Vehicle type discrimination device, vehicle type discrimination method, and vehicle type discrimination program

Abstract

To enable minute discrimination of a vehicle type of a vehicle with a simple configuration without using a sensor other than a camera.SOLUTION: A vehicle type discrimination device 10 includes a vehicle type narrowing-down section 21 and a vehicle type discrimination section 22. The vehicle type narrowing-down section 21 narrows down a vehicle type of a vehicle from information such as a number indicated by a license plate of the vehicle and a combination of a background color with a character color on the license plate. The vehicle type discrimination section 22 minutely discriminates the vehicle type among the vehicle types narrowed-down by the narrowing-down section 21 with image data of the vehicle as an input.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a technology for identifying a vehicle type. [Background technology]

[0002] There was a method to distinguish the type of vehicle based on the number plate information recognized by a camera. However, this method could only distinguish a limited number of vehicle types, such as large trucks, buses, and other types of vehicles. In addition, plates with patterns were introduced. This made it difficult to distinguish between light vehicles and registered vehicles (hereinafter referred to as ordinary vehicles) by the color of the number plate.

[0003] Patent Document 1 describes the use of other sensors in addition to a camera to precisely identify the vehicle type. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2002-216288 A Summary of the Invention [Problem to be solved by the invention]

[0005] The technology described in Patent Document 1 requires the introduction of a sensor in addition to a camera, which makes the configuration complicated and increases the cost required for introduction. The present disclosure aims to enable detailed determination of vehicle type using a simple configuration. [Means for solving the problem]

[0006] The vehicle type discrimination device according to the present disclosure is A vehicle type narrowing-down unit that narrows down the vehicle type of the vehicle based on information of the license plate of the vehicle; a vehicle type discrimination unit that receives image data of the vehicle as an input and discriminates which vehicle type is included among the vehicle types narrowed down by the narrowing down unit; Equipped with. Effect of the Invention

[0007] In the present disclosure, image data of a vehicle is input, and the vehicle type is identified from among the vehicle types narrowed down based on license plate information. This makes it possible to identify the vehicle type in detail without introducing a sensor in addition to the camera. [Brief description of the drawings]

[0008] [Figure 1] 1 is a configuration diagram of a vehicle type discrimination device 10 according to a first embodiment. [Diagram 2] 3 is a flowchart showing the overall process of the vehicle type discrimination device 10 according to the first embodiment. [Diagram 3] 4 is a flowchart of a vehicle type narrowing down process according to the first embodiment. [Figure 4] FIG. 13 is an explanatory diagram of a combination of background color and character color of a license plate. [Diagram 5] An illustration of a license plate with a design. [Figure 6] 4 is a flowchart of a vehicle type discrimination process according to the first embodiment. [Figure 7] FIG. 2 is a configuration diagram of a vehicle type discrimination device 10 according to a first modified example. [Figure 8] FIG. 11 is a configuration diagram of a vehicle type discrimination device 10 according to a second embodiment. [Figure 9] 10 is a flowchart showing the overall process of the vehicle type discrimination device 10 according to the second embodiment. [Figure 10] 11 is a flowchart of a taxi discrimination process according to the second embodiment. [Figure 11] FIG. 11 is an explanatory diagram of the position of a signboard portion relative to the position of a license plate in the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Embodiment 1 ***Configuration Description*** The configuration of a vehicle type discrimination device 10 according to the first embodiment will be described with reference to FIG. The vehicle type discrimination device 10 is a computer. The vehicle type discrimination device 10 includes the following hardware components: a processor 11, a memory 12, a storage 13, and a communication interface 14. The processor 11 is connected to other hardware components via signal lines and controls these other hardware components.

[0010] The processor 11 is an IC that performs processing. IC is an abbreviation for Integrated Circuit. Specific examples of the processor 11 include a CPU, a DSP, and a GPU. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

[0011] The memory 12 is a storage device that temporarily stores data. Specific examples of the memory 12 include SRAM and DRAM. SRAM is an abbreviation for Static Random Access Memory. DRAM is an abbreviation for Dynamic Random Access Memory.

[0012] The storage 13 is a storage device that stores data. A specific example of the storage 13 is an HDD. HDD is an abbreviation for Hard Disk Drive. The storage 13 may also be a portable recording medium such as an SD (registered trademark) memory card, CompactFlash (registered trademark), NAND flash, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, or a DVD. SD is an abbreviation for Secure Digital. DVD is an abbreviation for Digital Versatile Disk.

[0013] The communication interface 14 is an interface for communicating with an external device. Specific examples of the communication interface 14 include Ethernet (registered trademark), USB, and HDMI (registered trademark) ports. USB is an abbreviation for Universal Serial Bus. HDMI is an abbreviation for High-Definition Multimedia Interface.

[0014] The vehicle type discrimination device 10 includes, as functional components, a vehicle type narrowing down unit 21 and a vehicle type discrimination unit 22. The functions of the functional components of the vehicle type discrimination device 10 are realized by software. The storage 13 stores a program that realizes the function of each functional component of the vehicle type discrimination device 10. The program is loaded into the memory 12 by the processor 11 and executed by the processor 11. In this way, the function of each functional component of the vehicle type discrimination device 10 is realized.

[0015] 1 shows only one processor 11. However, there may be a plurality of processors 11, and the plurality of processors 11 may cooperate to execute programs that realize the respective functions.

[0016] ***Explanation of Operation*** The operation of the vehicle type discrimination device 10 according to the first embodiment will be described with reference to FIGS. The operation procedure of the vehicle type discrimination device 10 according to the embodiment 1 corresponds to the vehicle type discrimination method according to the embodiment 1. Moreover, the program for realizing the operation of the vehicle type discrimination device 10 according to the embodiment 1 corresponds to the vehicle type discrimination program according to the embodiment 1.

[0017] The overall process of the vehicle type discrimination device 10 according to the first embodiment will be described with reference to FIG. (Step S1 in Fig. 2: Car type narrowing down process) The vehicle type narrowing-down unit 21 narrows down the vehicle type from the information on the license plate of the vehicle.

[0018] This will be specifically described with reference to FIG. The vehicle type narrowing down unit 21 reads the number from the license plate included in the image data of the vehicle (step S11). The vehicle type narrowing down unit 21 identifies whether the license plate size is large, medium, or small (step S12). The size of the license plate can be identified using existing technology. If the license plate size is large, the vehicle type narrowing down unit 21 narrows down the vehicle type to large vehicles, etc. (step S16-1). If the license plate size is small, the vehicle type narrowing down unit 21 narrows down the vehicle type to motorcycles, etc. (step S16-5).

[0019] If the license plate size is medium, the vehicle type narrowing-down unit 21 determines whether it is possible to determine whether the vehicle is a standard vehicle or a light vehicle based on the license plate classification number (step S13). The classification numbers of license plates are partially overlapping between standard vehicles and light vehicles. For example, the classification numbers of small freight vehicles and light freight vehicles for standard vehicles overlap. The classification numbers of small passenger cars and passenger cars for standard vehicles overlap with those of light passenger cars. The classification numbers of small special-purpose vehicles for standard vehicles overlap with those of light special-purpose vehicles. In the case of a classification number that is used only for either a normal car or a light car, it is possible to determine whether the car is a normal car or a light car. On the other hand, in the case of a classification number that is used in both a normal car and a light car, it is impossible to determine whether the car is a normal car or a light car. In the case where it is possible to determine whether the car is a normal car or a light car, the vehicle type narrowing-down unit 21 narrows down the vehicle type to either a normal car or a light car according to the classification number (step S16-4).

[0020] If it is impossible to distinguish, the vehicle type narrowing down unit 21 distinguishes the color of the license plate (step S14). The vehicle type narrowing down unit 21 distinguishes whether it is a standard vehicle or a light vehicle from the background color and the color of the characters on the license plate (step S15). As shown in Figure 4, there are four combinations of background and character colors for license plates. Previously, when the background color was white and the character color was green, and when the background color was green and the character color was white, the vehicle type was identified as a standard vehicle. Also, when the background color was yellow and the character color was black, and when the background color was black and the character color was yellow, the vehicle type was identified as a light vehicle. However, as shown in Figure 5, license plates with designs have been introduced. Therefore, when the background color was white and the character color was green, and when the background color was green and the character color was white, it is not possible to determine whether the vehicle type is a standard vehicle or a light vehicle. Therefore, when the background color is white and the character color is green, and when the background color is green and the character color is white, the vehicle type narrowing down unit 21 narrows down the vehicle type to a standard car or a light car (step S16-2). In other words, when the background color is white and the character color is green, and when the background color is green and the character color is white, the vehicle type is not narrowed down to whether it is a standard car or a light car. When the background color is yellow and the character color is black, and when the background color is black and the character color is yellow, the vehicle type narrowing down unit 21 narrows down the vehicle type to a light car (step S16-3).

[0021] (Step S2 in FIG. 2: Vehicle type determination process) The vehicle type discrimination unit 22 receives image data of the vehicle and discriminates which vehicle type it is from among the vehicle types narrowed down in step S1.

[0022] This will be specifically described with reference to FIG. The vehicle type discrimination unit 22 extracts feature amounts from the image data of the vehicle (step S21). The feature amounts of the image data are information that quantifies the vehicle features in the image data. The quantification of the features can be realized by existing technology. The vehicle type discrimination unit 22 inputs the feature amounts to a vehicle type inference model that infers the vehicle type (step S22). In the first embodiment, the vehicle type inference model calculates the degree of similarity between the shape of the vehicle shown in the image data and the shape of the vehicle for each vehicle name (step S23). Then, the vehicle type inference model identifies the vehicle name with the highest similarity, and outputs the vehicle type corresponding to the identified vehicle name (step S24). Note that the vehicle name and the vehicle type are associated in advance. The vehicle type discrimination unit 22 discriminates that the vehicle is of the vehicle type output from the vehicle type inference model.

[0023] In the above description, the feature amount extracted from the image data is input to the vehicle type inference model. However, depending on the configuration of the vehicle type inference model, the image data may be input to the vehicle type inference model.

[0024] At this time, when the vehicle type is narrowed down to a standard vehicle or a light vehicle in step S16-2 of FIG. 3, the vehicle type discrimination unit 22 discriminates whether the vehicle type is a standard vehicle or a light vehicle. When the vehicle type is narrowed down to a standard car, the vehicle type discrimination unit 22 may specify a detailed vehicle type such as a taxi, a minivan, or a sedan. When the vehicle type is narrowed down to a large vehicle, a light vehicle, or a motorcycle, the vehicle type discrimination unit 22 may similarly specify a detailed vehicle type. For example, when the vehicle type is narrowed down to a large vehicle, the vehicle type discrimination unit 22 may specify a detailed vehicle type such as a truck, a bus, a special vehicle such as a crane, or a construction vehicle such as a road roller.

[0025] The process shown in FIG. 2 is executed between 10 milliseconds and 50 milliseconds, for example.

[0026] ***Advantages of the First Embodiment*** As described above, the vehicle type discrimination device 10 according to the first embodiment discriminates the vehicle type from among the vehicle types narrowed down based on the license plate information. This makes it possible to discriminate the vehicle type in detail without introducing a sensor in addition to the camera.

[0027] ***Other configurations*** <Variation 1> In the first embodiment, each functional component is realized by software. However, as a first modification, each functional component may be realized by hardware. The following describes the first modification in terms of differences from the first embodiment.

[0028] The configuration of a vehicle type discrimination device 10 according to the first modified example will be described with reference to FIG. When each functional component is realized by hardware, the vehicle type discrimination device 10 includes an electronic circuit 15 instead of the processor 11, the memory 12, and the storage 13. The electronic circuit 15 is a dedicated circuit for realizing the functions of each functional component, the memory 12, and the storage 13.

[0029] The electronic circuit 15 may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array. Each functional component may be realized by one electronic circuit 15, or each functional component may be distributed across multiple electronic circuits 15.

[0030] <Variation 2> As a second modification, some of the functional components may be realized by hardware, and other functional components may be realized by software.

[0031] The processor 11, the memory 12, the storage 13, and the electronic circuit 15 are collectively referred to as a processing circuit. In other words, the functions of the respective functional components are realized by the processing circuit.

[0032] Embodiment 2 The second embodiment differs from the first embodiment in that when the vehicle type is determined to be a taxi, the taxi company is determined. In the second embodiment, this difference will be described, and a description of the same points will be omitted.

[0033] ***Configuration Description*** The configuration of a vehicle type discrimination device 10 according to the second embodiment will be described with reference to FIG. 1 in that the vehicle type discrimination device 10 includes a taxi discrimination unit 23 as a functional component. The function of the taxi discrimination unit 23 is realized by software or hardware, like the other functional components.

[0034] ***Explanation of Operation*** The operation of the vehicle type discrimination device 10 according to the second embodiment will be described with reference to FIGS. The operation procedure of the vehicle type discrimination device 10 according to the embodiment 2 corresponds to the vehicle type discrimination method according to the embodiment 2. Moreover, the program for realizing the operation of the vehicle type discrimination device 10 according to the embodiment 2 corresponds to the vehicle type discrimination program according to the embodiment 2.

[0035] The overall process of the vehicle type discrimination device 10 according to the second embodiment will be described with reference to FIG. The processes in steps S1 and S2 are the same as those in the first embodiment.

[0036] (Step S3: Taxi discrimination process) When the vehicle type is determined to be a taxi in step S2, the taxi discrimination unit 23 discriminates the taxi company based on a partial image of a taxi signboard portion in the image data.

[0037] This will be specifically described with reference to FIG. The taxi discrimination unit 23 extracts a feature amount of a partial image of a taxi signboard portion from the vehicle image data (step S31). The taxi discrimination unit 23 inputs the feature amount to a company inference model that infers a taxi company (step S32). In the second embodiment, the similarity between the sign shown by the partial image and the sign of each taxi company is calculated by the company inference model (step S33). Then, the taxi company with the highest similarity is identified by the company inference model and output (step S34). The taxi discrimination unit 23 discriminates that the vehicle is a vehicle of the taxi company output from the company inference model.

[0038] In step S31, the taxi discrimination unit 23 calculates the feature amount of the partial image based on the shape, size, and color of the signboard portion, the characters written on the signboard portion, etc. At this time, as shown in Fig. 11, the taxi discrimination unit 23 may calculate the feature amount taking into consideration the position of the signboard portion relative to the position of the license plate. In this way, the taxi company is discriminated taking into consideration the position of the signboard portion relative to the position of the license plate.

[0039] In the above description, the feature amount extracted from the partial image is input to the agent inference model. However, depending on the configuration of the agent inference model, the partial image may be input to the agent inference model.

[0040] When cutting out a partial image of the signboard portion, the taxi discrimination unit 23 may specify the cutting position taking into consideration the position of the signboard portion relative to the position of the license plate for each taxi company. For example, it is possible to specify the cutting position so as to include the positions of the signboard portions for all taxi companies. The position of the license plate is specified in step S1. Therefore, it becomes possible to easily specify the position of the signboard portion from the position of the license plate. As a result, the process of specifying the signboard portion can be speeded up.

[0041] ***Effects of the second embodiment*** As described above, the vehicle type discrimination device 10 according to the second embodiment discriminates a taxi company based on a partial image of a signboard portion. This makes it possible to discriminate a taxi company without introducing a sensor in addition to a camera.

[0042] In addition, the word "part" in the above description may be read as a "circuit," "step," "procedure," "processing," or "processing circuit."

[0043] The above describes the embodiments and modifications of the present disclosure. Some of these embodiments and modifications may be combined and implemented. Also, one or some of them may be partially implemented. Note that the present disclosure is not limited to the above embodiments and modifications, and various modifications are possible as necessary. [Explanation of symbols]

[0044] 10 vehicle type discrimination device, 11 processor, 12 memory, 13 storage, 14 communication interface, 15 electronic circuit, 21 vehicle type narrowing down unit, 22 vehicle type discrimination unit, 23 taxi discrimination unit.

Claims

1. A vehicle type narrowing-down unit that narrows down the vehicle type of the vehicle based on information of the license plate of the vehicle; a vehicle type discrimination unit that identifies a vehicle name of the vehicle from the shape of the vehicle captured in the image data of the vehicle, and thereby discriminates which vehicle type of the vehicle is included among the vehicle types narrowed down by the vehicle type narrowing down unit; A vehicle type discrimination device comprising:

2. A vehicle type narrowing-down unit that narrows down the vehicle type of the vehicle based on information of the license plate of the vehicle; a vehicle type discrimination unit that, when the vehicle type is narrowed down to a standard vehicle or a light vehicle by the vehicle type narrowing unit, identifies a vehicle name of the vehicle from the shape of the vehicle captured in the image data of the vehicle to discriminate whether the vehicle is a standard vehicle or a light vehicle; A vehicle type discrimination device comprising:

3. The vehicle type determination unit determines which vehicle type the vehicle is by inputting the image data or a feature amount extracted from the image data into a vehicle type inference model that infers the vehicle type.

3. The vehicle type discrimination device according to claim 1 or 2.

4. The vehicle type includes a taxi; The vehicle type discrimination device further comprises: a taxi discrimination unit that discriminates a taxi company based on a partial image of a taxi signboard portion in the image data when the vehicle type discrimination unit discriminates that the vehicle type is a taxi. The vehicle type discrimination device according to any one of claims 1 to 3, further comprising:

5. The taxi discrimination unit discriminates the taxi company by taking into consideration the position of the signboard portion relative to the position of the license plate. The vehicle type discrimination device according to claim 4.

6. The taxi discrimination unit discriminates a taxi company by inputting the partial image or a feature amount extracted from the partial image into a company inference model that infers a taxi company.

6. The vehicle type discrimination device according to claim 4 or 5.

7. A vehicle type discrimination unit that discriminates whether the vehicle is a certain type by identifying the name of the vehicle from the shape of the vehicle captured in the image data of the vehicle. A vehicle type discrimination device comprising:

8. The computer narrows down the model of the vehicle based on the license plate information of the vehicle, A vehicle type discrimination method in which a computer identifies the name of the vehicle from the shape of the vehicle captured in image data of the vehicle, thereby discriminating which of the narrowed-down vehicle types the vehicle is.

9. A vehicle type narrowing process for narrowing down the vehicle type of the vehicle based on the license plate information of the vehicle; a vehicle type discrimination process for identifying a vehicle name of the vehicle from the shape of the vehicle captured in the image data of the vehicle, and thereby discriminating which vehicle type of the vehicle is included among the vehicle types narrowed down by the vehicle type narrowing down process; A vehicle type discrimination program that causes a computer to function as a vehicle type discrimination device that performs the above.

Images