JP5035713B2 - Road recognition device, road recognition method, and road recognition program - Google Patents

Description

  The present invention relates to a road recognition device, a road recognition method, and a road recognition program.

  If an advanced driving support function is to be realized in the navigation system, a map database in which road attributes such as road regulations and road structures are registered is required. 2. Description of the Related Art Conventionally, a method for registering position information of a new road in a map database based on a travel locus of a vehicle is known (see, for example, Patent Document 1). Patent Document 1 also recognizes the number of lanes according to the behavior of the lane change, registers the recognized number of lanes as a road attribute, recognizes the road type of an expressway according to the vehicle speed, and A method of registering a type as a road attribute is disclosed. However, according to the method disclosed in Patent Document 1, since the road attribute cannot be recognized unless the vehicle takes a behavior capable of recognizing the road attribute, there is a problem that the recognition accuracy of the road attribute is low. For example, in the method disclosed in Patent Document 1, even if a vehicle is traveling on a road with one side of a plurality of lanes, the vehicle cannot be recognized as a road with one side of a plurality of lanes unless the vehicle changes lanes on the road.

JP 2004-251790 A

  The present invention has been created in view of the above-described problems, and an object of the present invention is to provide a road recognition device, a road recognition method, and a road recognition program that can accurately register road attributes of roads in a map database.

(1) the object road recognition apparatus for achieving includes road specifying means for vehicle identifying a traveling road, and brightness acquisition unit that acquires the brightness of the external world of the vehicle as the irradiance waveform data, tunnel interior Based on an illuminance pattern database representing a brightness pattern of the road, a determination unit that determines whether a pattern of a tunnel section appears in the illuminance waveform data, and a tunnel section of the road is recognized based on a determination result by the determination unit Recognizing means for registering, and registering means for registering the section of the tunnel of the road in a map database.
When entering a tunnel, passing through the tunnel, and leaving the tunnel, a characteristic change occurs in the brightness of the outside of the vehicle. Specifically, the outside of the vehicle becomes dark when entering the tunnel in the daytime, the brightness of the outside of the vehicle periodically fluctuates due to the lighting inside the tunnel while passing through the tunnel, and the outside of the vehicle becomes bright when leaving the tunnel in the daytime. . According to this road recognition device, in order to identify the road on which the vehicle travels and recognize the tunnel section by analyzing the brightness of the outside world of the vehicle, the tunnel section of the road on which the vehicle travels can be registered in the map database. it can.
(2) In the road recognition device for achieving the above object, the recognition means uses the position of the vehicle at the time when the brightness of the outside world starts to decrease as one end point of the tunnel section, and the brightness of the outside world. The position of the vehicle when it starts to rise is recognized as the other end point of the tunnel section.
(3) In the road recognition device for achieving the above object, the brightness pattern inside the tunnel is a cycle and amplitude of illuminance that is changed by the light emitted by the illumination device provided in the tunnel .

(4) A road recognition method for achieving the above object is to identify a road on which a vehicle travels , acquire the brightness of the outside of the vehicle as an illuminance waveform pattern, and represent an illumination pattern representing the brightness pattern inside the tunnel. Based on a database, it is determined whether a pattern of a tunnel section appears in the illuminance waveform data, the tunnel section of the road is recognized according to a determination result , and the tunnel section of the road is registered in a map database. Including that.

(5) Road recognition program for achieving the above object, a road specification means a vehicle for identifying a traveling road, and brightness acquisition unit that acquires the brightness of the external world of the vehicle as irradiance waveform pattern, tunnel interior Based on an illuminance pattern database representing a brightness pattern of the road, a determination unit that determines whether a pattern of a tunnel section appears in the illuminance waveform data, and a tunnel section of the road is recognized based on a determination result by the determination unit And a registration means for registering the section of the tunnel of the road in a map database to cause the computer to function.

  It should be noted that the order of each operation of the method described in the claims is not limited to the order of description as long as there is no technical obstruction factor, and may be executed in any order, or may be executed simultaneously. Also good. In addition, each function of the plurality of means provided in the present invention is realized by a hardware resource whose function is specified by the configuration itself, a hardware resource whose function is specified by a program, or a combination thereof. The functions of the plurality of means are not limited to those realized by hardware resources that are physically independent of each other.

The schematic diagram which concerns on one Embodiment of this invention. The block diagram which concerns on one Embodiment of this invention. The flowchart which concerns on one Embodiment of this invention. The screen figure concerning one embodiment of the present invention. The flowchart which concerns on one Embodiment of this invention. The schematic diagram which concerns on one Embodiment of this invention. The flowchart which concerns on one Embodiment of this invention. The schematic diagram which concerns on one Embodiment of this invention. The graph which concerns on one Embodiment of this invention.

Embodiments of the present invention will be described below based on examples.
[Configuration of road recognition device]
FIG. 2 is a block diagram showing a road recognition device 1 to which the present invention is applied. The road recognition device 1 is configured as a part of a navigation system mounted on a vehicle as a moving body such as an automobile or a motorcycle.

  The camera unit 10 includes a color image sensor such as a CCD image sensor, a drive circuit thereof, and an image signal processing circuit, and is mounted on a vehicle on which the road recognition device 1 is mounted. The camera unit 10 generates a digital image representing the external field of view of the vehicle at a predetermined frame rate. Hereinafter, a digital image representing the field of view of the outside of the vehicle is simply referred to as a neighborhood image. The camera unit 10 may generate a neighborhood image in which the luminance value of each pixel is represented by an analog signal. In this case, AD conversion by an interface circuit (not shown) provided between the camera unit 10 and the RAM 26 is required.

  The illuminance sensor 12 is an optical sensor for detecting the brightness of the outside of the vehicle. The illuminance sensor 12 detects the illuminance of the light receiving surface directed outside the vehicle, and outputs illuminance data representing the illuminance of the light receiving surface as a digital signal. The illuminance sensor 12 may output illuminance data as an analog signal. In this case, AD conversion by an interface circuit (not shown) provided between the illuminance sensor 12 and the RAM 26 is necessary.

The speed sensor 14 as the road specifying means is used for dead reckoning navigation for specifying the road on which the vehicle is traveling. The mileage is obtained by integrating the vehicle speed obtained from the number of rotations of the wheel per unit time with time. The travel distance may be obtained using a Doppler ground speed sensor using radio waves or ultrasonic waves, or a ground speed sensor using light and a spatial filter.
The GPS unit 16 as a road identification means receives orbit data transmitted from three or four satellites used for satellite navigation for identifying the road on which the vehicle is traveling, and determines the current position of the vehicle. It consists of an antenna, ASIC, etc. for outputting latitude and longitude data.

The azimuth sensor 18 as a road identification means is composed of a geomagnetic sensor, a left and right wheel speed difference sensor, a vibration gyro, a gas rate gyro, an optical fiber gyro, and the like used for dead reckoning navigation to identify the road on which the vehicle is traveling. Detect the direction of travel of the car.
The ROM 22 is a nonvolatile storage medium such as a flash memory, and stores a boot program and a road recognition program.

The CPU 24 functions as a road identification unit, an image acquisition unit, a recognition unit, and a registration unit by executing a road recognition program.
The RAM 24 is a volatile storage medium, and functions as a work memory in which a program executed by the CPU 22 and processing target data of the program are temporarily stored.

  The hard disk device (HDD) 20 stores a map database (DB). The map DB may be stored in another large-capacity nonvolatile storage medium such as a CD or a DVD. The road recognition program may be stored in the HDD 20. The map DB and the road recognition program can be installed in the road recognition device 1 by downloading them via a communication line or reading them from a removable memory.

  The map DB is a database composed of information obtained by digitally representing a map with a graph structure, and is used for specifying a road on which a vehicle travels. In the map DB 42, intersections, junctions, turning points, dead ends, and the like are registered as nodes, and roads are registered as links connecting nodes. Each node is defined by an identifier, a latitude / longitude representing the absolute position of the node, a node type (intersection, turn point, tunnel end point, etc.), and the like. In addition, each link includes an identifier, an identifier of a node to be connected, presence / absence of a predetermined traffic sign / sign, distance, number of lanes, width, road type (highway, national road, etc.), regulation (limited speed, one direction, both Direction) and form classification (tunnel, bridge, etc.). For predetermined traffic signs and traffic signs, their types (signals, stop lines, etc.) and positions are defined in association with the links corresponding to the roads on which they exist.

[Operation of road recognition device 1]
FIG. 3 is a flowchart showing a flow of processing in which the road recognition device 1 recognizes road attributes of roads by analyzing neighborhood images and registers the recognized road attributes in the map DB. The processing shown in FIG. 3 is executed by the CPU 24 repeatedly executing a predetermined module of the road recognition program.

  In step S100, GPS information is acquired and the road on which the vehicle is currently traveling is specified. Specifically, latitude / longitude data representing the current position of the vehicle is read from the GPS unit 16 into the RAM 26, and map matching for correcting the current position on the road registered in the map DB is executed by the CPU 24. As a result, the road on which the vehicle is traveling at an arbitrary time is specified. In a section such as a tunnel where the orbit data cannot be received from the satellite, the road on which the vehicle is currently traveling is specified by autonomous navigation. When the vehicle is traveling on a road that is not registered in the map DB, the travel locus of the vehicle represented by the latitude / longitude data itself obtained from the trajectory data deviates greatly from the road registered in the map DB. In this case, it is also possible to register the road attribute of the road while registering the position information about the road on which the vehicle is traveling in the map DB. A method for registering road position information in the map DB is publicly known, and is disclosed in, for example, Japanese Patent Application Laid-Open No. 2004-251790, and thus the description thereof is omitted.

In step S102, a neighborhood image is acquired. Specifically, a neighborhood image representing a front view of the outside of the vehicle is read from the camera unit 10 into the RAM 26.
In step S104, a pattern recognition database of attribute resources is acquired. Specifically, a pattern recognition database of attribute resources is read from the ROM 22 or HDD 20 into the RAM 26. The attribute resource means a road sign, a road marking, a lane marking, a partition structure, and the like that exists on the road and defines the road attribute. The attribute resource pattern recognition database is a database for detecting attribute resources by analyzing neighborhood images, and is organized by feature information such as lines and regions constituting patterns corresponding to the attribute resources. As a method for detecting the attribute resource by analyzing the neighborhood image, any pattern recognition method such as structure matching, template matching, or relaxation method can be adopted.

  In step S106, it is determined whether an attribute resource pattern appears in the neighborhood image. If the attribute resource pattern does not appear in the neighborhood image, the process returns to step S100 and the above-described processing is repeated. If an attribute resource pattern appears in the neighborhood image, that is, if an attribute resource pattern is detected, the process proceeds to step S108. The processing of step S106 will be specifically described based on FIGS.

FIG. 4 is a screen diagram showing an example of a neighborhood image. FIG. 5 is a flowchart showing the detailed processing flow of step S106.
In step S1060, the neighborhood image is sampled. Specifically, the CPU 24 converts the resolution and the number of colors of the neighborhood image, or spatially differentiates the neighborhood image, so that an image having a resolution and the number of colors suitable for attribute resource recognition, and an edge component of the neighborhood image. Is generated as sampling data.

In step S1062, the noise of the sampling data is removed. Specifically, for example, the CPU 24 performs region expansion processing, region reduction processing, smoothing processing, and the like on the differential image.
In step S1064, segmentation is executed. That is, the sampling data is divided by the CPU 24 into a plurality of areas suitable for recognition of attribute resources.
In step S1066, feature extraction processing is executed. Specifically, the CPU 24 analyzes the sampling data based on the attribute resource pattern recognition database, and extracts the features of the lines and regions constituting the pattern appearing in the neighborhood image for each line and each region.

  In step S1068, pattern recognition processing is executed. Specifically, the CPU 24 determines whether or not a pattern matching the feature information and the pattern configured by the combination of the line and region from which the feature is extracted in step S1066 is registered in the pattern recognition database. Then, it is determined that the attribute resource corresponding to the pattern defined in the pattern recognition database appears in the neighborhood image. For example, when the neighborhood image shown in FIG. 4 is to be processed, a stop line 34, a traveling direction indication sign 38, a national road number guide sign 30, a maximum speed restriction sign 32, a traffic light 28, a median strip 40, a lane boundary line 36, It is determined that the roadway center line 39 and the roadway outer line 35 appear in the vicinity image as attribute resources. The median strip 40, the lane boundary line 36, the lane center line 39, and the lane outside line 35 correspond to compartments.

In step S108, CPU24 recognizes a road attribute based on the attribute resource detected by determination of step S1068, and registers it in map DB. This will be specifically described with reference to FIGS.
FIG. 1 is a schematic diagram showing registered contents of the map DB. FIG. 6 is a schematic diagram showing a travel locus of the vehicle. In the state immediately before the vehicle travels on the road in the trajectory shown in FIGS. 6A and 6B, the roads 48, 54, and 62 are nodes 46, 52, 57, and 70 as shown in FIG. , Links 50, 56, and 68 are registered in the map DB, and road attributes for these roads are not registered in the map DB at all.

(Example 1)
It is assumed that at a certain point in time, the vehicle is traveling at a point P2 with a maximum speed regulation sign 58 of 40 km / h after turning right at an intersection at the point P1. In this case, in step S108, the maximum speed restriction mark 58 of 40 km / h is detected as an attribute resource. At that time, since the vehicle is traveling on the road 48, the maximum speed limit of 40 km / h is recognized as the road attribute of the road 48, and the maximum speed limit: 40 km / h is registered in the map DB as the road attribute of the road 48. Specifically, the maximum speed limit: 40 km / h is registered as the attribute of the link 50 that defines the road in the section from the point P1 to the point P3. As a result, the position of the node 46 connected by the link 50 is registered as the position of the start point of the section having the road speed attribute of maximum speed limit: 40 km / h. The start point of the section in which the road attribute is registered may be the position of the node immediately before the attribute resource as described above, or may be a point where the attribute resource exists. That is, the CPU 24 may determine the start point of the section in which the road attribute is registered as the position of the node immediately before the attribute resource, or may determine the point where the attribute resource exists. When registering the start point of a section as a point having an attribute resource, the start point of the section is specified by analysis of the neighborhood image. In that case, an interpolation point or a node may be registered at a point where an attribute resource exists, or a start point position of the section may be registered as a link attribute using latitude and longitude.

(Example 2)
It is assumed that the vehicle is traveling on the road 65 via points P1, P2, P3, P8, and P9 at a certain time. At this time, as described in Example 1, the maximum speed limit: 40 km / h is registered as the road attribute of the road 48, and the maximum speed limit: 30 km / h is registered as the road attribute of the road 54. Further, the road 65 running at this time has no maximum speed restriction sign. Since the vehicle turns left without going straight through the intersection at the point P9 after passing the point with the maximum speed regulation sign 64 of 30 km / h, the CPU 24 does not register the maximum speed limit: 30 km / h as the road attribute of the road 65 . That is, when the CPU 24 turns right or left at the intersection, the intersection is determined as the end point of the section in which the road attribute recognized for the road before the intersection is to be registered. Based on the maximum speed limit: the section in which the road attribute of 30 km / h is registered is determined from the point P3 to the point P9. The behavior of a left or right turn at a vehicle intersection is determined by identifying from the map DB and the current position of the vehicle that the connection attribute of the two links corresponding to the roads before and after the intersection where the vehicle travels corresponds to the right and left turn. It can be analyzed, or it can be analyzed by detecting the operation of the blinker or the handle. The CPU 24 can also determine the stop point of the vehicle as the end point of the section in which the road attribute recognized for the road on which the vehicle traveled before stopping is registered.

(Example 3)
It is assumed that the vehicle is traveling at a point P9 via points P1, P2, and P3 at a certain time. However, it is assumed that the maximum speed regulation sign 64 of 30 km / h is not present at the point P8. In this case, while the road 54 is running, the maximum speed restriction sign is not detected, but the road attribute of the road 48 before the intersection at P3 where the vehicle goes straight is recognized as the maximum speed limit: 40 km / h. Therefore, the CPU 24 registers the road attribute of the road 54 as the maximum speed limit: 40 km / h. That is, the CPU 24 determines the road attribute that the vehicle has recognized last before passing through the intersection unless the vehicle turns right or left at the intersection and unless the road attribute that does not match the last recognized road attribute is recognized. Register.

(Example 4)
It is assumed that the vehicle is traveling at a point P4 via P1, P2, and P3 at a certain time. In this case, the national road number guide sign 60 is detected as an attribute resource in step S108. At that time, since the vehicle is traveling on the road 62, the road type of the road 62 is recognized as the road attribute of the road 62, and the road type: national road No. 1 is registered in the map DB as the road attribute of the road 62. Specifically, road type: national highway No. 1 is registered as an attribute of the link 68 defining the road 62 in the section from the point P3 to the point P7.

(Example 5)
At a certain point in time, it is assumed that the median strip 40, the lane boundary line 36, the roadway center line 39, and the roadway outer line 35 appear in the neighborhood image as shown in FIG. In this case, since one lane boundary line 36 appears in the road width from the road center line 39 to the road outer line 35, the road attribute of two lanes on one side is recognized. In addition, since the median strip 40 appears, the two-way traffic classification and the median strip: presence are recognized as road attributes. Further, the distance from the road center line 39 to the road outer line 35 is recognized as the width of the road by analyzing the neighborhood image based on the calibration information of the camera unit 10. These recognized road attributes are registered in the map DB as road attributes of the road on which the vehicle is currently passing.

(Example 6)
At a certain point in time, as shown in FIG. In this case, the positions of the traffic light 28, the stop line 34, and the traveling direction indication sign 38 are specified by latitude and longitude by analyzing the vicinity image based on the current position of the vehicle and the calibration information of the camera unit 10. And the position of the traffic light 28, the stop line 34, and the advancing direction instruction | indication sign 38 is registered into map DB as a road attribute of the road where the vehicle is drive | working at that time. Specifically, the CPU 24 registers the positions of the traffic light 28, the stop line 34, and the traveling direction indication sign 38 in the map DB in association with the link corresponding to the road on which the vehicle is traveling at that time.

[Operation of road recognition device 2]
FIG. 7 is a flowchart showing a flow of processing in which the road recognition apparatus 1 recognizes a tunnel section by analyzing the brightness of the outside of the vehicle and registers the recognized tunnel section in the map DB. The processing shown in FIG. 7 is executed by the CPU 24 repeatedly executing a predetermined module of the road recognition program.

In step S200, the same process as in step S100 already described is executed, and the road on which the vehicle is currently traveling is specified.
In step S202, illuminance data is acquired, and the brightness of the external environment of the vehicle at a certain point is specified. Specifically, it is as follows. Illuminance data representing the illuminance of the light receiving surface directed from the illuminance sensor 12 to the outside of the vehicle is read into the RAM 26 at predetermined time intervals (for example, every 50 msec). The illuminance data read from the illuminance sensor 12 is stored in the RAM 26 in the order of acquisition in association with the current position of the vehicle for a certain time (for example, 10 minutes). When new illumination data is acquired, the oldest illumination data is discarded. A data group in which the illuminance data for a certain time accumulated in the RAM 26 is arranged in the order of acquisition is referred to as illuminance waveform data. Every time new illuminance data is acquired, noise removal processing of the illuminance waveform data is executed. Specifically, a smoothing process or the like is executed.

  In step S204, the illuminance pattern database of the tunnel section is acquired. Specifically, the illuminance pattern database of the tunnel section is read from the HDD 20 or ROM 22 into the RAM 26. The illuminance pattern database for the tunnel section is a database in which patterns for detecting the tunnel section by analyzing the illuminance data are registered, and the illuminance generated during the period when the vehicle is traveling through tunnels of various structures Organized with feature information of waveform data. The illuminance pattern database in the tunnel section will be specifically described with reference to FIG.

FIG. 8A is a schematic diagram for explaining a general tunnel structure, and FIG. 8B is a diagram showing the illuminance detected by the illuminance sensor 12 when the vehicle travels through the tunnel shown in FIG. It is a graph showing a change.
When the vehicle enters the tunnel 42 during the daytime, the outside of the vehicle suddenly becomes dark immediately after entering. When the vehicle is traveling inside the tunnel 42, the brightness of the external environment of the vehicle is periodically in a range that is darker than the brightness outside the tunnel 42 due to the light emitted by the plurality of lighting devices 44 provided in the tunnel 42. Change. During the daytime, when the vehicle exits the tunnel 42, the external environment of the vehicle suddenly becomes bright immediately before leaving. Such a change pattern of brightness that occurs when the vehicle passes through the tunnel 42 is determined according to the specific structure of the tunnel 42, but is common to some extent in any tunnel. Therefore, the length of the tunnel 42, the brightness of the lighting device 44 provided in the tunnel 42, the installation interval of the lighting device 44, the ceiling height of the tunnel 42, the brightness outside the tunnel 42, the traveling speed of the vehicle, etc. Accordingly, various pattern features of the illuminance waveform data detected by the illuminance sensor 12 when the vehicle travels through the tunnel 42 can be specified in advance. The illuminance pattern database is feature information that represents the characteristics of the pattern of the illuminance waveform data that appears when passing through the tunnel (such as the change period length when the illuminance changes, the change width of the illuminance, the illuminance range, the period and amplitude at which the illuminance vibrates) An organized database.

  In step S206, it is determined based on the illuminance pattern database whether the pattern of the tunnel section appears in the illuminance waveform data. If the tunnel section pattern does not appear in the illuminance waveform data, the process returns to step S200 and the above-described processing is repeated. If the pattern of the tunnel section appears in the illuminance waveform data, the process proceeds to step S208. Specifically, it is as follows. First, the length of the period in which the illuminance is drastically reduced, the change in illuminance in the period in which the illuminance is drastically reduced, the length of the period in which the illuminance is drastically increased, and the illuminance in the period during which the illuminance is drastically increased And the period and amplitude of a period in which the illuminance changes periodically in a dark range are extracted as feature information of the illuminance waveform data. Next, it is determined whether or not feature information that matches the extracted feature information is registered in the illuminance pattern database. If registered, it is determined that the pattern of the tunnel section appears in the illuminance waveform data.

  In step S208, the CPU 24 registers the tunnel section corresponding to the pattern detected by the determination in step S206 in the map database. Specifically, the position of the vehicle at the time when the illuminance data corresponding to the start of the time period in which the illuminance starts to decrease sharply in the detected pattern is acquired from the illuminance sensor 12 is the position of one end point of the tunnel section. be registered. In addition, the position of the vehicle at the time when the illuminance data corresponding to the end of the time period in which the illuminance starts to rise rapidly in the detected pattern is acquired from the illuminance sensor 12 is registered as the position of the other end point of the tunnel section. At this time, the current position of the vehicle stored in the RAM 26 in association with each illuminance data is registered as the position of the end point of the tunnel section.

  The process shown in FIG. 7 will be described more specifically based on FIGS. Assume that at a certain point in time, after the vehicle enters the tunnel 66 on the road 62 from the point P5, the vehicle exits the tunnel 66 at the point P6. In this case, the illuminance detected by the illuminance sensor 12 at the point P5 rapidly decreases, and the illuminance detected by the illuminance sensor 12 periodically varies in a dark range in the section from the point P5 to the point P6. The illuminance detected by 12 increases rapidly. For this reason, after passing through the point P6, the pattern of the tunnel section is detected in the period corresponding to the point P6 from the point P5 of the illuminance waveform data. Then, the position of the point P5 is registered in the map DB as one end point of the tunnel section, and the position of the point P6 is registered in the map DB as the other end point of the tunnel section. At this time, interpolation points 86 and 92 corresponding to the points P5 and P6 may be registered for the link 68 corresponding to the road 62. The interpolation points 86 and 92 are defined by an identifier, a type (such as a tunnel end point), and a latitude and longitude representing a position. A link 94 connecting the node 52 and the interpolation point 86, a link 88 connecting the interpolation point 86 and the interpolation point 92, and a link 90 connecting the interpolation point 92 and the node 70 are registered. As type classification: information such as a tunnel may be registered.

According to the road recognition device 1 described above, when the vehicle travels on the road shown in FIG. 6, as shown in FIG. 1A, for example, as shown in FIG. Road attributes 72, 74, 76, 78, 80, 82, 84 are registered in the map DB. For this reason, when the vehicle travels again on the road shown in FIG. 6, since the road attributes of the roads 48, 54, and 62 are registered in the map DB, an advanced driving support function is provided to the driver by the navigation device. Is possible.
As described above, the present invention has been described based on the embodiments. However, the present invention is not limited to the above-described embodiments, and can be applied to various embodiments without departing from the gist thereof.

1: road recognition device, 10: camera unit, 12: illuminance sensor (light sensor), 14: speed sensor (road identification means), 16: GPS unit (road identification means), 18: direction sensor (road identification means), 24: CPU (road identification means, image acquisition means, recognition means, registration means, 35: road outer line (compartment), 36: lane boundary line (compartment), 39: road center line (compartment), 40: Median strip (compartment), 66: Tunnel, 72, 74, 76, 78, 80, 82, 84: Road attribute

Claims (5)

Road identification means for identifying the road on which the vehicle is traveling;
Brightness acquisition means for acquiring the brightness of the outside of the vehicle as illuminance waveform data ;
Based on an illuminance pattern database representing a brightness pattern inside the tunnel, determination means for determining whether a pattern of a tunnel section appears in the illuminance waveform data;
Recognizing means for recognizing a section of the tunnel of the road according to a determination result by the determining means ;
Registration means for registering a section of the tunnel of the road in a map database;
A road recognition device comprising: The recognizing means uses the position of the vehicle when the brightness of the outside world starts to decrease as one end point of the tunnel section, and sets the position of the vehicle when the brightness of the outside world starts to increase in the tunnel section. Recognize it as the other endpoint,
The road recognition device according to claim 1. The pattern of brightness inside the tunnel is characterized by the period and amplitude of illuminance that varies depending on the light emitted by the illuminating device provided in the tunnel.
The road recognition device according to claim 1. Identify the road on which the vehicle is running,
Obtain the brightness of the outside of the vehicle as an illuminance waveform pattern ,
Based on the illuminance pattern database representing the brightness pattern inside the tunnel, determine whether the pattern of the tunnel section appears in the illuminance waveform data,
Recognize the tunnel section of the road according to the judgment result ,
Register the tunnel section of the road in a map database;
Road recognition method including that. Road identification means for identifying the road on which the vehicle is traveling;
Brightness acquisition means for acquiring the brightness of the outside of the vehicle as illuminance waveform data ;
Based on an illuminance pattern database representing a brightness pattern inside the tunnel, determination means for determining whether a pattern of a tunnel section appears in the illuminance waveform data;
Recognizing means for recognizing a section of the tunnel of the road according to a determination result by the determining means ;
Registration means for registering a section of the tunnel of the road in a map database;
A road recognition program that makes computers work.

Images