JP2006178825A - Probe system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a probe system, which photographs the road conditions of unidentified multiple spots by using a probe car mounting a camera and distributes them, to secure the quality of an image, while ensuring the privacy of the photographed image. <P>SOLUTION: The probe car attaches vehicle ID information to image data of the image and transmits it. An image converting part has a obfuscating parameter α for performing image processing in an area including privacy information concerning the image. The obfuscating parameter α is set in response to the vehicle ID. When the length of the image in a longitudinal direction is defined as L, the image is expressed by an area which is obtained by dividing the upper part of the image by αL in response to the longitudinal length L and an area which is obtained by dividing the lower part of the image by (1-α)L. Then, the image processing is performed in the area positioned in the lower part of the image. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a probe system that performs image processing on privacy information in an image photographed by a probe car traveling on a road.

  Conventionally, a service has been provided in which a fixed camera is installed beside the road, and images and moving images observed at a fixed point by the fixed camera are uploaded to the network and made public. However, since the public situation is photographed and distributed, the problem of privacy may become obvious.

  Therefore, in order to protect the privacy of the public, a traffic situation image providing system that distributes an image captured by a fixed camera with processing is proposed (for example, see Patent Document 1). This system receives a fixed camera installed on the side of a road, a wireless base station that transmits images taken by the fixed camera to the Internet, and an image transmitted from the wireless base station via the Internet, and processes the image And a mobile terminal for viewing an image processed by the web server.

  In such a system, the web server performs any one of image processing such as embossing that distorts an image, processing that emphasizes edges, and mosaic processing that displays an average color for each section on the entire original image. Then, the processed and privacy-protected image is transmitted to the mobile terminal. For example, the color balance can be changed according to the degree of congestion.

  Unlike the above-described image processing, a vehicle traffic monitoring / management device that extracts information on people and vehicles from continuous images using a fixed camera and replaces them with template images prepared in advance has been proposed. (For example, refer to Patent Document 2).

  This automobile traffic monitoring / management apparatus performs a process of replacing a template camera with a TV camera that is fixed to the side of the road and shoots the road situation as a moving image (that is, continuously captures images) and a vehicle that appears in the moving image captured by the TV camera And a data processing device.

In such an automobile traffic monitoring / managing apparatus, a data processing apparatus detects a moving object (that is, a vehicle) from images continuously captured by a TV camera, and replaces the vehicle portion in the image with a template image. In this way, an image obtained by replacing the vehicle in the image with the template image is transmitted to the outside through the data transmission system. In this way, the vehicle in the photographed image is replaced with the template image to protect the privacy of the vehicle.
JP 2002-150483 A Japanese Patent Laid-Open No. 2000-231893

  In recent years, a probe system using the vehicle itself as a sensor (probe car) has been studied. In this probe system, a camera is mounted on a probe car, and information (position, time, speed, etc.) at the time of photographing is used and redistributed in cooperation with a map by a server. Thereby, the user can acquire the image of various places in real time.

  However, since this probe system also transmits an image of a public place, it is necessary to protect the privacy as in the conventional technique. Therefore, the inventors examined whether privacy in an image photographed with a probe car can be protected by the above-described conventional technique.

  First, regarding the traffic situation image providing system disclosed in Patent Document 1, since this system performs image processing on the entire captured original image, privacy can be maintained. However, since it is assumed that processing is performed on the entire image, the content itself (quality) of the image is sacrificed if an attempt is made to maintain certain privacy in the image.

  On the other hand, the automobile traffic monitoring / managing apparatus disclosed in Patent Document 2 captures a moving image and processes only a necessary portion, that is, a vehicle, so that the quality of the image content can be maintained. However, the TV camera is installed beside the road and takes a moving image only at a certain place. For this reason, when a discontinuous still image of multiple points is captured by a probe car moving on a road, it is difficult to detect the motion of the captured image. In addition, since it is necessary to perform processing on all of a large number of continuous images, the load on a machine that distributes images is high, and a certain amount of time is required until distribution. This is not to say that road conditions can be distributed in real time.

  In view of the above points, the present invention secures image quality while maintaining privacy of captured images in a probe system that captures and distributes road conditions at an unspecified number of points using a probe car equipped with a camera. It is an object of the present invention to provide a probe system that can be used.

  In order to achieve the above object, in the invention described in claim 1, the server (30) specifies a part of the image received from the probe car (10) as a place where privacy information is included, and An image conversion unit (32) that performs image processing for protecting privacy information is provided.

  As described above, in the probe system, only the area where the privacy information of the image taken by the probe car is captured is selectively image-processed. As a result, only the area where the privacy information is copied is image-processed, and the entire image is not subjected to image processing. Therefore, only the privacy information can be protected while maintaining the quality of the entire image.

  In the invention according to claim 2, the probe car is adapted to transmit the vehicle ID information to the image data of the image, and the image conversion unit performs image processing on an area including privacy information in the image. The image processing parameter α is set according to the vehicle ID. When the vertical length of the image is L, the image is set according to the vertical length L. The upper part of the image is represented by an area partitioned by αL, and the lower part of the image is represented by an area partitioned by (1-α) L, and image processing is performed on the lower region of the image.

  In the image, the lower part of the image is taken near the camera, and the upper part of the image is taken away from the camera. Therefore, image processing is performed by determining a region ((1-α) L) for image processing using vehicle ID information, for example, an image processing parameter α corresponding to the vehicle type. In this way, since only the lower part of the image close to the shooting point is processed, the quality of the entire image can be ensured. Further, privacy information of, for example, a license plate that is predicted to be frequently photographed at the lower part of the image can be protected.

  In the invention according to claim 3, the image processing parameter α is set to a value larger than the value of the image processing parameter corresponding to the arbitrary speed when the speed of the probe car is larger than the arbitrary speed. When the speed is smaller than an arbitrary speed, the image processing parameter is set to a value smaller than the value of the image processing parameter corresponding to the arbitrary speed.

  In this way, the value of the image processing parameter α is set according to the speed. As a result, when the probe car speed is high, the object near the probe car is photographed in a blurred manner, so that the image processing area can be reduced by setting α large. That is, an area where image processing is not performed can be ensured, and image quality can be sufficiently secured. On the other hand, when the speed of the probe car is slow, it is considered that the front is clearly photographed. Therefore, privacy information can be protected by reducing the value of α and widening the image processing area.

  In the invention described in claim 4, the probe car transmits the image data of the image with the position information obtained by capturing the image, and the server stores the map database (36) in which the map data is stored. And receiving a request for an image including the destination (LM) from the user via the wide area network, the image conversion unit calculates the position of the image based on the positional relationship between the probe car and the destination based on the position information and the map data. It is characterized in that image processing is performed on an area excluding the destination.

  Thus, map data is used. Thereby, in the image, an area other than the target object can be selected as an area for image processing from the positional relationship between the probe car and the target object. Thereby, privacy information other than the destination can be protected.

  In the invention according to claim 5, the probe car is equipped with a plurality of cameras for photographing the front, photographs a parallax image by each camera, and transmits image data of the parallax image. When the image data of the parallax image is received by the server via the image, the image conversion unit obtains the distance between the probe car and the object captured in the parallax image based on the parallax image, and the distance is the privacy information of the image. It is characterized in that image processing is performed on an object when the distance predicted to be captured is exceeded.

  Thus, using the parallax image, the distance to the object ahead is measured, and when the distance exceeds the distance where the privacy information of the image is expected to be captured, only that portion is image processed. As a result, it is possible to selectively perform image processing only on a part of the image where privacy information is considered to be clearly visible, and privacy information can be protected while ensuring image quality.

  In the invention according to claim 6, the server determines whether or not to perform image processing based on a priority rule table (38) in which priority rules for preferentially performing image processing on images are stored, and image When it is determined that processing is to be performed, the image processing unit has a priority processing determination unit (37) that stores the name of the image in a priority processing table (39) that performs image processing with priority. The image conversion unit is stored in the priority processing table. It is characterized in that the image name is referred to and the image processing of this image is performed.

  In this way, it is determined whether or not to perform image processing according to the priority rule for performing image processing. Thereby, it is possible to preferentially select and perform image processing on an image to be image-processed from among a large number of images transmitted from the probe car.

  The invention described in claim 7 is characterized in that the lens of the camera mounted on the probe car is focused in the distance.

  In this way, a lens that is in focus far away is adopted for the camera. Thereby, it is possible to blur and photograph a place near the probe car where privacy information is photographed.

  In the invention described in claim 8, image data of an image taken by a camera mounted on the probe car (10) is received via the wide area network (20), and a part of the received image is privacy-protected. An image conversion unit (32) that performs image processing to protect the privacy information for a part of the information is specified as a place where information is included, and the terminal (40) operated by the user via a wide area network When a desired image is requested, information on the request is received, and an image processed by the image conversion unit in response to the request is delivered to the terminal.

  By using such a server, it is possible to perform image processing so that privacy information is hidden in an image to be distributed to the user in the probe system.

  In addition, the code | symbol in the bracket | parenthesis of each said means shows the correspondence with the specific means as described in embodiment mentioned later.

(First embodiment)
Hereinafter, a first embodiment of the present invention will be described with reference to the drawings.

  FIG. 1 is a system configuration diagram of a probe system according to the first embodiment of the present invention. As shown in FIG. 1, the probe system includes a probe car 10, a wide area network 20, a server 30, and a terminal 40.

  The probe car 10 is a vehicle on which a camera is mounted and the road situation is photographed with this camera. For example, a bus, a taxi, or a patrol car is employed for such a probe car 10, and a vehicle ID that can identify each vehicle is set in each probe car 10. The camera mounted on the probe car 10 is fixed to the vehicle so that the front of the vehicle can be photographed. For example, the camera captures road conditions every 10 seconds when the blinker is activated or when the vehicle starts or stops. Furthermore, the probe car 10 is equipped with a GPS so that the position and time of the shooting location can be detected.

  In such a probe car 10, when a road situation is photographed by a camera, a vehicle ID, an image file name, a photographing position, a photographing time, a photographing speed, a photographing direction, blinker information, and the like are included in the image. The image data to which the information is attached is transmitted to the server 30.

  The wide area network 20 is a well-known Internet that transmits image data transmitted from the probe car 10 to the server 30.

  The server 30 identifies a part of the image received from the probe car 10 as a place where privacy information is included, performs image processing (privacy protection processing) for protecting the privacy information with respect to this part, and the image processed image Data is distributed to users. Such a server 30 is a known computer having a CPU, a memory, a hard disk, and the like.

  FIG. 2 is a block configuration diagram of the server 30. As shown in FIG. 2, the server 30 includes a probe information reception unit 31, an image conversion unit 32, a database management unit 33, an image database 34, and a probe information distribution unit 35.

  The probe information receiving unit 31 is an interface that receives image data from the probe car 10 via the wide area network 20. The probe information reception unit 31 outputs image data received via the Internet to the image conversion unit 32.

  The image converting unit 32 performs privacy protection processing on the image input from the probe information receiving unit 31. The image conversion unit 32 has a blur parameter α for performing this privacy protection process. Note that the blur parameter α corresponds to the image processing parameter α of the present invention. The image processing performed by the image conversion unit 32 will be described in detail in the operation of this system. The image data processed by the image conversion unit 32 is output to the database management unit 33.

  The database management unit 33 manages image data that has undergone image processing. Specifically, the database management unit 33 stores image data in an image database 34 described later, reads image data from the image database 34 in response to a request from a terminal 40 described later, and outputs the image data to the probe information distribution unit 35. Do that.

  The image database 34 stores the image data image-converted by the image conversion unit 32. In this image database 34, together with image data of one image, a vehicle ID, a photographing time, a photographing position, a vehicle speed, a photographing direction, and an image file name as image information of the image are stored.

  The probe information distribution unit 35 is an interface that outputs image data of an image subjected to image processing to the wide area network 20. That is, the probe information distribution unit 35 transmits the image data input from the database management unit 33 to the Internet.

  The terminal 40 shown in FIG. 1 is a receiver that receives image data to be distributed. Examples of such a terminal 40 include a PC 41, a vehicle 42, and a mobile phone 43. The user can request the server 30 for an image using these terminals 40 and receive the image data transmitted from the server 30, thereby knowing the road condition of the place that the user wants to check.

  Note that the vehicle 42 itself is not the terminal 40, and for example, a car navigation system mounted on the vehicle 42 functions as the terminal 40.

  Next, the operation of the probe system will be described with reference to FIGS. In the following, the operation of the entire system will be described by following image data of one image taken by an arbitrary probe car 10.

  First, the road situation is photographed by a camera mounted on the probe car 10 on the road. The image data of the image thus captured by the probe car 10 is transmitted to the server 30 via the wide area network 20 together with the vehicle ID, the imaging time, the imaging position, the vehicle speed, the imaging direction, and the image file name information.

  Hereinafter, the processing in the server 30 will be described with reference to FIG. FIG. 3 is a diagram showing the processing contents executed by the server 30 of the probe system. This process is performed by the CPU executing a processing program stored in the server 30.

  As shown in FIG. 3, first, in step 100, image data from the probe car 10 is acquired. That is, image data is input from the probe car 10 to the probe information receiving unit 31 of the server 30 via the wide area network 20.

  In the subsequent steps, privacy protection processing is performed on the image. Here, how the image is processed will be described with reference to FIG. In the present embodiment, processing is not performed on the entire image, but processing is performed only on an area where privacy should be protected in the image, so that the quality of the image is maintained.

  FIG. 4 is a diagram for explaining an image processing area for a captured image. As shown in FIG. 4, when the front of the vehicle is photographed by the camera of the probe car 10, the rear portion of the vehicle is photographed when the vehicle is present ahead. At that time, the license plate of the vehicle is also photographed.

  In the present embodiment, as shown in FIG. 4, an image processing is performed on an area in which a license plate is captured so as to protect privacy information such as a license plate in a captured image. Specifically, the length of the captured image in the vertical direction is set to L, and only the region in which the weight of the blurring parameter α is considered for the length L is subjected to image processing.

  That is, the image is formed with a region (non-processed region) formed when the vertical length L of the image is αL and a region (processed) formed when the length L is (1−α) L. Area). As shown in FIG. 4, the machining area is narrowed as the value of α is large, and the machining area is widened as the value of α is small. Specific values of the blur parameter α are shown in FIG.

  FIG. 5 is a table showing the blur parameter α corresponding to the vehicle ID. As shown in FIG. 5, the blur parameter α is assigned to the vehicle ID. Depending on the position of the camera mounted on the probe car 10 (height from the road), for example, where the license plate of the vehicle ahead appears in the image changes. For example, when the probe car 10 is a bus, since the camera is installed at a high place away from the road surface, it is conceivable that the license plate of the vehicle appears in the vicinity of the center of the image. Therefore, it is necessary to process a wider area of the image. For this reason, for example, if the vehicle ID of the bus is 0001, the blur parameter α is 0.5, that is, the lower half of the image is processed.

  Further, in the case where the probe car 10 is a vehicle having a vehicle height lower than that of a bus, such as a taxi, even if the front vehicle is photographed with a camera, it is considered that the license plate appears in the lower part of the image. Therefore, the lower range of the image only needs to be processed. For example, if the taxi vehicle ID is 0002, the blur parameter α is 0.7, that is, the region corresponding to 30% of the vertical length of the image is processed. It will be. As described above, the blur parameter α is set according to the vehicle type of the probe car 10 equipped with the camera, and the privacy protection process is performed on the image based on the blur parameter α.

  Therefore, in step 110, the value of α is retrieved from the vehicle ID. That is, the blur parameter α corresponding to the vehicle ID is retrieved from the image conversion unit 32 from the vehicle ID added to the image data.

  In step 120, image conversion processing is performed by the image conversion unit 32. This image conversion process will be described with reference to FIG. FIG. 6 shows the contents of the image conversion process. First, as shown in FIG. 6A, an image processing range is detected. That is, based on the blur parameter α searched in step 110, a processing area to be subjected to image processing is determined.

  Subsequently, the gradation reduction processing of the processing area is performed on the image. As shown in FIG. 6B, the subtractive gradation process is a process of reducing, for example, 256 colors so that the number of colors is smaller than that. By this gradation reduction process, the number of colors in the processing area in the image is reduced. In FIG. 6, the gradation indicating the color density is expressed by the density of point hatching.

  Thereafter, a selection process is performed. In this selection process, as shown in FIG. 6C, in the area subjected to the gradation reduction process, the gradation of the color of an arbitrary dot is set to the gradation with the largest number of dots around the dot. It is a process to match. This process is performed for all dots in the processing region of M rows and N columns. By performing this process, the processing area of the image is blurred.

FIG. 7 shows images before and after the privacy protection process. As shown in this figure, the numbers on the license plate of the vehicle after processing are blurred and not visible with respect to the image before processing. However, the road conditions captured in the image are well understood,
The quality of the entire image is maintained. In this way, only the areas in the image where privacy should be protected are processed. The image data of the processed image is output from the image conversion unit 32 to the database management unit 33.

  Subsequently, in step 130 shown in FIG. 3, database registration is performed. This is because when the image data of the image subjected to the privacy protection process in the above step 120 is input to the database management unit 33, the image data of the image after the privacy protection process is stored in the image database 34 by the database management unit 33. .

  In response to the privacy protection processing and storage of the image data in this way, the user requests the server 30 for an image near the destination in order to know the road conditions near the destination, for example. As described above, when a user requests an image from the server 30, the image is transmitted to the user as follows.

  First, the user requests the server 30 for an image of a place that the user wants to browse using the terminal 40. Thereby, the request information is transmitted from the terminal 40 to the probe information distribution unit 35 of the server 30 via the wide area network 20. Upon receiving the request information, the probe information distribution unit 35 outputs the request information to the database management unit 33.

  Based on the request information, the database management unit 33 accesses the image database 34 to read out image data of the corresponding image, and outputs the image data to the probe information distribution unit 35. Note that the request information includes a location, time, and the like that the user wants to browse, and the database management unit 33 reads out image data of an image that matches the request information from the image database 34.

  The probe information distribution unit 35 distributes the image data of the image input from the database management unit 33 to the terminal 40 that transmitted the request information via the wide area network 20. Then, the terminal 40 receives image data of an image in which the road situation at the location requested by the user is captured. Thereby, the user can confirm the road condition of the requested location. At this time, the image delivered to the terminal 40 is subjected to privacy protection processing. For this reason, the privacy of the public is maintained in the image, and the quality of the image is ensured because only the area where the privacy should be protected is processed in the image as described above.

  As described above, in the present embodiment, only the area where the privacy information of the image captured by the probe car 10 is captured is selectively subjected to image processing. As a result, only the area where the privacy information is copied is image-processed, and the entire image is not subjected to image processing. Therefore, only the privacy information can be protected while maintaining the quality of the entire image.

  In the image, the lower part of the image is taken near the camera of the probe car 10 and the upper part of the image is taken far from the camera. Therefore, the blurring parameter α is set according to the vehicle ID, and the region ((1-α) L) for image processing is determined by the blurring parameter α to perform image processing. In this way, since only the lower part of the image close to the shooting point is processed, the quality of the entire image can be ensured.

(Second Embodiment)
In the present embodiment, only different parts from the first embodiment will be described. The present embodiment is different from the first embodiment in that a processing region is determined according to the speed of the probe car 10 when privacy protection processing is performed on an image taken while the probe car 10 is traveling. That is, in this embodiment, it is suitable for maintaining the privacy of, for example, a pedestrian (its face). Hereinafter, the probe system in the second embodiment will be described.

  As described above, the processing region of the image is determined according to the speed of the probe car 10. For this reason, the image conversion unit 32 of the server 30 used in the present embodiment has a function of determining the blur parameter α according to the speed of the probe car 10.

  In the present embodiment, the blur parameter α is set to a value larger than the blur parameter value corresponding to the arbitrary speed when the speed of the probe car 10 is higher than the arbitrary speed, and the speed of the probe car 10 is arbitrary. Is smaller than the blur parameter value corresponding to an arbitrary speed. This will be specifically described below.

FIG. 8 is a diagram showing the relationship between the speed of the probe car 10 and the blurring parameter α. As shown in FIG. 8, the speed of the probe car 10 is a constant blur parameter α ₁ from 0 to the speed v ₁ , and the blur parameter α increases with a constant gradient from the speed v ₁ to the speed v _2. When the speed v ₂ is exceeded, a constant blur parameter α ₂ is obtained.

Blurring parameter α of between speed velocity v ₁ of the probe car 10 to the speed v ₂ can be determined by Equation 1 below. If the speed of the probe car 10 is v,
(Formula 1)
α = {(α ₂ −α ₁ ) / (v ₂ −v ₁ )} v + {(v ₂ α ₁ −v ₁ α ₂ ) / (v ₂ −v ₁ )}
When the speed of the probe car 10 is a value between the speed v ₁ and the speed v ₂ , the image conversion unit 32 calculates the blur parameter α based on the above formula 1. The values of α ₁ , α ₂ , v ₁ , v ₂ can be arbitrarily set by the administrator of the server 30.

  As described above, in the present embodiment, the speed of the probe car 10 is high, and when photographing road conditions, there is a large difference in relative speed between the probe car 10 and the vicinity thereof, so The blur is expected to be large. For this reason, the area | region which performs privacy protection processing can be made small by enlarging the value of the blurring parameter α. In some cases, the camera captures the face of a pedestrian. However, since the traveling probe car 10 approaches the pedestrian, the captured image due to the speed of the probe car 10 is blurred. Therefore, the pedestrian's privacy information is protected without photographing the pedestrian's face in detail.

  Next, the operation of the probe system according to the present embodiment will be described with reference to FIG. FIG. 9 is a diagram showing the processing contents executed by the server 30 of the probe system according to the present embodiment. First, in step 200, processing similar to that in step 100 of the first embodiment is performed.

  In step 210, the blur parameter α is calculated from the speed of the probe car 10. That is, in the image conversion unit 32, the speed of the probe car 10 attached to the image data acquired in step 210 is referred to, and the blurring parameter α corresponding to the speed is determined as described above.

  In steps 220 and 230, processing similar to that in steps 120 and 130 of the first embodiment is performed.

  As described above, in the present embodiment, the area for image privacy protection processing is automatically determined using the speed of the probe car 10 at the time of photographing.

  As described above, the value of the blur parameter α is set according to the speed of the probe car 10. Thereby, when the speed of the probe car 10 is high, the object near the probe car 10 is photographed by blurring. Therefore, by setting α to a large value, the image processing area can be reduced. On the other hand, when the speed of the probe car 10 is low, it is considered that the front is clearly photographed. Therefore, the privacy information can be protected by reducing the value of α and widening the image processing area.

(Third embodiment)
In the present embodiment, only parts different from the first and second embodiments will be described. In the probe system shown in the present embodiment, privacy information other than landmarks in an image taken with a landmark, for example, is reduced in the image taken with the camera of the probe car 10. That is, in the present embodiment, for example, privacy protection processing is performed on information other than the landmark that the user is requesting. Hereinafter, the probe system according to the third embodiment will be described. Note that the landmark means a destination.

  FIG. 10 is a block diagram of the server 30 according to the third embodiment. The components of the server 30 used in the present embodiment are the same as those of the server 30 used in the first and second embodiments, but the input / output paths for image data are different. In the present embodiment, the server 30 is provided with a map database 36. The map database 36 is well-known map data stored on, for example, a DVD or a hard disk.

  In the present embodiment, as described above, the privacy protection process is performed on the image data of the image requested by the user, and the processed image data is distributed to the user. That is, the image conversion unit 32 of the server 30 of this embodiment has a function of reducing privacy information other than landmarks in the image.

  Hereinafter, the operation of the probe system according to the present embodiment will be described with reference to FIGS. 10 and 11.

  First, when image data is transmitted from the probe car 10, the image data is received by the probe information receiving unit 31 of the server 30 via the wide area network 20. Then, the image data is input from the probe information receiving unit 31 to the database management unit 33. The image data input to the database management unit 31 is output to the image database 34 and stored in the image database 34.

  On the other hand, when the user requests landmark information from the server 30 using the terminal 40, the request information is received by the probe information distribution unit 35 of the server 30 via the wide area network 20 and output to the database management unit 33.

  Then, the database management unit 33 that has received the request information reads an image of the request location (position) from the image database 34 and outputs the image data of the read image to the image conversion unit 32. Further, the database management unit 33 reads the map data of the requested place (position) from the map database 36 and outputs the map data to the image conversion unit 32.

  Next, the image conversion unit 32 performs processing for protecting privacy information other than the landmarks in the image. FIG. 11 is a diagram showing the content of privacy protection processing performed by the image conversion unit 32. FIG. 11A shows a positional relationship between the probe car 10 and the landmark LM, and FIG. 11B shows an area where privacy protection processing is performed on the image based on the positional relationship between the probe car 10 and the landmark LM. FIG. 11C is a diagram showing an example of an image subjected to privacy protection processing.

  As shown in FIG. 11A, from the image capturing position of the probe car 10 and map data, the positional relationship between the probe car 10 and the landmark LM is such that the probe car 10 and the landmark LM in the traveling direction of the probe car 10. And the distance y between the probe car 10 and the landmark LM in the direction perpendicular to the traveling direction of the probe car 10, and the store width w of the landmark LM.

In such a positional relationship between the probe car 10 and the landmark LM, as shown in FIG. 11B, a landscape including the landmark LM is photographed at the viewing angle γ of the camera. The landmark LM is photographed in the range of the viewing angle α of the camera. That is, privacy protection processing is performed on an area other than the viewing angle α where the landmark LM is captured in the image. In this embodiment, the traveling direction of the probe car 10 is used as an axis, and the viewing angle from the axis to the boundary of the region defined by the viewing angle α is β. These viewing angles α and β are expressed as α = tan ⁻¹ ((x + w) / y) and β = tan ⁻¹ (x / y) from the relationship of trigonometric functions.

  By defining α and β, as shown in FIG. 11B, the length at which the landmark LM is displayed with respect to the horizontal length T of the image and the privacy protection processing is not performed is αT. / Γ. Note that the length of the privacy protection process including the viewing angle β with respect to the horizontal length T of the image is (T / 2) + (βT / γ).

  The image conversion unit 32 performs privacy protection processing on an area other than the area including the landmark LM in the image in the same manner as in the first embodiment. When the privacy protection process is performed in this way, as shown in FIG. 11C, the privacy of the area other than the area where the landmark LM appears in the image is protected.

  When the privacy protection process is performed by the image conversion unit 32 in this manner, the image data of the protected image is output to the probe information distribution unit 35 and distributed to the terminal 40 via the wide area network 20. Thereby, the user can browse the state of the landmark LM on the terminal 40. At this time, since the area other than the landmark LM in the image is protected for privacy, it is not necessary for the user to know the privacy information in the image.

  As described above, map data is used in this embodiment. Thereby, in the image, an area other than the target object can be selected as an area for image processing from the positional relationship between the probe car 10 and the target object. Thereby, privacy information other than the destination can be protected.

(Fourth embodiment)
In the present embodiment, only different parts from the first embodiment will be described. In the probe system shown in this embodiment, two cameras are mounted on the probe car 10 and the privacy protection process is determined using the parallax of each camera. By using the parallax image in this way, it is possible to perform the privacy protection process by limiting only a place near the probe car 10 in the photographed image. Hereinafter, the probe system according to the fourth embodiment will be described.

  As described above, in the present embodiment, two cameras are mounted on the probe car 10. Each camera is separated and mounted on the probe car 10 so that parallax occurs in the images captured by the respective cameras. Then, the probe car 10 transmits the image data of the images captured by the cameras and the distance between the preceding vehicle and the host vehicle to the server 30 via the wide area network 20.

  Hereinafter, the operation of the probe system according to the present embodiment will be described with reference to FIG. FIG. 12 is a diagram illustrating processing contents executed by the server 30 of the probe system according to the present embodiment.

  First, in step 300, the same processing as in step 100 of the first embodiment is performed.

  In step 310, distance measurement is performed using a parallax image. Specifically, when image data of an image captured by each camera is input to the image conversion unit 32 in FIG. 2, the distance between the preceding vehicle and the probe car 10 is obtained based on the parallax of each image. .

  In step 320, it is determined whether or not the distance obtained in step 310 exceeds a predetermined distance Z. The predetermined distance Z is a reference parameter for determining whether or not privacy processing protection is applied to an image, and can be freely set by the administrator of the server 30. If the distance obtained in step 310 exceeds the predetermined distance Z, the process proceeds to step 340. On the other hand, if the distance obtained in step 310 is less than the predetermined distance Z, the process proceeds to step 330.

  In step 330, a privacy protection process is performed on a portion closer to the predetermined distance Z. This is done by the same method as in the first embodiment. FIG. 13 is a diagram showing an example in which privacy protection processing is performed only on a portion below the predetermined distance Z in front of the vehicle, that is, only the front vehicle. FIG. 13A is an image before privacy protection processing, and FIG. 13B is an image after privacy protection processing.

  As shown in FIG. 13A, for example, a vehicle is traveling in front of the probe car 10 and the state is photographed, and the distance between the vehicle and the probe car 10 is shorter than the predetermined distance Z. And Therefore, as shown in FIG. 13B, only the portion of the vehicle ahead is subjected to privacy protection processing in the image.

  In step 340, the same processing as in step 130 of the first embodiment is performed.

  As described above, the distance from the front object is measured using the parallax images taken by a plurality of cameras. Then, when the distance exceeds the distance predicted to capture the privacy information of the image, only that portion is subjected to image processing. As a result, it is possible to selectively perform image processing only on a part of the image where privacy information is considered to be clearly visible, and privacy information can be protected while ensuring image quality.

(Fifth embodiment)
In the present embodiment, only different portions from the first to fourth embodiments will be described. In the probe system shown in the present embodiment, a camera lens mounted on the probe car 10 is used with a focus at a long distance. Hereinafter, the probe system in the fifth embodiment will be described.

  The configuration of the probe system according to the present embodiment is, for example, a configuration in which the image conversion unit 32 is eliminated from the server 30 of the first embodiment. That is, the image data received by the probe information receiving unit 31 is directly input to the database management unit 33.

  As described above, in this embodiment, the focus of the lens of the camera mounted on the probe car 10 is focused far away. As a result, it is possible to clearly photograph a far object and not to clearly photograph a nearby object. In other words, it is possible to blur and photograph a subject that should protect privacy, such as a nearby object such as a license plate of a forward vehicle or a pedestrian.

  FIGS. 14A and 14B are diagrams for explaining the contents of the fifth embodiment. FIG. 14A is a diagram showing a photographing range of a camera mounted on the probe car 10, and FIG. 14B is an example of a photographed image. FIG. As shown in FIG. 14A, in the range of the radius d0 centering on the probe car 10, the camera lens is out of focus, and the captured image exists within this range. Things are taken blurry. That is, photographing itself is privacy protection processing. On the other hand, since the camera is in focus at a position far from the probe car 10, for example, a building, a signboard, and the like are photographed clearly.

  Further, as shown in FIG. 14B, the lower part of the image shows a place close to the probe car 10. For this reason, the camera is not in focus, the captured image is blurred, and privacy information is protected. The upper part of the image is far away from the probe car 10 so that the camera is in focus. However, since the shooting size of the object whose privacy should be protected is small, privacy information cannot be confirmed on the image, so privacy protection processing must be performed There is no.

  As described above, in the present embodiment, a lens that is in focus at a distance is used for the camera. Thereby, it is possible to blur and photograph a place near the probe car 10 where privacy information is photographed.

(Sixth embodiment)
In the present embodiment, only parts different from the first to third embodiments will be described. In the present embodiment, privacy-related information is preferentially detected and privacy protection processing is performed. Hereinafter, a probe system in the sixth embodiment will be described.

  FIG. 15 is a block configuration diagram of the server 30 according to the sixth embodiment. As shown in FIG. 15, the server 30 of the present embodiment has a configuration in which a priority processing determination unit 37, a priority rule table 38, and a priority processing table 39 are provided to the server 30 of the first embodiment. Yes.

  The priority processing determination unit 37 has a function of determining whether or not to perform privacy protection processing on an image in accordance with a priority rule preset in a priority rule table 38 to be described later. When the priority processing determining unit 37 receives the image data of the image from the probe information receiving unit 31, the priority processing determining unit 37 accesses the priority rule table 38 and checks whether information attached to the image (imaging position, speed, etc.) corresponds to the priority rule. Determine whether or not. If the image information corresponds to the priority rule, the image is stored in a priority processing table 39 described later, and the image data is output to the database management unit 33.

  The priority rule table 38 is a table in which priority rules serving as determination materials for performing privacy protection processing on images are set, and priority rules are set in descending order of priority. This priority rule assumes that there is a high probability that privacy information is captured more clearly in an image captured by the camera of the probe car 10, and in order to perform privacy protection processing on the image captured in such a case It is a criterion.

  For example, when the front of the probe car 10 is photographed while the vehicle is stopped, there is a high possibility that the license plate of the vehicle located in front of the probe car 10 is photographed clearly. Therefore, when the vehicle speed of the probe car 10 is 0, the privacy protection process is preferentially performed. Further, when the vehicle type of the probe car 10 is a bus, since the camera is installed at a high position from the road, there is a high possibility that a wide area will be captured clearly. Therefore, when the probe car 10 is a bus, privacy protection processing is preferentially performed. In this way, priority rules are set in accordance with situations where privacy information is clearly captured, and privacy protection processing is actively performed on images corresponding to the priority rules. The priority rule is set by the administrator of the server 30.

  The priority processing table 39 is a table in which the images determined to be subjected to privacy protection processing by the priority processing determination unit 37 are arranged in priority order. Here, the priority order is the order stored in 39 in the priority processing table.

  Next, the operation of the server 30 of the probe system according to the present embodiment will be described with reference to FIG. FIG. 16 is a diagram illustrating processing contents executed by the server 30 according to the present embodiment. In the present embodiment, the processing for preferentially picking up the image for which privacy protection processing is performed in the image transmitted from the probe car 10 (image pickup processing) and the privacy protection processing for the picked-up image are asynchronous, that is, independent of each other. To be made.

  First, processing for preferentially picking up an image for which privacy protection processing is performed on the image will be described. In FIG. 16, in step 400, the same processing as in step 100 of the first embodiment is performed.

  In step 410, it is determined whether the image information of the image corresponds to the priority rule. Specifically, when image data of an image is input from the probe information receiving unit 31 to the priority processing determination unit 37, the priority processing determination unit 37 accesses the priority rule table 38, and the image information of the image corresponds to the priority rule. Whether or not to do so is determined from a priority rule with a high priority.

  If the image information of the image does not correspond to the priority rule, the process proceeds to step 430. On the other hand, if the image information corresponds to at least one priority rule among the priority rules, the process proceeds to step 420 in order to perform privacy protection processing on the image.

  In step 430, priority processing table registration is performed. That is, the image determined to be preferentially subjected to the privacy protection process in step 420 is stored in the priority processing table 39 together with the image file name according to the priority. In this way, the processing for preferentially picking up the image for which privacy protection processing is performed on the image ends.

  If it is determined in step 410 that the privacy protection process is not preferentially performed, step 430 is executed. In step 430, the same processing as in the first embodiment 130 is performed.

  On the other hand, the privacy protection process is performed on the image stored in the priority processing table 39 by the image conversion unit 32. In step 500 of FIG. 16, the image processing process is initialized. This is a process for erasing the previously performed image processing content and enabling a new image processing.

  In step 510, the priority processing table 39 is referred to. That is, the image conversion unit 32 accesses the priority processing table 39 and refers to a high-priority image file name to be subjected to privacy protection processing. Furthermore, the image conversion unit 32 instructs the database management unit 33 to read the referenced image file name from the image database 34, and acquires image data of the image.

  In steps 520 and 530, processing similar to that in steps 120 and 130 of the first embodiment is performed.

  In step 540, the record of the priority processing table 39 is deleted. That is, the image file name referred to in step 510 is deleted from the priority processing table 39 by the image conversion unit 32. Thereafter, the process returns to step 500 again, and privacy protection processing is sequentially performed on the images stored in the priority processing table 39.

  As described above, whether or not to perform image processing is determined according to the priority rule for performing image processing. Thereby, it is possible to preferentially select and perform image processing on an image to be processed from among a large number of images transmitted from the probe car 10.

(Other embodiments)
In the first to sixth embodiments, the probe system transmits and receives image data via the wide area network 20, that is, the Internet. You may make it transmit to. Although the real-time property is inferior, the data may be directly copied to the server 30 once a day using a flash memory or a portable hard disk.

  In the fourth embodiment, the distance between the front vehicle and the probe car 10 is measured based on the two parallax images. For example, the distance between the front vehicle and the probe car 10 is measured by a sensor such as a laser radar. The distance may be measured.

  In the first to fourth and sixth embodiments, the privacy protection process performed by the image conversion unit 32 of the server 30 is not limited to blurring the image, and privacy protection information may be hidden by changing the color tone or the like. .

  Note that the steps shown in each figure correspond to means for executing various processes.

1 is a system configuration diagram of a probe system according to a first embodiment of the present invention. It is a block block diagram of the server shown by FIG. It is the figure which showed the processing content performed in the server of the probe system shown by 1st Embodiment. It is a figure for demonstrating the image processing area | region with respect to the image | photographed image. It is the figure which showed the blurring parameter (alpha) corresponding to vehicle ID with a table | surface. It is the figure which showed the content of the image conversion process which concerns on 1st Embodiment. It is the figure which showed the image before a privacy protection process and after a process. It is the figure which showed the relationship between the speed of a probe car, and the blurring parameter (alpha). It is the figure which showed the processing content performed with the server of the probe system which concerns on 2nd Embodiment. It is a block block diagram of the server which concerns on 3rd Embodiment. It is the figure which showed the content of the privacy protection process which the image conversion part which concerns on 3rd Embodiment performs, (a) is the figure which showed the positional relationship of a probe car and a landmark, (b) is a probe car and a landmark. (C) is a diagram showing an example of an image subjected to privacy protection processing. It is the figure which showed the processing content performed with the server of the probe system which concerns on 4th Embodiment. It is the figure which showed the example which performed the privacy protection process only to the part below the predetermined distance Z in the front of a vehicle, (a) is a figure before a privacy protection process, (b) is a figure after a privacy protection process. It is a figure explaining the content of 5th Embodiment, (a) is the figure which showed the imaging | photography range of the camera mounted in the probe car, (b) is the figure which showed the image processing result. It is a block block diagram of the server which concerns on 6th Embodiment. It is the figure which showed the processing content performed in the server of the probe system which concerns on 6th Embodiment.

Explanation of symbols

10 ... probe car, 20 ... wide area network, 30 ... server,
32 ... Image conversion unit, 36 ... Map database, 37 ... Priority processing determination unit,
38 ... Priority rule table, 39 ... Priority processing table, 40 ... Terminal.

Claims (8)

A probe car (10) for photographing the front or the periphery thereof with a camera and transmitting image data of the photographed image;
The image data of the image and the vehicle information are received from the probe car via the wide area network (20), and the privacy information photographed in the image is concealed, and the user requests via the wide area network. A server (30) for distributing an image subjected to privacy protection processing according to
A probe system comprising: a terminal (40) for requesting a desired image from images captured by the probe car via the wide area network and receiving the requested image from the server;
The server includes an image conversion unit (32) that identifies a part of an image received from the probe car as a place where privacy information is included, and performs image processing for protecting the privacy information with respect to the part. A probe system characterized by that. The probe car is adapted to transmit vehicle ID information attached to the image data of the image,
The image conversion unit has an image processing parameter α for performing image processing on an area including the privacy information in the image, and the image processing parameter α is set according to the vehicle ID, When the length in the vertical direction is L, the image is divided into an area where the upper part of the image is divided by αL and a lower part of the image is divided by (1-α) L according to the length L in the vertical direction. The probe system according to claim 1, wherein image processing is performed on a region below the image. The image processing parameter α is set to a value larger than the value of the image processing parameter corresponding to the arbitrary speed when the speed of the probe car is higher than the arbitrary speed, and the speed of the probe car is set to the arbitrary speed. 3. The probe system according to claim 2, wherein the probe system is set to a value smaller than the value of the image processing parameter corresponding to the arbitrary speed when the speed is smaller than the first speed. The probe car is adapted to transmit the image data of the image with the location information obtained by capturing the image,
When the server has a map database (36) in which map data is stored and receives a request for an image including a destination (LM) from the user via the wide area network, the image conversion unit The image processing is performed on a region excluding the destination in the image from a positional relationship between the probe car and the destination based on information and the map data. The probe system according to any one of the above. The probe car is equipped with a plurality of cameras that photograph the front, photographs parallax images with each camera, and transmits image data of the parallax images.
When the image data of the parallax image is received by the server via the wide area network, the image conversion unit calculates a distance between the probe car and an object captured in the parallax image based on the parallax image. 5. The image processing is performed on the object when the distance exceeds a distance where the privacy information of the image is predicted to be captured. 6. Probe system as described in one. The server determines whether or not to perform image processing based on a priority rule table (38) in which priority rules for preferentially performing image processing on the image are stored. A priority processing determination unit (37) for storing the name of the image in a priority processing table (39) for preferentially image processing;
6. The image conversion unit according to claim 1, wherein the image conversion unit refers to the name of an image stored in the priority processing table and performs image processing on the image. Probe system. The probe system according to claim 1, wherein a lens of a camera mounted on the probe car is focused far away. The image data of the image taken by the camera mounted on the probe car (10) is received via the wide area network (20), and a part of the received image is specified as a place including privacy information, An image conversion unit (32) that performs image processing for protecting the privacy information with respect to the portion;
When a desired image is requested from the terminal (40) operated by the user via the wide area network,
A server that receives the information of the request and distributes the image processed by the image conversion unit to the terminal in response to the request.

Images