Information processing apparatus and information processing method

Abstract

An information processing device is provided with: a communication unit that receives, from a server, a license plate list which is a list of character strings of license plates to be detected; and a control unit that recognizes a character string of a license plate from a camera image captured by the vehicle-mounted camera, and transmits an image in which the camera image is hidden through the communication unit when the recognized character string is included in a license plate list and the recognition accuracy is equal to or less than a high accuracy threshold. When the accuracy exceeds the high accuracy threshold, the recognized character string is transmitted through the communication unit.

Description

TECHNICAL FIELD

[0001] The present application relates to an information processing apparatus and an information processing method. BACKGROUND

[0002] In the past, a technology of managing a vehicle by capturing a license plate of a vehicle present in a parking lot with a camera installed in the parking lot is known. For example, a photographing apparatus is disclosed in Japanese Patent Application Publication No. 2009-238124, which includes a photographing mechanism that captures a license plate surface of a vehicle present at a prescribed position in a parking lot, and a character data conversion mechanism that identifies characters from the captured license plate surface image and converts them into character data. The photographing apparatus further includes a character data collating mechanism that collates the character data stored in advance with the converted character data, and a transmission mechanism that transmits collation result data indicating the collation result to an external device. SUMMARY

[0003] However, the technology described in Japanese Patent Application Publication No. 2009-238124 performs collation of a license plate, but since all information of the collation is transmitted to a server, there is a case where privacy is not considered.

[0004] The present application extracts information that is useful and has high commonality from image information of a vehicle-mounted camera, and provides the information while considering privacy.

[0005] An information processing apparatus according to an embodiment of the present application includes a communication unit that receives a list of characters of a license plate that is a detection target from a server, and a control unit that identifies a character of a license plate from a camera image captured by a vehicle-mounted camera, transmits, in a case where the identified character is included in the list of characters of the license plate and in a case where accuracy of the identification is below a high accuracy threshold, an image that anonymizes the camera image through the communication unit, and transmits, in a case where the accuracy exceeds the high accuracy threshold, the identified character through the communication unit.

[0006] An information processing method according to an embodiment of the present application includes a step in which a server transmits a list of characters of a license plate that is a detection target, a step in which an information processing apparatus receives the list of characters of the license plate, identifies a character of a license plate from a camera image captured by a vehicle-mounted camera, transmits, in a case where the identified character is included in the list of characters of the license plate and in a case where accuracy of the identification is below a high accuracy threshold, an anonymized image that anonymizes the camera image to the server, and transmits, in a case where the accuracy exceeds the high accuracy threshold, the identified character to the server, and a step in which the server stores the anonymized image or the character.

[0007] According to an embodiment of the present application, useful and highly common information can be quickly extracted from image information of a vehicle-mounted camera, and the information can be provided while privacy is considered. BRIEF DESCRIPTION OF DRAWINGS

[0008] Features, advantages, and technical and industrial significance of exemplary embodiments of the present application will be described below with reference to the accompanying drawings, wherein the same reference numerals are denoted throughout the several views, and wherein:

[0009] Figure 1 is a diagram showing a configuration example of an information processing system according to an embodiment.

[0010] Figure 2 is a diagram illustrating a process of a collating section of an information processing apparatus according to an embodiment.

[0011] Figure 3 is a flowchart showing a process step example of an information processing method according to an embodiment. DETAILED DESCRIPTION

[0012] Configuration of Information Processing System

[0013] Reference Figure 1 A configuration of an information processing system according to an embodiment will be described. Figure 1 The information processing system 1 shown is provided with an information processing apparatus 10, a vehicle-mounted camera 20, and a server 30.

[0014] The vehicle-mounted camera 20 is connected to the information processing apparatus 10. The vehicle-mounted camera 20 can be integrated with the information processing apparatus 10. The vehicle-mounted camera 20 can be mounted on a vehicle in a plurality. The vehicle-mounted camera 20 has a photographing element that photographs an image of a vehicle periphery.

[0015] The server 30 acquires and stores, in advance from a police, a list of strings of license plates that are detection targets, i.e., a license plate list. The license plates that are detection targets are, for example, license plates of vehicles related to crimes, incidents, traffic accidents, and the like.

[0016] The information processing apparatus 10 is an apparatus mounted on a moving vehicle, and performs wireless communication with the server 30. Figure 1 The information processing apparatus 10 shown is provided with an input section 11, a storage section 12, a control section 13, an output section 14, and a communication section 15.

[0017] The input section 11 includes at least one input interface. The input interface is, for example, a physical key, an electrostatic capacitance key, a pointing device, a touch screen provided integrally with a display, or a microphone. Further, the input section 11 includes an interface with the vehicle-mounted camera 20. The input section 11 inputs a real-time image photographed by the vehicle-mounted camera 20 (hereinafter, referred to as "camera image").

[0018] The storage section 12 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, a random access memory (RAM), a read only memory (ROM), or a flash memory. The flash memory is, for example, a solid-state drive (SSD). The magnetic memory is, for example, a hard disk drive (HDD). The storage section 12 stores the camera images.

[0019] The output section 14 includes at least one output interface. The output interface is, for example, a display that outputs information as an image or a speaker that outputs information as a sound. The display is, for example, a liquid crystal display (LCD) or an organic electro luminescent (EL) display.

[0020] The communication section 15 includes at least one wireless communication interface for wireless communication with the server 30.

[0021] The control section 13 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a central processing unit (CPU) or a graphics processing unit (GPU), or a dedicated processor for a specific processing. The programmable circuit is, for example, a field-programmable gate array (FPGA). The dedicated circuit is, for example, an application specific integrated circuit (ASIC). The control section 13 controls each section of the information processing apparatus 10 while executing a processing related to the operation of the information processing apparatus 10. The control section 13 includes a license plate recognition section 131 and a collation section 132.

[0022] The license plate recognition unit 131 acquires the camera image captured by the in-vehicle camera 20 and recognizes the character string (characters and numbers) of the license plate. Specifically, the license plate recognition unit 131 detects the image of the license plate from the camera image. The license plate recognition unit 131 can input the camera image to a machine learning model trained with the image of the license plate as a correct label to detect the image of the license plate. Then, the license plate recognition unit 131 recognizes the character string of the license plate from the image of the license plate using an existing recognition technology such as an optical character recognition / reader (OCR). Also, the license plate recognition unit 131 calculates the accuracy (reliability) of recognition each time the recognition is performed and outputs the recognized character string together with the accuracy of recognition to the collation unit 132.

[0023] The collation unit 132 acquires the license plate list from the server 30 via the communication unit 15 and collates the character string recognized by the license plate recognition unit 131 with the license plate list. The collation unit 132 transmits collation information to the server 30 in a case where it is determined that the recognized character string is included in the license plate list. The collation information is information including the time at which the collation is performed by the collation unit 132, the position information of the information processing apparatus 10 (the vehicle on which the information processing apparatus 10 is mounted) at that time, and the camera image or the recognized character string that are anonymized.

[0024] Reference Figure 2 The processing of the collation unit 132 will be described. In Figure 2 In the present embodiment, the minimum value of the accuracy of recognition is set to 0 and the maximum value is set to 1. The region A is a region in which the accuracy of recognition is below the recognition threshold value. In a case where the accuracy of recognition corresponds to the region A, the collation unit 132 regards the recognition as a failure and does not perform the collation of the character string recognized by the license plate recognition unit 131 with the license plate list. Thus, it is possible to reduce the possibility of providing false information due to false recognition.

[0025] The region B is a region whose accuracy exceeds the recognition threshold and is below the high accuracy threshold. In a case where the accuracy corresponds to the region B, the recognition is successful but the accuracy is not high, and thus the camera image used for the recognition is anonymized and transmitted to the server 30 on that basis. Specifically, the collating section 132 detects a privacy-related image from the camera image used for the recognition. The collating section 132 can input the camera image to a machine learning model that has been trained with a privacy-related image as a correct label to detect a privacy-related image. Then, the collating section 132 anonymizes the privacy-related image by performing blur processing, mosaic processing, fill processing, or the like by an existing image processing technique. The collating section 132 transmits the anonymized camera image to the server 30 via the communication section 15. By anonymizing the camera image, it is possible to provide information while taking privacy into consideration. Also, since the alert of the acquisition of information enables the image to be analyzed to determine the vehicle type or the like, it is possible to improve the accuracy of the information.

[0026] The region C is a region whose accuracy exceeds the high accuracy threshold. In a case where the accuracy corresponds to the region C, since the accuracy of the recognition is high, it is not necessary to transmit the image, and the string of the recognized license plate is transmitted to the server 30 via the communication section 15. In this case, since the image is not transmitted, there is no problem of privacy, and it is possible to reduce the amount of information.

[0027] The server 30 includes a storage section 31, a control section 32, and a communication section 33.

[0028] The storage section 31 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The storage section 31 stores a license plate list. Also, the storage section 31 stores collation information indicating a collation result.

[0029] The control section 32 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The control section 32 controls each section of the server 30 while executing processing relating to the operation of the server 30.

[0030] The communication section 33 includes at least one wireless communication interface for wireless communication with the information processing apparatus 10. The communication section 33 transmits the license plate list to the information processing apparatus 10. Also, the communication section 33 receives the collation information from the information processing apparatus 10 and stores it in the storage section 31. Note that, in the present embodiment, the server 30 is provided as one, but the server that stores the license plate list and transmits it to the information processing apparatus 10 and the server that receives the collation information from the information processing apparatus 10 and stores it can be different.

[0031] Operation Example

[0032] Next, reference will be made to Figure 3A processing step example of the information processing method will be described.

[0033] The information processing device 10 receives a license plate list from the server 30 (S101).

[0034] Also, the information processing device 10 acquires a camera image from the in-vehicle camera 20 during travel of a vehicle on which the information processing device 10 is mounted (S102), and recognizes a character string of a license plate by the license plate recognition section 131 (S103).

[0035] In a case where the accuracy of recognition exceeds the recognition threshold (S104-Yes), the information processing device 10 collates the character string recognized by the license plate recognition section 131 with the license plate list acquired from the server 30 (S105). In a case where the accuracy of recognition is below the recognition threshold (S104-No), the processing is returned to S102 without collation.

[0036] In a case where it is determined by the collation section 132 that the character string recognized by the license plate recognition section 131 is included in the license plate list (in a case of collation agreement) (S106-Yes), the information processing device 10 compares the accuracy with a high accuracy threshold. In a case of collation disagreement (S106-No), the processing is returned to S102.

[0037] In a case where the accuracy of recognition is below the high accuracy threshold (S107-No), the information processing device 10 transmits an anonymized image of the camera image to the server 30 together with the time of collation and the position information of the vehicle (S108). In a case where the accuracy of recognition exceeds the high accuracy threshold (S107-Yes), the information processing device 10 transmits the recognized character string to the server 30 together with the time of collation and the position information of the vehicle (S109).

[0038] As described above, the information processing device 10 receives a license plate list from the server 30, and recognizes a character string of a license plate from a camera image captured by the in-vehicle camera 20, and the recognized character string is sometimes included in the license plate list. In this case, the information processing device 10 compares the accuracy of recognition with a high accuracy threshold, and in a case where the accuracy is below the high accuracy threshold, transmits an anonymized image of the camera image to the server 30, and in a case where the accuracy exceeds the high accuracy threshold, transmits the recognized character string to the server 30. Thus, it is possible to promptly extract information that is useful and highly public from image information of the in-vehicle camera 20, and provide the information while considering privacy.

[0039] Program

[0040] The functions of the information processing apparatus 10 can be realized by a program related to the present embodiment being executed by a processor as the control unit 13 (i.e., by software). The program causes a computer to execute the actions of the information processing apparatus 10, and the computer functions as the information processing apparatus 10.

[0041] The program can be stored in a non-transitory computer-readable medium. The medium is a flash memory, a magnetic recording device, an optical disk, a magneto-optical recording medium, a ROM, or the like. The distribution of the program is performed by selling, transferring, or lending a portable medium storing the program. The portable medium is a Secure Digital (SD) card, a digital versatile disc (DVD), a compact disc read only memory (CD-ROM), or the like storing the program. The program can be stored in a storage of a server, and the program can be distributed to other computers from the server. The program can be provided as a program product.

[0042] The computer temporarily stores the program stored in the portable medium or the program transmitted from the server in a main storage device, for example. Then, the computer reads the program stored in the main storage device with the processor, and executes the processing according to the read program with the processor. The computer can directly read the program from the portable medium, and execute the processing according to the program. The computer can sequentially execute the processing instructed by the received program each time the program is transmitted from the server to the computer. The transmission of the program from the server to the computer can not be performed, and the processing can be executed by a so-called application service provider (ASP) type service that realizes the functions by only executing the instructions and the result acquisition. The program is information for the electronic computer-based processing, and includes the information according to the program. For example, although not a direct instruction to the computer, data having the nature of specifying the processing of the computer corresponds to "the content according to the program".

[0043] The above-described embodiments are representative examples, and various modifications or changes can be made within the scope of the present application. For example, as to the constituent modules or processing steps described in the embodiments, a plurality of them can be combined into one or one can be divided into a plurality of them.

Claims

1. An information processing device, characterized in that, have: The communications department receives a list of license plate strings (i.e., a list of license plates) from the server that are the targets of the detection; and The control unit identifies a license plate string from camera images captured by a vehicle-mounted camera. If the identified string is included in the license plate list and the accuracy of the identification is below a high accuracy threshold, the control unit transmits an image that conceals the camera image via the communication unit. If the accuracy exceeds the high accuracy threshold, the control unit transmits the identified string via the communication unit.

2. The information processing device according to claim 1, characterized in that, When the accuracy of the identification is below the high accuracy threshold, the control unit detects images involving privacy from the camera images and performs blurring, mosaicking, or overlay processing on the images to conceal the camera images.

3. The information processing apparatus according to claim 1 or 2, characterized in that, If the accuracy of the recognition is below the recognition threshold, the control unit will not verify the recognized string against the license plate list.

4. An information processing method, characterized in that, Includes the following steps: The server sends a list of license plates that are the targets of the detection; The information processing device receives the license plate list, identifies the license plate string from the camera image captured by the vehicle-mounted camera, and sends the hidden image of the camera image to the server when the identified string is included in the license plate list and the accuracy of the identification is below the high accuracy threshold. When the accuracy exceeds the high accuracy threshold, the identified string is sent to the server. and The server stores the obfuscated image or the string.

Images