JP2013072793A - Stop line detection system, stop line detection device, stop line detection method and computer program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a stop line detection system, a stop line detection device, a stop line detection method and a computer program, enabling an appropriate detection of a stop line formed on a road surface.SOLUTION: In a stop line detection system, when a feature serving as a candidate of a stop line (stop line candidate) is detected using a high accuracy location system in which a stop line is set as a recognition object, if it is determined that the stop line candidate is configured with a plurality of line segments having a form smaller than a prescribed length with respect to a road width direction, that each distance from a vehicle to the plurality of line segments is equidistance, and that a length between outside end points of respective two line segments positioned at both end points with respect to the road width direction in the plurality of line segments is a prescribed length or longer, the stop line candidate is detected as a stop line.

Description

  The present invention relates to a stop line detection system, a stop line detection device, a stop line detection method, and a computer program that detect a road marking of a stop line.

  2. Description of the Related Art In recent years, a navigation device is often mounted on a vehicle that provides vehicle travel guidance so that a driver can easily arrive at a desired destination. Here, the navigation device detects the current position of the vehicle by a GPS receiver or the like, acquires map data corresponding to the current position through a recording medium such as a DVD-ROM or HDD or a network, and displays it on a liquid crystal monitor. It is a device that can do. Further, such a navigation device has a route search function for searching for an optimum route from the departure place to the destination when a desired destination is input. The guidance route set based on the search result is displayed on the display screen, and when approaching a branch point (hereinafter referred to as a guidance branch point) for guidance such as turning left or right, a voice or display screen is displayed. By performing the guidance used, the user is surely guided to a desired destination. In recent years, some cellular phones, PDAs (Personal Digital Assistants), personal computers, and the like have functions similar to those of the navigation device. Furthermore, it is also possible to perform the above guidance for pedestrians and two-wheeled vehicles as well as vehicles.

  Here, when performing guidance such as turning left or right at the guidance branch point, it is important to perform guidance at an appropriate timing. In order to perform the guidance at an appropriate timing, it is necessary to accurately detect the current position of the vehicle or the like. Here, as one of the methods for accurately detecting the position of the vehicle or the like, a map information DB that detects white lines and road surface paint captured from the camera behind the vehicle by image recognition, and further stores the white lines and road surface paint in advance. A technique for detecting a detailed current position of a vehicle by checking is known.

  In the vehicle position detection method based on the image recognition, it is important to appropriately select a white line or road surface paint to be recognized. Here, since the road marking of the stop line is almost installed at a certain branch point of the traffic light, it can be recognized at regular intervals regardless of the area where the vehicle travels. It is suitable for being a recognition target in the position detection method. However, since the stop line is arranged with respect to the width direction of the road, the paint easily wears when the vehicle passes over the stop line, and the stop line that does not have the original shape with the passage of time ( For example, there are many stop lines or the like that are divided into a plurality of line segments at a point where a tire passes. As a result, it has been difficult to accurately identify whether the detected object is a stop line. Therefore, for example, in Japanese Patent Application Laid-Open No. 2006-33158, when a part of the stop line image is missing in the captured image obtained by capturing the stop line, the image loss is based on the construction history, the average vehicle speed, and the road type. And a technique for performing stop line recognition processing using the corrected image.

Japanese Patent Laying-Open No. 2006-33158 (pages 11 to 13, FIGS. 7 and 8)

  Here, in the technique of the above-mentioned Patent Document 1, the extent to which the stop line is rubbed (that is, the size of the missing portion) is estimated based on the construction history, the average vehicle speed, and the road type, and the image loss is determined based on the estimation result. Correct it. However, the estimated size of the missing part and the actual size of the missing part do not always match. Therefore, for example, when the actual size of the missing portion is larger than the estimated size of the missing portion, the stop line may not be detected properly even if the image is corrected.

  The present invention has been made to solve the above-described conventional problems, and even a stop line divided into a plurality of line segments due to paint wear or the like can be appropriately detected as a stop line. A stop line detection system, a stop line detection device, a stop line detection method, and a computer program are provided.

In order to achieve the object, the stop line detection system (1) according to claim 1 of the present application obtains detection results obtained by detecting features of the stop line candidates (101 to 104) existing around the moving body (81). A feature detection result acquisition means (13) for performing the operation, and the stop line candidate is composed of a plurality of line segments having a shape less than a predetermined length with respect to the road width direction. Arrangement determining means (13) for determining whether or not the distance between the two line segments located at both ends of the plurality of line segments is equal to or greater than the predetermined length. ) And the arrangement determining means, the stop line candidate is configured from the plurality of line segments having a shape less than a predetermined length in the road width direction, and each distance from the moving body to the plurality of line segments is Equal distance and within the plurality of line segments in the road width direction Stop line specifying means (13) for specifying the stop line candidate as a stop line when it is determined that the length between the outer ends of the two line segments located at both ends is equal to or greater than the predetermined length; It is characterized by having.
The “moving body” includes a pedestrian and a two-wheeled vehicle in addition to the vehicle.
The “stop line candidate” is a feature that may be a stop line, and the feature corresponds to an object whose position or angle is fixed on or near the road. And road signs (including road markings).
The “equal distance” is not limited to the case where the distances are completely the same distance, but includes the case where the difference between the distances is within a certain error range (for example, within 15 cm).

  Further, the stop line detection system (1) according to claim 2 is the stop line detection system according to claim 1, wherein the feature detection result acquisition means (13) is installed in the moving body (81). Based on the image picked up by the picked-up image pickup means (19), a detection result obtained by detecting the stop line candidates (101 to 104) formed on the road on which the moving body moves is obtained.

  The stop line detection system (1) according to claim 3 is the stop line detection system according to claim 1 or 2, wherein the feature detection result acquisition means (13) is a predetermined branch point. A detection result obtained by detecting the features of the stop line candidates (101 to 104) at a predetermined interval from when the moving body (81) is positioned before the distance until the moving body passes through the branch point. It is characterized by acquiring.

  A stop line detection system (1) according to claim 4 is the stop line detection system according to any one of claims 1 to 3, wherein the stop line candidates (101 to 104) are arranged at predetermined intervals. Arrangement interval determining means (13) for determining whether or not the plurality of arranged line segments are configured, and the stop line specifying means (13) is configured such that the stop line candidate is predetermined by the arrangement interval determining means. When it is determined that the plurality of line segments are arranged at intervals, the stop line candidate is identified as a stop line.

  A stop line detection system (1) according to claim 5 is the stop line detection system according to any one of claims 1 to 4, wherein the stop line detection unit (13) specifies the stop line detection system (1). On the basis of the feature information acquired by the feature information acquisition means (13) that acquires feature information in which the stop line and the position information of the stop line are associated, and the feature information acquisition means, And position detecting means (13) for detecting the position of the moving body (81).

  Moreover, the stop line detection apparatus (1) according to claim 6 acquires a feature detection result for acquiring a detection result of detecting features of the stop line candidates (101 to 104) existing around the moving body (81). The means (13) and the stop line candidate are composed of a plurality of line segments having a shape less than a predetermined length in the road width direction, and each distance from the moving body to the plurality of line segments is an equal distance. And the arrangement | positioning determination means (13) which determines whether the length between the outer side edge parts of two line segments located in both ends among the said some line segments is more than the said predetermined length, The said arrangement | positioning determination The stop line candidate is composed of the plurality of line segments having a shape less than a predetermined length in the road width direction by means, and each distance from the moving body to the plurality of line segments is equal, and Two line segments located at both ends in the road width direction among the plurality of line segments When the length between the outer end unit determines that the not less than a predetermined length, and having a, a stop line specifying means (13) for identifying the stop line candidate and the stop line.

  The stop line detection method according to claim 7 is a feature detection result acquisition step of acquiring a detection result of detecting features of stop line candidates (101 to 104) existing around the mobile body (81), The stop line candidate is composed of a plurality of line segments having a shape less than a predetermined length in the road width direction, each distance from the moving body to the plurality of line segments is equal, and the plurality of lines The stop line candidate is determined by the placement determination step for determining whether or not the length between the outer end portions of the two line segments located at both ends within the minute is equal to or greater than the predetermined length, and the placement determination step. It is composed of the plurality of line segments having a shape less than a predetermined length with respect to the width direction, each distance from the moving body to the plurality of line segments is equal, and a road within the plurality of line segments Outer end of two line segments located at both ends in the width direction If the length of is determined to the be a predetermined length or more, and having a a stop line specifying step of specifying the stop line of the stop line candidate.

  Furthermore, the computer program according to claim 8 has a feature detection result acquisition function for acquiring a detection result of detecting features of the stop line candidates (101 to 104) existing around the moving body (81) in the computer. , The stop line candidate is composed of a plurality of line segments having a shape less than a predetermined length in the road width direction, each distance from the moving body to the plurality of line segments is equal, and the plurality of the plurality of line segments The stop line candidate is determined by an arrangement determination function that determines whether or not the length between the outer ends of two line segments located at both ends of the line segment is equal to or greater than the predetermined length, and the arrangement determination function. It is composed of the plurality of line segments having a shape less than a predetermined length with respect to the road width direction, each distance from the moving body to the plurality of line segments is equal, and within the plurality of line segments Two lines located at both ends of the road width direction Of if the length between the outer end unit determines that the at least a predetermined length, characterized in that to execute a stop line specifying function of specifying the stop line of the stop line candidate.

  According to the stop line detection system according to claim 1 having the above-described configuration, when a stop line candidate divided into a plurality of line segments satisfies a predetermined condition, the stop line candidate is detected as a stop line. Even a stop line divided into a plurality of line segments due to paint wear or the like can be appropriately detected as a stop line. In addition, it is possible to prevent a feature other than the stop line from being erroneously detected as a stop line.

  Further, according to the stop line detection system according to claim 2, since the stop line candidate is detected based on the image picked up by the image pickup means installed on the moving body, the image pickup means used in the existing system is diverted. Thus, it is possible to detect stop line candidates around the moving body. As a result, the system can be realized without providing a new means or system for detecting stop line candidates.

  Further, according to the stop line detection system according to claim 3, since the section for detecting the stop line candidate is limited to the section where the stop line may be arranged, the processing burden related to the detection of the stop line candidate is reduced. It becomes possible to reduce.

  According to the stop line detection system of claim 4, when the stop line candidate is composed of a plurality of line segments arranged at a predetermined interval, the stop line candidate is detected as a stop line. Based on the arrangement interval, it is possible to accurately determine whether the stop line candidate is a stop line divided into a plurality of line segments due to paint wear or the like.

  According to the stop line detection system according to claim 5, when the stop line candidate is identified as the stop line, the feature information in which the stop line is associated with the position information of the stop line is acquired. Since the position of the moving body is detected based on the acquired feature information, the position of the moving body is accurately detected based on the detection result by detecting the stop line around the moving body. Is possible. As a result, it is possible to execute guidance and control for the moving body at an appropriate timing.

  Further, according to the stop line detection device of the sixth aspect, when the stop line candidate divided into a plurality of line segments satisfies the predetermined condition, the stop line candidate is detected as a stop line. Even a stop line divided into a plurality of line segments due to wear or the like can be appropriately detected as a stop line. In addition, it is possible to prevent a feature other than the stop line from being erroneously detected as a stop line.

  According to the stop line detection method of claim 7, when the stop line candidate divided into a plurality of line segments satisfies a predetermined condition, the stop line candidate is detected as a stop line. Even a stop line divided into a plurality of line segments due to wear or the like can be appropriately detected as a stop line. In addition, it is possible to prevent a feature other than the stop line from being erroneously detected as a stop line.

  Furthermore, according to the computer program according to claim 8, when a stop line candidate divided into a plurality of line segments satisfies a predetermined condition, the stop line candidate is detected as a stop line. Thus, even a stop line divided into a plurality of line segments can be appropriately detected as a stop line. In addition, it is possible to prevent a feature other than the stop line from being erroneously detected as a stop line.

It is the block diagram which showed the navigation apparatus which concerns on this embodiment. It is the figure which showed an example of the traffic signal and stop line which are arrange | positioned at a branch point. It is the figure which showed an example of the guidance phrase condition table. It is a figure explaining the guidance start point prescribed | regulated by the guidance phrase condition table. It is a flowchart of a branch point guidance processing program according to the present embodiment. It is the figure which showed an example of the feature table. It is a flowchart of the vehicle position detection processing program which concerns on this embodiment. It is the side view which showed the vehicle which images a stop line candidate. It is the figure which showed an example of the stop line candidate. It is the figure which showed the positional relationship of a stop line and a pedestrian crossing.

  Hereinafter, a stop line detection system and a stop line detection apparatus according to the present invention will be described in detail with reference to the drawings based on an embodiment in which the navigation apparatus is embodied. First, a schematic configuration of the navigation device 1 according to the present embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing a navigation device 1 according to this embodiment.

  As shown in FIG. 1, the navigation device 1 according to the present embodiment includes a current position detection unit 11 that detects a current position of a vehicle on which the navigation device 1 is mounted, a data recording unit 12 that records various data, A navigation ECU 13 that performs various arithmetic processes based on the input information, an operation unit 14 that receives operations from the user, and a liquid crystal display 15 that displays a map around the vehicle and facility information related to the facility to the user. Communicating between a speaker 16 that outputs voice guidance regarding route guidance, a DVD drive 17 that reads a DVD as a storage medium, and an information center such as a probe center or a VICS (registered trademark: Vehicle Information and Communication System) center And a communication module 18 for performing. The navigation device 1 is connected to a back camera 19 for detecting features on the road, which will be described later.

Below, each component which comprises the navigation apparatus 1 is demonstrated in order.
The current position detection unit 11 includes a GPS 21, a vehicle speed sensor 22, a steering sensor 23, a gyro sensor 24, and the like, and can detect the current vehicle position, direction, vehicle traveling speed, current time, and the like. . Here, in particular, the vehicle speed sensor 22 is a sensor for detecting a moving distance and a vehicle speed of the vehicle, generates a pulse according to the rotation of the driving wheel of the vehicle, and outputs a pulse signal to the navigation ECU 13. And navigation ECU13 calculates the rotational speed and moving distance of a driving wheel by counting the generated pulse. Note that the navigation device 1 does not have to include all of the above five types of sensors, and the navigation device 1 may include only one or more of these types of sensors.

  Further, the data recording unit 12 reads an external storage device and a hard disk (not shown) as a recording medium, a map information DB 31 recorded on the hard disk, a guidance phrase condition table 32, a feature table 33, a predetermined program, and the like. A recording head (not shown) as a driver for writing predetermined data to the hard disk is also provided. The data recording unit 12 may be configured by a memory card, an optical disk such as a CD or a DVD, instead of the hard disk.

  Here, the map information DB 31 includes, for example, link data 34 relating to roads (links), node data 35 relating to node points, branch point data 36 relating to each branch point, and features on the road surface, particularly stop lines. The storage means stores feature data 37 relating to road markings, facility data relating to facilities, map display data for displaying a map, search data for searching for a route, search data for searching for a point, and the like.

  Here, as the link data 34, for example, a link ID for identifying the link, end node information for specifying a node located at the end of the link, road type of the road constituting the link, road width, lane Numbers etc. are stored. As the node data 35, a node ID for identifying the node, position coordinates of the node, connection destination node information for specifying a connection destination node to which the node is connected via a link, and the like are stored. Further, as the branch point data 36, relevant node information for specifying a node forming the branch point (intersection), connection link information for specifying a link connected to the branch point (hereinafter referred to as a connection link), a branch point The traffic signal information 38 and the like related to traffic signals installed in the vicinity of is stored.

  In addition, the traffic signal information 38 is the direction in which the traffic light is installed (that is, the direction in which the traffic light is facing) of the traffic signal installed around each branch point (intersection) in the whole country. ), The number of lamps (3-lamp type, 2-lamp type, 1-lamp type, etc.), the position coordinates where the traffic light is installed (hereinafter referred to as installation coordinates), and the like are stored. Furthermore, when a plurality of traffic lights are installed at one branch point, the installation direction, installation coordinates, etc. are stored for each of the traffic lights. For example, as shown in FIG. 2, eight traffic lights 52 to 59 are installed at a branching point 51 where two one-lane roads intersect. Accordingly, as the traffic signal information 38 of the branch point 51, the installation direction, installation coordinates, and the like of the traffic signals 52 to 59 are stored.

The traffic signal information 38 is the traffic signal on the most exit side for each exit direction from the branch point (that is, the traffic signal that can be visually recognized at the end of the branch point when the vehicle passes through the branch point). It is good also as a structure which memorize | stores only the information regarding a side signal apparatus. For example, at the branch point 51 shown in FIG. 2, information on the traffic signal 53 that is the exit side traffic signal is stored for the exit direction from the bottom to the top of the diagram, and the exit side is displayed for the exit direction from the top to the bottom of the diagram. Stores information on the traffic light 55 that is a traffic light, stores information on the traffic light 57 that is a traffic light on the exit side with respect to the exit direction from the left to the right in the figure, and exits on the exit direction from the right to the left in the figure. Information on the traffic signal 59 that is a traffic signal is stored. That is, it is good also as a structure which memorize | stores only the installation direction and installation coordinate of the traffic lights 53, 55, 57, 59 among the 8 traffic lights 52-59. In addition, for each approach direction from a branch point, as a configuration for storing only information related to a traffic light that is closest to the entry side (that is, the departure side) (that is, a traffic light that can be visually recognized by the vehicle first, hereinafter referred to as an entry side traffic signal). Also good.
And navigation ECU13 is based on each data memorize | stored in map information DB31 as mentioned later, and the branch existing in the departure place side of a guidance route from this guidance branch point ahead of the advancing direction of a vehicle. A point (hereinafter referred to as a front branch point) is specified. Moreover, the traffic signal information 38 of the traffic lights around the guidance branch point and the front branch point and the feature data 37 of the stop line are acquired. Then, a feature table 33 (see FIG. 6), which will be described later, is created based on the information on the specified guidance branch point and near branch point, the acquired traffic signal information 38, and the feature data 37. The guidance branch point is a branch point to which guidance such as a right / left turn instruction is given when the navigation device 1 performs traveling guidance according to the guidance route set in the navigation device 1.

On the other hand, the feature data 37 stores information related to the road marking of the stop line, among the features formed on the road. Specifically, the identification ID, the coordinate data for specifying the position of the stop line on the map, and the branch point ID for identifying the branch point where the stop line is installed are stored. Note that the coordinate data may be specified not by the absolute position but by the relative position of the branch point where the stop line is installed with respect to the node point. For example, as shown in FIG. 2, stop lines 60 to 63 are installed at four points at a branch point 51 where roads of two lanes on one side intersect. Therefore, as the feature data 37, various information regarding the stop lines 60 to 63 is stored.
Then, the navigation ECU 13 detects a stop line candidate formed on the road surface from the captured image captured by the back camera 19, and associates the detected stop line candidate with the detected stop line when the detected stop line candidate is identified as a stop line. Based on the obtained coordinate data, it becomes possible to detect the detailed current position of the vehicle (or correct the already detected position). And guidance and vehicle control are performed based on the detected current position.

  In addition, the guidance phrase condition table 32 is a table that stores the guidance branch point guidance, the contents of the spoken phrase, the conditions for starting the guidance utterance, and the like. Hereinafter, the guidance phrase condition table 32 will be described in more detail with specific examples. FIG. 3 shows an example of the guidance phrase condition table 32. FIG. 4 is a diagram for explaining a guidance start point defined in the guidance phrase condition table 32 shown in FIG. In FIG. 3, the number of traffic lights located between the current position of the vehicle and the guidance branch point is shown in the case where a traffic light is installed at the guidance branch point among the guidance performed at the guidance branch point. The guidance for specifying the guidance branch point will be described. In the following description of the embodiment, the guide branch point and the front branch point are both branch points where a traffic light is installed, and the branch on the one side before the guide branch point (the departure side along the guide route). The point is referred to as the first front branch point, the branch point on the further one side of the first front branch point (the departure side along the guide route) is referred to as the second front branch point, and further to the second front branch point. A branch point on the front side (the departure side along the guide route) will be referred to as a third front branch point.

As shown in Fig. 3, the guidance for specifying the guidance branch point using the number of traffic lights located between the current position of the vehicle and the guidance branch point is “the third signal is in the left (right) direction. "And the second signal is in the left (right) direction" and "the next signal is in the left (right) direction". Furthermore, a guidance start condition, which is a condition for starting a guidance utterance, is associated with each guidance phrase.
For example, in the case of guiding “the second signal is in the left (right) direction”, the user can count two traffic lights including the guidance branch point before entering the guidance branch point. In the meantime, the guidance utterance needs to be started. Therefore, the guidance phrase “the second signal is in the left (right) direction” is guided on the condition that the vehicle has passed the guidance start point set for the exit side traffic light at the second front branch point. To start. In addition, the guidance start point set for the exit side traffic light at the second front branch point is a point (for example, 5 meters before) a predetermined distance before the exit side traffic signal at the second front branch point or a vehicle occupant (especially a driver). There is a point where the exit side traffic light at the second front branch point is switched from a state where it is visible to a state where it is not visible. For example, in the example shown in FIG. 4, a point A that is 5 meters before the exit side traffic signal 73 of the second front branch point 72 that is two ahead of the guide branch point 71 is a guidance start point, and the vehicle passes through the point A. At this point, guidance at the guidance branch point is started. As a result, the user who has received the guidance can count the branch points where two traffic lights, the first front branch point 74 and the guide branch point 71, are installed before entering the guidance branch point 71. It becomes possible to clearly specify that the “second signal” in the sentence is the approach side traffic signal 75 installed at the guidance branch point 71.
The number of traffic lights in the guidance phrase is preferably the number of traffic lights in the branch point unit. That is, when a plurality of traffic signals are provided at the same branch point on a large road or the like, it is desirable that the plurality of traffic signals be counted as one traffic signal. In that case, the number of traffic lights in the guidance phrase corresponds to the number of branch points where traffic lights are installed (that is, traffic signal intersections). However, even when counting is performed in units of branch points, it is desirable to count the number of traffic lights (for example, push button type traffic lights) installed outside the branch point. The same applies to the following description.

  Similarly, other guidance phrases are stored in the guidance phrase condition table 32. In addition to the left (right) direction, there are a right (left) diagonal direction, a right (left) front direction, and the like as the guidance direction of the guidance branch point. Each numerical value (5 m or the like) for specifying the guidance start condition can be changed as appropriate.

  The feature table 33 is created by the navigation ECU 13 when the vehicle reaches within a predetermined distance (for example, within 1.47 km) with respect to the guidance branch point as will be described later. The feature table 33 is a table that specifies the relative positional relationship between the stop line at the guide branch point and the front branch point and the exit side traffic signal with reference to the guide branch point in the forward direction of the vehicle. Yes (see FIG. 6). Details of the feature table 33 will be described later.

  On the other hand, the navigation ECU (Electronic Control Unit) 13 is an electronic control unit that controls the entire navigation device 1. The CPU 41 as an arithmetic device and a control device, and a working memory when the CPU 41 performs various arithmetic processes. In addition to the RAM 42 for storing route data when a route is searched, a control program, a branch point guidance processing program (see FIG. 5) described later, and a vehicle position detection processing program (FIG. 7). And the like, and an internal storage device such as a flash memory 44 for storing a program read from the ROM 43. The navigation ECU 13 constitutes various means as processing algorithms. For example, the feature detection result acquisition unit acquires a detection result of detecting a feature of a stop line candidate existing around the vehicle (moving body). The arrangement determining means includes a plurality of line segments in which the stop line candidate has a shape less than a predetermined length with respect to the road width direction, each distance from the vehicle to the plurality of line segments is equal, and the plurality of lines It is determined whether or not the length between the outer ends of two line segments located at both ends of the minute is equal to or greater than a predetermined length. The stop line specifying means is composed of a plurality of line segments in which the stop line candidate has a shape less than a predetermined length in the road width direction, and each distance from the vehicle to the plurality of line segments is equal, and a plurality of When it is determined that the length between the outer ends of two line segments located at both ends in the road width direction within the line segment is equal to or longer than a predetermined length, the stop line candidate is identified as a stop line. The arrangement interval determining means determines whether or not the stop line candidate is composed of a plurality of line segments arranged at a predetermined interval. The feature information acquisition unit acquires the feature information in which the stop line specified by the stop line specifying unit and the position information of the stop line are associated with each other. The position detection means detects the position of the vehicle based on the feature information acquired by the feature information acquisition means.

  The operation unit 14 is operated when inputting a departure point as a travel start point and a destination as a travel end point, and includes a plurality of operation switches (not shown) such as various keys and buttons. Then, the navigation ECU 13 performs control to execute various corresponding operations based on switch signals output by pressing the switches. The operation unit 14 can also be configured by a touch panel provided on the front surface of the liquid crystal display 15. Moreover, it can also be comprised with a microphone and a speech recognition apparatus.

  The liquid crystal display 15 includes a map image including a road, traffic information, operation guidance, operation menu, key guidance, guidance route from the departure point to the destination, guidance information along the guidance route, news, weather forecast, Time, mail, TV program, etc. are displayed. In particular, in the present embodiment, when the guidance branch point approaches within a predetermined distance (for example, 300 m) ahead of the traveling direction of the vehicle, an enlarged view near the guidance branch point and the traveling direction at the guidance branch point of the vehicle are displayed.

  The speaker 16 outputs voice guidance for guiding traveling along the guidance route based on an instruction from the navigation ECU 13 and traffic information guidance. In particular, in the present embodiment, when the guidance branch point is ahead of the traveling direction of the vehicle, a voice guidance indicating that the predetermined guidance start timing based on the guidance content (for example, “the second signal is to the left”) When outputting, the voice guidance at the guidance branch point is output at the timing of passing a predetermined distance before the exit side traffic light at the second branch point before.

  The DVD drive 17 is a drive that can read data recorded on a recording medium such as a DVD or a CD. Based on the read data, music and video are reproduced, the map information DB 31 is updated, and the like.

  The communication module 18 is a communication device for receiving traffic information composed of information such as traffic jam information, regulation information, and traffic accident information transmitted from a traffic information center, for example, a VICS center or a probe center. For example, a mobile phone or DCM is applicable.

  The back camera 19 uses a solid-state image sensor such as a CCD, for example, and is installed near the upper center of the license plate mounted on the rear side of the vehicle, and installed with the line-of-sight direction downward from the horizontal by a predetermined angle. Is done. Then, an image is taken of the rear of the vehicle that is opposite to the traveling direction of the vehicle during traveling. And the kind and position of the feature in the circumference | surroundings of a vehicle are detected by performing the image recognition process of a captured image. In particular, in this embodiment, a stop line or a road marking on a pedestrian crossing is a detection target. Further, even for a feature having no stop line shape, if the feature satisfies a predetermined condition, the feature is detected as a road marking of the stop line. Further, the detailed position of the vehicle is calculated based on the detected road marking of the stop line.

  Next, a branch point guidance processing program executed by the navigation ECU 13 in the navigation device 1 having the above configuration will be described with reference to FIG. FIG. 5 is a flowchart of the branch point guidance processing program according to this embodiment. Here, the branch point guidance processing program is a program that is repeatedly executed at a predetermined interval (for example, every detection cycle of the current position of the vehicle) after the vehicle ACC is turned on, and guides the guidance branch point on the guidance route. . The programs shown in the flowcharts of FIGS. 5 and 7 below are stored in the RAM 42 and the ROM 43 provided in the navigation device 1 and are executed by the CPU 41.

  First, in step (hereinafter abbreviated as S) 1 in the branch point guidance processing program, the CPU 41 determines whether route guidance based on the guidance route set in the navigation device 1 is being performed. Here, the guidance route is a recommended route from the departure point (for example, the current position of the host vehicle) to the destination selected by the user, and is set based on the result of the route search process. The route search process is performed by a known Dijkstra method or the like using link data 34, node data 35, traffic information acquired from the VICS center, and the like stored in the map information DB 31.

  And when it determines with the route guidance based on the guidance route set in the navigation apparatus 1 being performed (S1: YES), it transfers to S2. On the other hand, when it is determined that route guidance based on the guidance route set in the navigation device 1 is not performed (S1: NO), the branch point guidance processing program is terminated.

  In S <b> 2, the CPU 41 acquires the current position of the vehicle based on the detection result of the current position detection unit 11, the detection result of a vehicle position detection processing program (FIG. 7) described later, and dead reckoning navigation. A map matching process for specifying the current position of the vehicle on the map data is also performed. Here, the vehicle position detection processing program (FIG. 7) is a process for specifying the current position of the vehicle in detail using a high-accuracy location technology as will be described later. Here, the high-precision location technology is a feature that detects features such as white lines and road surface paint captured from the back camera 19 behind the vehicle by image recognition, and further stores features such as white lines and road surface paint in advance. This is a technology that makes it possible to detect a traveling lane and a highly accurate vehicle position by collating with the data 37. In particular, in the present embodiment, the vehicle position is detected by detecting a stop line provided at a branch point as a feature.

  Next, in S <b> 3, the CPU 41 obtains a guidance route (including a guidance branch point in the guidance route) set in the navigation device 1.

  Subsequently, in S4, the CPU 41 determines a guidance branch point within a predetermined distance (for example, within 1.47 km) ahead of the traveling direction of the vehicle based on the current position of the vehicle acquired in S2 and the guidance route acquired in S3. It is determined whether or not there is. Note that the guidance branch point is a branch point to which guidance such as a right / left turn instruction is given when the navigation device 1 guides traveling according to the guidance route set in the navigation device 1 as described above.

  If it is determined that there is a guidance branch point within a predetermined distance ahead of the traveling direction of the vehicle (S4: YES), the process proceeds to S5. On the other hand, when it is determined that there is no guidance branch point within a predetermined distance ahead of the traveling direction of the vehicle (S4: NO), the branch point guidance processing program is terminated.

  In S5, the CPU 41 determines whether or not guidance for a guidance branch point in front of the vehicle traveling direction has already been performed. In S5, it is determined whether or not voice guidance for instructing a right or left turn or the like at the guidance branch point among the guidance for the guidance branch point has been performed.

  And when it determines with guidance with respect to the guidance branch point ahead of the advancing direction of a vehicle having already been performed (S5: YES), the said branch point guidance process program is complete | finished. On the other hand, when it is determined that the guidance for the guidance branch point ahead of the traveling direction of the vehicle is not performed (S5: NO), the process proceeds to S6.

  In S6, the CPU 41 determines whether or not the feature table 33 for the guidance branch point located in front of the traveling direction of the vehicle has been created. Here, the feature table 33 is created in S7, which will be described later, and is based on the guide branch point ahead of the traveling direction of the vehicle, and the relative of the stop line and the exit side signal at the guide branch point and the front branch point. It is a table that specifies a specific positional relationship.

  And when it determines with the feature table 33 having been prepared with respect to the guidance branch point located ahead of the advancing direction of a vehicle (S6: YES), it transfers to S9. On the other hand, when it determines with the feature table 33 with respect to the guidance branch point located ahead of the advancing direction of a vehicle not being created (S6: NO), it transfers to S7.

  In S <b> 7, the CPU 41 acquires position information of each branch point from the map information DB 31 for the guide branch point located in front of the traveling direction of the vehicle and the front branch point located in front of the guide branch point. Further, information (position coordinates, number of lamps, etc.) related to the exit side traffic lights installed at the guidance branch point and the front branch point is acquired from the traffic signal information 38. Further, information (position coordinates, distance to the branch point, etc.) regarding the stop line (including the virtual stop line in addition to the actual stop line) arranged at the guidance branch point and the front branch point is acquired from the feature data 37. And the feature table 33 is created based on each acquired information. The front branch points to be created in the feature table 33 may be all front branch points from the current position of the vehicle to the guide branch point, or only a predetermined front branch point (for example, the first front branch point). To the third front branch point).

Here, FIG. 6 is a diagram showing an example of the feature table 33 created in S7. In the feature table 33 shown in FIG. 6, the guide branch point 82, the first front branch point 83, the second front branch point 84, and the third front side are based on the guide branch point 82 ahead of the traveling direction of the vehicle 81. The relative positional relationship between the exit side traffic lights 86 to 89 and the stop lines 90 to 93 at the branch point 85 is recorded.
For example, it is recorded that the exit side traffic signal 86 at the guidance branch point 82 is a three-lamp type and is installed at a position 10 m away from the guidance branch point 82 in the direction opposite to the departure side. In addition, the stop line 92 at the second front branch point 84 is a virtual stop line of “ID: 345”, and it is recorded that it is installed at a position 220 m away from the guide branch point 82 on the departure side. The The relative distance of the exit side traffic lights 86 to 89 from the guidance branch point 82 is calculated based on, for example, the position coordinates of the guidance branch point 82 and the position coordinates of the exit side traffic lights 86 to 89 acquired from the traffic signal information 38. Is done. The relative distances of the stop lines 90 to 93 from the guide branch points 82 are based on, for example, the position coordinates of the branch points 82 to 85 and the position data of the stop lines 90 to 93 acquired from the feature data 37. Calculated.

  Next, in S8, based on the feature table 33 created in S7, the CPU 41 determines the contents of the guidance phrase when performing guidance for the guidance branch point and the guidance start point for starting guidance for the guidance branch point. Set. For example, if the guidance route is a route that turns left at a guidance branch point ahead of the direction of travel of the vehicle, the guidance phrases are “3rd traffic light left”, “2nd traffic light left And “Next signal is to the left” are set. Further, for guidance that “the third signal is in the left direction”, a point a predetermined distance before the exit side traffic light at the third branch point before (for example, 5 m before) is set as the guidance start point. Similarly, for guidance that “the second signal is in the left direction”, a point a predetermined distance (for example, 5 m before) of the exit side traffic light of the second front branch point is set as the guidance start point. Similarly, for guidance that “the next signal is in the left direction”, a point a predetermined distance (for example, 5 m before) of the exit side traffic light at the first branch point is set as the guidance start point. In S8, the CPU 41 stores the set guidance phrase and guidance start point in the RAM 42 or the like. Thereafter, the process proceeds to S9.

  In S9, the CPU 41 determines whether or not the vehicle has reached the guidance start point based on the current position of the vehicle acquired in S2.

  And when it determines with the vehicle having reached the guidance start point (S9: YES), it transfers to S10. On the other hand, when it is determined that the vehicle has not reached the guidance start point (S9: NO), the branch point guidance processing program is terminated.

In S10, the CPU 41 performs guidance related to the guidance branch point using the guidance phrase corresponding to the reached guidance start point. Specifically, guidance for identifying the guidance branch point and guidance for identifying the exit direction of the vehicle at the guidance branch point (that is, guidance for identifying the exit road from which the vehicle exits the guidance branch point) are performed. For example, in this embodiment, the guidance phrases include “the third signal is to the left”, “the second signal is to the left”, and “the next signal is to the left”. The guidance start point is set corresponding to. For example, when the vehicle reaches the guidance start point set a predetermined distance before the exit side traffic light at the second branch point, the phrase “The second signal is in the left (right) direction” with the phrase 16 to output. Further, when the guidance branch point approaches within a predetermined distance (for example, 300 m) of the vehicle, an enlarged view near the guidance branch point and the traveling direction at the guidance branch point of the vehicle are displayed on the liquid crystal display 15.
As a result, it becomes possible for the user to accurately specify the guidance branch point and the road from which the vehicle exits from the guidance branch point.

  Next, a vehicle position detection processing program executed by the navigation ECU 13 in the navigation device 1 will be described with reference to FIG. FIG. 7 is a flowchart of the vehicle position detection processing program according to this embodiment. Here, the vehicle position detection processing program is repeatedly executed at predetermined intervals (for example, every detection cycle of the current position of the vehicle) after the ACC of the vehicle is turned ON, and detects the detailed current position of the vehicle by the high-precision location technology (or This is a program for correcting a position that has already been detected. Note that the vehicle position detection processing program may be executed only in a state where the guide branch point is located within a predetermined distance (for example, within 1.47 km) in front of the traveling direction of the vehicle.

  First, in S11, the CPU 41 determines whether or not there is a branch point within a predetermined distance (for example, within 100 m) in front of the traveling direction of the vehicle. Specifically, the determination is made based on the current position of the vehicle and the branch point data 36. The current position of the vehicle is detected based on the detection result of the current position detection unit 11 and dead reckoning navigation in addition to the vehicle position detection processing program, and is stored in the RAM 42 or the like. The stored information is updated every time a current position of a new vehicle is detected.

  If it is determined that there is a branch point within a predetermined distance ahead of the traveling direction of the vehicle (S11: YES), the process proceeds to S12. On the other hand, when it is determined that there is no branch point within a predetermined distance ahead in the traveling direction of the vehicle (S11: NO), the vehicle position detection processing program is terminated.

  In S12, the CPU 41 starts the feature recognition process at a predetermined interval in parallel with the vehicle position detection process program. Here, the feature recognition process is a feature formed on the road on which the vehicle travels by performing image processing (for example, binarization processing or pattern matching processing) on the image captured by the back camera 19. Is a process of recognizing (detecting). Further, information on the type of the feature recognized (detected) in the feature recognition process is acquired. In particular, in the present embodiment, a stop line or a pedestrian crossing that is a road marking around a branch point is a recognition (detection) target by the feature recognition processing.

  Next, in S13, the CPU 41 recognizes (detects) a feature that is a candidate for a stop line (hereinafter referred to as a stop line candidate) based on the detection result of the feature recognition process started in S12. judge. Here, the stop line candidate is a road marking that may be a stop line, and corresponds to, for example, a long strip-shaped white line arranged in the width direction of the road.

  And when it determines with having recognized (detected) the stop line candidate (S13: YES), it transfers to S14. On the other hand, when it is determined that the stop line candidate has not been recognized (detected) (S13: NO), the process proceeds to S21.

  In S14, the CPU 41 acquires the shape of the detected stop line candidate. Specifically, the calculation is based on the result of the image recognition process of the stop line candidate. Here, as shown in FIG. 8, the rear camera 19 is attached so that the optical axis L is directed downward from the horizontal by a predetermined angle θ (for example, 45 degrees) so that the rear side of the rear bumper 98 of the vehicle 81 can be imaged. The imaging range is fixed. Therefore, the shape and size of the subject 99 can be calculated from the position (specifically, the number of pixels) of the image data in the captured image captured by the back camera 19. Furthermore, a distance X from the vehicle 81 to the subject 99 (more specifically, a distance from the back camera 19 to the subject 99) can be calculated.

  Here, in general, the road marking of the stop line is composed of a long strip-shaped white line as shown in FIG. However, since the road marking of the stop line is arranged with respect to the width direction of the road, the paint easily wears when the vehicle passes over the stop line and does not have the original shape with the passage of time. There are many stop lines. For example, as shown in FIG. 9 (B), there is a stop line that is divided into a plurality of line segments with a location where the tire passes as a boundary. When the stop line shown in FIG. 9A is detected by the image recognition process, the feature 101 having the shape of one line segment arranged in the road width direction is recognized as a stop line candidate. On the other hand, when the stop line shown in FIG. 9B is detected by the image recognition process, a plurality of line-shaped features 102 to 104 arranged at predetermined intervals in the width direction of the road are stop line candidates. Recognized as

  In S14, for example, when the stop line shown in FIG. 9A is detected by image recognition processing, the length (width) of the road 101 in the road traveling direction in addition to the length W of the feature 101 in the road width direction. And brightness values are also acquired. On the other hand, when the stop line shown in FIG. 9B is detected by the image recognition processing, the road width direction lengths W1 to W3 of the features 102 to 104, the arrangement intervals H1 and H2 of the features 102 to 104, The length Wt between the outer ends of the two features 102 and 104 located at both ends in the road width direction among the features 102 to 104 and the distances X1 to X3 from the vehicle to the features 102 to 104 are respectively acquired. The

  Next, in S15, the CPU 41 determines that the length of the detected stop line candidate in the road width direction (W, W1 to W3 in the example shown in FIG. 9) is a predetermined length based on the shape of the stop line candidate acquired in S14. It is determined whether or not it is greater than or equal to. Here, the predetermined length serving as the determination criterion in S15 is generally the minimum length that can be taken by a stop line arranged on the road, and is, for example, 160 cm. Also, as shown in FIG. 9B, when a plurality of line segment-shaped features 102 to 104 are detected as stop line candidates, the determination process of S15 is performed on the features 102 to 104. Is done.

  And when it determines with the length of the detected stop line candidate of the road width direction being more than predetermined length (S15: YES), it transfers to S16. On the other hand, when it is determined that the detected length of the stop line candidate in the road width direction is less than the predetermined length (S15: NO), the process proceeds to S22.

  In S16, the CPU 41 determines whether or not other conditions for estimating a stop line candidate as a stop line are also satisfied. Specifically, the condition is that the length (width) of the stop line candidate in the road traveling direction is 30 cm or more and less than 45 cm, the luminance value is a predetermined value or more, and the like.

  And when it determines with satisfy | filling also other conditions for estimating a stop line candidate as a stop line (S16: YES), it transfers to S17. On the other hand, when it is determined that the other condition for estimating the stop line candidate as the stop line is not satisfied (S16: NO), the process proceeds to S20.

  In S17, the CPU 41 determines whether or not the pedestrian crossing has been recognized in the feature recognition process started in S12, and if the pedestrian crossing is recognized, the detected stop line candidate is within a predetermined separation distance on the vehicle traveling direction side. It is determined whether or not there is a pedestrian crossing (for example, within 5 m). Here, as shown in FIG. 10, when a pedestrian crossing 110 and a stop line 111 are generally provided at a branching point, respectively, at a position separated from the pedestrian crossing 110 by a predetermined distance M in the branching point exit direction. A stop line 111 is installed. The distance M differs depending on the area where the branch point exists, but is generally included in the range of 1 m to 5 m. Therefore, when there is a pedestrian crossing within a predetermined distance (upper limit value of the range (for example, within 5 m)) on the traveling direction side of the vehicle from the detected stop line candidate, the stop line candidate may be a stop line. Extremely high. On the other hand, as shown in FIG. 10, when the bicycle crossing band 112 is provided on the pedestrian crossing 110, it is arranged adjacent to the pedestrian crossing 110 as in the stop line 111, but in the direction opposite to the stop line 111 ( It is provided on the branch point side) from the pedestrian crossing 110. Therefore, when there is a pedestrian crossing within a predetermined distance (for example, within 5 m) on the traveling direction side of the vehicle from the detected stop line candidate, the possibility that the stop line candidate is a bicycle crossing band is extremely low.

  As described above, when it is determined that there is a pedestrian crossing recognized within a predetermined separation distance on the traveling direction side of the vehicle from the detected stop line candidate (S17: YES), the process proceeds to S18. On the other hand, when it is determined that the pedestrian crossing is not recognized in the feature recognition process or that there is no pedestrian crossing recognized within the predetermined separation distance on the vehicle traveling direction side from the detected stop line candidate (S17: NO) To S20.

  In S18, the CPU 41 specifies the detected stop line candidate as a stop line. Thereafter, the process proceeds to S19.

In S19, the CPU 41 detects the detailed current position of the vehicle based on the detected stop line (stop line candidate specified as the stop line). Specifically, the “distance from the detected stop line to the current position of the vehicle” is calculated based on the distance from the stop line to the vehicle when the stop line is detected, the travel distance of the vehicle since the stop line is detected, etc. To do. Then, the detailed current position of the vehicle is specified by the “distance from the detected stop line to the current position of the vehicle” and the feature table 33 (that is, the current position of the vehicle is detected). Note that the position coordinates of the vehicle can be calculated by using the feature data 37 that stores the detected position coordinates of the stop line. It is also possible to calculate the road distance from the vehicle to the guidance branch point in front of the vehicle, the stop line, and the exit side traffic signal using the feature table 33.
In S19, the CPU 41 updates the current position of the vehicle stored in the RAM 42 based on the detected position of the vehicle. As a result, the current position of the vehicle is corrected based on the detailed current position of the vehicle detected (corrected) based on the detection result obtained by detecting the stop line with the back camera 19. Therefore, it is possible to accurately determine whether or not the vehicle has reached the guidance start point thereafter (S9).

  On the other hand, in S20, the CPU 41 specifies the detected stop line candidate as a feature other than the stop line (for example, a white line constituting a bicycle crossing or a pedestrian crossing). Thereafter, the process proceeds to S21.

  In S21, the CPU 41 determines whether or not the vehicle has passed the branch point determined to be within the predetermined distance in S11. For example, when the vehicle travels more than the width of the intersection road from the node at the branch point, it is determined whether the vehicle has passed through the branch point.

  Then, when it is determined that the vehicle has passed the branch point determined to be within the predetermined distance in S11 (S21: YES), the current position of the vehicle stored in the RAM 42 is not updated and the vehicle is updated. The position detection processing program is terminated. On the other hand, when it is determined that the vehicle has not passed the branch point determined to be within the predetermined distance in S11 (S21: NO), the process returns to S13, and stop line candidates are continuously selected. A feature recognition process for detection is performed. That is, the detection result of the feature recognition process for detecting the road marking of the stop line candidate at a predetermined interval between the time when the vehicle is positioned a predetermined distance before the branch point and the time when the vehicle passes the branch point. Will be acquired.

  On the other hand, in S22 that is executed when it is determined that the length in the road width direction of the stop line candidate detected in the determination process of S15 is less than a predetermined length (for example, less than 160 cm), the CPU 41 determines that the stop line candidate is It is determined whether or not a plurality of line segments having a shape less than a predetermined length (for example, less than 160 cm) in the road width direction are included.

  And when it determines with a stop line candidate being comprised from the some line segment which has a shape less than predetermined length with respect to a road width direction (S22: YES), it transfers to S23. On the other hand, when it is determined that the stop line candidate is not composed of a plurality of line segments having a shape less than a predetermined length in the road width direction (for example, composed of only one line segment) (S22: NO) The process proceeds to S20 and specifies that the stop line candidate is not a stop line.

  In S23, the CPU 41 determines whether or not the distances from the vehicle to the plurality of line segments constituting the stop line candidate are equal distances. For example, when the stop line candidate shown in FIG. 9B is detected by the image recognition process, it is determined whether or not X1 to X3 are equidistant. Note that “equal distance” does not have to be completely the same distance, and is considered to be an equal distance if a measurement error or the like is considered and within a certain error range (for example, within 15 cm).

  And when it determines with each distance from a vehicle to the some line segment which comprises a stop line candidate being equal distance (S23: YES), it transfers to S24. On the other hand, if it is determined that the distances from the vehicle to the plurality of line segments constituting the stop line candidate are not equidistant (S23: NO), the process proceeds to S20, and the stop line candidate is not a stop line. Identify.

  In S24, the CPU 41 determines whether or not the stop line candidate is composed of a plurality of line segments arranged at predetermined intervals. For example, when the stop line candidate shown in FIG. 9B is detected by the image recognition process, it is determined whether or not H1 and H2 are at a predetermined interval. Note that the “predetermined interval” that is the determination criterion in S24 is set in consideration of the width of the vehicle tire. That is, it is desirable to set the width of the narrowest tire on the market as the lower limit, the width of the widest tire on the market as the upper limit, and a certain allowance. For example, 10-30 cm is set as the predetermined interval. Note that the lower limit may not be set.

  And when it determines with a stop line candidate being comprised from the some line segment arrange | positioned at predetermined intervals (S24: YES), it transfers to S25. On the other hand, when it is determined that the stop line candidate is composed of a plurality of line segments arranged at intervals wider or narrower than the predetermined interval (S24: NO), the process proceeds to S20, where the stop line candidate is the stop line. If not, specify.

  Further, in S25, the CPU 41 determines whether or not the length between the outer end portions of two line segments located at both ends of the plurality of line segments constituting the stop line candidate is equal to or longer than a predetermined length. For example, when the stop line candidate shown in FIG. 9B is detected by the image recognition process, it is determined whether Wt is equal to or longer than a predetermined length. Note that the “predetermined length” serving as the determination criterion in S25 is the same as the predetermined length serving as the determination criterion in S15. In other words, it is generally the minimum length that can be taken by a stop line arranged on the road, for example, 160 cm.

  And when it determines with the length between the outer side edge parts of two line segments located in both ends among the several line segments which comprise a stop line candidate being more than predetermined length (S25: YES) To S17. If the conditions after S17 are satisfied, the detected stop line candidate is identified as a stop line (S18).

  On the other hand, when it determines with the length between the outer side edge parts of two line segments located in both ends among the several line segments which comprise a stop line candidate being less than predetermined length (S25: NO) The process proceeds to S20 and specifies that the stop line candidate is not a stop line.

As described above in detail, according to the navigation device 1 according to the present embodiment, the stop line detection method using the navigation device 1 and the computer program executed by the navigation device 1, a high-precision location with a stop line as a recognition target. When a feature (stop line candidate) that is a stop line candidate is detected using the system, the stop line candidate is composed of a plurality of line segments having a shape less than a predetermined length in the road width direction, and the vehicle Each distance from the line segment to the plurality of line segments is equal, and the length between the outer ends of the two line segments located at both ends in the road width direction within the plurality of line segments is equal to or greater than a predetermined length. If it is determined that the stop line candidate is detected as a stop line, even if the stop line is divided into a plurality of line segments due to paint wear or the like, it can be appropriately detected as a stop line. . In addition, it is possible to prevent a feature other than the stop line from being erroneously detected as a stop line.
Further, since the stop line candidate is detected based on the image captured by the back camera 19 installed in the vehicle, the stop line candidate around the vehicle is detected using the back camera 19 used in the existing system. Is possible. As a result, the system can be realized without providing a new means or system for detecting stop line candidates.
In addition, since the detection result of detecting the feature of the stop line candidate at a predetermined interval is acquired from the time when the vehicle is positioned before the branch point until the vehicle passes through the branch point, the stop line candidate is acquired. Can be limited to a section where a stop line may be arranged, and the processing burden related to detection of a stop line candidate can be reduced.
In addition, when the stop line candidate is composed of a plurality of line segments arranged at a predetermined interval, the stop line candidate is detected as a stop line. It is possible to accurately determine whether or not the stop line is divided into a plurality of line segments.
Further, when the stop line candidate is identified as the stop line, the feature information in which the stop line and the stop line position information are associated with each other is acquired, and the position of the vehicle is acquired based on the acquired feature information. (S19), it is possible to accurately detect the position of the vehicle based on the detection result by detecting a stop line around the vehicle. As a result, it is possible to execute guidance and control for the vehicle at an appropriate timing.

Note that the present invention is not limited to the above-described embodiment, and various improvements and modifications can be made without departing from the scope of the present invention.
For example, in the present embodiment, the guidance branch point guidance by the navigation device 1 is output by voice guidance from the speaker 16, but the guidance may be performed by displaying text on the liquid crystal display 15.

  Moreover, you may abbreviate | omit a part of each process of S15-S17 for identifying the stop line candidate performed in a vehicle position detection process (FIG. 7) as a stop line, and S22-S25. Further, the processing order may be changed. Furthermore, other conditions may be added. For example, the process (S24) related to the arrangement interval of the stop line candidates may be omitted, or the process (S17) related to the pedestrian crossing may be omitted.

  In the present embodiment, features such as stop line candidates and pedestrian crossings are detected by image recognition using the back camera 19, but other means (for example, a vehicle) A front camera or a sensor that acquires a front image may be used. The position of the pedestrian crossing may be stored in advance in the DB or center and acquired from the DB or center.

  In this embodiment, as guidance for the guidance branch point, guidance is performed using the number of traffic lights (or branch points where traffic lights are installed) from the current position of the vehicle to the guidance branch point. You may make it perform guidance of. However, the effect of the present invention is remarkable particularly when performing guidance using a traffic light or a branch point.

  In addition to the navigation device, the present invention can be applied to a device having a function of detecting the current position of a moving body such as a vehicle. For example, the present invention can be applied to a portable terminal such as a cellular phone or a PDA, a personal computer, a portable music player, etc. (hereinafter referred to as a portable terminal or the like). Further, the present invention can be applied to a system including a server and a mobile terminal. In that case, each step of the above-described branch point guidance processing program (FIG. 5) and vehicle position detection processing program (FIG. 7) may be configured to be implemented by either a server or a portable terminal. In addition, when the present invention is applied to a mobile terminal or the like, a mobile body other than a vehicle, for example, a user such as a mobile terminal or a vehicle position such as a two-wheeled vehicle may be detected.

1 Navigation device 13 Navigation ECU
19 Back camera 31 Map information DB
33 feature table 37 feature data 41 CPU
42 RAM
43 ROM
81 Vehicle 101-104 Stop line candidate

Claims (8)

A feature detection result acquisition means for acquiring a detection result of detecting a feature of a stop line candidate existing around the moving body;
The stop line candidate is composed of a plurality of line segments having a shape less than a predetermined length in the road width direction, each distance from the moving body to the plurality of line segments is equal, and the plurality of lines Arrangement determining means for determining whether or not the length between the outer end portions of two line segments located at both ends within the minute is equal to or greater than the predetermined length;
The arrangement determining means includes the plurality of line segments in which the stop line candidate has a shape less than a predetermined length in the road width direction, and each distance from the moving body to the plurality of line segments is equal. And when it is determined that the length between the outer ends of two line segments located at both ends in the road width direction among the plurality of line segments is not less than the predetermined length, the stop line candidate And a stop line specifying means for specifying the stop line as a stop line.   The feature detection result acquisition unit acquires a detection result of detecting the stop line candidate formed on a road on which the moving body moves based on an image captured by an imaging unit installed on the moving body. The stop line detection system according to claim 1.   The feature detection result acquisition means is configured to detect the feature of the stop line candidate at a predetermined interval between the time when the moving body is positioned a predetermined distance before the branch point and the time when the mobile body passes the branch point. The stop line detection system according to claim 1 or 2, wherein the detected detection result is acquired. An arrangement interval determining means for determining whether or not the stop line candidate is composed of the plurality of line segments arranged at a predetermined interval;
The stop line specifying unit specifies the stop line candidate as a stop line when the arrangement interval determining unit determines that the stop line candidate is composed of the plurality of line segments arranged at a predetermined interval. The stop line detection system according to any one of claims 1 to 3, wherein Feature information acquisition means for acquiring feature information in which the stop line specified by the stop line specifying means is associated with position information of the stop line;
5. A position detection unit that detects a position of the moving body based on the feature information acquired by the feature information acquisition unit. 6. Stop line detection system. A feature detection result acquisition means for acquiring a detection result of detecting a feature of a stop line candidate existing around the moving body;
The stop line candidate is composed of a plurality of line segments having a shape less than a predetermined length in the road width direction, each distance from the moving body to the plurality of line segments is equal, and the plurality of lines Arrangement determining means for determining whether or not the length between the outer end portions of two line segments located at both ends within the minute is equal to or greater than the predetermined length;
The arrangement determining means includes the plurality of line segments in which the stop line candidate has a shape less than a predetermined length in the road width direction, and each distance from the moving body to the plurality of line segments is equal. And when it is determined that the length between the outer ends of two line segments located at both ends in the road width direction among the plurality of line segments is not less than the predetermined length, the stop line candidate And a stop line specifying means for specifying a stop line as a stop line. A feature detection result acquisition step for acquiring a detection result of detecting a feature of a stop line candidate existing around the moving body;
The stop line candidate is composed of a plurality of line segments having a shape less than a predetermined length in the road width direction, each distance from the moving body to the plurality of line segments is equal, and the plurality of lines An arrangement determining step for determining whether or not a length between outer end portions of two line segments located at both ends within the minute is equal to or longer than the predetermined length;
In the arrangement determining step, the stop line candidate is composed of the plurality of line segments having a shape less than a predetermined length in the road width direction, and each distance from the moving body to the plurality of line segments is equal. And when it is determined that the length between the outer ends of two line segments located at both ends in the road width direction among the plurality of line segments is not less than the predetermined length, the stop line candidate And a stop line identifying step for identifying the stop line as a stop line. On the computer,
A feature detection result acquisition function for acquiring a detection result of detecting a feature of a stop line candidate existing around a moving object;
The stop line candidate is composed of a plurality of line segments having a shape less than a predetermined length in the road width direction, each distance from the moving body to the plurality of line segments is equal, and the plurality of lines An arrangement determining function for determining whether or not the length between the outer ends of two line segments located at both ends within the minute is equal to or greater than the predetermined length;
By the arrangement determination function, the stop line candidate is composed of the plurality of line segments having a shape less than a predetermined length in the road width direction, and each distance from the moving body to the plurality of line segments is equal. And when it is determined that the length between the outer ends of two line segments located at both ends in the road width direction among the plurality of line segments is not less than the predetermined length, the stop line candidate A stop line identification function for identifying a stop line,
A computer program for executing

Images