JP6500607B2 - Vehicle position determination device and vehicle position determination method - Google Patents

Description

  The present invention relates to a vehicle position determination device and a vehicle position determination method.

  2. Description of the Related Art Conventionally, there is known a technique for correcting a vehicle position specified using a GPS receiver. In Patent Document 1, the intersection ahead of the host vehicle is detected, the distance from the intersection to the host vehicle is calculated using the traffic signal information present at the detected intersection, and the host vehicle position is corrected using the calculated distance. .

JP-A-9-243389

  However, in Patent Document 1, there are cases where it is not possible to correct the vehicle position on a road having few intersections such as a freeway.

  The present invention has been made in view of the above problems, and an object thereof is to provide an own-vehicle position determination apparatus and an own-vehicle position determination method capable of accurately correcting an own-vehicle position in various traveling environments. It is.

The vehicle position determination apparatus according to an aspect of the present invention includes a map database storing the positions of features present around the road, detects the current position of the vehicle, and images the surroundings of the vehicle. If it is determined that the area around the vehicle is congested, it is determined from the captured image that a feature existing in the sky is identified as the type of feature to be recognized. The identified feature is recognized, and the current position of the vehicle is corrected using the position relationship between the recognized feature and the vehicle.

  According to the present invention, it is possible to correct the vehicle position accurately in various traveling environments.

FIG. 1 is a block diagram of a vehicle position determination device according to an embodiment of the present invention. FIG. 2 is a table showing an example of the relationship between the vehicle environmental condition and the recognition target feature according to the embodiment of the present invention. FIGS. 3A and 3B are diagrams showing an example of an image of a camera installed in the vehicle according to the embodiment of the present invention. FIGS. 4 (a) and 4 (b) are diagrams showing other examples of images of cameras installed in the vehicle according to the embodiment of the present invention. FIG. 5 is a flow chart for explaining an operation example of the vehicle position determination apparatus according to the embodiment of the present invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the description of the drawings, the same parts will be denoted by the same reference numerals and the description thereof will be omitted.

  An own vehicle position determination device 1 according to the present embodiment will be described with reference to FIG. As shown in FIG. 1, the vehicle position determination device 1 provides information to the camera 10, the GPS receiver 20, the vehicle speed sensor 30, the map database 40, the communication I / F 50, the controller 70 and the driver. It has a display 80 to present.

  The camera 10 (imaging means) is a camera equipped with a pan and tilt function, and is installed at a position where it can image the front of the host vehicle. The camera 10 captures the front of the host vehicle and outputs the captured image to the controller 70. Camera 10 may be installed in the position which can picturize circumferences other than the front of self-vehicles.

  The GPS receiver 20 (vehicle position detection means) detects the current position and the current time of the vehicle on the ground by receiving radio waves from the artificial satellite. The GPS receiver 20 outputs the detected current position and current time of the host vehicle to the controller 70.

  The vehicle speed sensor 30 detects the speed of the vehicle from the number of rotations of the wheels, and outputs the detected speed to the controller 70.

  Map information such as road information and facility information is recorded in the map database 40. The map database 40 also records various features existing around the road and the positions of the features. The landmarks recorded in the map database 40 include road signs (speed limit signs, stop signs, one-way signs, pedestrian crossing signs, parking prohibition signs, etc.), road markings (stop line, pedestrian crossing, pedestrian crossing notice Paint, section lines, etc., and information signs (including direction signs, service area information signs, parking area information signs, branch information signs, facility information signs, etc.) are included. In addition, features include road structures and equipment such as distance cards, traffic lights, telegraph poles, tunnels, bridges, piers, emergency stops, toll plazas, gun trays and the like.

  The communication I / F 50 is, for example, a communication device that wirelessly transmits and receives signals to and from the outside. The communication I / F 50 receives various types of information from the outside, for example, by the Intelligent Transportation System (ITS) that transmits traffic information such as traffic congestion information and traffic restrictions, weather information and the like in real time. The ITS includes VICS (Vehicle Information and Communication System (registered trademark), telematics, etc.). The communication I / F 50 outputs the received information to the controller 70.

  The controller 70 displays a map on the display 80 or displays a mark indicating the current position of the vehicle using the information acquired from the GPS receiver 20, the map database 40, and the communication I / F 50. Further, the controller 70 corrects the current position of the vehicle using information acquired from the camera 10, the GPS receiver 20, and the vehicle speed sensor 30.

The correction of the current position of the vehicle by the controller 70 will be described below.
The controller 70 functionally and conceptually includes an information acquisition unit 71, a traveling environment determination unit 72, a vehicle state determination unit 73, a feature identification unit 74, a camera control unit 75, and a feature recognition unit 76. A positional relationship calculation unit 77 and a vehicle position correction unit 78 are provided.

  The information acquisition unit 71 uses VICS to transmit road traffic information such as traffic jams and traffic restrictions in real time to acquire road traffic information in the area where the vehicle is currently traveling, or to use the telematics Get weather information for the area you are currently driving. The information acquisition unit 71 outputs the acquired traffic congestion information and weather information to the traveling environment determination unit 72.

  The traveling environment determining unit 72 determines the environment around the host vehicle using the information acquired from the information acquiring unit 71, the camera 10, the GPS receiver 20, and the vehicle speed sensor 30. Specifically, the traveling environment determination unit 72 determines weather, day and night, road surface condition, road condition ahead, traveling place, congestion condition, etc., as the environment around the host vehicle.

  The types of weather that the traveling environment determination unit 72 determines include, for example, sunny, rain, snow, and fog. The traveling environment determination unit 72 determines the weather using the weather information acquired from the information acquisition unit 71.

  For the day and night, the traveling environment determination unit 72 determines whether it is daytime or nighttime from the current time acquired from the GPS receiver 20.

  As a kind of road surface state, there are, for example, a wet state, a snowy state, a bad road, etc. in addition to a so-called normal state. The traveling environment determination unit 72 determines the road surface condition using the image of the camera 10.

  The road condition ahead refers to how many other vehicles of the vehicle type are present in front of the host vehicle. The traveling environment determination unit 72 determines the road condition ahead using the image of the camera 10.

  Further, using the current position acquired from the GPS receiver 20, the traveling environment determination unit 72 determines whether the traveling location where the vehicle is currently traveling is an urban area, a suburb, or an expressway. In addition, the driving | running | working place which the driving | running | working environment judgment part 72 judges is not restricted to these, A mountain path etc. may be included.

  Further, the traveling environment determination unit 72 determines the degree of traffic congestion on the traveling road. Conditionally, the traveling environment judging unit 72 judges the degree of traffic congestion using the image of the camera 10 and the information of the VICS, or the average speed of the vehicle speed sensor 30 per predetermined time. The traveling environment determination unit 72 determines that the traveling road is congested when other vehicles are closely displayed in the image of the camera 10 or congestion information is acquired from the VICS. In addition, the traveling environment determining unit 72 determines that the traveling road is congested when the average speed of the vehicle speed sensor 30 per predetermined time is very low.

  Then, the traveling environment determination unit 72 outputs, to the feature identification unit 74, the determination results of weather, day and night, road surface condition, forward road condition, traveling place, congestion condition and the like.

  The host vehicle state determination unit 73 determines the traveling state of the host vehicle. Specifically, using the vehicle speed acquired from the vehicle speed sensor 30, the vehicle state determination unit 73 determines whether the vehicle is traveling at high speed or traveling at low speed. When the host vehicle travels at a high speed, the host vehicle state determination unit 73 can determine that the host vehicle travels on an expressway. In addition, when the host vehicle travels at a lower speed than the legal speed, the host vehicle state determination unit 73 can determine that the traveling road is congested. In addition, the vehicle state determination unit 73 uses the information acquired from the camera 10 and the GPS receiver 20 to determine the traveling lane in which the vehicle is traveling. Then, the vehicle state determination unit 73 outputs the determination result to the feature identification unit 74.

  The feature identification unit 74 (feature identification means) is a recognition target among various features based on the environment around the host vehicle and the traveling condition of the host vehicle (hereinafter simply referred to as the vehicle environment condition). Identify the type of feature to be A method of specifying a specific feature type based on vehicle environmental conditions will be described with reference to FIG.

  As shown in FIG. 2, when the weather is fine as the vehicle environment condition, the feature identifying unit 74 identifies a distance tag, a road sign, and a road marking as the type of the feature to be recognized. In addition, when the weather is rainy as the vehicle environmental condition, it is difficult to accurately recognize the road markings because the road is wet. Therefore, when the weather is rainy, the feature specifying unit 74 specifies a guide sign and a road sign existing in the sky as the type of the feature to be recognized. In addition, when the weather is snow as the vehicle environment condition, since the snow is accumulated on the road, it is difficult to accurately recognize the road marking as in the case of rain. Therefore, when the weather is snow, the feature specifying unit 74 specifies a guide sign and a road sign existing in the sky as the type of a feature to be recognized. In addition, when the weather is fog as a vehicle environment condition, it becomes difficult to recognize features other than the features present in the vicinity of the host vehicle. Therefore, when the weather is fog, the feature identifying unit 74 identifies a road marking existing in the vicinity of the host vehicle as the type of the feature to be recognized.

  When the time is daytime as the vehicle environment condition, the feature specifying unit 74 specifies a road marking, a distance card, and a road sign as types of features to be recognized. Moreover, when time is night as vehicle environmental conditions, it becomes difficult to recognize features other than the feature which is light-emitting. Therefore, in the case of night, the feature specifying unit 74 specifies an emergency call emitting light, a light emitting guide sign, and a light emitting traffic light as the type of the feature to be recognized.

  When the road surface condition is a bad road as the vehicle environmental condition, it becomes difficult to accurately recognize the road marking. Therefore, when the road surface state is a bad road, the feature identification unit 74 identifies a road sign as the type of feature to be recognized.

  When the traveling state is high vehicle speed traveling as the vehicle environment condition, the feature identifying unit 74 identifies a guidance sign and an emergency call as the type of the feature to be recognized.

  When the traveling condition is traffic congestion as a vehicle environment condition, it may be difficult to recognize features ahead of the vehicle depending on the road conditions ahead. For example, there may be a case where the camera 10 can not capture an information sign or a road sign present in the front because a truck is present immediately in front of the host vehicle. Therefore, when the traveling road is congested, the traveling environment judgment unit 72 specifies a telegraph pole or a distance slip that is less susceptible to other vehicles ahead as the type of feature to be recognized.

  In addition, when there are a plurality of lanes (for example, 3 lanes) as the vehicle environment condition and the vehicle is traveling in the right lane, the feature identifying unit 74 determines the right side of the road as the type of features to be recognized. Identify the types of features present in. When the host vehicle is traveling in the left lane, the traveling environment determination unit 72 specifies the type of feature present on the left side of the road as the type of feature to be recognized. In addition, when the host vehicle travels in the central lane, the traveling environment determination unit 72 specifies the type of feature existing in the sky as the type of feature to be recognized.

  The type of feature may be specified by combining vehicle environmental conditions such as weather, time, road surface condition, traveling condition and the like.

  As described above, the feature identifying unit 74 identifies the type of the feature to be recognized according to the vehicle environment condition, and outputs the identified feature (hereinafter, simply referred to as a specific feature) to the camera control unit 75.

  The camera control unit 75 controls the angle of the camera 10 so that the specific feature appears in the imaging range of the camera 10.

  The feature recognition unit 76 (feature recognition unit) performs predetermined image processing (such as pattern matching) on an image captured by the camera 10 controlled by the camera control unit 75 to recognize a specific feature. The feature recognition unit 76 outputs the recognized specific feature to the positional relationship calculation unit 77.

  The positional relationship calculation unit 77 uses the pixel information of the specific feature recognized by the feature recognition unit 76 to calculate the distance and direction (positional relationship) between the specific feature and the vehicle. Then, the positional relationship calculation unit 77 outputs the calculated distance and direction to the vehicle position correction unit 78. A radar sensor (not shown) may be installed in the vehicle, and the positional relationship calculation unit 77 may calculate the distance and direction between the specific feature and the vehicle using a reflected wave from the specific feature. .

  The host vehicle position correction unit 78 (host vehicle position correction means) corrects the current position of the host vehicle using the distance and direction between the specific feature and the host vehicle acquired from the positional relationship calculation unit 77. Then, the vehicle position correction unit 78 causes the display 80 to reflect the corrected current position of the vehicle.

  The controller 70 is a computer including, for example, a CPU, a ROM, a RAM, a data bus connecting them, and an input / output interface, and the CPU performs predetermined processing in accordance with a program stored in the ROM. The programs stored in the ROM include an image processing program.

  Next, with reference to FIGS. 3A and 3B, an example of the feature specifying method performed by the feature specifying unit 74 will be described.

  As shown in FIG. 3A, when the vehicle is traveling on a highway where snow is piled, road markings are excluded from the types of features to be recognized because they are invisible in snow. Therefore, the feature specifying unit 74 specifies the road mark M1, the guide mark M2, and the guide mark M3 existing in the sky as the type of the feature to be recognized. As described above, even in a traveling environment in which there are almost no intersections, as in a freeway, the vehicle position determination device 1 can correct the current position of the vehicle by using these specific features. In addition, since the task of detecting each feature from the image becomes unnecessary by specifying the type of the feature to be recognized, the feature recognition unit 76 can efficiently recognize the specific feature. This reduces the system load involved in the vehicle position correction. Also, the feature identifying unit 74 can identify one feature that the feature recognizing unit 76 can easily recognize from among the three features surrounded by the one-point chain point in FIG. 3A. In the example shown to Fig.3 (a), since the own vehicle is drive | working at high speed, it becomes easy to recognize as a large sized feature. Therefore, as shown in FIG. 3B, the feature identification unit 74 can identify the guide mark M2 as a feature to be recognized. In this case, the feature recognition unit 76 may recognize only the guide mark M2 from the image, thereby further reducing the system load involved in the vehicle position correction.

  Next, another example of the feature identifying method performed by the feature identifying unit 74 will be described with reference to FIGS. 4 (a) and 4 (b).

  As shown in FIG. 4A, in the case of a congested general road, road markings are excluded from the types of features to be recognized because they can not be seen behind other vehicles. Therefore, the feature identifying unit 74 identifies the type of feature whose recognition target is the traffic signal M4, the road sign M5, and the telephone pole M6 existing in the sky. By specifying the type of feature to be recognized in this manner, the operation of detecting features one by one from the image becomes unnecessary. This reduces the system load involved in the vehicle position correction. Also, the feature identifying unit 74 can identify one feature that the feature recognizing unit 76 can easily recognize from among the three features surrounded by the one-point chain point in FIG. 4A. In the example shown in FIG. 4A, it can be said that the traffic light M4 which is characterized by its shape and emits light can be easily identified. Therefore, as shown in FIG. 4B, the feature identifying unit 74 can identify the signal M4 as a feature to be recognized. In this case, the feature recognition unit 76 may recognize only the traffic light M4 from the image, thereby further reducing the system load involved in the vehicle position correction.

  Next, an operation example of the vehicle position determination device 1 will be described with reference to the flowchart of FIG. This flowchart starts when the ignition switch is turned on.

  In step S101, the traveling environment determining unit 72 uses the information acquired from the information acquiring unit 71, the camera 10, the GPS receiver 20, and the vehicle speed sensor 30, and the weather, day and night, road surface condition, forward road condition, traveling place, traffic jam Determine the vehicle environment conditions such as the condition.

  In step S102, the vehicle state determination unit 73 uses the information acquired from the camera 10, the GPS receiver 20, and the vehicle speed sensor 30 to determine the vehicle environment conditions such as the vehicle speed of the vehicle and the traveling lane in which the vehicle is traveling. to decide.

  In step S103, the feature identifying unit 74 is based on vehicle environment conditions such as weather, day and night, road surface condition, road condition ahead, traveling place, congestion condition, vehicle speed of own vehicle, and traveling lane where own vehicle is traveling. To identify the type of feature to be recognized.

  In step S104, the camera control unit 75 controls the angle of the camera 10 so that the specific feature appears in the imaging range of the camera 10.

  In step S105, the feature recognition unit 76 performs predetermined image processing on the image captured by the camera 10 to recognize a specific feature.

  In step S106, the positional relationship calculation unit 77 calculates the distance and direction between the specific feature and the vehicle.

  In step S107, the vehicle position correction unit 78 corrects the current position of the vehicle using the distance and direction between the specific feature and the vehicle, and reflects the corrected current position of the vehicle on the display 80.

  As described above, according to the own vehicle position determination device 1 according to the present embodiment, the following effects can be obtained.

  The vehicle position determination device 1 specifies in advance the type of feature to be recognized based on the vehicle environmental conditions, and corrects the current position of the vehicle using the specific feature. Thereby, the own vehicle position determination device 1 can correct the current position of the own vehicle in various traveling environments, including a traveling environment in which there are few intersections as in a freeway. Further, since the vehicle position determination device 1 can correct the current position of the vehicle using various features existing around the road, the frequency of correction increases. As a result, the vehicle position determination device 1 can maintain the current position with high accuracy. In addition, the vehicle position determination device 1 captures and recognizes a specific feature with the camera 10. As a result, there is no need to detect a feature one by one from the image, so that the vehicle position determination apparatus can efficiently recognize the specific feature and can reduce the system load involved in the vehicle position correction.

  In addition, the host vehicle position determination device 1 specifies in advance the type of feature to be used for host vehicle position correction based on the vehicle environment conditions related to the vehicle speed of the host vehicle and the traveling state such as the traveling lane where the host vehicle is traveling Do. As a result, the vehicle position determination device 1 does not need to detect the features one by one from the image, and can efficiently recognize the specific features, and correct the current position of the vehicle accurately. it can. In addition, the own vehicle position determination device 1 can specify one feature that can be easily recognized from among various features based on the vehicle environment condition related to the traveling state. As a result, the vehicle position determination device 1 need only recognize one specific feature from the image, and the system load related to the vehicle position correction can be further reduced.

  In addition, the vehicle position determination device 1 uses the vehicle position correction based on the vehicle environment conditions related to the environment around the vehicle, such as weather, day and night, road surface condition, road condition ahead, traveling place, traffic condition. Identify the type of feature in advance. As a result, the vehicle position determination device 1 does not need to detect the features one by one from the image, and can efficiently recognize the specific features, and correct the current position of the vehicle accurately. it can. In addition, the host vehicle position determination device 1 can specify one feature that is easy to recognize from various features based on the vehicle environment condition related to the environment around the host vehicle. As a result, the vehicle position determination device 1 need only recognize one specific feature from the image, and the system load related to the vehicle position correction can be further reduced.

  While the embodiments of the present invention have been described above, it should not be understood that the statements and drawings that form a part of this disclosure limit the present invention. Various alternative embodiments, examples and operation techniques will be apparent to those skilled in the art from this disclosure.

  For example, although weather information is acquired using telematics in the present embodiment, the weather may be determined using a rain sensor or an illuminance sensor. In addition, it may be detected whether the wiper is in operation and it may be determined whether it is raining. Further, it may be determined whether or not the road surface is frozen using a slip sensor capable of measuring the slip rate. Also, depending on the position of the sun, it may be backlit to the camera 10, so the features present in the sky susceptible to the influence of sunlight become shadows and appear dark, and the feature recognition unit 76 recognizes features It may not be possible. Therefore, when the position of the sun is backlit with respect to the camera 10, a road marking present on the ground that is not easily affected by sunlight may be specified as the type of feature to be recognized.

10 Camera 20 GPS receiver 30 Vehicle speed sensor 40 Map database 50 Communication I / F
70 controller 71 information acquisition unit 72 travel environment determination unit 73 vehicle state determination unit 74 feature identification unit 75 camera control unit 76 feature recognition unit 77 position relationship calculation unit 78 vehicle position correction unit 80 display

Claims (3)

A map database that stores the locations of features that exist around the road,
Vehicle position detection means for detecting the current position of the vehicle;
Imaging means for imaging the surroundings of the host vehicle;
A traveling environment judging means for judging whether or not the surroundings of the host vehicle are congested;
If the ambient of the vehicle is determined to be congested by the driving environment determination means, and the feature identifying unit for specific as the type of the feature that the feature existing in the sky and recognized,
A feature recognition unit that recognizes a feature identified by the feature identification unit from an image captured by the imaging unit;
Vehicle position determination means characterized by comprising: vehicle position correction means for correcting the current position of the vehicle using the position of the feature recognized by the feature recognition means and the positional relationship between the vehicle and the vehicle apparatus. The feature identifying unit, the vehicle position determination apparatus according to claim 1, characterized in that to identify the type of feature to be the recognition target, based on the running state before Symbol vehicle. Detect the current position of the vehicle,
Taking an image of the surroundings of the vehicle
It is determined whether or not there is traffic congestion around the vehicle.
When it is determined that the area around the host vehicle is congested , a feature existing in the sky is specified as a type of feature to be recognized from among features whose position is recorded in the map database,
Recognize features identified from the captured image,
A vehicle position determination method comprising: correcting a current position of the vehicle using the recognized positional relationship between the feature and the vehicle.

Images