JP7364365B2 - Onboard equipment and driving evaluation system - Google Patents

Description

The present invention relates to an on-vehicle device and a driving evaluation system.

BACKGROUND ART Conventionally, on-vehicle devices such as digital tachographs installed in vehicles use driving information such as vehicle speed information to support safe driving and to evaluate the driving operations of the driver of the vehicle. The safe driving support device of Patent Document 1 activates the peripheral visibility device to capture and display images of the left and right directions in front of the vehicle only when a road sign such as "Stop" is detected by image recognition while the vehicle is running. It is something to do. The driving support device of Patent Document 2 recognizes traffic signs from image data captured around the vehicle, and when a designated sign is recognized, notifies the presence of the designated sign. If two or more exist, notification is prohibited. Further, in relation to a technology for recognizing characters, Patent Document 3 discloses a technology for assigning the same character code to a plurality of characters having similar shapes.

Japanese Patent Application Publication No. 2002-219998 JP2017-102665A Japanese Patent Application Publication No. 9-245047

In driving evaluations, evaluation items include whether drivers drove appropriately at places where they should stop, such as at intersections, in other words, whether they stopped at appropriate locations and checked safety. It can be expected to improve awareness. In order to detect where vehicles should temporarily stop, image recognition is used to detect "stop" signs on the road. This image recognition uses a graphical information database (template image, dictionary) stored in the on-vehicle device that stores graphical information representing the shapes of the characters ``stop'', ``ma'', and ``re''. ) and these graphical information to determine each character. However, because the font of the "stop" road markings differs depending on the prefecture, the degree of matching between the photographed image and the graphic information database may be low, and the recognition rate of the road markings may be reduced. On the other hand, if you prepare a graphic information database that corresponds to each of all the fonts in Japan and try to match it with all the graphic information databases, there is a possibility that false positives will increase. Furthermore, the amount of data in the graphic information database becomes large, making it difficult to maintain the graphic information database in an on-vehicle device with limited storage capacity.

The present invention has been made in view of the above-mentioned circumstances, and its purpose is to make it possible to improve the recognition rate and reduce the misrecognition rate of specific road markings or signs.

In order to achieve the above-mentioned object, the on-vehicle device and driving evaluation system according to the present invention are characterized by the following (1) to (5).
(1) An on-vehicle device installed in a vehicle,
an image acquisition unit that acquires a captured image of the front of the vehicle;
a position acquisition unit that acquires position information of the vehicle;
a recognition unit that recognizes a specific road marking or sign from the photographed image by referring to a graphic information database associated with the position information;
a recording section for recording recognition results;
Equipped with
The specific road marking or sign has a marking consisting of a character string composed of a plurality of characters,
The recognition unit compares the degree of agreement between the pattern characteristics of each character detected from the photographed image and the characteristics of all the characters included in the graphic information database associated with the position information, If a character that is extremely similar is detected, and the degree of matching with the detected character is equal to or higher than a threshold, a state in which the character represented by one pattern has been successfully recognized is determined, and the character composed of the plurality of characters is determined. If the column is successfully recognized, confirm the recognition of the specific road marking or sign.
An on-vehicle device characterized by:
(2) The specific road markings or signs have different markings for each region that indicate the same meaning;
The recognition unit recognizes the specific road marking or sign by referring to a graphical information database associated with the area indicated by the positional information among graphical information databases corresponding to the markings that differ for each region. The on-vehicle device according to (1) above, characterized in that:
(3) The first specific road marking for the first region and the second specific road marking for the second region have the same meaning, and the characteristics of the first specific road marking and the characteristics of the second specific road marking If they are similar, a common graphic information database common to the first region and the second region is prepared,
(2) above, wherein the recognition unit refers to the common graphic information database and recognizes the specific road marking or sign when the position information indicates within the first area or the second area. ).
(4) comprising a collection unit that collects operation information of the vehicle;
(1) to (3) above, wherein the recording unit records the operation information in association with the photographed image and the position information when the recognition unit recognizes the specific road marking or sign. On-vehicle equipment listed in any one of the above.
(5) The on-vehicle device described in (4) above,
a driving evaluation device that acquires content recorded by the recording unit from the on-vehicle device and evaluates the driving of the driver of the vehicle based on the content;
A driving evaluation system comprising:

The on-vehicle device configured in (1) above identifies the shape by referring to the graphic information database (or learning dictionary) associated with the vehicle's position information among the graphic information databases that store graphic information representing the shape of the recognition target. Recognize road markings or signs. With this configuration, it is possible to improve the recognition rate and reduce the rate of misrecognition of specific road markings or signs that vary from region to region, such as a "stop" road sign that instructs a temporary stop. In addition, by referring only to the graphical information database corresponding to the vehicle's current position, it is possible to suppress the increase in the recognition processing load and the increase in the false recognition rate, and to improve the recognition performance of specific road markings or signs even with a CPU with low processing capacity. can be improved.

According to the on-vehicle device configured as described in (2) above, even if the font of specific road markings or signs differs depending on the region, such as a "stop" road marking, graphical information is associated with position information. By referring to the database, specific road markings or signs can be recognized with high accuracy.

According to the on-vehicle device configured in (3) above, regions with similar marking characteristics are grouped together and a common graphic information database is used, thereby maintaining the recognition rate of specific road markings or signs. The amount of data in the graphic information database can be reduced.

According to the on-vehicle device having the configuration (4) above, the specific road marking or sign can be recognized with a high recognition rate, so that the operation information associated with the specific road marking or sign can be appropriately collected.

According to the driving evaluation system configured in (5) above, specific road markings or signs can be recognized with a high recognition rate. You can understand driving information such as length and appropriately evaluate driving. The driving evaluation device may be built into the vehicle-mounted device, or may be provided in an office PC that can communicate with the vehicle-mounted device.

According to the present invention, it is possible to improve the recognition rate and reduce the misrecognition rate of specific road markings or signs.

The present invention has been briefly described above. Furthermore, the details of the present invention will be further clarified by reading the mode for carrying out the invention (hereinafter referred to as "embodiment") described below with reference to the accompanying drawings. .

FIG. 1 is a diagram showing the configuration of the driving evaluation system of this embodiment. FIG. 2 is a diagram illustrating an example of an image frame including a front image of a vehicle. FIG. 3 is a diagram illustrating an example of a "stop" road marking with different fonts depending on the region. FIG. 4 is a diagram showing an example of correspondence between regions and graphic information databases. FIG. 5 is a flowchart illustrating an example of the operation of the onboard device when selecting a graphic information database corresponding to vehicle position information. FIG. 6 is a flowchart illustrating an example of the operation of the on-vehicle device when image-recognizing road characters. FIG. 7 is a diagram showing an example of the operation of the office PC.

Specific embodiments of the present invention will be described below with reference to each figure.
FIG. 1 is a diagram showing the configuration of a driving evaluation system 5 of this embodiment. The driving evaluation system 5 evaluates the driving of a driver riding a vehicle, and includes a driving recorder (hereinafter referred to as a digital tachograph) 10, which is an onboard device, and an office PC 30, which are connected via a network 70. It has a configuration including. Note that the on-vehicle device and the office PC do not need to be connected via a network; in that case, the office PC is configured to read a memory card that records driving record data measured by the on-vehicle device. . Further, the vehicle-mounted device may be a drive recorder or the like.

The office PC 30 is composed of a general-purpose computer device installed in the office, and manages the operating status of the vehicle. The network 70 is a packet communication network such as the Internet to which the wireless base station 8 and office PC 30 that perform wide area communication with the digital tachograph 10 are connected, and relays data communication between the digital tachograph 10 and the office PC 30. do. Communication between the digital tachograph 10 and the wireless base station 8 may be performed using a mobile communication network (mobile line network) such as LTE (Long Term Evolution)/4G (4th Generation), or a wireless LAN (Local Area Network).

The digital tachograph 10 is mounted on a vehicle and records operation data (operation information) such as entry/exit time, travel distance, travel time, travel speed, overspeed, overengine speed, sudden start, sudden acceleration, sudden deceleration, etc. . The digital tachograph 10 includes a CPU 11 (image acquisition unit, recognition unit, collection unit), nonvolatile memory 26A, volatile memory 26B, recording unit 17, card I/F 18, audio I/F 19, RTC (clock IC) 21, and SW input unit. 22 and a display section 27.

The CPU 11 centrally controls each part of the digital tachograph 10. The nonvolatile memory 26A stores operating programs and the like executed by the CPU 11. Volatile memory 26B is used to temporarily hold various data.

The recording unit 17 records data such as operation data and video in a predetermined storage area. A memory card 65 owned by the driver is removably connected to the card I/F 18. The CPU 11 writes the operation information (including operation data, video data, etc.) and warning event recorded by the recording unit 17 to the memory card 65 connected to the card I/F 18. Note that the recording unit 17 may record operation data and the like in the volatile memory 26B. A built-in speaker 20 is connected to the audio I/F 19. The built-in speaker 20 emits sounds such as alarms.

The RTC 21 (timekeeping section) measures the current time. The SW input unit 22 receives ON/OFF signals for various buttons such as an exit button and an input button. The display unit 27 is composed of an LCD (liquid crystal display), and displays communication and operation status as well as alarms and the like.

Further, the digital tachograph 10 includes a speed I/F 12A, an engine rotation I/F 12B, an external input I/F 13, a sensor input I/F 14, an analog input I/F 29, a GPS receiving section 15 (position acquisition section), and a camera I/F 16. , a communication section 24 and a power supply section 25.

A vehicle speed sensor 51 that detects the speed of the vehicle is connected to the speed I/F 12A, and a speed pulse from the vehicle speed sensor 51 is input. The vehicle speed sensor 51 may be provided as an option in the digital tachograph 10, or may be provided as a separate device from the digital tachograph 10. A rotation pulse from an engine rotation speed sensor (not shown) is input to the engine rotation I/F 12B. External equipment (not shown) is connected to the external input I/F 13.

An acceleration sensor (G sensor) 28 that detects acceleration (G value) (senses impact) is connected to the sensor input I/F 14, and a signal from the G sensor 28 is input. The analog input I/F 29 receives signals from a temperature sensor (not shown) that detects engine temperature (coolant temperature), a fuel amount sensor (not shown) that detects fuel amount, and the like. The CPU 11 detects various operating states based on information input via these I/Fs.

The GPS receiving unit 15 is connected to a GPS antenna 15a, receives signals transmitted from GPS satellites, and acquires position information (GPS information) indicating the current position of the vehicle.

A camera 23A and a camera 23B are connected to the camera I/F 16, and captured images (videos, still images) are constantly input to the CPU 11. The camera 23A is installed in the vehicle and captures images of the surroundings of the vehicle (for example, the front of the vehicle, including the road surface on which the vehicle travels) to obtain image data (photographed images). The camera 23B is installed in front of the meter inside the vehicle, and obtains image data by photographing the inside of the vehicle including the driver's face. The images captured by the camera 23A include the preceding vehicle in front of the host vehicle, white lines representing the boundaries of the lane in which the host vehicle is traveling, and road markings such as traffic regulations ("stop," stop lines, crosswalks, etc.). appear. The cameras 23A and 23B have at least one image sensor in which, for example, 300,000 pixels, 1 million pixels, or 2 million pixels are arranged on the imaging surface, and are capable of capturing images such as stereo images. The image sensor may be configured with a CMOS (complementary metal oxide semiconductor) sensor or a CCD (charge coupled device) sensor. Note that a camera that takes images of the sides and rear of the vehicle may be connected to the camera I/F 16.

FIG. 2 shows an example of an image frame 100A including a front image of the vehicle (photographed image) taken by the camera 23A. In the image frame 100A shown in FIG. 2, an image in front of the own vehicle, which is photographed before the intersection 101 while the own vehicle is traveling, appears. In the example of FIG. 2, the image frame 100A includes patterns such as an intersection 101, a stop line road marking 102, a white line road marking 103, and a road marking 104 indicating a temporary stop. In this case, the painted pattern of the road marking 104 is a character string of "stop", indicating that the vehicle is required to temporarily stop (temporary stop point). However, road markings indicating a temporary stop may be replaced with various character strings that differ from region to region. For example, character strings such as "stop", "stop", and "stop" may be used as signs indicating the same temporary stop.

Furthermore, even if the road marking 104 has the same character string "stop", the font is different depending on the region. FIG. 3 is a diagram illustrating an example of a "stop" road marking with different fonts depending on the region. As shown in Figure 3, road markings MA to MF in areas A to F have different fonts, but road markings MA in area A and road markings MB in area B have different font (character shape) characteristics. resemble. Furthermore, the road markings MD in region D and the road markings ME in region E have similar font characteristics. Therefore, in this embodiment, a graphical information database common to regions A and B, a graphical information database common to regions D and E, and a graphical information database for each region are prepared for regions C and F. In other words, for the "Stop" road markings, which differ depending on the region, which means a place where you should stop temporarily, there are multiple types of graphic information databases (different shapes for each region) associated with each region A to F. information database). Each graphical information database stores graphical information representing the shapes of the characters "stop," "ma," and "re," which vary from region to region. Here, the amount of data in the graphic information database can be reduced by combining regions with similar font characteristics into one graphic information database (for regions A and B, and for regions D and E).

FIG. 4 is a diagram showing an example of correspondence between regions and graphic information databases. As shown in FIG. 4, graphical information databases T1 to T11 are prepared for each region, each corresponding to the "stop" road sign in the typeface used in that region. In the example shown in FIG. 4, the digital tachograph 10 recognizes a "stop" road sign by referring to one of the graphic information databases T1 to T11 associated with the area indicated by the vehicle position information. As shown in FIG. 4, a plurality of (11 in the example of FIG. 4) graphic information databases covering all of Japan are prepared. For a plurality of regions where road markings with fonts with similar characteristics are used, a graphic information database (dictionary) common to these regions is created. The graphic information databases T1 to T11 may be stored in the memory card 65 or in the nonvolatile memory 26A. By storing the graphic information databases T1 to T11 in the large-capacity memory card 65, the storage capacity within the digital tachograph 10 can be saved, and the graphic information database can be easily updated. Note that the digital tachograph 10 may include only a part of the graphic information database. That is, when the digital tachograph 10 is mounted on a taxi vehicle, only the graphical information database associated with the area within the business area of the taxi vehicle is stored in the internal nonvolatile memory 26A. Then, the remaining graphic information database is stored in a storage medium such as a memory card 65. With this configuration, the storage capacity within the digital tachograph 10 can be saved, and a frequently used graphic information database can be easily accessed.

The CPU 11 of the digital tachograph 10 recognizes a "stop" road marking (hereinafter also referred to as a "specific road marking") by a method described later, based on the photographed image taken by the camera 23A. By detecting specific road markings through image recognition, the CPU 11 can determine where to stop based on the actual road markings without using map information. Therefore, accurate driving evaluation is possible even at locations where the vehicle should stop, such as locations where new road markings have been added, which cannot be determined from map information. Further, the CPU 11 of the digital tachograph 10 may recognize the direction of the driver's face and the eye open state using a known method based on the image captured by the camera 23B. The images captured by the cameras 23A and 23B are respectively recorded in time series by the recording unit 17. The recording unit 17 stores the captured images captured by the camera 23A, the images captured by the camera 23B, and the operation information collected by the CPU 11, based on the captured images, the time when the specific road marking was recognized, and the current position of the vehicle. (location information) and record it. Note that, in addition to capturing visible light images, the camera may include an infrared camera so that images can be captured even at night.

The communication unit 24 performs wide area communication, and when connected to the wireless base station 8 via a mobile line network (mobile communication network), communicates with the office PC 30 via a network 70 such as the Internet connected to the wireless base station 8. communicate. The power supply section 25 supplies power to each section of the digital tachograph 10 when an ignition switch is turned on or the like.

On the other hand, the office PC 30 is a PC that operates on a general-purpose operating system. The office PC 30 functions as a driving evaluation device, acquires the content recorded by the recording unit 17 from the digital tachograph 10, and evaluates the driving of the vehicle driver based on this content. The office PC 30 includes a CPU 31, a communication section 32, a display section 33, a storage section 34, a card I/F 35, an operation section 36, an output section 37, an audio I/F 38, and an external I/F 48.

The CPU 31 centrally controls each part of the office PC 30. The communication unit 32 can communicate with the digital tachograph 10 via the network 70. The communication unit 32 can also connect to various databases (not shown) connected to the network 70, and can acquire necessary data.

The display unit 33 displays a driving evaluation screen and the like. The storage unit 34 stores a driving evaluation program and the like for evaluating driving based on data measured by the digital tachograph 10.

A memory card 65 is removably inserted into the card I/F 35. The card I/F 35 inputs operation information measured by the digital tachograph 10 and stored in the memory card 65. The operation unit 36 has a keyboard, a mouse, etc., and accepts operations by the administrator of the office PC 30. The output unit 37 outputs various data. A microphone 41 and a speaker 42 are connected to the audio I/F 38. The administrator can also make voice calls using the microphone 41 and speaker 42.

External storage devices (not shown) such as an operation data database (DB) and a hazard map database (DB) can be connected to the external I/F 48 . The operation data DB includes operation data such as entry/exit times, speed, mileage, etc., as well as sudden acceleration/deceleration, sudden steering, excessive speed, excessive engine speed, and temporary information at places where there are road markings instructing to stop. Various event information is recorded, including whether or not the vehicle has stopped and the length of time the vehicle has stopped. Map data is registered in the hazard map DB, in which marks representing points where accidents have occurred in the past (accident points), places where temporary stop violations are likely to occur, etc. are superimposed on a map. Note that this hazard map may also describe areas where disasters such as natural disasters are expected, evacuation sites, and the like.

The office PC 30 has a function of inputting the operation data stored in the memory card 65 and analyzing the actual operation state of the corresponding vehicle. This analysis function also includes a function that processes event data (temporary stop event data) at locations where road markings such as "stop" are detected and reflects the data in the evaluation of each crew member. Details will be described later.

Next, an example of the operation when the digital tachograph 10 performs image recognition of a "stop" road sign will be described. FIG. 5 shows an example of the operation when the digital tachograph 10 selects a graphic information database corresponding to vehicle position information. Further, FIG. 6 shows an example of the operation when the digital tachograph 10 recognizes road characters as images. The CPU 11 in the digital tachograph 10 executes the control shown in FIGS. 5 and 6. The image recognition function of the digital tachograph 10 described below is always in operation when the vehicle is traveling at a speed of 50 kilometers per hour or less, and the flows shown in FIGS. 5 and 6 are repeatedly executed at predetermined intervals. By operating the image recognition function that recognizes "stop" road signs at a realistic speed range of 50 kilometers per hour or less for vehicles approaching a stop position, we ensure the effectiveness of this recognition function. An increase in the processing load on the CPU 11 can be prevented. In addition, by operating various recognition functions divided into speed ranges, such as operating the recognition function of the distance between vehicles in front at speeds of 60 kilometers per hour or more, the necessary and sufficient recognition functions are operated in each speed range. The processing power of the CPU 11 can be effectively utilized. Note that the interval at which the flow shown in FIG. 5 is repeatedly executed and the interval at which the flow shown in FIG. 6 is repeatedly executed may be different or may be the same.

As shown in FIG. 5, the digital tachograph 10 acquires vehicle position information in step S1, and in step S2 specifies which of the regions shown in FIG. 4 includes the current location of the vehicle. Next, the digital tachograph 10 selects a graphic information database (graphic information DB) corresponding to the specified area (step S3), and ends the process of FIG. 5.

Next, an example of the operation in which the digital tachograph 10 performs image recognition of road characters by referring to the graphic information database selected as described above will be described with reference to FIG. The digital tachograph 10 (CPU 11) acquires a captured image captured by the camera 23A (step S11). In step S11, the CPU 11 acquires the image photographed by the camera 23A frame by frame through the camera I/F 16 as image data such as the image frame 100A (see FIG. 2). Next, the CPU 11 detects and recognizes the road character "Stop" in the acquired photographic image (step S12). In step S12, the CPU 11 performs image processing on the area on the road surface in each frame, applies the selected graphic information database, that is, the graphic information database associated with the current position of the vehicle, and recognizes the character pattern. Execute. If at least one pattern candidate that may be a character is detected, there is a possibility that it is a pattern for "stop", which is a temporary stop sign, so detection for "stop" is executed.

In reality, when your vehicle approaches a painted "stop" sign (road marking), it is easy to recognize "re", "ma", and "stop" in order from the position closest to your vehicle (the amount of information is large). (see FIG. 2), pattern recognition is performed individually for each character in this order. In this pattern recognition, the characteristics of each character pattern detected from the input image (photographed image) and all the characters such as "re", "ma", "stop" included in the selected graphic information database are used. The degree of matching (degree of matching) with each feature is compared, and characters that are most similar are detected. Then, when the degree of matching with this character is equal to or greater than a threshold value, it is determined that the character represented by one pattern has been successfully recognized. When the CPU 11 succeeds in recognizing the character string "stop", the CPU 11 determines recognition of the specific road marking (step S13). At this time, the digital tachograph 10 refers to the graphical information database associated with the vehicle's current position and recognizes the "stop" road sign, even if the font is different depending on the region. Able to correctly recognize signs. Further, in step S13, the CPU 11 (recording unit 17) records the recognition result as, for example, "pause event data." This event data includes information indicating that a "stop" road sign has been detected, information such as vehicle speed, position, and time (operation information, position information), and information on captured images. That is, this event data includes information indicating whether the vehicle has stopped temporarily when a "stop" road sign is detected. In addition to this event data, in addition to the stopping position and stopping time of the vehicle, information indicating the presence or absence of left and right safety confirmation actions is included, which is determined from the direction of the driver's face recognized based on the image taken by the camera 23B. May include. The CPU 11 records this temporary stop event data in the memory card 65, and ends the process of FIG. 6. The temporary stop event data recorded on the memory card 65 can be used for driving evaluation in the office PC 30.

An example of the operation of the office PC 30 is shown in FIG. The operation shown in FIG. 7 will be explained below.
The administrator who operates the office PC 30 turns on the power of the office PC 30 and makes it usable, and then starts a dedicated application software for data analysis (hereinafter simply referred to as an "app"). (Step S31). According to the administrator's input operation, the analysis application running on the office PC 30 reads the operation data and event data recorded on each crew member's memory card 65 (step S32). When the administrator instructs the analysis application to select a mode for analyzing pause events, the application extracts only the corresponding event data (pause event data) from the data read in step S32 as a processing target ( Step S33).

Based on the contents of all the pause event data extracted in step S33, the application calculates the number of times the digital tachograph 10 recognized a "stop" road sign (total number of recognitions) and the number of times a pause was not made among them (total number of recognitions). (number of violations) is detected (step S34). The application then calculates the violation rate (number of violations/total number of recognition) in step S34. The application uses the violation rate calculated in step S34 to add or subtract points to the evaluation of the relevant crew member (step S35). For example, for crew members whose violation rate is lower than the average value of all crew members, points corresponding to (average value - violation rate) are added to the evaluation, and for crew members whose violation rate is higher than the average value, A score corresponding to (violation rate - average value) is subtracted from the evaluation, and the actual driving condition is reflected in the evaluation.

After completing the evaluation of all the crew members reflecting the operation data of the day, the application creates an evaluation ranking based on the evaluation data of all the crew members (step S36). For example, the evaluation data of all crew members is arranged in descending order of evaluation scores, and several crew members with the highest ratings and several crew members with the lowest ratings are extracted and displayed together with their evaluation scores.

After the application completes the evaluation that reflects the day's operation data for all the crew members, the application extracts the crew members who should be the subject of guidance from all the crew members based on the evaluation data of the entire crew members (step S37). . For example, crew members whose violation rate for specific items such as temporary stop violations are higher than a threshold value, or crew members whose overall evaluation score is lower than a threshold value, are extracted and selected as subjects who require safe driving guidance and education.

The app aggregates the operation data and event data of all crew members for each location, and detects locations that require attention, for example, where the rate of violations of specific items, such as temporary stop violations, tends to be particularly high. Then, information on the detected cautionary position is registered in a hazard map DB (not shown) connected to the external I/F 48, along with information on types of events, violations, etc. (step S38). The hazard map DB will be configured so that all crew members can freely access and share information. As a result, even crew members using only general on-board devices that do not have advanced recognition and judgment functions will be able to grasp the locations where caution is most likely to occur, such as when a violation of a temporary stop is likely to occur.

As described above, in this embodiment, a specific road marking is recognized by referring to a graphic information database (or learning dictionary) associated with vehicle position information. With this configuration, it is possible to improve the recognition rate and reduce the rate of misrecognition of specific road markings that have different fonts depending on the region, such as a "stop" road marking that instructs a temporary stop. In addition, by referring only to the graphical information database corresponding to the vehicle's current position, the recognition performance of specific road markings is improved even with a CPU with low processing power, while suppressing an increase in the recognition processing load and an increase in the false recognition rate. can. Furthermore, for regions with similar display characteristics, by grouping them together and using a common graphic information database, that is, by learning them together in one dictionary, while maintaining the recognition rate of specific road markings or signs, The amount of data in the graphic information database can be reduced.

Furthermore, according to the present embodiment, specific road markings can be recognized with a high recognition rate, so for example, when a road marking that says "Stop" is recognized, operation information such as whether there is a temporary stop or the length of time the stop is made is recognized. Understand this and be able to appropriately evaluate driving.

Note that the present invention is not limited to the embodiments described above, and can be modified, improved, etc. as appropriate. In addition, the material, shape, size, numerical value, form, number, arrangement location, etc. of each component in the embodiments described above are arbitrary as long as they can achieve the present invention, and are not limited. For example, in the embodiment described above, an example of the road marking 104 (a string of "stop" characters painted on the road surface) was shown as a road marking instructing a temporary stop. good. Further, in the embodiment described above, an example was shown in which the office PC 30 functions as a driving evaluation device, but the driving evaluation device may be incorporated into the digital tachograph 10 or installed in a data server that can communicate with the digital tachograph 10. May be provided.

Here, the features of the on-vehicle device and the driving evaluation system according to the embodiments of the present invention described above are briefly summarized and listed below in [1] to [5].
[1] An on-vehicle device (digital tachograph 10) mounted on a vehicle,
an image acquisition unit (CPU 11) that acquires a captured image of the front of the vehicle;
a position acquisition unit (GPS reception unit 15) that acquires position information of the vehicle;
a recognition unit (CPU 11) that recognizes a specific road marking (road marking 104) or a sign from the photographed image with reference to the graphic information database (T1 to T11) associated with the position information;
a recording section (17) for recording recognition results;
An on-vehicle device (digital tachograph 10) characterized by comprising:
[2] The specific road markings or signs have different markings (MA to MF) for each region that indicate the same meaning,
The recognition unit recognizes the specific road marking or sign by referring to a graphical information database associated with the area indicated by the location information among graphical information databases corresponding to different signs for each region. The on-vehicle device according to the above [1], characterized by:
[3] The first specific road marking for the first region and the second specific road marking for the second region have the same meaning, and the characteristics of the first specific road marking and the characteristics of the second specific road marking If they are similar, a common graphic information database common to the first region and the second region is prepared,
[2] wherein the recognition unit refers to the common graphic information database and recognizes the specific road marking or sign when the position information indicates within the first area or the second area. ] The on-vehicle device described in
[4] A collection unit (CPU 11) that collects operation information of the vehicle,
[1] to [3] above, wherein the recording unit records the operation information in association with the photographed image and the position information when the recognition unit recognizes the specific road marking or sign. On-vehicle equipment listed in any one of the above.
[5] The on-vehicle device described in [4] above,
a driving evaluation device (office PC 30) that acquires the content recorded by the recording unit from the on-vehicle device and evaluates the driving of the driver of the vehicle based on the content;
A driving evaluation system (5) characterized by comprising:

5 Driving evaluation system 8 Wireless base station 10 Digital tachograph (onboard device)
11 CPU (image acquisition unit, recognition unit, collection unit)
12A speed I/F
12B Engine rotation I/F
13 External input I/F
14 Sensor I/F
15 GPS receiving section 15a GPS antenna 16 Camera I/F
17 Recording section 18 Card I/F
19 Audio I/F
20 Built-in speaker 21 RTC (clock IC)
22 SW input section 23A, 23B Camera 24 Communication section 25 Power supply section 26A Nonvolatile memory 26B Volatile memory 27 Display section 28 G sensor 29 Analog input I/F
30 Office PC (operation evaluation device)
31 CPU
32 Communication section 33 Display section 34 Storage section 35 Card I/F
36 Operation unit 37 Output unit 38 Audio I/F
41 Microphone 42 Speaker 51 Vehicle speed sensor 65 Memory card 70 Network 100A Image frame 101 Intersections 102, 103, 104 Road markings T1 to T11 Graphic information database

Claims (5)

An on-vehicle device installed in a vehicle,
an image acquisition unit that acquires a captured image of the front of the vehicle;
a position acquisition unit that acquires position information of the vehicle;
a recognition unit that recognizes a specific road marking or sign from the photographed image by referring to a graphic information database associated with the position information;
a recording section for recording recognition results;
Equipped with
The specific road marking or sign has a marking consisting of a character string composed of a plurality of characters,
The recognition unit compares the degree of agreement between the pattern characteristics of each character detected from the photographed image and the characteristics of all the characters included in the graphic information database associated with the position information, If a character that is extremely similar is detected, and the degree of matching with the detected character is equal to or higher than a threshold, a state in which the character represented by one pattern has been successfully recognized is determined, and the character composed of the plurality of characters is determined. If the column is successfully recognized, confirm the recognition of the specific road marking or sign.
An on-vehicle device characterized by: The specific road markings or signs have different markings for each region that indicate the same meaning,
The recognition unit recognizes the specific road marking or sign by referring to a graphical information database associated with the area indicated by the positional information among graphical information databases corresponding to the markings that differ for each region. The on-vehicle device according to claim 1, characterized in that: The first specific road marking for the first region and the second specific road marking for the second region have the same meaning, and the features of the first specific road marking and the features of the second specific road marking are similar. If so, a common graphic information database common to the first region and the second region is prepared,
2. The recognition unit, when the positional information indicates within the first area or the second area, refers to the common graphic information database and recognizes the specific road marking or sign. On-vehicle equipment listed in. comprising a collection unit that collects operation information of the vehicle,
Any one of claims 1 to 3, wherein the recording unit records the operation information in association with the photographed image and the position information when the recognition unit recognizes the specific road marking or sign. The on-vehicle device described in paragraph 1. The on-vehicle device according to claim 4;
a driving evaluation device that acquires content recorded by the recording unit from the on-vehicle device and evaluates the driving of the driver of the vehicle based on the content;
A driving evaluation system comprising:

Images