Vehicle information acquisition system, vehicle information acquisition method, and computer program

Abstract

To provide a vehicle information acquisition system that can acquire accurate information on a vehicle.SOLUTION: A vehicle information acquisition system comprises: a plate information acquisition unit that acquires license plate information including information indicated on a license plate of a vehicle; a vehicle model information acquisition unit that acquires vehicle model information for the vehicle; an accuracy acquisition unit that acquires an accuracy of each of the license plate information and the vehicle model information; and a correction unit that, using high accuracy information which is either information of the license plate information and the vehicle model information that is relatively higher in the accuracy, corrects low accuracy information, which is information relatively lower in the accuracy by .SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present disclosure relates to a vehicle information acquisition system, a vehicle information acquisition method, and a computer program.

Background Art

[0002] Conventionally, a vehicle type identification device has been proposed that identifies the vehicle type of a vehicle existing in a captured image from a captured image by a camera (see, for example, Patent Document 1).

[0003] In the vehicle type identification device described in Patent Document 1, feature amounts of components such as headlamps, front grills, bumpers, etc. are calculated from an image, and the vehicle type of the vehicle is identified based on the calculated component feature amounts.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the component feature amounts registered in the vehicle type identification device are the feature amounts of genuine parts. For this reason, in the case of a vehicle equipped with third-party exterior option parts or a modified vehicle, etc., where parts other than genuine parts are equipped, the vehicle type may not be accurately identified. Also, since the component feature amounts of vehicles of different vehicle types with similar appearances are also similar, the vehicle type may not be accurately identified in some cases. Thus, according to the conventional vehicle type identification device, there is a possibility that accurate vehicle information cannot be obtained.

[0006] [[ID=​​​

[0007] A vehicle information acquisition system according to one aspect of the present disclosure includes: a plate information acquisition unit that acquires license plate information including information written on the license plate of a vehicle; a vehicle type information acquisition unit that acquires vehicle type information of the vehicle; an accuracy acquisition unit that acquires the accuracy of the license plate information and the vehicle type information, respectively; and a correction unit that corrects low-accuracy information, which is information with a relatively low accuracy, using high-accuracy information, which is information with a relatively high accuracy, from among the license plate information and the vehicle type information.

[0008] A vehicle information acquisition method according to another aspect of the present disclosure is a vehicle information acquisition method performed by a vehicle information acquisition system, comprising the steps of: acquiring license plate information including information inscribed on the license plate of a vehicle; acquiring vehicle type information of the vehicle; acquiring the accuracy of each of the license plate information and the vehicle type information; and correcting low-accuracy information, which is information with a relatively low accuracy, using high-accuracy information, which is information with a relatively high accuracy, from among the license plate information and the vehicle type information.

[0009] A computer program according to another aspect of the present disclosure causes the computer to function as a plate information acquisition unit that acquires license plate information including information written on the license plate of a vehicle, a vehicle type information acquisition unit that acquires vehicle type information, an accuracy acquisition unit that acquires the accuracy of the license plate information and the vehicle type information, and a correction unit that corrects low-accuracy information, which is information with a relatively low accuracy, using high-accuracy information, which is information with a relatively high accuracy, from among the license plate information and the vehicle type information.

[0010] Furthermore, this disclosure can also be implemented as a computer program for causing a computer to execute characteristic steps included in the vehicle information acquisition method. Needless to say, such a computer program can be distributed via computer-readable non-temporary recording media such as CD-ROMs (Compact Disc-Read Only Memory) or communication networks such as the Internet. Additionally, this disclosure can be implemented as a semiconductor integrated circuit that implements part or all of the vehicle information acquisition system. [Effects of the Invention]

[0011] According to this disclosure, accurate vehicle information can be obtained. [Brief explanation of the drawing]

[0012] [Figure 1] Figure 1 is a block diagram showing the configuration of a vehicle information acquisition system according to an embodiment of this disclosure. [Figure 2] Figure 2 shows an example of license plate correspondence table information. [Figure 3] Figure 3 shows an example of vehicle type correspondence table information. [Figure 4] Figure 4 shows an example of trend information. [Figure 5] Figure 5 shows another example of trend information. [Figure 6] Figure 6 is a diagram illustrating an example of the vehicle information correction process performed by the correction unit. [Figure 7] Figure 7 shows an example of candidate vehicle information corresponding to the vehicle category "regular passenger car" after replacement. [Figure 8] Figure 8 is a diagram illustrating an example of the license plate information correction process performed by the correction unit. [Figure 9] Figure 9 shows an example of candidate license plate information corresponding to the vehicle category "regular passenger car" after replacement. [Figure 10]FIG. 10 is a flowchart showing an example of a processing procedure of a vehicle information acquisition device according to an embodiment of the present disclosure. [Figure 11] FIG. 11 is a flowchart showing details of the matching process (step S6 in FIG. 10). [Figure 12] FIG. 12 is a flowchart showing details of the correction process (step S15 in FIG. 11). [Figure 13] FIG. 13 is a diagram showing a plurality of license plate information acquired by a license plate information acquisition unit and vehicle type classification information corresponding to the license plate information. [Figure 14] FIG. 14 is a diagram showing a plurality of vehicle type information acquired by a vehicle type information acquisition unit and vehicle type classification information corresponding to the vehicle type information.

MODE FOR CARRYING OUT THE INVENTION

[0013] [Summary of Embodiment of the Present Disclosure] First, the summary of the embodiment of the present disclosure will be listed and described. (1) A vehicle information acquisition system according to an embodiment of the present disclosure includes a license plate information acquisition unit that acquires license plate information including information described on a license plate of a vehicle, a vehicle type information acquisition unit that acquires vehicle type information of the vehicle, a accuracy acquisition unit that acquires the accuracy of each of the license plate information and the vehicle type information, and a correction unit that corrects low-accuracy information, which is information with a relatively low accuracy, using high-accuracy information, which is information with a relatively high accuracy, among the license plate information and the vehicle type information.

[0014] According to this configuration, by correcting the low-accuracy information using the high-accuracy information, incorrect information included in the low-accuracy information can be corrected to correct information. Thereby, accurate vehicle information can be acquired.

[0015] (2) The correction unit may correct the low-accuracy information based on a vehicle type classification corresponding to the high-accuracy information.

[0016] For identical vehicles, the vehicle classification corresponding to the license plate information and the vehicle classification corresponding to the vehicle classification must be the same. This configuration allows for the correction of either the license plate information or vehicle classification based on the consistent vehicle classification if they differ. This ensures that the license plate information or vehicle classification is corrected to accurate information.

[0017] (3) The correction unit may also correct the low-accuracy information based on trend information indicating the appearance tendency of at least one of the license plate information and the vehicle type information.

[0018] This configuration allows for correction of low-accuracy information by considering the occurrence trends of license plate information or vehicle type information. Therefore, low-accuracy information can be corrected more accurately.

[0019] (4) Furthermore, if multiple low-accuracy pieces of information have been acquired, the correction unit may select the low-accuracy piece of information with the highest accuracy corresponding to the vehicle type category corresponding to the high-accuracy piece of information from among the multiple low-accuracy pieces of information as the corrected low-accuracy piece of information.

[0020] This configuration allows for the selection of the most accurate low-reliability information corresponding to the correct vehicle classification from among multiple low-reliability data points. Therefore, the selected low-reliability information is accurate.

[0021] (5) Furthermore, if multiple low-accuracy information records have been acquired, the correction unit may select one of the acquired low-accuracy information records as the corrected low-accuracy information record based on trend information indicating the appearance tendency of at least one of the license plate information and the vehicle type information.

[0022] This configuration allows for the selection of the correct low-probability information from among multiple low-probability data sources, taking into account the occurrence trends of license plate information or vehicle type information. Therefore, more accurate low-probability information can be selected.

[0023] (6) The accuracy acquisition unit may also calculate the accuracy of the license plate information and the vehicle type information based on trend information that indicates the appearance tendency of at least one of the license plate information and the vehicle type information.

[0024] This configuration allows for the calculation of accuracy that takes into account the occurrence trends of license plate information or vehicle type information. Therefore, by considering the occurrence trends, it is possible to correct erroneous information contained in low-accuracy information into correct information.

[0025] (7) Furthermore, the correction unit does not need to correct the low-accuracy information if the accuracy of the license plate information and the vehicle type information is below the lower threshold.

[0026] This configuration allows for avoiding correction of low-accuracy information by discarding both license plate and vehicle type information if their reliability is low. This prevents unnecessary correction processing.

[0027] (8) The above-described vehicle information acquisition system may further include a determination unit that determines that the vehicle is a modified vehicle or a vehicle with a replaced license plate when the accuracy of the license plate information and the vehicle type information are above an upper threshold and the vehicle type classification indicated by the license plate information and the vehicle type information are different.

[0028] It is unlikely that the vehicle classification would differ from that of a vehicle, even if both the license plate information and the vehicle type information are highly reliable. Therefore, in such cases, it can be concluded that some kind of alteration has been made to the vehicle or license plate that changed its vehicle classification.

[0029] (9) The above-described vehicle information acquisition system may further include an output unit that outputs the judgment result of the judgment unit.

[0030] This configuration allows for the detection of a vehicle that has undergone some modification, such as changing its vehicle classification, and enables notification to users of the vehicle information acquisition system.

[0031] (10) The above-described vehicle information acquisition system may further include an output unit that outputs at least one of the high-accuracy information and the corrected low-accuracy information.

[0032] This configuration allows for the notification of corrected license plate information or vehicle information to users of the vehicle information acquisition system.

[0033] (11) A vehicle information acquisition method according to another embodiment of the present disclosure is a vehicle information acquisition method performed by a vehicle information acquisition system, comprising the steps of: acquiring license plate information including information written on the license plate of a vehicle; acquiring vehicle type information of the vehicle; acquiring the accuracy of each of the license plate information and the vehicle type information; and correcting low-accuracy information, which is information with a relatively low accuracy, using high-accuracy information, which is information with a relatively high accuracy, from among the license plate information and the vehicle type information.

[0034] This configuration includes the characteristic processing steps of the vehicle information acquisition system described above. Therefore, this configuration can achieve the same functions and effects as the vehicle information acquisition system described above.

[0035] (12) Computer programs according to other embodiments of the present disclosure cause the computer to function as a plate information acquisition unit that acquires license plate information including information written on the license plate of a vehicle, a vehicle type information acquisition unit that acquires vehicle type information, an accuracy acquisition unit that acquires the accuracy of the license plate information and the vehicle type information, and a correction unit that corrects low accuracy information, which is information with a relatively low accuracy, using high accuracy information, which is information with a relatively high accuracy, from among the license plate information and the vehicle type information.

[0036] This configuration allows the computer to function as the vehicle information acquisition system described above. Therefore, it can achieve the same functions and effects as the vehicle information acquisition system described above.

[0037] [Details of the embodiments of this disclosure] The embodiments of this disclosure will be described below with reference to the drawings. The embodiments described below are all specific examples of this disclosure. The numerical values, shapes, materials, components, arrangement and connection configurations of components, steps, and the order of steps shown in the following embodiments are examples and do not limit this disclosure. Furthermore, components in the following embodiments that are not described in the independent claims are optional components that can be added. Also, the figures are schematic diagrams and do not necessarily represent the exact details.

[0038] Furthermore, identical components will be assigned the same symbols. Since their functions and names are also identical, their explanations will be omitted as appropriate.

[0039] [Overall configuration of the vehicle information acquisition system] Figure 1 is a block diagram showing the configuration of a vehicle information acquisition system according to an embodiment of this disclosure. The vehicle information acquisition system 100 is a system for acquiring at least one of the following information about a vehicle (automobile): license plate information, vehicle type information, and vehicle type classification information. It comprises a vehicle information acquisition device 1, a camera 2, a camera 3, and a display device 4.

[0040] The vehicle information acquisition system 100 can be used, for example, for parking lot management or travel time calculation. For example, the vehicle information acquisition system 100 can be used to detect vehicles parked in the wrong location in a parking lot where parking spaces are designated for each vehicle type. The vehicle information acquisition system 100 can also be used to calculate the travel time of vehicles for each vehicle type or vehicle type category.

[0041] Cameras 2 and 3 are installed, for example, in a parking lot or on the roadside, to photograph moving vehicles. Preferably, cameras 2 and 3 are capable of capturing color images. Cameras 2 and 3 may also be the same camera. In other words, camera 3 may not be provided, and the image captured by camera 2 may be input to both the plate information acquisition unit 11 and the vehicle type information acquisition unit 12, which will be described later.

[0042] The vehicle information acquisition device 1 is connected to cameras 2 and 3 and acquires at least one of the vehicle's license plate information, vehicle type information, and vehicle type classification information based on the vehicle images captured by cameras 2 and 3, respectively. The vehicle information acquisition device 1 may be installed inside camera 2 or camera 3, or it may be connected to camera 2 or camera 3 via a communication network.

[0043] The display device 4 consists of a display device such as a liquid crystal display or an organic EL (electroluminescence) display. The display device 4 is connected to the vehicle information acquisition device 1 and displays at least one of the license plate information, vehicle type information, and vehicle type classification information acquired by the vehicle information acquisition device 1. The display device 4 may also display various processing results of the vehicle information acquisition device 1. The installation location of the display device 4 is not limited. For example, the display device 4 may be installed near the vehicle information acquisition device 1, or it may be installed in a location far from the vehicle information acquisition device 1 via a network.

[0044] The vehicle information acquisition device 1 is configured, for example, with a general-purpose computer and comprises a control unit 10 and a storage unit 20.

[0045] The storage unit 20 is composed of memory such as ROM (Read Only Memory), RAM (Random Access Memory), and HDD (Hard Disk Drive), and stores the computer program 21, license plate correspondence table information 22, vehicle type correspondence table information 23, and trend information 24. The storage unit 20 also stores temporary data from processing by the control unit 10.

[0046] Figure 2 shows an example of the license plate correspondence table information 22. The license plate correspondence table information 22 is table information that shows the correspondence between license plate information obtained from license plates attached to vehicles and vehicle type classification information. The license plate correspondence table information 22 is information that is uniquely determined based on laws and regulations.

[0047] License plate information includes, for example, the classification number, plate size, purpose (commercial / private), and plate color. The classification number is a one- to three-digit number on the license plate that indicates the type of vehicle.

[0048] The plate size refers to the size of the license plate, which comes in three sizes: large, medium, and small.

[0049] The intended use (commercial / private) is determined by the color scheme of the license plate and lettering. For example, commercial vehicles have white lettering on a green background, or yellow lettering on a black background, while private vehicles have green lettering on a white background, or black lettering on a yellow background. The plate color refers to the background color of the license plate and includes green, white, black, and yellow backgrounds.

[0050] Vehicle classification information indicates the type of vehicle as defined by law, and includes large trucks, medium-sized trucks, light trucks, large buses, medium-sized buses, passenger cars, light vehicles, special vehicles, large special vehicles, large special vehicles (construction), and small motorcycles.

[0051] According to the license plate correspondence table information 22, for example, a vehicle with a license plate whose classification number is in the range of "1, 10-19, 100-199", whose plate size is "large", whose purpose (commercial / private) is "commercial", and whose plate color is "green" is classified as a "large truck".

[0052] Figure 3 shows an example of the vehicle type correspondence table information 23. The vehicle type correspondence table information 23 is a table that shows the correspondence between vehicle type information and vehicle type classification information. The vehicle type correspondence table information 23 is uniquely determined for each vehicle type.

[0053] Vehicle information includes the name of the manufacturer and the vehicle's common name. For example, the manufacturer name "I" and the common name "Q" represent one vehicle model. Vehicle classification information is the same as that of the license plate correspondence table information 22.

[0054] According to the license plate correspondence table information 22, for example, a vehicle whose manufacturer name is "I" and whose common name is "Q" is classified as a "large truck".

[0055] Figure 4 shows an example of trend information 24. Trend information 24 is information that shows the appearance trend of at least one of the license plate information and vehicle type information. Referring to Figure 4, trend information 24 includes environmental conditions, license plate information, and vehicle type information. Trend information 24 shows combinations of license plate information and vehicle type information that frequently occur under given environmental conditions.

[0056] Environmental conditions include location, time of day, and weather. Location is the point where the vehicle is traveling. Time of day is the time of day the vehicle is traveling. Weather is the weather at the time the vehicle is traveling, including, for example, sunny, rainy, and snowy.

[0057] License plate information includes the serial number, the land transport bureau, the classification number, the purpose (in hiragana), and the purpose (commercial / private use).

[0058] The classification number and intended use (commercial / private) are as described above. The serial number is the four-digit number written in large numbers on the license plate. The Land Transport Bureau indicates the location of the Land Transport Bureau that issued the license plate. The intended use (in hiragana) is the hiragana character representing the vehicle's purpose (e.g., private, rental car, commercial).

[0059] In trend information 24, "*" indicates any information. For example, if "*" is used for time of day, it indicates that any time of day within the 24-hour period is acceptable. If "*" is used for weather, it indicates that any weather condition is acceptable. Classification number "3*" indicates any number starting with 3.

[0060] According to trend information 24, for example, on National Route X, during the sunny hours of 6:00-12:00, there is a tendency for many T-company vehicles with license plates whose classification number starts with 3 and whose Land Transport Bureau is "Naniwa". Also, on National Route X, during the snowy hours of 6:00-12:00, there is a tendency for many snowplows with license plates whose classification number starts with 9 to be on the road.

[0061] Figure 5 shows another example of trend information 24. Referring to Figure 5, trend information 24 includes license plate information, vehicle type information, and remarks information. The trend information 24 shown in Figure 5 shows frequently occurring combinations of license plate information and vehicle type information. The license plate information and vehicle type information are the same as those shown in Figure 4. The remarks section indicates the conditions under which license plate information and vehicle type information frequently appear. According to trend information 24, for example, a vehicle manufactured by Company T with the common name "C" that has a classification number starting with 3, a usage (in hiragana) of "i", and a license plate indicating usage (commercial / private) as "commercial" is a vehicle commonly used as a taxi.

[0062] Referring again to Figure 1, the control unit 10 is composed of a processor such as a CPU (Central Processing Unit) and includes a plate information acquisition unit 11, a vehicle type information acquisition unit 12, an accuracy acquisition unit 13, a correction unit 14, a judgment unit 15, and an output unit 16.

[0063] Each processing unit 11 to 16 is functionally realized when the control unit 10 executes the computer program 21 stored in the memory unit 20.

[0064] The plate information acquisition unit 11 acquires license plate information derived from the license plate installed on the vehicle by applying predetermined image processing to the image of the vehicle captured by the camera 2.

[0065] License plate information includes the information inscribed on the license plate. This includes, for example, the vehicle registration number (or vehicle number), the plate size, and the purpose of use (commercial / private). Hereafter, the vehicle number will also be referred to as the vehicle registration number.

[0066] The vehicle registration number is the letters or numbers inscribed on the license plate, and includes the serial number, the land transport bureau, the classification number, and the purpose (in hiragana). Each of these is explained above. The plate size and intended use (commercial / private) are as described above.

[0067] The plate information acquisition unit 11, for example, detects the license plate from the vehicle's video footage and obtains the vehicle registration number by performing character recognition processing on the license plate. Known methods can be used for the license plate detection and character recognition processing. For example, the plate information acquisition unit 11 may perform license plate detection or character recognition by performing template matching with a predetermined model image. Alternatively, the plate information acquisition unit 11 may detect the license plate by inputting the image captured by camera 2 into a machine learning model that has been trained using images of license plates as training data. Furthermore, the plate information acquisition unit 11 may recognize the vehicle registration number contained in the license plate by inputting the detected license plate image into a machine learning model that has been trained using images of characters or numbers as training data.

[0068] Furthermore, the plate information acquisition unit 11 detects the size of the license plate from the detection results of the license plate detection process described above. For example, the plate information acquisition unit 11 may determine whether the license plate is large, medium, or small by performing threshold processing on the size of the license plate in the image.

[0069] Furthermore, the plate information acquisition unit 11 may determine the vehicle's purpose (commercial / private) by determining the plate color and character color of the license plate through image processing. The plate information acquisition unit 11 may also determine the color by, for example, thresholding the RGB values ​​of each pixel constituting the image.

[0070] Note that the appearance of license plates may change depending on the time of day and weather. For this reason, model images, learning models, or thresholds may be prepared for each time of day or weather condition. The plate information acquisition unit 11 acquires license plate information using the model image, learning model, or threshold corresponding to the time of day or weather condition to be determined.

[0071] The vehicle information acquisition unit 12 acquires vehicle information by applying predetermined image processing to the vehicle image captured by the camera 3. Vehicle information includes, for example, the name of the manufacturer that produced the vehicle and the vehicle's common name.

[0072] The image processing method is not limited, and vehicle type can be recognized using known methods. For example, the vehicle type information acquisition unit 12 extracts four features from the image of the vehicle captured by the camera 3: vehicle size, color, bumper shape, and headlight shape. The vehicle type information acquisition unit 12 calculates the similarity between the extracted set of four features and the set of four features of vehicles pre-registered for each vehicle type. Specifically, it calculates the similarity between each extracted feature and the pre-registered feature, and then weights and adds the four calculated similarities. The vehicle type information acquisition unit 12 determines that the vehicle with the highest weighted sum is the vehicle type included in the image. Note that the four features mentioned above are just examples, and other features may be included, or any of the four features may be omitted.

[0073] Note that the appearance of a vehicle may change depending on the time of day or weather. For this reason, similarity weights may be prepared for each time of day or weather condition. For example, the vehicle information acquisition unit 12 may weight and add the four extracted similarity values ​​using similarity weights corresponding to the time of day or weather condition being judged.

[0074] The accuracy acquisition unit 13 acquires the accuracy of license plate information from the plate information acquisition unit 11 and the accuracy of vehicle information from the vehicle information acquisition unit 12.

[0075] For example, the accuracy acquisition unit 13 acquires the result (similarity) of template matching performed by the plate information acquisition unit 11 as character recognition processing as the accuracy of the license plate information. Alternatively, the accuracy acquisition unit 13 may acquire the confidence level of the recognition result obtained from the learning model as the accuracy when the plate information acquisition unit 11 inputs an image into the learning model as character recognition processing.

[0076] Specifically, the accuracy acquisition unit 13 acquires the accuracy of the serial number, land transport bureau, classification number, and purpose (in hiragana) from the vehicle information acquisition unit 12, and calculates the accuracy of the license plate information by weighting and adding the multiple accuracy values ​​acquired. The accuracy acquisition unit 13 further normalizes the accuracy of the license plate information to a value in the range of 0 to 100.

[0077] Alternatively, the accuracy acquisition unit 13 may acquire the similarity of the set of feature quantities calculated by the vehicle information acquisition unit 12 as the accuracy of the vehicle information.

[0078] Specifically, the accuracy acquisition unit 13 obtains a value obtained by weighting and summing the four similarity scores calculated by the vehicle information acquisition unit 12 as the accuracy of the vehicle information. The accuracy acquisition unit 13 further normalizes the accuracy of the vehicle information to a value in the range of 0 to 100.

[0079] The correction unit 14 corrects the low-accuracy information, which is information with a relatively low accuracy, using the high-accuracy information, which is information with a relatively high accuracy, obtained by the accuracy acquisition unit 13, from among the license plate information acquired by the plate information acquisition unit 11 and the vehicle information acquired by the vehicle information acquisition unit 12.

[0080] (1. High-probability information: License plate information; Low-probability information: Vehicle type information) First, we will explain the processing of the correction unit 14 when the accuracy of the license plate information is higher than the accuracy of the vehicle information.

[0081] The correction unit 14 acquires license plate information from the plate information acquisition unit 11, vehicle type information from the vehicle type information acquisition unit 12, and the accuracy of the license plate information and the accuracy of the vehicle type information from the accuracy acquisition unit 13. The correction unit 14 also identifies the vehicle type corresponding to the acquired license plate information based on the license plate correspondence table information 22. Furthermore, the correction unit 14 identifies the vehicle type corresponding to the acquired vehicle type information based on the vehicle type correspondence table information 23.

[0082] Figure 6 is a diagram illustrating an example of the vehicle type information correction process performed by the correction unit 14. Figure 6(A) shows the license plate information acquired by the correction unit 14 from the license plate information acquisition unit 11, the vehicle type classification corresponding to the license plate information identified by the correction unit 14, and the accuracy of the license plate information acquired by the correction unit 14 from the accuracy acquisition unit 13.

[0083] For example, the license plate information obtained from the plate information acquisition unit 11 includes the serial number "12-34", the land transport bureau "Naniwa", the classification number "330", the purpose (in hiragana) "sa", the plate size "medium", and the purpose (commercial / private) "private".

[0084] The correction unit 14 refers to the license plate correspondence table information 22 shown in Figure 2 and identifies the vehicle type "ordinary automobile" from the license plate information, which corresponds to the classification number "330", plate size "medium", and usage (commercial / private) "private", as the vehicle type corresponding to the license plate information. Furthermore, the accuracy of the license plate information acquired by the correction unit 14 from the accuracy acquisition unit 13 is "90".

[0085] Figure 6(B) shows the vehicle information acquired by the correction unit 14 from the vehicle information acquisition unit 12, the vehicle category corresponding to the vehicle information identified by the correction unit 14, and the accuracy of the vehicle information acquired by the correction unit 14 from the accuracy acquisition unit 13. For example, the vehicle information obtained from the vehicle information acquisition unit 12 includes the manufacturer name "I" and the common name "G".

[0086] The correction unit 14 refers to the vehicle type correspondence table information 23 shown in Figure 3 and identifies the vehicle type category "large truck" corresponding to the manufacturer name "I" and common name "G" as the vehicle type category corresponding to the vehicle type information. Furthermore, the accuracy of the vehicle information acquired by the correction unit 14 from the accuracy acquisition unit 13 is "60".

[0087] The vehicle classification "passenger car" in the license plate information and the vehicle classification "large truck" in the vehicle information are different. Therefore, the correction unit 14 replaces the vehicle classification "large truck" in the less accurate vehicle information with the vehicle classification "passenger car" in the more accurate license plate information.

[0088] Furthermore, the correction unit 14 extracts candidate vehicle information corresponding to the replacement vehicle category "ordinary automobile" from the vehicle correspondence table information 23 shown in Figure 3.

[0089] Figure 7 shows an example of candidate vehicle information corresponding to the vehicle category "ordinary automobile" after replacement. In other words, the correction unit 14 extracts four candidate vehicle information corresponding to the vehicle category "ordinary automobile" from the vehicle correspondence table information 23 shown in Figure 3. For example, these candidates include manufacturer name "T" and common name "P", manufacturer name "N" and common name "F", manufacturer name "H" and common name "A", and manufacturer name "T" and common name "C".

[0090] The correction unit 14 obtains vehicle information for the most likely vehicle from the vehicle information acquisition unit 12. In other words, the vehicle information acquisition unit 12 selects one vehicle information from the vehicle information candidates by applying predetermined image processing to the vehicle image captured by camera 3. For example, for each vehicle information candidate, the vehicle information acquisition unit 12 calculates the similarity between the set of feature quantities pre-registered for that candidate and the set of feature quantities extracted from the vehicle image captured by camera 3. The vehicle information acquisition unit 12 selects the vehicle information candidate with the highest calculated similarity. The correction unit 14 acquires the vehicle information candidate selected by the vehicle information acquisition unit 12 as the vehicle information for the most likely vehicle. As an example, the correction unit 14 obtains the manufacturer name "T" and the common name "P" as vehicle information from the vehicle information acquisition unit 12. The correction unit 14 corrects the vehicle information using the acquired manufacturer name "T" and common name "P".

[0091] Figure 6(C) shows the license plate information after the vehicle type information has been corrected by the correction unit 14. The license plate information is not corrected and is therefore the same as that shown in Figure 6(A).

[0092] Figure 6(D) shows the vehicle information after correction by the correction unit 14. As the vehicle classification corresponding to the vehicle information is replaced with "Passenger car", the manufacturer name is corrected to "T" and the common name is corrected to "P".

[0093] (2. High-probability information: Vehicle type information; Low-probability information: License plate information) Next, we will explain the processing of the correction unit 14 when the accuracy of the vehicle information is higher than the accuracy of the license plate information.

[0094] The correction unit 14 acquires license plate information from the plate information acquisition unit 11, vehicle type information from the vehicle type information acquisition unit 12, and the accuracy of the license plate information and the accuracy of the vehicle type information from the accuracy acquisition unit 13. The correction unit 14 also identifies the vehicle type corresponding to the acquired license plate information based on the license plate correspondence table information 22. Furthermore, the correction unit 14 identifies the vehicle type corresponding to the acquired vehicle type information based on the vehicle type correspondence table information 23.

[0095] Figure 8 is a diagram illustrating an example of the license plate information correction process performed by the correction unit 14. Figure 8(A) shows the license plate information acquired by the correction unit 14 from the license plate information acquisition unit 11, the vehicle type classification corresponding to the license plate information identified by the correction unit 14, and the accuracy of the license plate information acquired by the correction unit 14 from the accuracy acquisition unit 13.

[0096] For example, the license plate information obtained from the plate information acquisition unit 11 includes the serial number "12-34", the land transport bureau "Naniwa", the classification number "160", the purpose (in hiragana) "sa", the plate size "large", and the purpose (commercial / private) "private".

[0097] The correction unit 14 refers to the license plate correspondence table information 22 shown in Figure 2 and identifies the vehicle type "large truck" that corresponds to the classification number "160", plate size "large", and usage (commercial / private) "private" in the license plate information as the vehicle type corresponding to the license plate information. Furthermore, the accuracy of the license plate information acquired by the correction unit 14 from the accuracy acquisition unit 13 is "60".

[0098] Figure 8(B) shows the vehicle information acquired by the correction unit 14 from the vehicle information acquisition unit 12, the vehicle category corresponding to the vehicle information identified by the correction unit 14, and the accuracy of the vehicle information acquired by the correction unit 14 from the accuracy acquisition unit 13. For example, the vehicle information obtained from the vehicle information acquisition unit 12 includes the manufacturer name "T" and the common name "P".

[0099] The correction unit 14 refers to the vehicle type correspondence table information 23 shown in Figure 3 and identifies the vehicle type category "Passenger car" corresponding to the manufacturer name "T" and common name "P" as the vehicle type category corresponding to the vehicle type information. Furthermore, the accuracy of the vehicle information acquired by the correction unit 14 from the accuracy acquisition unit 13 is "90".

[0100] The vehicle classification "large truck" in the license plate information and the vehicle classification "regular passenger car" in the vehicle information are different. Therefore, the correction unit 14 replaces the less accurate vehicle classification "large truck" in the license plate information with the more accurate vehicle classification "regular passenger car".

[0101] Furthermore, the correction unit 14 extracts candidate license plate information corresponding to the replacement vehicle category "ordinary automobile" from the license plate correspondence table information 22 shown in Figure 2.

[0102] Figure 9 shows an example of candidate license plate information corresponding to the vehicle type classification "ordinary automobile" after replacement. In other words, the correction unit 14 extracts eight candidate license plate information corresponding to the vehicle type classification "ordinary automobile" from the license plate correspondence table information 22 shown in Figure 2. For example, one candidate includes the classification number "3,30-39,300-399", plate size "medium", usage (commercial / private) "commercial", and plate color "green".

[0103] The correction unit 14 obtains the most likely vehicle's license plate information from the license plate information acquisition unit 11. In other words, the license plate information acquisition unit 11 selects one license plate from the license plate information candidates by applying predetermined image processing to the vehicle image captured by the camera 2. For example, the license plate information acquisition unit 11 performs image processing such as character recognition on the license plate image captured by the camera 2, after imposing the constraint that the combination of classification number, plate size, and plate color is one of the eight candidates shown in Figure 9. As an example, the license plate information acquisition unit 11 obtains the serial number "12-34", land transport bureau "Naniwa", classification number "560", usage (hiragana) "sa", plate size "medium", and usage (commercial / private) "private" as a result of the image processing. The correction unit 14 obtains the license plate information acquired by the license plate information acquisition unit 11 from the license plate information acquisition unit 11. The correction unit 14 corrects the license plate information based on the acquired license plate information.

[0104] Figure 8(C) shows the license plate information after correction by the correction unit 14. The vehicle classification corresponding to the license plate information has been replaced with "regular passenger car," resulting in the classification number being corrected to "560" and the plate size being corrected to "medium-sized."

[0105] Figure 8(D) shows the vehicle type information after the license plate information has been corrected by the correction unit 14. Since the vehicle type information is not corrected, it is the same as shown in Figure 8(B).

[0106] The correction unit 14 outputs the corrected license plate information and vehicle type information to the output unit 16. The correction unit 14 performs the correction process described above if the vehicle classification corresponding to the license plate information and vehicle type information is different. If the two are the same, the correction unit 14 does not perform the correction process. Even in this case, the correction unit 14 outputs the license plate information obtained from the plate information acquisition unit 11 and the vehicle type information obtained from the vehicle type information acquisition unit 12 to the output unit 16.

[0107] Referring again to Figure 1, the determination unit 15 determines whether a vehicle is a modified vehicle or a vehicle with a replaced license plate (hereinafter, both types of vehicles are referred to as "counterfeit vehicles") based on the license plate information acquired by the plate information acquisition unit 11, the vehicle type information acquired by the vehicle type information acquisition unit 12, and the accuracy of the license plate information and vehicle type information acquired by the accuracy acquisition unit 13. The determination unit 15 outputs the determination result to the output unit 16.

[0108] Specifically, the determination unit 15 determines that a vehicle photographed by cameras 2 and 3 is a counterfeit vehicle if the accuracy of both the license plate information and the vehicle information is 90 or higher, and the vehicle classification corresponding to the license plate information differs from the vehicle classification corresponding to the vehicle information. This is because a situation where the vehicle classification does not match despite high reliability of both the license plate information and the vehicle information is thought to occur when the vehicle's exterior has been modified in a way that changes the vehicle classification, or when the license plate has been replaced in a way that changes the vehicle classification.

[0109] The output unit 16 acquires license plate information and vehicle type information from the correction unit 14. The output unit 16 outputs an image showing the acquired information to the display device 4 and displays it on the screen of the display device 4. The output unit 16 also acquires the judgment result for counterfeit vehicles from the judgment unit 15. The output unit 16 outputs an image showing the acquired result to the display device 4 and displays it on the screen of the display device 4. The output unit 16 may also output the information acquired from the correction unit 14 or the judgment unit 15 as audio via a speaker, or transmit it to another device via a network.

[0110] [Processing procedure for vehicle information acquisition device 1] Figure 10 is a flowchart showing an example of the processing procedure of the vehicle information acquisition device 1 according to the present disclosure. The plate information acquisition unit 11 acquires images captured by camera 2, and the vehicle information acquisition unit 12 acquires images captured by camera 3 (step S1).

[0111] The plate information acquisition unit 11 and the vehicle type information acquisition unit 12 each determine whether or not a vehicle is included in the acquired image (step S2). The determination method is not limited. For example, the plate information acquisition unit 11 may extract the moving object region by performing a difference process between the acquired target image and an image acquired one frame before the target image, and if the size of the extracted moving object region is within a predetermined range of the vehicle size, it may determine that a vehicle is included in the target image.

[0112] If neither the plate information acquisition unit 11 nor the vehicle information acquisition unit 12 determines that a vehicle is included in the acquired image (NO in step S2), the process in step S1 is repeated.

[0113] If both the plate information acquisition unit 11 and the vehicle type information acquisition unit 12 determine that a vehicle is included in the image they have acquired (YES in step S2), the plate information acquisition unit 11 performs image processing on the image captured by the camera 2 to acquire the license plate information of the vehicle in the image. The plate information acquisition unit 11 outputs the acquired license plate information to the correction unit 14 (step S3).

[0114] Furthermore, the vehicle information acquisition unit 12 acquires vehicle information of the vehicle in the image by performing image processing on the image captured by the camera 3. The vehicle information acquisition unit 12 outputs the acquired vehicle information to the correction unit 14 (step S4). Note that the processes in steps S3 and S4 may be executed in parallel.

[0115] The accuracy acquisition unit 13 acquires the accuracy of license plate information from the plate information acquisition unit 11 and the accuracy of vehicle information from the vehicle information acquisition unit 12. The accuracy acquisition unit 13 outputs each acquired accuracy to the correction unit 14 and the judgment unit 15 (step S5).

[0116] The correction unit 14 performs a matching process to match the license plate information obtained from the plate information acquisition unit 11 with the vehicle type information obtained from the vehicle type information acquisition unit 12 (step S6).

[0117] Figure 11 is a flowchart detailing the alignment process (step S6 in Figure 10). The correction unit 14 identifies the vehicle type corresponding to the license plate information obtained from the plate information acquisition unit 11, based on the license plate correspondence table information 22. The correction unit 14 also identifies the vehicle type corresponding to the vehicle type information obtained from the vehicle information acquisition unit 12, based on the vehicle type correspondence table information 23 (step S11). The correction unit 14 determines whether the two vehicle classifications identified in step S11 are the same (step S12).

[0118] If the two vehicle classifications are the same (YES in step S12), the output unit 16 obtains the license plate information and vehicle information from the correction unit 14, outputs an image showing the two obtained pieces of information to the display device 4, and displays it on the screen of the display device 4 (step S13).

[0119] If the two vehicle classifications are different (NO in step S12), the determination unit 15 determines whether the accuracy of the license plate information and the accuracy of the vehicle information obtained from the accuracy acquisition unit 13 are both 90 or higher (step S14).

[0120] If the accuracy of either one is less than 90 (NO in step S14), the correction unit 14 performs correction processing for the license plate information or vehicle type information and outputs the corrected license plate information and vehicle type information to the output unit 16 (step S15). The flow of the correction processing will be described later.

[0121] The output unit 16 acquires the corrected license plate information and vehicle type information from the correction unit 14, outputs an image showing the two acquired pieces of information to the display device 4, and displays it on the screen of the display device 4 (step S13).

[0122] If both confidence levels are 90 or higher (YES in step S14), the determination unit 15 determines that the vehicle is a counterfeit vehicle and outputs the determination result to the output unit 16 (step S16).

[0123] The output unit 16 outputs an image showing the judgment result of the judgment unit 15 to the display device 4, causing it to be displayed on the screen of the display device 4 (step S17).

[0124] Figure 12 is a flowchart detailing the correction process (step S15 in Figure 11). The correction unit 14 compares the accuracy of the vehicle type information with the accuracy of the license plate information (steps S21, S25). If the accuracy of the vehicle type information is greater than the accuracy of the license plate information (YES in step S21), the correction unit 14 replaces the vehicle type classification corresponding to the license plate information with the vehicle type classification corresponding to the vehicle type information (step S22). This is explained with reference to Figure 8.

[0125] The correction unit 14 extracts candidate license plate information from the license plate correspondence table information 22 based on the vehicle type after replacement. The plate information acquisition unit 11 selects one most likely license plate information from the candidate license plate information. The correction unit 14 reacquires the license plate information selected by the plate information acquisition unit 11 from the plate information acquisition unit 11 (step S23). This is as explained with reference to Figure 8.

[0126] The correction unit 14 and the plate information acquisition unit 11 may also reacquire license plate information by referring to the trend information 24. For example, the correction unit 14 refers to the trend information 24 shown in Figure 4 to acquire vehicle trends from the vehicle's location, time of day, and weather conditions during the journey. As an example, the correction unit 14 acquires the trend that if the vehicle's location is "National Route X", the time of day is "6:00-12:00", and the weather conditions during the journey are "sunny", then vehicles with license plates whose land transport bureau is "Naniwa" and whose classification number starts with 3 frequently pass by. The correction unit 14 provides the acquired trend information to the plate information acquisition unit 11. The plate information acquisition unit 11 selects one license plate from the candidate license plate information by applying image processing to the vehicle's video so that candidate license plate information containing the land transport bureau "Naniwa" or a classification number starting with 3 is more easily detected. For example, if the license plate information acquisition unit 11 contains the land transport bureau "Naniwa" or a classification number starting with 3, it assigns a weight greater than 1 to the similarity (by multiplying the similarity by a coefficient greater than 1 to create a new similarity value) and selects the license plate information with the highest similarity. The correction unit 14 then reacquires the license plate information selected by the license plate information acquisition unit 11 from the license plate information acquisition unit 11.

[0127] The correction unit 14 and the plate information acquisition unit 11 may also reacquire license plate information by referring to the trend information 24 shown in Figure 5. For example, if the vehicle type information includes the manufacturer name "I" and the common name "G", the correction unit 14 will refer to the trend information 24 shown in Figure 5 and acquire the trend that vehicles (transport trucks) with license plates of classification number "100" frequently pass by. Then, as described above, the plate information acquisition unit 11 will select one license plate from the candidate license plate information based on the acquired trend information, and the correction unit 14 will reacquire the license plate information selected by the plate information acquisition unit 11.

[0128] The correction unit 14 corrects the license plate information acquired in step S3 of Figure 10 using the license plate information reacquired in step S23 (step S24). This is as explained with reference to Figure 8.

[0129] If the accuracy of the license plate information is greater than the accuracy of the vehicle type information (NO in step S21, YES in step S25), the correction unit 14 replaces the vehicle type classification corresponding to the vehicle type information with the vehicle type classification corresponding to the license plate information (step S26). This is explained with reference to Figure 6.

[0130] The correction unit 14 extracts candidate vehicle information from the vehicle correspondence table information 23 based on the vehicle type after replacement. The vehicle information acquisition unit 12 selects one most likely vehicle information from the candidate vehicle information. The correction unit 14 then reacquires the vehicle information selected by the vehicle information acquisition unit 12 from the vehicle information acquisition unit 12 (step S27). This is as explained with reference to Figure 6.

[0131] The correction unit 14 and the vehicle information acquisition unit 12 may also reacquire vehicle information by referring to the trend information 24. For example, the correction unit 14 refers to the trend information 24 shown in Figure 4 to acquire vehicle trends from the vehicle's driving location, driving time, and weather conditions during driving. As an example, the correction unit 14 acquires the trend that if the vehicle's driving location is "National Route X", the driving time is "6:00-12:00", and the weather conditions during driving are "sunny", then vehicles with manufacturer name "T" frequently pass by. The correction unit 14 provides the acquired trend information to the vehicle information acquisition unit 12. The vehicle information acquisition unit 12 selects one vehicle information from the candidate vehicle information by applying image processing to the vehicle image so that candidate vehicle information containing manufacturer name "T" is more easily detected. For example, if the vehicle information acquisition unit 12 contains the manufacturer name "T", it assigns a weight greater than 1 to the similarity (by multiplying the similarity by a coefficient greater than 1 to obtain a new similarity value) and selects the vehicle information with the highest similarity. The correction unit 14 then reacquires the vehicle information selected by the vehicle information acquisition unit 12 from the vehicle information acquisition unit 12.

[0132] The correction unit 14 and the vehicle information acquisition unit 12 may also reacquire vehicle information by referring to the trend information 24 shown in Figure 5. For example, if the license plate information includes a classification number starting with 3 and the usage (hiragana) "i", the correction unit 14 will refer to the trend information 24 shown in Figure 5 and acquire the trend that vehicles (taxis) with manufacturer name "T" and common name "C" frequently pass by. Then, as described above, the vehicle information acquisition unit 12 will select one vehicle information from the candidate vehicle information based on the acquired trend information, and the correction unit 14 will reacquire the vehicle information selected by the vehicle information acquisition unit 12.

[0133] The correction unit 14 corrects the vehicle information acquired in step S4 of Figure 10 using the vehicle information reacquired in step S27 (step S28). This is as explained with reference to Figure 6.

[0134] If the accuracy of the vehicle information and the accuracy of the license plate information are equal (NO in step S21, NO in step S25), the correction unit 14 does not correct the vehicle information and the license plate information. However, if both accuracy levels are equal, the license plate information may be corrected according to steps S22 to S24, or the vehicle information may be corrected according to steps S26 to S28.

[0135] [Effects of the embodiment, etc.] As described above, according to the embodiments of this disclosure, by correcting low-accuracy information using high-accuracy information, erroneous information contained in low-accuracy information can be corrected to correct information. This makes it possible to obtain accurate vehicle information.

[0136] For identical vehicles, the vehicle classification corresponding to the license plate information and the vehicle classification corresponding to the vehicle classification must be the same. According to the embodiments of this disclosure, if the two are different, the vehicle classifications can be made consistent, and then the license plate information or vehicle classification can be corrected based on the consistent vehicle classification. This makes it possible to correct the license plate information or vehicle classification to accurate information.

[0137] Furthermore, the correction unit 14 can correct low-accuracy information by considering the appearance trends of license plate information or vehicle type information. Therefore, low-accuracy information can be corrected more accurately.

[0138] Furthermore, the determination unit 15 can determine if a vehicle is a counterfeit or altered vehicle. It is unlikely that the vehicle classification corresponding to the information would be different even if both the license plate information and the vehicle type information are highly reliable. Therefore, in such cases, the determination unit 15 can determine that some kind of alteration has been made to the vehicle or license plate that changes the vehicle classification.

[0139] Furthermore, the output unit 16 outputs the judgment result of the judgment unit 15. This allows the system to notify users of the vehicle information acquisition system 100 that a vehicle has been detected that has undergone some kind of modification, such as changing its vehicle classification.

[0140] Furthermore, the output unit 16 outputs at least one of high-accuracy information and corrected low-accuracy information. This allows the corrected license plate information or vehicle information to be notified to the user of the vehicle information acquisition system 100. <Example 1>

[0141] In the above-described embodiment, when correcting license plate information, multiple candidate license plate information is extracted based on the vehicle classification corresponding to the vehicle type information, one is selected from the extracted candidates, and the license plate information acquired by the plate information acquisition unit 11 is corrected using the selected license plate information.

[0142] In contrast, the plate information acquisition unit 11 may have already acquired multiple license plate information. In such cases, the correction unit 14 may select the license plate information with the highest accuracy corresponding to the vehicle type category corresponding to the vehicle type information from among the multiple license plate information as the corrected license plate information.

[0143] Figure 13 shows multiple license plate information acquired by the license plate information acquisition unit 11 and vehicle type classification information corresponding to the license plate information. Referring to Figure 13, the license plate information acquisition unit 11 performs predetermined image processing on the vehicle image captured by the camera 2 and acquires a predetermined number (in this case, 3) of license plate information in order of highest accuracy. The vehicle type corresponding to the first highest accuracy license plate information is "large truck", the vehicle type corresponding to the second highest accuracy license plate information is "light vehicle", and the vehicle type corresponding to the third highest accuracy license plate information is "light truck".

[0144] Here, we assume that the vehicle category corresponding to the vehicle information acquired by the vehicle information acquisition unit 12 is "kei car" (light vehicle). Furthermore, we assume that the accuracy of this vehicle information is higher than the accuracy of the first most accurate license plate information acquired by the plate information acquisition unit 11. In this case, the correction unit 14 selects the second license plate information shown in Figure 13 as the license plate information with the highest accuracy corresponding to the vehicle category "kei car" from among the three license plate information acquired by the plate information acquisition unit 11.

[0145] According to Modification 1, the most accurate license plate information corresponding to the correct vehicle classification can be selected from among multiple license plate information entries. Therefore, the selected license plate information is accurate.

[0146] Furthermore, similar to the embodiment described above, the correction unit 14 may, when selecting license plate information, weight the similarity (accuracy) based on the trend information 24 and then select the license plate information with the highest accuracy corresponding to the correct vehicle classification. This makes it possible to select the correct license plate information from among multiple license plate information, taking into account the appearance trends of license plate information. <Modification 2>

[0147] In the above-described embodiment, when correcting vehicle information, multiple candidate vehicle information was extracted based on the vehicle classification corresponding to the license plate information, one was selected from the extracted candidates, and the vehicle information acquired by the vehicle information acquisition unit 12 was corrected with the selected vehicle information.

[0148] In contrast, the vehicle information acquisition unit 12 may have already acquired multiple vehicle information records. In such cases, the correction unit 14 may select the vehicle information record with the highest accuracy corresponding to the vehicle classification corresponding to the license plate information from among the multiple vehicle information records as the corrected vehicle information record.

[0149] Figure 14 shows multiple vehicle type information acquired by the vehicle type information acquisition unit 12 and vehicle type classification information corresponding to the vehicle type information. Referring to Figure 14, the vehicle type information acquisition unit 12 performs predetermined image processing on the vehicle image captured by the camera 3 and acquires a predetermined number (in this case, 3) of vehicle type information in order of highest accuracy. The vehicle type classification corresponding to the first highest accuracy vehicle type information is "large truck", the vehicle type classification corresponding to the second highest accuracy vehicle type information is "light truck", and the vehicle type classification corresponding to the third highest accuracy vehicle type information is "regular passenger car".

[0150] Here, we assume that the vehicle category corresponding to the license plate information acquired by the plate information acquisition unit 11 is "light truck". Furthermore, we assume that the accuracy of this license plate information is higher than the accuracy of the first most accurate vehicle information acquired by the vehicle information acquisition unit 12. In this case, the correction unit 14 selects the second vehicle information shown in Figure 14 as the vehicle information with the highest accuracy corresponding to the vehicle category "light truck" among the three vehicle information acquired by the vehicle information acquisition unit 12.

[0151] According to variation 2, the most accurate vehicle information corresponding to the correct vehicle category can be selected from among multiple vehicle information entries. Therefore, the selected vehicle information is accurate.

[0152] Furthermore, similar to the embodiment described above, the correction unit 14 may, when selecting vehicle information, weight the similarity (accuracy) based on the trend information 24 and then select the vehicle information with the highest accuracy corresponding to the correct vehicle classification. This makes it possible to select the correct vehicle information from among multiple vehicle information, taking into account the appearance trends of vehicle types. <Variation 3>

[0153] In the above embodiment, when reacquiring license plate information or vehicle type information, the similarity (accuracy) was weighted by referring to trend information 24. However, referring to trend information 24 is not limited to when reacquiring this information.

[0154] In other words, in the initial license plate information acquisition process (step S3 in Figure 10), the license plate information acquisition unit 11 may acquire the license plate information after weighting the similarity by referring to the trend information 24.

[0155] Alternatively, in the initial vehicle information acquisition process (step S4 in Figure 10), the vehicle information acquisition unit 12 may acquire vehicle information after weighting the similarity by referring to the trend information 24.

[0156] According to Modification 3, the accuracy can be calculated taking into account the occurrence trends of license plate information or vehicle type information. Therefore, by taking into account the occurrence trends, incorrect information contained in low-accuracy information can be corrected to correct information. <Modification 4>

[0157] The correction unit 14 may choose not to correct the low-accuracy information if the accuracy of the license plate information and vehicle information is below a lower threshold (for example, 30). The output unit 16 may also output information indicating that the accuracy of both pieces of information is below the lower threshold.

[0158] According to Modification 4, if the reliability of both the license plate information and the vehicle type information is low, both pieces of information can be discarded, thus preventing the correction of the low-accuracy information. This prevents unnecessary correction processing from being performed.

[0159] [Note] The vehicle information acquisition system 100 according to the embodiment of this disclosure has been described above, but this disclosure is not limited to this embodiment.

[0160] For example, some or all of the components constituting the vehicle information acquisition device 1 may consist of one or more semiconductor devices such as system LSIs.

[0161] Furthermore, the computer program 21 may be recorded on a computer-readable non-temporary recording medium, such as an HDD, CD-ROM, or semiconductor memory, and distributed. Alternatively, the computer program 21 may be transmitted and distributed via telecommunications lines, wireless or wired communication lines, networks such as the Internet, or data broadcasting. Furthermore, the vehicle information acquisition device 1 may be implemented by multiple computers or multiple processors.

[0162] For example, the plate information acquisition unit 11, accuracy acquisition unit 13, correction unit 14, judgment unit 15, and output unit 16 may be configured by a first computer, the vehicle information acquisition unit 12 may be configured by a second computer, and the first computer and the second computer may be connected via a network.

[0163] Furthermore, some or all of the functions of the vehicle information acquisition device 1 may be provided by cloud computing. In other words, some or all of the functions of the vehicle information acquisition device 1 may be implemented by a cloud server. Furthermore, at least some of the above embodiments and modifications may be combined as desired.

[0164] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of this disclosure is indicated by the claims, not in the sense described above, and all modifications are intended to be in the sense and scope equivalent to the claims. [Explanation of Symbols]

[0165] 1. Vehicle Information Acquisition Device 2 cameras 3 cameras 4 Display device 10 Control Unit 11 Plate information acquisition unit 12. Vehicle Information Acquisition Section 13 Accuracy acquisition unit 14 Correction section 15 Judgment Department 16 Output section 20 Memory section 21 Computer Programs 22. Information on tables compatible with license plates 23 Vehicle Compatibility Table Information 24 Trend Information 100 Vehicle Information Acquisition System

Claims

1. A plate information acquisition unit that acquires license plate information including information written on the vehicle's license plate, A vehicle information acquisition unit that acquires vehicle type information of the aforementioned vehicle, A precision acquisition unit that acquires the precision of the aforementioned license plate information and the aforementioned vehicle information, A vehicle information acquisition system comprising: a correction unit that corrects low-accuracy information, which is information with a relatively low accuracy, using high-accuracy information, which is information with a relatively high accuracy, from among the aforementioned license plate information and vehicle type information.

2. The vehicle information acquisition system according to claim 1, wherein the correction unit corrects the low-accuracy information based on the vehicle type classification corresponding to the high-accuracy information.

3. The vehicle information acquisition system according to claim 1 or 2, wherein the correction unit corrects the low-accuracy information based on trend information indicating the appearance tendency of at least one of the license plate information and the vehicle type information.

4. The vehicle information acquisition system according to claim 1 or 2, wherein, if a plurality of low-accuracy pieces of information have been acquired, the correction unit selects from among the plurality of low-accuracy pieces of information the low-accuracy piece of information with the highest accuracy corresponding to the vehicle type category corresponding to the high-accuracy information as the corrected low-accuracy piece of information.

5. The vehicle information acquisition system according to claim 1 or 2, wherein, when a plurality of low-accuracy information is acquired, the correction unit selects one of the acquired low-accuracy information as the corrected low-accuracy information based on trend information indicating the appearance tendency of at least one of the license plate information and the vehicle type information.

6. The vehicle information acquisition system according to claim 1 or claim 2, wherein the accuracy acquisition unit calculates the accuracy of the license plate information and the vehicle type information, respectively, based on trend information indicating the appearance tendency of at least one of the license plate information and the vehicle type information.

7. The vehicle information acquisition system according to claim 1 or 2, wherein the correction unit does not correct the low-accuracy information if the accuracy of the license plate information and the vehicle type information is below a lower threshold.

8. The vehicle information acquisition system according to claim 1 or 2, further comprising a determination unit that determines that the vehicle is a modified vehicle or a vehicle with a replaced license plate when the accuracy of each of the license plate information and the vehicle type information is above an upper threshold, and the vehicle type classifications indicated by each of the license plate information and the vehicle type information are different.

9. The vehicle information acquisition system according to claim 8, further comprising an output unit that outputs the judgment result of the judgment unit.

10. The vehicle information acquisition system according to claim 1 or claim 2, further comprising an output unit that outputs at least one of the high-accuracy information and the corrected low-accuracy information.

11. A method for acquiring vehicle information that is performed by a vehicle information acquisition system, The plate information acquisition unit acquires license plate information, including the information written on the vehicle's license plate. The vehicle information acquisition unit performs the step of acquiring the vehicle information of the said vehicle, The accuracy acquisition unit performs the steps of acquiring the accuracy of the license plate information and the vehicle information, A method for acquiring vehicle information, comprising the step of a correction unit correcting low-accuracy information, which is information with a relatively low accuracy, using high-accuracy information, which is information with a relatively high accuracy, from among the license plate information and the vehicle type information.

12. Computers, A plate information acquisition unit that acquires license plate information, including information written on the vehicle's license plate. A vehicle information acquisition unit that acquires vehicle type information of the aforementioned vehicle, A unit for acquiring the accuracy of the aforementioned license plate information and vehicle type information, and A computer program for functioning as a correction unit that corrects low-accuracy information, which is information with a relatively low accuracy, using high-accuracy information, which is information with a relatively high accuracy, from among the aforementioned license plate information and vehicle type information.

Images