JP2017067464A - Information processing device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To allow a road sign to be appropriately recognized by having a driver select a recognition result of the road sign.SOLUTION: An information processing device comprises a control unit 10 that obtains a photographic image obtained by photographing the outside of a vehicle, finds whether the photographic image includes a road sign or not, and recognizes a road sign included in the photographic image. The control unit 10 compares the recognized road sign with sign information in road information data 31, and makes a display to have a driver select any of the items on a display unit 12 if the recognized road sign is different from the sign information in the road information data 31.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus.

  As a background art of this technical field, Japanese Patent Laid-Open No. 2004-228561 discloses that “the image processing unit 25 performs image processing on an image captured by the camera 14 and specifies the contents indicated by the sign by collating with the sign pattern. The management unit 24 updates the map data and traffic information in the data storage unit 26 with the specified contents, and the driving support device 1 uses the data and information stored in the data storage unit 26 to provide route guidance by the route guidance unit 21. Processing, information provision processing by the information provision unit 22, and operation control by the operation control unit 23 are executed. "

JP 2006-275690 A

In the technology described in Patent Document 1, when information corresponding to information acquired by the information management unit (speed limit, temporary stop, under construction, etc.) exists in the data storage unit, the content indicated by the acquired sign and the data storage The contents stored in the section are compared, and if they do not match, the contents are changed to the contents acquired from the sign.
However, when recognizing a road sign, the road sign may not be recognized or may be misrecognized. In such a case, there is a possibility that the content of the sign may be set inappropriately. have.
The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an information processing apparatus capable of recognizing an appropriate road sign by allowing a driver to select a road sign recognition result. And

  In order to achieve the above object, according to the present invention, an information processing device mounted on a vehicle acquires a captured image obtained by photographing the outside of the vehicle, and whether or not a road sign is included in the captured image. And a controller for recognizing a road sign included in the photographed image, the controller compares the recognized road sign with the sign information of road information data, and the recognized road sign is the road When it is different from the sign information of the information data, the display unit displays one for selecting one by the driver.

  ADVANTAGE OF THE INVENTION According to this invention, recognition of a suitable road sign can be performed by making a driver | operator select the recognition result of a road sign.

It is a block diagram which shows the functional structure of the vehicle-mounted navigation apparatus which concerns on embodiment of this invention. It is explanatory drawing which shows the flow of the recognition process operation | movement of a road sign. It is explanatory drawing shown typically about an example of a picked-up image. It is explanatory drawing which shows the process of the recognition result of the speed sign using a likelihood function. It is explanatory drawing which shows the example of a display in case the display speed by a recognition result is "40". It is explanatory drawing which shows the other example of a display when the display speed by a recognition result is "40". It is explanatory drawing which shows the example of a display when the speed which the own vehicle is drive | working now, and the display speed by a recognition result differ greatly. It is explanatory drawing which shows the example of a display when a road sign is detected from the picked-up image, but the display speed of the road sign cannot be recognized. It is a flowchart which shows operation | movement of this embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing a functional configuration of an in-vehicle navigation device 1 (information processing device) of the information processing device according to the first embodiment.

The in-vehicle navigation device 1 is a device mounted on a vehicle, and has a function of detecting the current position of the vehicle for detecting the current position of the vehicle, and a map display for displaying the current position of the vehicle on a map displayed and displayed. A function to search, a route search to search for a route to the destination, a function to display a map, display a route to the destination on the map, and perform a route guidance to guide the route to the destination Prepare.
Hereinafter, a vehicle on which the in-vehicle navigation device 1 is mounted is expressed as “own vehicle”.

  As shown in FIG. 1, the in-vehicle navigation device 1 includes a control unit 10, an operation unit 11, a display unit 12, a storage unit 13, a GPS unit 14, a relative direction detection unit 15, an interface 16, a vehicle speed. An acquisition unit 17. The vehicle-mounted navigation device 1 outputs information to the ECU 18 (Electronic Control Unit). The ECU 18 controls automatic driving of the host vehicle based on predetermined driving control conditions.

The control unit 10 includes a CPU, a ROM, a RAM, other peripheral circuits, and the like, and controls each unit of the in-vehicle navigation device 1. For example, the CPU 10 controls each unit of the in-vehicle navigation device 1 in cooperation with hardware and software such that the CPU reads and executes a control program stored in the ROM.
The control unit 10 includes a sign detection unit 20, a sign recognition unit 21, and a display control unit 22.

  The display unit 12 includes a navigation display unit 25 mounted on the in-vehicle navigation device 1 and a meter panel display unit 26 mounted on a meter panel of the vehicle. The display unit 12 includes, for example, a liquid crystal display panel, an organic EL panel, and the like, and performs display based on a display control signal from the display control unit 22 of the control unit 10.

The operation unit 11 includes, for example, a touch panel in which a touch sensor is placed on the display panel of the navigation display unit 25 that constitutes the display unit 12. The touch panel detects a driver's touch operation using a touch sensor, and outputs a signal indicating the touch operation to the control unit 10.
Another example of the operation unit 11 may be a steering remote controller installed in the steering of the vehicle. The steering remote controller includes an operation switch, detects the operation of the driver by the operation switch, and outputs a signal indicating the operation to the control unit 10.
The control unit 10 executes a process corresponding to a user operation based on a signal input from the touch sensor or a signal input from the operation switch of the steering remote controller.
In addition, you may make it comprise the operation part 11 with both a touchscreen and a steering remote control.

The storage unit 13 includes a nonvolatile memory and stores various data.
The storage unit 13 stores map data 30.
The map data 30 includes parcel data. Parcel data is data used for the map display and route guidance described above, road drawing data related to the drawing of road shapes, background drawing data related to drawing backgrounds such as terrain, character strings such as administrative divisions Drawing data relating to the display of the map, such as character string drawing data relating to the drawing. The road drawing data includes node information having information on nodes corresponding to connection points in a road network such as intersections, and link information having information on links corresponding to roads formed between the nodes, It also contains information necessary for route guidance.
The map data 30 includes region data. Region data is data used in the route search described above, and corresponds to node information having information on nodes corresponding to connection points in a road network such as intersections, and roads formed between nodes. It includes information necessary for route search, such as link information having information about links.

The storage unit 13 stores road information data 31.
The road information data 31 is a database having a record for each road sign (a road sign managed by the map data 30) displayed on a map based on the map data 30.
One record of the road information data 31 includes sign information and corresponding road information.

The sign information is information related to the road sign, and includes a sign ID for uniquely identifying the road sign, sign type information indicating the type of the road sign, and sign position information indicating the position of the road sign. Here, the sign position information includes not only the position information of the sign fixed to the road but also the position information of the sign by an electric bulletin board, for example. Corresponding road information is information regarding a road on which a road sign is provided.
In addition, the storage unit 13 includes an image storage unit 32 and stores an image captured by an in-vehicle camera 35 as an imaging device described later.

  The GPS unit 14 receives GPS radio waves from GPS satellites via a GPS antenna (not shown), and acquires the current position and traveling direction of the host vehicle by calculation from GPS signals superimposed on the GPS radio waves. The GPS unit 14 outputs the acquisition result to the control unit 10.

  The relative orientation detection unit 15 includes a gyro sensor (not shown) and an acceleration sensor. The gyro sensor is constituted by, for example, a vibrating gyroscope and detects a relative direction (for example, a turning amount in the yaw axis direction) of the host vehicle. The acceleration sensor detects acceleration acting on the host vehicle (for example, tilt of the host vehicle with respect to the traveling direction). The relative orientation detection unit 15 outputs the detection results of the gyro sensor and the acceleration sensor to the control unit 10.

  The vehicle speed acquisition unit 17 is connected to, for example, a sensor that detects a vehicle speed pulse (not shown), detects the vehicle speed of the host vehicle based on the vehicle speed pulse input from the sensor, and communicates with the ECU 18, for example, to communicate with the ECU 18. Information on the vehicle speed is obtained from the vehicle to detect the vehicle speed of the host vehicle. The vehicle speed acquisition unit 17 outputs the detection result to the control unit 10. The control unit 10 detects the vehicle speed of the host vehicle based on the input from the vehicle speed acquisition unit 17.

  When detecting the position of the host vehicle, the control unit 10 detects the state of the host vehicle such as the detected vehicle speed based on the input from the GPS unit 14 and the relative direction detection unit 15 and the input from the vehicle speed acquisition unit 17. Based on the map data 30, the current position of the host vehicle is detected.

Moreover, the control part 10 displays the detected present position of the own vehicle on the map displayed on the navigation display part 25 provided with the touch panel, when performing map display.
In addition, when performing a route search, the control unit 10 searches for a route from the detected current position to the destination set by the driver based on the map data 30.
In addition, when performing route guidance, the control unit 10 displays the current position of the displayed vehicle on the map while guiding the route while showing the route to the destination on the map.

The interface 16 is connected to an external device, and communicates with the connected external device according to a predetermined protocol according to the control of the control unit 10. In the present embodiment, an in-vehicle camera 35 (imaging device) is connected to the interface 16 as an external device.
The in-vehicle camera 35 captures the front of the host vehicle, and the in-vehicle camera 35 outputs a captured image to the control unit 10 via the interface 16.

Next, a process for recognizing a road sign will be described. Here, in this embodiment, a case where the road sign is a maximum speed sign will be described as an example.
FIG. 2 is an explanatory diagram showing the flow of a road sign recognition processing operation. FIG. 3 is an explanatory diagram schematically illustrating an example of a captured image. FIG. 3 shows a case where the maximum speed display of the road sign is 40 km / h.

The sign detection unit 20 detects whether or not a road sign exists in the image based on an image obtained by photographing the front of the host vehicle with the in-vehicle camera 35.
Specifically, the sign detection unit 20 calculates the probability of the area where the road sign is present based on the parameter for detecting the existing area of the road sign, for example, by statistical processing for the captured image shown in FIG. Thus, a candidate road sign area in the captured image is extracted.
The sign detection unit 20 determines whether or not the probability of the area where the extracted road sign is present is greater than or equal to a predetermined threshold, and determines an area that is greater than or equal to the predetermined threshold as an extracted area where the road sign is present. In FIG. 3, an area surrounded by a broken line indicates an extraction area.
The threshold value can be set arbitrarily.

  When there are a plurality of extraction area candidates in which road signs exist, the sign detection unit 20 detects all areas of the road sign that are equal to or greater than the threshold as the extraction areas. The sign detection unit 20 sends the road sign extraction region to the sign recognition unit 21.

  The road sign detection process by the sign detection unit 20 is not limited to the statistical process described above, and any area detection process such as pattern matching may be used.

Next, the sign recognition unit 21 recognizes what kind of sign the road sign is in the road sign extraction region detected by the sign detection unit 20.
FIG. 4 is an explanatory diagram illustrating processing of the recognition result of the speed sign using the likelihood function.
As illustrated in FIG. 4, the sign recognition unit 21 numerically extracts feature points from the photographed image in the extraction region detected by the sign detection unit 20.
The sign recognizing unit 21 determines a parameter for obtaining a likelihood function with respect to the number represented on the road sign, in this embodiment, the display speed representing the maximum speed, based on the feature amount extracted from the captured image. With reference to this, a likelihood representing the likelihood of the display speed of the road sign is calculated. For example, the likelihood when the display speed represented by the road sign is “10” is the likelihood of “10”.
The parameters are set in advance for each display speed, such as a parameter when the road sign display speed is “10” and a parameter when the road sign is “20”, and stored in the storage unit 13, for example. .

The sign recognition unit 21 refers to the parameter when the display speed of the road sign is “10”, and obtains the likelihood when the display speed is “10”. Similarly, the sign recognition unit 21 refers to the parameter when the display speed of the road sign is “20” based on the feature amount extracted from the captured image, and the likelihood when the display speed is “20”. Find the degree.
After obtaining the likelihood according to each display speed by referring to the parameters of each display speed in this way, the sign recognition unit 21 arranges the likelihood according to each display speed as shown in FIG. A rearrangement process is performed, and the likelihood corresponding to each rearranged display speed is stored in the candidate table 40. The candidate table 40 is stored in the storage unit 13.

As shown in FIG. 4, the sign recognition unit 21 performs threshold processing on each likelihood stored in the candidate table 40 to determine whether each likelihood reaches the threshold. When the high candidate exceeds the threshold, the display speed at the likelihood of the first candidate is output to the display control unit 22 as a recognition result.
In the example of FIG. 4, the likelihood when the display speed is “40” is 0.9, the likelihood when the display speed is “10” is 0.5, and the display speed is “10”. An example in which the likelihood is 0.1 is shown.
In the example of FIG. 4, for example, when the threshold is 0.8, the likelihood of exceeding the threshold of 0.8 is only the likelihood 0.9 when the display speed is “40”. The sign recognition unit 21 outputs that the display speed is “40” as the display speed recognition result.

In this case, when the likelihood at all display speeds does not reach the threshold value, the sign recognition unit 21 determines that the display speed cannot be recognized. If the sign recognition unit 21 determines that the display speed cannot be recognized, it does not output the recognition result.
Further, when there are a plurality of display speeds of the likelihood that has reached the threshold, the sign recognition unit 21 outputs the display speed with the highest likelihood as the recognition result of the first candidate.
In this case, for example, there are a plurality of display speeds having very close likelihood values, such as when a display speed with a likelihood of 0.9 and a display speed with a likelihood of 0.89 are recognized as candidates. In some cases, since the likelihoods conflict and it is impossible to determine which display speed is correct, the sign recognition unit 21 determines that the display speed cannot be recognized.
In addition, when there are a plurality of display speeds with the likelihood that has reached the threshold value in this way, both display speeds may be displayed on the display unit 12 to be selected by the driver.

Further, as shown in FIG. 2, the sign recognition unit 21 stores the recognition result of the road sign as a history, and analyzes the stored history.
That is, when the host vehicle is traveling on one road, the display speed of the road sign usually does not fluctuate greatly. For this reason, when the recognition result history changes frequently when the recognition result history is analyzed, the sign recognition unit 21 determines that the display speed recognition is abnormal.
In this way, when it is determined that the recognition is abnormal, in the sign recognition process in the sign recognition unit 21, the process is performed by increasing the likelihood threshold. As a result, only the display speed having a high likelihood is adopted as the recognition result, and the accuracy rate of the recognition result can be increased.
In addition, when it is determined that the display speed is recognized as abnormal as described above, a process of making all these recognition results unrecognizable may be performed.

Further, the sign recognition unit 21 acquires the position of the road sign (including the electronic bulletin board) based on the current position of the host vehicle acquired by the control unit 10 and the sign position information of the sign information included in the road information data 31.
If the position of a road sign or the position of an electric bulletin board is known, the probability of detecting a sign increases when the host vehicle is traveling near the position of the sign. The threshold is set so as to lower the threshold when thresholding. Thereby, it becomes difficult to become unrecognizable, and it becomes possible to increase the accuracy rate of the recognition result of display speed.

Further, the control unit 10 extracts speed limit information on the road on which the host vehicle is currently traveling based on the sign type information of the sign information included in the road information data 31.
The control unit 10 compares the display speed based on the recognition result of the sign recognition unit 21 and the speed limit information. If the display speed based on the recognition result is different from the speed limit information, the display control unit 22 causes the display unit 12 to By controlling, the display speed based on the recognition result is displayed.
FIG. 5 is an explanatory diagram illustrating a display example when the display speed based on the recognition result is “40”.
As shown in FIG. 5, the display speed based on the recognition result is shown as an icon simulating a speed indicator above the speedometer 41 of the meter panel display unit 26.
By displaying the display speed on the meter panel display unit 26 in this way, the driver can easily check the display speed based on the recognition result.
In the present embodiment, when the display speed based on the recognition result matches the speed limit information, it is not displayed on the meter panel display unit 26.

FIG. 6 is an explanatory diagram showing another display example when the display speed based on the recognition result is “40”.
The control unit 10 causes the image storage unit 32 to store the captured image captured by the in-vehicle camera 35. As shown in FIG. 6, the display control unit 22 causes the meter panel display unit 26 to display the display speed based on the recognition result of the sign recognition unit 21 and the captured image stored in the image storage unit 32.
At this time, the display control unit 22 causes the meter panel display unit 26 to display the selection operation unit 42. In the present embodiment, the selection operation unit 42 includes a “setting” selection unit 43 and a “ignore” selection unit 44.
When the driver sets the display speed as the target speed as it is while viewing the display speed based on the recognition result displayed on the meter panel display section 26 and the captured image, the “setting” of the selection operation section 42 is set. The selection unit 43 is selected by a touch operation using a touch panel or a switch operation using a steering remote controller.

When the selection unit 43 for “setting” is selected by the driver, the control unit 10 outputs a display speed based on the recognition result to the ECU 18. Thereby, ECU18 is controlled by the new speed by a recognition result.
On the other hand, when the target speed is not changed, the driver selects and operates the “ignore” selection unit 44 of the selection operation unit 42. In this case, the display speed based on the recognition result is not output to the ECU 18.
In this way, by making the driver confirm the recognition result of the road sign, it is possible to prevent setting mistakes based on misrecognition.

FIG. 7 is an explanatory diagram showing a display example when the speed at which the host vehicle is currently traveling and the display speed based on the recognition result are greatly different.
The control unit 10 compares the current traveling speed of the host vehicle with the display speed based on the recognition result of the sign recognition unit 21. If the current traveling speed and the display speed are greatly different, the display control unit 22 As in the case of FIG. 6, the display speed based on the recognition result of the sign recognition unit 21 and the captured image stored in the image storage unit 32 are displayed on the meter panel display unit 26 and the selection operation unit 42 is displayed. .
Further, in the present embodiment, the display control unit 22 displays a message area 45 for displaying a message next to the display area of the captured image.

FIG. 7 shows an example where the current traveling speed of the host vehicle is “75” km / h and the display speed based on the recognition result of the sign recognition unit 21 is “40”, for example.
In such a case, the display control unit 22 displays a warning message in the message area 45 because the current traveling speed of the host vehicle and the display speed based on the recognition result are different by 35 km / h. Specifically, for example, a warning message that prompts the host vehicle to decelerate is displayed, such as “Warning to decelerate?”.
When the driver changes the traveling speed in accordance with the message, the control unit 10 selects and operates the “setting” selection unit 43 of the selection operation unit, so that the control unit 10 outputs the display speed based on the recognition result to the ECU 18. . Thereby, ECU18 is controlled by the new speed by a recognition result.
On the other hand, when the traveling speed of the host vehicle is not changed, the driver performs a selection operation on the “ignore” selection unit 44 of the selection operation unit 42. In this case, the display speed based on the recognition result is not output to the ECU 18.

FIG. 8 is an explanatory view showing a display example when the road sign is detected from the photographed image by the sign detection unit 20 but the display speed of the road sign cannot be recognized by the sign recognition unit 21.
That is, the sign detection unit 20 was able to detect whether or not a road sign is present in the image based on the photographed image. For example, the likelihood exceeding the threshold exists even if the threshold processing of likelihood is performed. When the sign recognition unit 21 cannot recognize the display speed of the road sign, such as when the display control unit 22 does not, the display control unit 22 displays the captured image stored in the image storage unit 32. The message area is displayed on the meter panel display unit 26, respectively.
The display control unit 22 displays a warning message in the message area 45. Specifically, for example, a message indicating that a road sign is detected is displayed, such as “a sign is detected”.
In addition, when displaying a warning message, you may make it alert by a voice with the display in the message area | region 45. FIG.

  Next, the operation of this embodiment will be described with reference to the flowchart shown in FIG.

First, the control unit 10 of the in-vehicle navigation device 1 acquires a captured image output from the in-vehicle camera 35 (step S1).
Next, the sign detection unit 20 detects whether or not a road sign exists in the photographed image based on the photographed image by the in-vehicle camera 35 (step S2). When the sign detection unit 20 detects an extraction area where a road sign is present (step S2: YES), the road sign extraction area is sent to the sign recognition unit 21.

The sign recognition unit 21 recognizes what kind of sign the road sign is in the road sign extraction region detected by the sign detection unit 20 (step S4).
That is, as described above, the sign recognition unit 21 numerically extracts feature points from the captured image in the extraction region detected by the sign detection unit 20, and is represented on the road sign based on the feature amount. The likelihood corresponding to the display speed of the road sign is calculated with reference to the parameter for obtaining the likelihood function with respect to the display speed.
The sign recognition unit 21 determines whether each likelihood exceeds a predetermined threshold (step S5). When the likelihood exceeds a predetermined threshold (step S5: YES), the sign recognition unit 21 corresponds to the likelihood. The display speed to be used is the recognition result.
On the other hand, when there is no likelihood exceeding the threshold (step S5: NO), the sign recognition unit 21 determines that the recognition is impossible and does not output the display speed recognition result (step S14).
Then, the sign recognition unit 21 determines whether or not there are a plurality of likelihoods exceeding the predetermined threshold (step S6), and when there are a plurality of likelihoods exceeding the predetermined threshold (step S6: YES), the recognition is performed. As a result of the competition, the display speed recognition result is not output (step S15).

  Further, when there is not a plurality of likelihoods exceeding the predetermined threshold (step S6: NO), the sign recognition unit 21 stores the recognition result of the road sign as a history, and analyzes the stored history (step S7). ). When the sign recognition unit 21 determines that the recognition result of the display speed frequently fluctuates from the recognition result history (step S8: YES), the sign recognition unit 21 determines that the display speed recognition is abnormal, and the sign recognition process in the sign recognition unit 21 In step S16, the likelihood threshold is set to be increased.

Further, when the sign recognition unit 21 determines that the display speed recognition result does not change (step S8: NO), the control unit 10 based on the sign type information of the sign information included in the road information data 31. The speed limit information on the road on which the host vehicle is currently traveling is extracted, and the display speed based on the recognition result of the sign recognition unit 21 is compared with the speed limit information (step S9).
When the control unit 10 determines that the display speed based on the recognition result is different from the speed limit information (step S9), the display control unit 22 controls the display unit 12 to display the display speed based on the recognition result (step S9). Step S10). If the control unit 10 determines that the display speed based on the recognition result is not different from the speed limit information (step S9), the control unit 10 ends the process.

After that, when the display speed recognized by the driver is selected by the “setting” selection unit 43 (step S11: YES), the recognition result is set as the target speed (step S12) and output to the ECU 18 (step S12). S13).
On the other hand, when the driver performs the selection operation of the selection unit 44 of “ignore” (step S11: NO), the process is terminated while keeping the target speed (step S17).

As described above, the in-vehicle navigation device 1 (information processing device) according to the present embodiment acquires a captured image obtained by capturing the outside of the host vehicle (vehicle), and the captured image includes a road sign. The controller 10 recognizes the road sign included in the photographed image and compares the recognized road sign with the sign information of the road information data 31, and recognizes the recognized road sign. Is different from the sign information of the road information data 31, the display unit 12 displays for the driver to select one.
According to this configuration, setting errors based on misrecognition can be prevented by allowing the driver to confirm the recognition result of the road sign.

Moreover, in this embodiment, the memory | storage part 13 which memorize | stores the road information data 31 and a picked-up image is provided, and the control part 10 displays the recognition result and picked-up image of a road sign on the display part 12. FIG.
According to this configuration, since the road sign recognition result and the captured image are displayed on the display unit 12, the driver can determine the road sign recognition result while confirming the captured image.

In this embodiment, the control unit 10 performs threshold processing on the likelihood obtained according to the road sign based on the captured image, and displays the road sign at the likelihood exceeding the threshold on the display unit 12 as a recognition result. To do.
According to this configuration, the likelihood obtained according to the road sign is subjected to threshold processing, and the road sign at the likelihood exceeding the threshold is displayed on the display unit 12 as the recognition result, so that the accuracy rate of recognition of the road sign is increased. be able to.

In the present embodiment, the control unit 10 performs threshold processing on the likelihood obtained according to the road sign based on the captured image, and determines that the likelihood is not recognized when the likelihood does not exceed the threshold, and the display unit 12 is not displayed.
According to this configuration, the control unit 10 performs threshold processing on the likelihood obtained according to the road sign based on the captured image, and determines that the recognition is impossible when the likelihood does not exceed the threshold. There is no need to make judgments using road signs with low accuracy.

In the present embodiment, the control unit 10 knows the position of the sign based on the sign information of the road information data 31 when thresholding the likelihood obtained according to the road sign based on the captured image. If yes, the likelihood is set to lower the threshold when thresholding.
According to this configuration, when the control unit 10 knows the position of the sign based on the sign information of the road information data 31, even if the threshold value when the likelihood is thresholded is lowered, It becomes possible to increase the accuracy rate of recognition.

In the present embodiment, the control unit 10 analyzes the history of the road sign recognition result, and when the road sign recognition result frequently fluctuates, determines that the road sign recognition is abnormal, and sets the likelihood as a threshold value. Set to increase the threshold for processing.
According to this configuration, the control unit 10 analyzes the history of the road sign recognition result, and when the road sign recognition result fluctuates frequently, determines that the road sign recognition is abnormal, and thresholds the likelihood. By raising the threshold value for the recognition, only the display speed having a high likelihood is adopted as the recognition result, and the accuracy rate of the recognition result can be increased.

In this embodiment, the control unit 10 compares the recognized road sign with the sign information of the road information data 31, and when the recognized road sign is significantly different from the sign information of the road information data 31, the display unit 12. Display a warning.
According to this configuration, when the recognized road sign is significantly different from the sign information of the road information data 31, the control unit 10 displays a warning on the display unit 12, thereby warning the driver of the confirmation of the road sign. It can be carried out.

Further, in the present embodiment, an interface 16 to which an in-vehicle camera 35 (imaging device) having an imaging function can be connected is provided, and the control unit 10 acquires a captured image from the in-vehicle camera 35 via the interface 16.
According to this configuration, the control unit 10 can recognize the road sign based on the captured image acquired from the in-vehicle camera 35.

In the present embodiment, when the driver selects the recognized road sign displayed on the display unit 12, the control unit 10 outputs the recognized road sign to the ECU 18.
According to this configuration, the control unit 10 outputs the road sign selected by the driver to the ECU 18, whereby the ECU 18 based on the selected road sign can be controlled.

The embodiment described above is merely an aspect of the present invention, and can be arbitrarily modified and applied within the scope of the present invention.
For example, in the above-described embodiment, the vehicle-mounted navigation device 1 has been described with respect to an example in which the maximum speed sign of the road sign is recognized. However, any sign may be recognized as long as it is a road sign. Good.
In the embodiment, the road information data 31 and the map data 30 are stored in the storage unit 13. For example, these data are acquired from an external server via a wireless communication network. Also good.

  In addition, FIG. 1 is a schematic diagram showing the functional configuration of the in-vehicle navigation device 1 classified according to main processing contents in order to facilitate understanding of the present invention. Accordingly, it can be classified into more components. Moreover, it can also classify | categorize so that one component may perform more processes. Further, the processing of each component may be executed by one hardware or may be executed by a plurality of hardware. Further, the processing of each component may be realized by one program or may be realized by a plurality of programs.

Moreover, the processing unit of the flowchart demonstrated using FIG. 9 is divided | segmented according to the main processing content, in order to make a process of the vehicle-mounted navigation apparatus 1 easy to understand. The present invention is not limited by the way of dividing the processing unit or the name. The processing of each device can be divided into more processing units according to the processing content. Moreover, it can also divide | segment so that one process unit may contain many processes. In addition, if the same free state determination can be performed, the processing order of the flowchart is not limited to the illustrated example.
Moreover, in the said embodiment, although the vehicle-mounted navigation apparatus 1 was a structure which acquires picked-up image data from the vehicle-mounted camera 35 which is an external device, the structure which the vehicle-mounted navigation apparatus 1 has a imaging | photography function may be sufficient.

1 In-vehicle navigation device (information processing device)
DESCRIPTION OF SYMBOLS 10 Control part 11 Operation part 12 Display part 13 Storage part 14 GPS unit 15 Relative direction detection unit 16 Interface 18 ECU
DESCRIPTION OF SYMBOLS 20 Sign detection part 21 Sign recognition part 22 Display control part 25 Navigation display part 26 Meter panel display part 30 Map data 31 Road information data 32 Image storage part 35 Car-mounted camera 42 Selection operation part

Claims (9)

In an information processing device mounted on a vehicle,
A control unit that acquires a captured image obtained by capturing the outside of the vehicle, detects whether the captured image includes a road sign, and recognizes the road sign included in the captured image,
The control unit compares the recognized road sign with the sign information of the road information data, and when the recognized road sign is different from the sign information of the road information data, the control unit selects any one for the driver. An information processing apparatus that performs a display to be performed. A storage unit for storing the road information data and the captured image;
The information processing apparatus according to claim 1, wherein the control unit displays a recognition result of the road sign and the captured image on a display unit.   The control unit performs threshold processing on the likelihood obtained according to the road sign based on the captured image, and displays the road sign at the likelihood exceeding the threshold as a recognition result on the display unit. The information processing apparatus according to claim 1 or 2.   The control unit performs threshold processing on the likelihood obtained according to the road sign based on the photographed image, and determines that the likelihood is not recognized when the likelihood does not exceed the threshold, and does not display it on the display unit. The information processing apparatus according to claim 3.   The control unit, when thresholding the likelihood obtained according to the road sign based on the captured image, when the position of the sign is known based on the sign information of the road information data, The information processing apparatus according to claim 3, wherein the likelihood is set so as to lower a threshold value when threshold processing is performed.   The control unit analyzes a history of the recognition result of the road sign, and when the recognition result of the road sign frequently fluctuates, the control unit determines that the road sign recognition is abnormal, and a threshold value when thresholding the likelihood The information processing apparatus according to claim 3, wherein the information processing apparatus is set so as to increase.   The control unit compares the recognized road sign with the sign information of the road information data, and displays a warning on the display unit when the recognized road sign is significantly different from the sign information of the road information data The information processing apparatus according to claim 3. It has an interface that can be connected to a shooting device with a shooting function
The information processing apparatus according to claim 1, wherein the control unit acquires the captured image from the imaging apparatus via the interface.   2. The control unit according to claim 1, wherein when the driver selects the recognized road sign displayed on the display unit, the control unit outputs the recognized road sign to the ECU. Item 9. The information processing device according to any one of Items 8 to 9.

Images