reducing the inconvenience of a large processing load on a computer. [Means for solving the problem]

[0010] According to the present invention, an entrance processing means for acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in association with each other; An exit acquisition means for acquiring the license plate information and the complementary information of an exiting vehicle; A first matching means for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification means for identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching means for performing a second matching process to match the complementary information of the exiting vehicle with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; a second identification means for identifying the entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; A processing apparatus is provided having:

[0011] Further, according to the present invention, The computer an entry processing step of acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in association with each other; An exit acquisition process for acquiring the license plate information and the complementary information of an exiting vehicle; A first matching process for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification step of identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching process for performing a second matching process in which the complementary information of the exiting vehicle is matched with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; a second identification process for identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; A processing method for performing the above is provided.

[0012] Further, according to the present invention, Computer, an entrance processing means for acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in a linked manner; An exit acquisition means for acquiring the license plate information and the complementary information of an exiting vehicle; a first matching means for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification means for identifying the entering vehicle that is the same as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching means for performing a second matching process to match the complementary information of the exiting vehicle with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; and a second identification means for identifying the entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; A program is provided to function as a Effect of the Invention

[0013] According to the present invention, it becomes possible to accurately identify the correspondence between entering and exiting vehicles while reducing the inconvenience of a large processing load on a computer. [Brief description of the drawings]

[0014] [Figure 1] FIG. 2 is a diagram illustrating an example of a hardware configuration of a processing device according to the present embodiment. [Diagram 2]FIG. 2 is a diagram illustrating an example of a functional block diagram of the processing apparatus according to the present embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of information processed by the processing device of the present embodiment. [Figure 4] FIG. 2 is a diagram showing an example of a processing flow of the processing device of the present embodiment. [Diagram 5] FIG. 2 is a diagram showing an example of a processing flow of the processing device of the present embodiment. [Figure 6] FIG. 2 is a diagram showing an example of a processing flow of the processing device of the present embodiment. [Figure 7] FIG. 2 is a diagram illustrating an example of a functional block diagram of the processing apparatus according to the present embodiment. [Figure 8] FIG. 2 is a diagram illustrating an example of information processed by the processing device of the present embodiment. [Figure 9] FIG. 2 is a diagram showing an example of a processing flow of the processing device of the present embodiment. [Figure 10] FIG. 2 is a diagram illustrating an example of a functional block diagram of the processing apparatus according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are given the same reference numerals and the description will be omitted as appropriate.

[0016] <First embodiment> "overview" First, an overview of the processing apparatus of this embodiment will be described, and a detailed description of the processing apparatus of this embodiment will be given later.

[0017] The processing device of this embodiment identifies the correspondence between the entering vehicle and the exiting vehicle by a matching process based on the license plate information and the complementary information. The complementary information is information that can be used to identify the vehicle and is different from the license plate information.

[0018] The processing device performs matching processing based on the license plate information and the complementary information in a unique flow, thereby reducing the inconvenience of a large processing load on the computer. In the matching processing, the processing device first performs matching based on the license plate information. If both the reliability of the license plate information reading result and the matching score of the license plate information satisfy a predetermined standard, the processing device identifies the correspondence between the entering vehicle and the exiting vehicle based on the result of matching the license plate information. In this case, matching based on the complementary information is not performed.

[0019] On the other hand, if at least one of the reliability of the license plate information reading result and the license plate information matching score does not satisfy a predetermined standard, the processing device performs matching based on the supplementary information, and identifies the correspondence between the entering vehicle and the exiting vehicle based on the license plate information matching result and the supplementary information matching result.

[0020] In this way, a processing device that uses other supplementary information in addition to license plate information to match vehicles can accurately identify the correspondence between entering and exiting vehicles. In addition, in the case of the processing device of this embodiment, matching based on supplementary information is performed only when necessary, which reduces the processing load on the computer.

[0021] "Hardware Configuration" Next, an example of the hardware configuration of the processing device will be described. Fig. 1 is a diagram showing an example of the hardware configuration of the processing device. Each functional unit of the processing device is realized by any combination of hardware and software, centering on a CPU (Central Processing Unit) of any computer, memory, programs loaded into the memory, a storage unit such as a hard disk for storing the programs (programs stored beforehand at the stage of shipping the device, as well as programs downloaded from storage media such as CDs (Compact Discs) or servers on the Internet, can be stored), and a network connection interface. Those skilled in the art will understand that there are various variations in the methods and devices for realizing the above.

[0022] As shown in FIG. 1, the processing device has a processor 1A, a memory 2A, an input / output interface 3A, a peripheral circuit 4A, and a bus 5A. The peripheral circuit 4A includes various modules. The processing device does not have to have the peripheral circuit 4A. The processing device may be composed of multiple physically and / or logically separated devices, or may be composed of a single device that is physically and logically integrated. When composed of multiple physically and / or logically separated devices, each of the multiple devices can have the above hardware configuration.

[0023] The bus 5A is a data transmission path for the processor 1A, memory 2A, peripheral circuit 4A, and input / output interface 3A to transmit and receive data to each other. The processor 1A is an arithmetic processing device such as a CPU or a GPU (Graphics Processing Unit). The memory 2A is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The input / output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, etc., and an interface for outputting information to an output device, an external device, an external server, etc. Examples of the input device include a keyboard, a mouse, a microphone, etc. Examples of the output device include a display, a speaker, a printer, a mailer, etc. The processor 1A can issue commands to each module and perform calculations based on the results of those calculations.

[0024] "Function Configuration" Next, the functional configuration of the processing device will be described. Fig. 2 shows an example of a functional block diagram of the processing device 10. As shown in the figure, the processing device 10 has an entrance processing unit 11, a memory unit 12, an exit acquisition unit 13, a first collation unit 14, a first identification unit 15, a second collation unit 16, and a second identification unit 17. As shown in Fig. 10, the processing device 10 does not need to have the memory unit 12. In this case, an external device configured to be able to communicate with the processing device 10 has the memory unit 12.

[0025] The entry processing unit 11 acquires the license plate information of the entering vehicle and complementary information related to the entering vehicle, and stores the license plate information and the complementary information in the memory unit 12 in association with each other.

[0026] An "entering vehicle" is a vehicle that enters a facility. The processing device 10 is used, for example, in a facility that requires management of entering and exiting vehicles. Examples of such facilities include, but are not limited to, toll roads, parking lots, and stores and factories where many incoming and outgoing vehicles enter and exit.

[0027] "License plate information" is information obtainable from a license plate affixed to a vehicle. For example, the license plate information may indicate at least one of the following: the address of a local transport bureau or a motor vehicle inspection and registration office, a classification number, a serial number, a use classification, the color of the background of the plate, and the color of the letters on the plate.

[0028] Such license plate information can be obtained by using various technologies. For example, a camera installed at an entrance gate through which an entering vehicle passes captures the license plate of the entering vehicle. The entrance processing unit 11 then analyzes the image generated by the camera to obtain the license plate information.

[0029] The "complementary information" is information that can be used to identify a vehicle and is different from license plate information. Specific examples of the complementary information will be described in the following embodiments.

[0030] 3 is a schematic diagram showing an example of the entering vehicle information stored in the storage unit 12. As shown in the figure, the entering vehicle information is information in which the license plate information and the complementary information are linked to each other.

[0031] Returning to FIG. 2, the exit acquisition unit 13 acquires the license plate information and complementary information of the exiting vehicle.

[0032] An "exiting vehicle" is a vehicle that is exiting the facility.

[0033] The license plate information and the complementary information are as described above. The license plate information and the complementary information of the exiting vehicle are acquired by the same means as the license plate information and the complementary information of the entering vehicle described above. For example, the license plate information and the complementary information of the exiting vehicle are acquired by analyzing an image generated by a camera installed at the exit gate through which the exiting vehicle passes.

[0034] The first matching unit 14 performs a first matching process to match the license plate information of the exiting vehicle with each of the license plate information of the entering vehicle stored in the storage unit 12 (see FIG. 3). The first matching unit 14 then calculates a first matching score for each pair of the exiting vehicle and each entering vehicle. The first matching score indicates the degree of match of the license plate information. The calculation algorithm of the first matching score is not particularly limited. For example, when the license plate information indicates multiple items among the address of the transport bureau or the motor vehicle inspection and registration office, the classification number, the serial designation number, the use classification, the color of the background of the plate, and the color of the characters of the plate, the first matching score may be calculated according to the number of items that match. In this case, the more the number of items that match, the higher the first matching score is calculated. Also, weighting values ​​may be set in advance for multiple items, and the higher the items with higher weighting values ​​match, the higher the first matching score is calculated.

[0035] When both the result of the first matching process and the reliability of the license plate information satisfy a criterion, the first identification unit 15 identifies the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process.

[0036] The "reliability of number plate information" is the reliability of the number plate information read by image analysis, and is also called the certainty. The reliability calculation algorithm is not particularly limited, and any technology according to the image analysis algorithm can be adopted. For example, when reading numbers or characters using character recognition technology, the reliability may be calculated based on the similarity between the characters in the image and a template. In this case, the higher the similarity, the higher the reliability. The reliability may also be calculated based on factors that may affect the image quality, such as the time of day and weather at the time of shooting. In this case, the more the number plate information read from an image taken under conditions that result in better image quality, the higher the reliability.

[0037] The "criteria for the reliability of license plate information" indicates the lower limit of the reliability at which it is acceptable to identify the correspondence between entering and exiting vehicles based only on the license plate information, without using any supplementary information. The condition that "the reliability of license plate information satisfies the criteria" is preferably that "both the reliability of the license plate information of the entering vehicle and the reliability of the license plate information of the exiting vehicle satisfy the criteria." However, depending on the performance required for the processing device 10, the condition may be that "at least one of the reliability of the license plate information of the entering vehicle and the reliability of the license plate information of the exiting vehicle satisfies the criteria."

[0038] The "result of the first matching process" is a first matching score between the license plate information of the exiting vehicle and the license plate information of each entering vehicle.

[0039] The "criterion for the result of the first matching process" indicates a condition under which it is permitted to identify the correspondence between an entering vehicle and an exiting vehicle based only on the result of the first matching process, without using the matching result of the complementary information. Examples of the condition include, but are not limited to, "there is a pair of an exiting vehicle and an entering vehicle whose first matching score of the first matching process is equal to or greater than a threshold" or "there is only one pair of an exiting vehicle and an entering vehicle whose first matching score of the first matching process is equal to or greater than a threshold." The threshold of the first matching score indicates a lower limit of the first matching score under which it is permitted to identify the correspondence between an entering vehicle and an exiting vehicle based only on the result of the first matching process, without using the matching result of the complementary information.

[0040] When both the result of the first matching process and the reliability of the license plate information satisfy the criteria, the first identification unit 15 identifies a pair of an exiting vehicle and an entering vehicle with the highest first matching score of the first matching process. Then, the first identification unit 15 identifies the entering vehicle of the identified pair as the same vehicle as the exiting vehicle of the identified pair. In other words, the first identification unit 15 identifies the entering vehicle and the exiting vehicle of the identified pair as the same vehicle.

[0041] If at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the above criteria, the second matching unit 16 performs a second matching process to match the complementary information of the exiting vehicle with each of the complementary information of the entering vehicle stored in the memory unit 12 (see Figure 3).

[0042] If at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the above criteria, the second identification unit 17 identifies an entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process.

[0043] Next, an example of the process flow of the processing device 10 will be described. Note that the purpose of this description is to describe the process flow. Since the details of the process have been described above, the description here will be omitted as appropriate.

[0044] First, the process executed when a vehicle enters a facility will be described with reference to the flowchart in FIG.

[0045] The processing device 10 acquires the license plate information and complementary information of the entering vehicle (S10). For example, the acquisition of the license plate information and complementary information of the entering vehicle by the processing device 10 is realized by analyzing an image generated by a camera installed at an entrance gate through which the entering vehicle passes.

[0046] Next, the processing device 10 links the acquired license plate information and complementary information with each other and registers them in the entering vehicle information (see FIG. 3) stored in the storage unit 12 (S11).

[0047] Next, the process executed when the vehicle exits the facility will be described with reference to the flowchart of FIG.

[0048] The processing device 10 acquires the license plate information and complementary information of the exiting vehicle (S20). For example, the acquisition of the license plate information and complementary information of the exiting vehicle by the processing device 10 is realized by analyzing an image generated by a camera installed at an exit gate through which the exiting vehicle passes.

[0049] Next, the processing device 10 executes a first matching process for matching the license plate information of the exiting vehicle with the license plate information of each entering vehicle registered in the entering vehicle information stored in the storage unit 12 (S21).

[0050] If both the result of the first matching process and the reliability of the license plate information satisfy the criteria (Yes in S22), the processing device 10 identifies an entering vehicle that is the same as the exiting vehicle based on the result of the first matching process in S21 (S23). Specifically, the processing device 10 identifies the pair of an exiting vehicle and an entering vehicle that has the highest first matching score in the first matching process. Then, the processing device 10 identifies the entering vehicle of the identified pair as the same vehicle as the exiting vehicle.

[0051] On the other hand, if at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criteria (No in S22), the processing device 10 executes a second matching process (S24) to match the complementary information of the exiting vehicle with the complementary information of each entering vehicle registered in the entering vehicle information stored in the memory unit 12. Then, the processing device 10 identifies an entering vehicle that is the same as the exiting vehicle based on the result of the first matching process in S21 and the result of the second matching process in S24 (S25).

[0052] "Action and effect" The processing device 10 of this embodiment identifies the correspondence between entering and exiting vehicles by a matching process based on the license plate information and the complementary information. By using not only the license plate information but also other complementary information, the accuracy of identifying the correspondence between entering and exiting vehicles is improved.

[0053] In addition, the processing device 10 of this embodiment performs a matching process based on the complementary information when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy a standard. Since matching based on the complementary information is performed only when necessary, the processing load on the computer can be reduced.

[0054] <Second embodiment> In this embodiment, the "supplementary information," "second matching process," and "process of identifying an entering vehicle that is the same as an exiting vehicle based on the results of the first matching process and the results of the second matching process" are made more specific.

[0055] The "supplementary information" includes at least one of the following: external appearance characteristics of the vehicle, external appearance characteristics of an occupant of the vehicle, and identification information of a mobile terminal present in the vehicle.

[0056] "Features of the vehicle's appearance" is information indicating the features of the vehicle's appearance. There is no particular limitation on the type of the features, and any technology can be used. For example, key points for key point matching detected based on a predetermined rule may be detected as the features of the vehicle's appearance. Alternatively, items that may differ for each vehicle or each model, such as the vehicle's color, width, height, width-to-height ratio, and wheel shape, may be detected as the features of the vehicle's appearance.

[0057] Such acquisition of the external characteristic quantities of the vehicle can be realized by using various techniques. For example, a camera installed at an entrance gate through which the entering vehicle passes captures the external characteristic quantities of the entering vehicle. Then, the entrance processing unit 11 analyzes the image generated by the camera to acquire the external characteristic quantities of the vehicle.

[0058] The "appearance feature of the vehicle occupant" is the facial feature of the occupant, the clothing feature, etc. The acquisition of such appearance feature of the vehicle occupant is realized by using various technologies. For example, a camera installed at an entrance gate through which the entering vehicle passes takes an image of the entering vehicle. Then, the entrance processing unit 11 acquires the appearance feature of the vehicle occupant by analyzing the image generated by the camera. Note that, when there are multiple occupants of the vehicle, the entrance processing unit 11 may acquire the appearance feature of all the multiple occupants. Alternatively, the entrance processing unit 11 may acquire the appearance feature of a representative of the multiple occupants. The representative may be, for example, a person sitting in the driver's seat, but is not limited to this.

[0059] "Identification information of a mobile terminal present in a vehicle" refers to identification information of a terminal carried by a passenger, such as a smartphone, tablet terminal, smart watch, mobile phone, portable game console, laptop computer, etc. Examples of such identification information include, but are not limited to, a MAC (Media Access Control) address and user identification information of an application installed on the mobile terminal.

[0060] Acquisition of such mobile terminal identification information can be realized by using various technologies. For example, a short-range wireless communication device is installed at an entrance gate through which an entering vehicle passes. Then, the short-range wireless communication device communicates with a mobile terminal present in an entering vehicle passing a predetermined position, and acquires the identification information of the mobile terminal from the mobile terminal.

[0061] If at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the above criteria, the second matching unit 16 performs a second matching process to match the complementary information of the exiting vehicle with each complementary information of the entering vehicle stored in the storage unit 12 (see FIG. 3). Then, the second matching unit 16 can calculate a second matching score for each pair of the exiting vehicle and each entering vehicle.

[0062] For example, the second matching unit 16 calculates the similarity between the external appearance feature of the exiting vehicle and the external appearance feature of the entering vehicle. In this case, the second matching unit 16 can calculate a higher second matching score as the similarity increases.

[0063] As another example, the second matching unit 16 calculates the similarity between the appearance feature of the passenger in the exiting vehicle and the appearance feature of the passenger in the entering vehicle. In this case, the second matching unit 16 can calculate a higher second matching score as the similarity is higher.

[0064] As another example, the second matching unit 16 determines whether the identification information of the mobile terminal in the exit vehicle matches the identification information of the mobile terminal in the entry vehicle. In this case, the second matching unit 16 can calculate a second matching score that is higher when there is a match than when there is no match.

[0065] As another example, the second matching unit 16 may perform the second matching process based on more than one of the external appearance feature of the vehicle, the external appearance feature of the vehicle occupant, and the identification information of the mobile device in the vehicle. In this case, the second matching unit 16 can calculate the second matching score based on the same criteria as above.

[0066] If at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the above criteria, the second identification unit 17 identifies an entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process. An example of a process for identifying an entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process will be described below. The second identification unit 17 can execute, for example, the following first or second identification example.

[0067] -First specific example- The second identification unit 17 calculates a similarity score for each pair of an exiting vehicle and each entering vehicle stored in the storage unit 12 based on the first matching score, which is the result of the first matching process, and the reliability of the license plate information. information The similarity score is a value that comprehensively evaluates the reliability of the first matching score and the number plate information. There are various methods for calculating the similarity score, but the higher the first matching score and the higher the reliability of the number plate information, the higher the similarity score will be.

[0068] Then, the second identification unit 17 extracts the pair of entering vehicles whose similarity scores are equal to or greater than a threshold value as candidates for the same vehicle as the exiting vehicle. The threshold value of the similarity score indicates the lower limit of the similarity score that is allowed to be extracted as a candidate for the same vehicle as the exiting vehicle.

[0069] When one candidate is extracted, the second identifying unit 17 identifies the extracted entering vehicle as the same vehicle as the exiting vehicle.

[0070] On the other hand, when there are multiple extracted candidates, the second identification unit 17 identifies an entry vehicle that is the same as the exit vehicle from among the multiple extracted entry vehicles based on the result of the second matching process. For example, the second identification unit 17 can identify an entry vehicle with the highest second matching score among the multiple extracted entry vehicles as the same as the exit vehicle. In addition, the second identification unit 17 may identify an entry vehicle with the highest total matching score, which will be described in the second identification example below, among the multiple extracted entry vehicles as the same as the exit vehicle. In addition, the second identification unit 17 may identify, among the multiple extracted entry vehicles, "an entry vehicle in which at least one of the passengers of the exit vehicle was aboard" or "an entry vehicle in which at least one of the identification information of the mobile terminal detected from the exit vehicle was detected" as the same as the exit vehicle.

[0071] In addition, when there are multiple extracted candidates, the second identification unit 17 may identify an entering vehicle that is the same as the exiting vehicle from among the extracted multiple entering vehicles by the following process. First, the second identification unit 17 identifies "an entering vehicle for which at least one of the identification information of the mobile terminal detected from the exiting vehicle has been detected" as the same vehicle as the exiting vehicle. Then, when there is no entering vehicle that satisfies the condition among the extracted multiple candidates, the second identification unit 17 extracts an entering vehicle with the highest similarity and an entering vehicle with the second highest similarity from among the extracted multiple candidates based on the similarity between the external characteristic amount of the exiting vehicle and the external characteristic amount of each entering vehicle. Then, when the difference in similarity between the two extracted entering vehicles is equal to or greater than a certain value, the second identification unit 17 identifies the entering vehicle with the highest similarity as the same vehicle as the exiting vehicle. On the other hand, if the difference in similarity between the two extracted entering vehicles is less than a certain value, the second identification unit 17 extracts the entering vehicle with the highest similarity from the extracted candidates based on the similarity between the appearance features of the occupants of the exiting vehicle and the appearance features of the occupants of each entering vehicle.Then, the second identification unit 17 identifies the entering vehicle with the highest similarity as the same vehicle as the exiting vehicle.

[0072] -Second specific example- The second identification unit 17 calculates a total matching score for each pair of an exiting vehicle and each entering vehicle based on the first matching score and the second matching score. There are various methods for calculating the total matching score, but the higher the first matching score and the higher the second matching score, the higher the total matching score.

[0073] Then, the second identifying unit 17 identifies the entering vehicle of the pair having the highest total matching score as the same vehicle as the exiting vehicle of the pair.

[0074] Next, an example of the flow of processing by the processing device 10 will be described.

[0075] The flow of the process executed when the vehicle enters the facility is similar to that in the first embodiment.

[0076] The flow of the process executed when the vehicle enters the facility is shown in the first embodiment, the flowchart of Fig. 5. In S25, for example, the processing device 10 can execute the first or second specific example described above.

[0077] Here, an example of the process of S25 in the flowchart of Fig. 5 will be described with reference to the flowchart of Fig. 6. Specifically, the process flow of the first specific example described above will be described.

[0078] The processing device 10 calculates a similarity score for each pair of the exiting vehicle and each of the entering vehicles stored in the storage unit 12 based on the first matching score, which is the result of the first matching process in S21, and the reliability of the license plate information (S30). Then, the processing device 10 extracts the pair of entering vehicles whose similarity scores are equal to or greater than a threshold value as candidates for the same vehicle as the exiting vehicle (S31).

[0079] If one candidate is extracted ("one" in S32), the processing device 10 identifies the one extracted entering vehicle as the same vehicle as the exiting vehicle (S34).

[0080] On the other hand, when there are multiple extracted candidates ("multiple" in S32), the processing device 10 identifies an entering vehicle that is the same as the exit vehicle from among the multiple extracted entering vehicles based on the result of the second matching process (S33). For example, the processing device 10 can identify the entering vehicle with the highest second matching score among the multiple extracted entering vehicles as the same as the exit vehicle. In addition, the processing device 10 may identify the entering vehicle with the highest total matching score described in the second identification example among the multiple extracted entering vehicles as the same as the exit vehicle. In addition, the processing device 10 may identify "an entering vehicle in which at least one of the passengers of the exit vehicle was riding" or "an entering vehicle in which at least one of the identification information of the mobile terminal detected from the exit vehicle was detected" among the multiple extracted entering vehicles as the same as the exit vehicle.

[0081] Alternatively, the processing device 10 may execute the following process as the process of S33. First, the processing device 10 identifies "an entering vehicle in which at least one of the identification information of the mobile terminal detected from the exiting vehicle has been detected" as the same vehicle as the exiting vehicle. Then, if there is no entering vehicle that satisfies the condition among the extracted multiple candidates, the processing device 10 extracts an entering vehicle with the highest similarity and an entering vehicle with the second highest similarity from the extracted multiple candidates based on the similarity between the external characteristic amount of the exiting vehicle and the external characteristic amount of each entering vehicle. Then, if the difference in similarity between the two extracted entering vehicles is equal to or greater than a certain value, the processing device 10 identifies the entering vehicle with the highest similarity as the same vehicle as the exiting vehicle. On the other hand, if the difference in similarity between the two extracted entering vehicles is less than a certain value, the processing device 10 extracts an entering vehicle with the highest similarity from the extracted multiple candidates based on the similarity between the external characteristic amount of the passenger of the exiting vehicle and the external characteristic amount of the passenger of each entering vehicle. Then, the processing device 10 identifies the entering vehicle having the highest similarity as the same vehicle as the exiting vehicle.

[0082] Other configurations of the processing apparatus 10 of this embodiment are similar to those of the first embodiment.

[0083] According to the processing device 10 of this embodiment, the same action and effect as the first embodiment is realized. In addition, the processing device 10 of this embodiment can use at least one of the external characteristic amount of the vehicle, the external characteristic amount of the vehicle occupant, and the identification information of the mobile terminal present in the vehicle as complementary information for matching. By using such characteristic information as complementary information, the accuracy of identifying the correspondence between the entering vehicle and the exiting vehicle is improved.

[0084] Furthermore, the processing device 10 of this embodiment can perform matching using identification information of a mobile terminal present in a vehicle as complementary information. License plate information is acquired by image analysis, but identification information of a mobile terminal is acquired by a method different from image analysis, specifically, by short-range wireless communication with a mobile terminal. By performing matching using various information acquired by various methods, even if acquisition of a certain type of information does not go well, the failure can be compensated for based on other types of information that have been successfully acquired.

[0085] <Third embodiment> The processing device 10 of this embodiment further has a function of determining the amount to be charged, etc., based on entry information indicating the characteristics of the entry and exit information indicating the characteristics of the exit, after identifying the correspondence between entering vehicles and exiting vehicles.

[0086] 7 shows an example of a functional block diagram of the processing device 10 of this embodiment. As shown in the figure, the processing device 10 has an entrance processing unit 11, a memory unit 12, an exit acquisition unit 13, a first collation unit 14, a first identification unit 15, a second collation unit 16, a second identification unit 17, and a processing decision unit 18. Note that the processing device 10 does not need to have the memory unit 12. In this case, an external device configured to be able to communicate with the processing device 10 has the memory unit 12.

[0087] As shown in FIG. 8, the entry processing unit 11 associates the license plate information and complementary information of the entering vehicle with the entry information indicating the entry characteristics of the entering vehicle, and stores the associated information in the storage unit 12.

[0088] The entrance information includes at least one of entrance location information indicating the entrance location and entrance date and time information indicating the entrance date and time. When there are multiple entrances, such as a toll road, and it is necessary to manage which entrance the person entered through, the entrance location information is included in the entrance information. In addition, when it is necessary to manage the time spent within a facility, such as a parking lot, the entrance date and time information is included in the entrance information. Such entrance information is generated by identifying the gate through which the entering vehicle passed and the date and time of passage.

[0089] After an entering vehicle that is the same vehicle as the exiting vehicle is identified, the processing decision unit 18 decides the content of the processing to be performed on the vehicle based on the entry information of the identified entering vehicle and the exit information that indicates the exit characteristics of the exiting vehicle.

[0090] The exit information includes at least one of exit location information indicating the exit location and exit date and time information indicating the exit date and time. When there are multiple exits, such as a toll road, and it is necessary to manage which exit the vehicle exited from, the exit information includes the exit location information. Also, when it is necessary to manage the time spent within a facility, such as a parking lot, the exit information includes the exit date and time information. Such exit information is generated by identifying the gate through which the exiting vehicle passed and the date and time of passage.

[0091] The processing decision unit 18 may determine the billing amount based on, for example, the entry position indicated by the entry information and the exit position indicated by the exit information. The processing device 10 may use any conventional technology to identify other attribute information such as the type and weight of the entering and exiting vehicles. The processing decision unit 18 may then determine the billing amount by taking into consideration the entry position indicated by the entry information and the exit position indicated by the exit information as well as the above vehicle attribute information. The billing amount is determined by using any technology, such as by referring to a table showing the relationship between the entry and exit positions and the billing amount.

[0092] Additionally, the processing decision unit 18 may determine the billing amount based on, for example, the entry date and time indicated in the entry information and the exit date and time indicated in the exit information. The processing device 10 may use any conventional technology to identify other attribute information such as the type and weight of the entering and exiting vehicles. The processing decision unit 18 may then determine the billing amount by taking into consideration the entry date and time indicated in the entry information and the exit date and time indicated in the exit information as well as the vehicle attribute information. The billing amount is determined by using any technology, such as by referring to a table showing the relationship between the stay time and the billing amount.

[0093] Thereafter, a request for payment of the determined billing amount, a settlement process for the determined billing amount, etc. may be performed by any means. For example, credit card information may be registered in advance in the processing device 10 in association with the license plate information of the vehicle. The processing device 10 may then use the credit card information to perform a settlement process for the determined billing amount.

[0094] In addition, the destination of the invoice (user's name, address, e-mail address, etc.) may be registered in association with the license plate information of the vehicle. Then, an invoice for payment of the determined invoice amount may be sent to the user by mail, e-mail, etc.

[0095] Other configurations of the processing apparatus 10 of this embodiment are similar to those of the first and second embodiments. According to the processing apparatus 10 of this embodiment, the same effects as those of the first and second embodiments are achieved.

[0096] <Fourth embodiment> The processing device 10 of this embodiment, like the first to third embodiments, identifies the correspondence between entering and exiting vehicles by a matching process based on the license plate information and the complementary information. However, the processing device 10 of this embodiment differs from the first to third embodiments in the flow of the matching process based on the license plate information and the complementary information.

[0097] The flow of the process executed when the vehicle enters the facility is similar to that in the first to third embodiments.

[0098] Next, the flow of the process executed when the vehicle exits the facility will be described with reference to the flowchart of FIG.

[0099] The processing device 10 acquires the license plate information and complementary information of the exiting vehicle (S40). For example, the acquisition of the license plate information and complementary information of the exiting vehicle by the processing device 10 is realized by analyzing an image generated by a camera installed at an exit gate or the like through which the exiting vehicle passes, or by communication between a short-range wireless communication device installed at the exit gate or the like and a mobile terminal present in the exiting vehicle.

[0100] Next, the processing device 10 executes a first matching process to match the license plate information of the exiting vehicle with the license plate information of each entering vehicle registered in the entering vehicle information stored in the memory unit 12 (S41). The processing device 10 also executes a second matching process to match the complementary information of the exiting vehicle with the complementary information of each entering vehicle registered in the entering vehicle information stored in the memory unit 12 (S42). Note that the processing order of S41 and S42 is not limited to this. Details of the first matching process and the second matching process are the same as those of the first and second embodiments.

[0101] Thereafter, the processing device 10 identifies an entering vehicle that is the same as the exiting vehicle based on the result of the first matching process in S41 and the result of the second matching process in S42 (S43). 5 In other words, in S43, the processing device 10 2 The first or second specific example described in the embodiment can be implemented.

[0102] Other configurations of the processing apparatus 10 of this embodiment are similar to those of the first and second embodiments.

[0103] The processing device 10 of this embodiment identifies the correspondence between entering and exiting vehicles by a matching process based on the license plate information and the complementary information. By using not only the license plate information but also other complementary information, the accuracy of identifying the correspondence between entering and exiting vehicles is improved.

[0104] In addition, the processing device 10 of the present embodiment can use at least one of the following as complementary information: the external appearance characteristic amount of the vehicle, the external appearance characteristic amount of the vehicle occupant, and the identification information of the mobile terminal present in the vehicle. By using such characteristic information as complementary information, the accuracy of identifying the correspondence between the entering vehicle and the exiting vehicle is improved.

[0105] Furthermore, the processing device 10 of this embodiment can perform matching using identification information of a mobile terminal present in a vehicle as complementary information. License plate information is acquired by image analysis, but identification information of a mobile terminal is acquired by a method different from image analysis, specifically, by short-range wireless communication with a mobile terminal. By performing matching using various information acquired by various methods, even if acquisition of a certain type of information does not go well, the failure can be compensated for based on other types of information that have been successfully acquired.

[0106] In this specification, "acquisition" includes at least one of the following: "the device itself goes to retrieve data stored in another device or storage medium (active acquisition)" based on user input or based on program instructions, such as receiving data by making a request or inquiry to another device, or accessing another device or storage medium and reading it, and "the device itself inputs data output from another device (passive acquisition)" based on user input or based on program instructions, such as receiving data that is distributed (or transmitted, push notification, etc.), and selecting and acquiring data from among the received data or information, and "editing data (converting it to text, rearranging data, extracting some data, changing the file format, etc.) to create new data and acquire the new data."

[0107] A part or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes. 1. An entrance processing means for acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in association with each other; An exit acquisition means for acquiring the license plate information and the complementary information of an exiting vehicle; A first matching means for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification means for identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching means for performing a second matching process to match the complementary information of the exiting vehicle with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; a second identification means for identifying the entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; A processing device having 2. The processing device according to claim 1, wherein the complementary information is identification information of a mobile terminal obtained from the mobile terminal present in a vehicle passing through a specified position. 3. A processing device according to 1 or 2, wherein the complementary information is a feature of the vehicle's appearance. 4. A processing device according to any one of 1 to 3, wherein the complementary information is a feature of the appearance of a vehicle occupant. 5. The second specifying means Calculating a similarity score between the exiting vehicle and each of the entering vehicles stored in the memory unit based on a result of the first matching process and the reliability of the license plate information; extracting the entering vehicle having the similarity score equal to or greater than a threshold as a candidate for the same vehicle as the exiting vehicle; If there is one extracted candidate, the extracted one entering vehicle is identified as the same vehicle as the exiting vehicle; A processing device described in any one of 1 to 4, which, when there are multiple extracted candidates, identifies the entering vehicle that is the same as the exiting vehicle from among the multiple extracted entering vehicles based on the result of the second matching process. 6. The entry processing means links the license plate information and the complementary information to entry information indicating the entry characteristics of the entering vehicle and stores the linked information in the storage unit; A processing device as described in any one of 1 to 5, further having a processing determination means for determining the content of processing to be performed on the vehicle based on the entry information of the identified entering vehicle and exit information indicating the exit characteristics of the exiting vehicle after the entering vehicle is identified, which is the same vehicle as the exiting vehicle. 7. The entry information indicates an entry position, and the exit information indicates an exit position; 7. The processing device according to claim 6, wherein the processing determination means determines the amount to be charged based on the entry location and the exit location. 8. The entry information indicates the entry date and time, and the exit information indicates the exit date and time, 7. The processing device according to claim 6, wherein the processing determination means determines the amount to be charged based on the entry date and time and the exit date and time. 9. The computer: an entry processing step of acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in association with each other; An exit acquisition process for acquiring the license plate information and the complementary information of an exiting vehicle; A first matching process for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification step of identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching process for performing a second matching process in which the complementary information of the exiting vehicle is matched with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; a second identification process for identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; The processing method to be performed. 10. Computer an entrance processing means for acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in a linked manner; An exit acquisition means for acquiring the license plate information and the complementary information of an exiting vehicle; a first matching means for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification means for identifying the entering vehicle that is the same as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching means for performing a second matching process to match the complementary information of the exiting vehicle with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; and a second identification means for identifying the entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; A program that functions as a

[0108] This application claims priority based on Japanese Patent Application No. 2021-095759, filed on June 8, 2021, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0109] 10 Processing equipment 11 Admissions Processing Section 12 Storage section 13 Ejection Obtaining Department 14 First collation section 15 First Specific Part 16 Second Collation Unit 17 Second Specific Part 18 Processing decision unit 1A Processor 2A Memory 3A input / output I / F 4A Peripheral circuit 5A Bus

Claims

1. an entrance processing means for acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in association with each other; An exit acquisition means for acquiring the license plate information and the complementary information of an exiting vehicle; a first matching means for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification means for identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching means for performing a second matching process to match the complementary information of the exiting vehicle with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; a second identification means for identifying the entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; A processing device having

2. The processing device according to claim 1 , wherein the complementary information is identification information of a mobile terminal that is present in a vehicle passing through a predetermined position and that is acquired from the mobile terminal.

3. The processing device according to claim 1 , wherein the complementary information is a feature quantity of an external appearance of the vehicle.

4. The processing device according to claim 1 , wherein the complementary information is an external appearance feature of a vehicle occupant.

5. The second identification means includes: Calculating a similarity score between the exiting vehicle and each of the entering vehicles stored in the memory unit based on a result of the first matching process and the reliability of the license plate information; extracting the entering vehicle having the similarity score equal to or greater than a threshold as a candidate for the same vehicle as the exiting vehicle; If there is one extracted candidate, the extracted one entering vehicle is identified as the same vehicle as the exiting vehicle; A processing device described in any one of claims 1 to 4, when there are multiple extracted candidates, based on the result of the second matching process, identifies an entering vehicle that is the same vehicle as the exiting vehicle from among the multiple extracted entering vehicles.

6. The entry processing means associates the license plate information and the complementary information with entry information indicating the entry characteristics of the entering vehicle and stores the associated information in the storage unit, A processing device as described in any one of claims 1 to 5, further comprising a processing determination means for determining the content of processing to be performed on the vehicle based on the entry information of the identified entering vehicle and exit information indicating the exit characteristics of the exiting vehicle after the entering vehicle which is the same vehicle as the exiting vehicle is identified.

7. The entry information indicates an entry position, and the exit information indicates an exit position, 7. The processing device according to claim 6, wherein said processing determining means determines a charge amount based on said entrance position and said exit position.

8. The entry information indicates an entry date and time, and the exit information indicates an exit date and time, The processing device according to claim 6 , wherein the processing determining means determines a charge amount based on the entry date and time and the exit date and time.

9. The computer an entry processing step of acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in association with each other; An exit acquisition process for acquiring the license plate information and the complementary information of an exiting vehicle; A first matching process for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification step of identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching process for performing a second matching process in which the complementary information of the exiting vehicle is matched with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; a second identification process for identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; The processing method to be performed.

10. Computer, an entrance processing means for acquiring license plate information of an entering vehicle and complementary information related to the entering vehicle, and storing the license plate information and the complementary information in a storage unit in a linked manner; An exit acquisition means for acquiring the license plate information and the complementary information of an exiting vehicle; a first matching means for performing a first matching process for matching the license plate information of the exiting vehicle with the license plate information of the entering vehicle stored in the storage unit; a first identification means for identifying the entering vehicle that is the same vehicle as the exiting vehicle based on the result of the first matching process when both the result of the first matching process and the reliability of the license plate information satisfy a criterion; a second matching means for performing a second matching process of matching the complementary information of the exiting vehicle with the complementary information of the entering vehicle stored in the storage unit when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; and a second identification means for identifying the entering vehicle that is the same as the exiting vehicle based on the result of the first matching process and the result of the second matching process when at least one of the result of the first matching process and the reliability of the license plate information does not satisfy the criterion; A program that functions as a

Images