JP2017129980A - Vehicle recognition device and vehicle recognition method - Google Patents

Abstract

A vehicle recognizing device and a vehicle recognizing method capable of appropriately notifying a driver of an approaching rear vehicle are provided.
A vehicle recognition apparatus according to an embodiment includes a rear vehicle detection unit, a lane determination unit, and a notification unit. The rear vehicle detection unit detects a rear vehicle approaching the host vehicle from the rear on the same lane as the host vehicle. The lane determination unit determines whether or not the lane in which the host vehicle is traveling is an overtaking lane. The notification unit outputs notification information for notifying the rear vehicle detected by the rear vehicle detection unit only when the lane determination unit determines that the vehicle is a passing lane.
[Selection] Figure 2

Description

  The present invention relates to a vehicle recognition device and a vehicle recognition method.

  2. Description of the Related Art Conventionally, there is known a vehicle recognition device that recognizes other vehicles around the host vehicle and notifies the driver of the vehicle so that the driver of the vehicle can perform appropriate driving according to the surrounding situation. This type of device notifies the driver of the host vehicle of an appropriate driving operation.

  In addition, when the host vehicle running on a road with multiple lanes on one side changes lanes, the driver of the host vehicle changes lanes by notifying the presence of a rear vehicle approaching from behind the lane adjacent to the running lane. A technique that facilitates this has been proposed (see, for example, Patent Document 1).

JP 2013-168063 A

  However, in the above-described conventional technology, for example, when the host vehicle is traveling in an overtaking lane, the rear vehicle approaching the host vehicle from the rear of the same lane as the host vehicle is not a target of notification. For this reason, the driver of the own vehicle is unaware of the rear vehicle, and the rear vehicle cannot pass the own vehicle, which may cause a traffic jam. Thus, the prior art has room for improvement in that it appropriately notifies the driver of the approaching rear vehicle.

  This invention is made in view of the above, Comprising: It aims at providing the vehicle recognition apparatus and vehicle recognition method which can notify a driver of the approaching rear vehicle appropriately to a driver | operator.

  In order to solve the above-described problems and achieve the object, a vehicle recognition device according to the present invention includes a rear vehicle detection unit, a lane determination unit, and a notification unit. The rear vehicle detection unit detects a rear vehicle approaching the host vehicle from the rear on the same lane as the host vehicle. The lane determination unit determines whether or not the lane in which the host vehicle is traveling is an overtaking lane. The notification unit outputs notification information for notifying the rear vehicle detected by the rear vehicle detection unit only when the lane determination unit determines that the vehicle is a passing lane.

  According to the present invention, it is possible to appropriately notify the driver of an approaching rear vehicle.

FIG. 1A is a diagram illustrating an outline of a vehicle recognition method according to the embodiment. FIG. 1B is a diagram illustrating an outline of a vehicle recognition method according to the embodiment. FIG. 2 is a block diagram illustrating a configuration of a vehicle on which the vehicle recognition device according to the embodiment is mounted. FIG. 3A is a diagram (No. 1) illustrating a detection method of a rear vehicle. FIG. 3B is a diagram (part 2) illustrating the detection method of the rear vehicle. FIG. 4 is a diagram illustrating a lane determination method. FIG. 5 is a diagram showing the surrounding situation information. FIG. 6 is a diagram (part 1) illustrating a situation around the vehicle. FIG. 7 is a diagram (part 2) illustrating a situation around the vehicle. FIG. 8 is a diagram (part 3) illustrating a situation around the vehicle. FIG. 9 is a diagram (part 4) illustrating a situation around the vehicle. FIG. 10 is a flowchart illustrating a processing procedure of notification processing executed by the vehicle recognition device according to the embodiment.

  Hereinafter, embodiments of a vehicle recognition device and a vehicle recognition method disclosed in the present application will be described in detail with reference to the accompanying drawings. In addition, this invention is not limited by embodiment shown below.

<1. Overview of vehicle recognition method>
First, an outline of the vehicle recognition method according to the embodiment will be described. 1A and 1B are diagrams illustrating a vehicle recognition method according to an embodiment. The vehicle recognition method according to the embodiment is executed by the vehicle recognition device 1 mounted on the host vehicle 10.

  In FIG. 1A and FIG. 1B, an example of a situation in which the rear vehicle 100 approaches from the rear while the host vehicle 10 (hereinafter may be simply referred to as “vehicle 10”) is traveling on a multi-lane road. I will give you a description. The types of the host vehicle 10 and the rear vehicle 100 include buses, taxis, motorcycles, and the like in addition to the automobiles shown in FIGS. 1A and 1B, but are limited to these as long as they can travel on the road. It is not what is done.

  Moreover, the road of one side multiple lanes is, for example, an expressway or a general road, and includes a travel lane L2 where the vehicle travels during normal times and an overtaking lane L1 which travels when overtaking another vehicle. In the following, a lane generally adopted in a country where left-hand traffic is adopted (for example, Japan) will be described as an example. In such a country, of the multiple lanes on one side, the lane on the right side of the traveling direction is the overtaking lane L1, and the lane on the left side of the overtaking lane L1 is the traveling lane L2. And the turn to the overtaking lane L1 side (the side where the oncoming lane exists) is a right turn.

  Here, as shown in FIG. 1A, when the rear vehicle 100 approaches from the rear of the host vehicle 10 traveling on the overtaking lane L1, if the driver of the host vehicle 10 notices and does not avoid it, the rear vehicle 100 cannot overtake the host vehicle 10, and traffic jams may occur behind the rear vehicle 100.

  Therefore, the vehicle recognition method according to the embodiment allows the driver of the host vehicle 10 to move the rear vehicle 100 approaching from the rear of the detected same lane only when the host vehicle 10 is traveling on the overtaking lane L1. It is a notification.

  Specifically, first, the vehicle recognition device 1 according to the embodiment detects the rear vehicle 100 approaching the host vehicle 10 from the rear on the same lane as the host vehicle 10.

  The detection of the rear vehicle 100 is performed by, for example, extracting the optical flow from a frame image captured at a predetermined time interval by a camera on the host vehicle 10 to detect the rear vehicle 100 traveling in the same lane as the host vehicle 10. To detect.

  Further, the vehicle recognition device 1 determines whether or not the type of lane in which the host vehicle 10 is traveling is the overtaking lane L1. In other words, it is specified whether the lane in which the host vehicle 10 is traveling is the overtaking lane L1 or the driving lane L2, and if it is the overtaking lane L1, a notification for notifying the detected rear vehicle 100 Output information.

  The notification information is information indicating the content of the notification to be made to the driver of the host vehicle 10, for example, information such as notification that prompts the approach of the rear vehicle 100 or a lane change for avoiding the rear vehicle 100. Including.

  The output notification information is, for example, displayed in text or voiced by the output unit (not shown) of the host vehicle 10 such as “the vehicle behind is approaching. Please change lanes”. Thus, the driver of the host vehicle 10 is notified.

  On the other hand, when the host vehicle 10 is traveling in the travel lane L2, the approaching rear vehicle 100 generally changes the lane to the overtaking lane L1 and passes the host vehicle 10, so the host vehicle 10 avoids the rear vehicle 100. There is no need. For this reason, if notification is also made about the approach of the rear vehicle 100, the driver feels troublesome.

  Therefore, as shown in FIG. 1B, the vehicle recognition method according to the embodiment does not output notification information even when the approach of the rear vehicle 100 is detected when the host vehicle 10 is traveling in the traveling lane L2. The driver of the host vehicle 10 is not notified.

  As described above, in the vehicle recognition method according to the embodiment, the host vehicle 10 is notified of the rear vehicle 100 approaching the host vehicle 10 only while the host vehicle 10 is traveling on the overtaking lane L1, so that the host vehicle 10 is notified of the approaching rear vehicle 100. Ten drivers can be notified appropriately.

  Furthermore, in the vehicle recognition method according to the embodiment, the driver of the host vehicle 10 receives a notification that prompts the driver to change the lane and changes the lane from the overtaking lane L1 to the traveling lane L2, so that the rear vehicle 100 passes the own vehicle 10. It is possible to prevent traffic jams.

  In the vehicle recognition method according to the embodiment, even when the host vehicle 10 is traveling on the overtaking lane L1, for example, it is necessary to make a turn such as making a right turn at an intersection on a planned travel route. When the predetermined condition is satisfied, the output of the notification information may be stopped even if the approaching rear vehicle 100 is detected. Such a case will be described later with reference to FIGS.

<2. Configuration of Vehicle Recognition Device 1>
Next, the configuration of the vehicle recognition device 1 in which the vehicle recognition method shown in FIG. 1 is executed will be specifically described with reference to FIG. FIG. 2 is a block diagram illustrating a configuration of the vehicle 10 on which the vehicle recognition device 1 according to the embodiment is mounted.

  As shown in FIG. 2, the vehicle 10 includes a vehicle recognition device 1, a camera 2, a position detection unit 3, an input unit 4, and an output unit 5. First, a configuration other than the vehicle recognition device 1 will be described.

  The camera 2 is a camera including an image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor), and is installed at a position for imaging the rear of the vehicle 10. Further, the camera 2 outputs a frame image obtained by capturing the rear of the vehicle 10 at a predetermined time interval (for example, 30 fps) to the vehicle recognition device 1.

  The position detection unit 3 detects the position (for example, latitude and longitude) where the vehicle 10 is traveling. The position detection unit 3 receives signals output from a plurality of GPS (Global Positioning System) satellites, and uses the position where the vehicle 10 is traveling based on the received signals as position information to the vehicle recognition apparatus 1. Notice.

  The input unit 4 is an input device such as a touch panel, for example, receives an input operation from the driver, and outputs a signal corresponding to the operation content to the vehicle recognition device 1. For example, the input unit 4 receives an instruction for setting a guide route from the departure point of the vehicle 10 to the destination from the driver, and outputs it to the vehicle recognition device 1.

  The output unit 5 is, for example, a speaker or the like, and converts the notification information signal output from the vehicle recognition device 1 into a sound or the like, and outputs it to the driver of the vehicle 10 to approach the rear vehicle 100. Notice. The output unit 5 is not limited to a speaker, and may be a liquid crystal display or a display such as a HUD (Head Up Display) that converts notification information into characters or images for display.

<2.1. Storage unit 7>
The vehicle recognition device 1 according to the embodiment includes a control unit 6 and a storage unit 7. First, the storage unit 7 will be described. The storage unit 7 is a storage unit configured by a storage device such as a nonvolatile memory or a hard disk drive, and stores the map information 7a, the peripheral state information 7b, and the notification information 7c described above.

  The map information 7a is so-called electronic map data, and includes road network data represented by nodes representing intersections and points on the road and links representing roads connecting the nodes. The node includes a node ID for identifying each node, attribute information such as information on a right turn exclusive lane, and the like. The link includes a link ID for identifying each link, attribute information such as the number of lanes, the lane type, and the road type (for example, a highway) corresponding to the link.

  The surrounding situation information 7b is information indicating the surrounding situation of the vehicle 10, and includes information indicating a situation where the output of the notification information 7c should be stopped. The specific contents of the surrounding situation information 7b will be described later with reference to FIG.

<2.2. Control unit 6>
The control unit 6 includes a rear vehicle detection unit 6a, a lane determination unit 6b, a situation determination unit 6c, a route setting unit 6d, and a notification unit 6e.

  The control unit 6 is a microcomputer including, for example, a CPU (Central Processing Unit), a RAM (Random Access Memory), and a ROM (Read Only Memory). For example, the CPU functions as the rear vehicle detection unit 6a, the lane determination unit 6b, the situation determination unit 6c, the route setting unit 6d, and the notification unit 6e by performing arithmetic processing according to a program stored in advance in the ROM. To do.

<2.2.1. Rear vehicle detection unit 6a>
The rear vehicle detection unit 6 a detects the rear vehicle 100 approaching the vehicle 10 from the rear on the same lane as the vehicle 10. The detection of the rear vehicle 100 by the rear vehicle detection unit 6a is performed using a frame image captured by the camera 2, for example.

  Here, with reference to FIG. 3A and FIG. 3B, the detection method of the back vehicle 100 by the back vehicle detection part 6a is demonstrated concretely. 3A and 3B are diagrams illustrating a method of detecting the rear vehicle 100. FIG.

  Each of the frame images 30 and 31 shown in FIGS. 3A and 3B is an image of the rear side of the vehicle 10 captured by the camera 2, and the lane lines 21, 22, the rear vehicle 100, and the rear vehicle 101 are shown in the image. Yes. The frame images 30 and 31 are images that are continuous in time series, and the frame image 30 is captured before the frame image 31.

  First, the rear vehicle detection unit 6a, for each frame image, is a pixel in which the luminance is discontinuous, that is, a pixel that is a boundary of an object such as the lane markings 21 and 22 and the rear vehicles 100 and 101, or the background in the frame image Are extracted as feature points (for example, four points including feature points P10 and P20 in the rear vehicle 100).

  In FIG. 3A and FIG. 3B, for convenience of explanation, only some feature points are selectively shown for each object, and any pixel that is a boundary of each object is extracted as a feature point. Can be done.

  The feature point P10 in the frame image 30 is the same feature point as the feature point P11 in the frame image 31. This indicates that the position coordinate of the feature point P10 in the frame image has changed to the position coordinate of the feature point P11 due to the movement of the rear vehicle 100. Also, the feature points P20 and P21 are the same feature point, which indicates that the position coordinate of the feature point P20 has changed to the position coordinate of the feature point P21 due to the movement of the rear vehicle 100.

  And the back vehicle detection part 6a synthesize | combines the frame images 30 and 31, and produces | generates an optical flow by connecting the same feature point among the feature points extracted from each frame image.

  For example, the optical flow F1 illustrated in FIG. 3B is generated by connecting the feature point P10 of the frame image 30 and the feature point P11 of the frame image 31. The optical flow F2 is generated by connecting the feature point P20 of the frame image 30 and the feature point P21 of the frame image 31.

  Further, the frame image 31 has a vanishing point VP that is an intersection on an extension line of each optical flow to be generated. And the back vehicle detection part 6a determines whether the object is approaching by the direction with respect to the vanishing point VP of the optical flow of each object.

  For example, the rear vehicle detection unit 6 a determines that the rear vehicles 100 and 101 are approaching the vehicle 10 because the optical flow of the rear vehicles 100 and 101 is generated in a direction extending from the vanishing point VP. . On the other hand, since the optical flow F31 of the lane line 21 is generated in the direction toward the vanishing point VP, the lane line 21 is an object that moves away from the vehicle 10, and thus is determined not to be approaching.

  Further, the rear vehicle detection unit 6a determines whether or not the rear vehicles 100 and 101 are traveling in the same lane as the vehicle 10 based on the direction in which the optical flow of the rear vehicles 100 and 101 diffuses from the vanishing point VP.

  Specifically, the rear vehicle detection unit 6a is configured so that the rear vehicle 100 is traveling in the same lane as the vehicle 10 because the optical flows F1 and F2 of the rear vehicle 100 are radially diffused from the vanishing point VP. Judge that there is. On the other hand, the rear vehicle detection unit 6a has the same rear vehicle 101 because the optical flows F11 and F12 of the rear vehicle 101 are diffused from the vanishing point VP in substantially the same direction (the lower right direction of the frame image 31). Determine that you are not driving in a lane.

  In FIG. 3B, the vanishing point VP is shown at the upper center of the frame image 31, which means that the vehicle 10 is traveling straight ahead. On the other hand, when the vehicle 10 runs in a curve, the position of the vanishing point VP is shifted in the left-right direction from the center upper part according to the curvature of the curve.

  In this case, the rear vehicle detection unit 6a uses the center upper portion of the frame image 31 as the reference coordinates of the vanishing point VP, and if the position coordinates of the vanishing point VP are shifted from the reference coordinates in the left-right direction, After the conversion, the determination process is performed.

  As described above, the rear vehicle detection unit 6a easily detects the rear vehicle 100 approaching from the rear on the same lane as the vehicle 10 by generating an optical flow using the frame image captured by the camera 2. Can do.

<2.2.2. Lane determination unit 6b>
Next, the lane determination unit 6b shown in FIG. 2 will be described with reference to FIG. The lane determination unit 6b performs a lane determination process for determining whether the lane in which the vehicle 10 is traveling is the overtaking lane L1. FIG. 4 is a diagram illustrating a lane determination method.

  As shown in FIG. 4, the left and right ends of the road of one-side multiple lanes are usually defined by lane markings 20 and 21 that are solid lines, and the region sandwiched between the lane markings 20 and 21 is a lane that is a broken line. The line 22 is divided into an overtaking lane L1 and a traveling lane L2.

  For example, the lane determination unit 6b specifies the type of the lane in which the vehicle 10 is traveling by paying attention to the types of the lane markings 20 to 22 (solid lines or broken lines). Specifically, the lane determination unit 6b searches for an area that matches the template image of the lane line to be detected from the frame image (see FIG. 3A) acquired from the camera 2 using a template matching method or the like.

  In other words, the lane determination unit 6b, based on the luminance value of the pixel in the frame image and the luminance value of the pixel of the template image, SSD (Sum of Squared Difference) or SAD (SAD (Similarity between the frame image and the template image). Calculate the Sum of Absolute Difference.

  Then, the lane determination unit 6b detects, based on the calculated similarity, whether or not there is a lane line in the frame image, the installation position of the lane line, whether the lane line is a solid line or a broken line, etc. To do.

  As shown in FIG. 4, the lane determination unit 6b of the detected lane lines is the solid lane line 21 on the right side of the lane with respect to the traveling direction 40 of the vehicle 10, and the lane line 22 on the left side is the broken line. In this case, it is determined that the lane in which the vehicle 10 is traveling is the overtaking lane L1.

  On the other hand, if the right side of the lane with respect to the traveling direction 40 of the vehicle 10 is the dashed lane line 22 and the left side is the solid lane line 20, the lane in which the vehicle 10 is traveling is the traveling lane L2, that is, It determines with it not being the overtaking lane L1.

  Further, when the left and right sides of the traveling direction 40 of the vehicle 10 are solid lane markings, for example, it is determined that one lane, that is, the lane in which the vehicle 10 is traveling is not the overtaking lane L1. And the lane determination part 6b notifies the above-mentioned determination result to the situation determination part 6c.

  Note that the types and arrangement of the dividing lines 20 to 22 shown in FIG. 4 are examples, and the present invention is not limited to these. For example, the dividing line 21 that separates the road in the lane in which the vehicle 10 is traveling and the road in the opposite lane in which the traveling direction 40 is the reverse direction may be configured by two lines or a yellow line.

  The lane detection method by the lane determination unit 6b is not limited to image processing using a frame image. For example, plotting the travel position of the vehicle 10 on the electronic map data based on the electronic map data of the map information 7a and the lane type information included in the link and the position information of the vehicle 10 acquired by the position detection unit 3 You may identify the lane you are driving.

<2.2.3. Situation determination unit 6c>
The situation determination unit 6c determines whether or not the situation around the vehicle 10 satisfies a predetermined condition based on the surrounding situation information 7b, and notifies the notification unit 6e of the determination result.

<2.2.4. Notification unit 6e>
The notification unit 6e outputs notification information 7c for notifying the approach of the rear vehicle 100 detected by the rear vehicle detection unit 6a only when the lane determination unit 6b determines that the vehicle is traveling on the overtaking lane L1. Thereby, the driver can be appropriately notified of the approaching rear vehicle 100.

  In addition, the notification part 6e stops the output of this notification information 7c, when the determination result that the surrounding condition of the vehicle 10 satisfy | fills predetermined conditions is received from the condition determination part 6c. That is, the notification unit 6e does not notify the driver of the approach of the rear vehicle 100.

<2.2.5. Determination process of situation determination unit 6c>
Here, with reference to FIG. 5, the surrounding situation information 7b which is used as an indicator of the determination process by the situation determination unit 6c will be described. FIG. 5 is a diagram showing the surrounding situation information 7b. The peripheral situation information 7b shown in FIG. 5 includes items such as “No.”, “Ambient situation”, and “Condition”. In addition, the surrounding situation information 7b shown in FIG. 5 is an example, and is not limited to this.

  “No.” indicates a number for identifying each peripheral situation. The “peripheral situation” indicates the peripheral situation of the vehicle 10. The “condition” indicates a condition for determining that the “peripheral situation” is satisfied by the situation determination unit 6 c.

  That is, the situation determination unit 6c determines whether or not the surrounding situation of the vehicle 10 satisfies a condition corresponding to each surrounding situation according to the surrounding situation information 7b, and when the condition is satisfied, the output of the notification information 7c is stopped. The notification unit 6e is notified. Hereinafter, the surroundings of the vehicle 10 shown in FIG. 5 will be specifically described with reference to FIGS.

<Peripheral situation no. 1: Approaching the intersection to turn right>
6 to 9 are diagrams illustrating the surrounding situation of the vehicle 10. First, with reference to FIG. 6, the case where the vehicle 10 approaches the intersection which should turn right is demonstrated. FIG. 6 shows a case where the front of the vehicle 10 is an intersection 50. In addition, the vehicle 10 is going to turn right at the intersection 50 according to the guidance route set by the route setting part 6d mentioned later.

  As shown in FIG. 6, in order for the vehicle 10 to turn right at the intersection 50, it is necessary to travel on the overtaking lane L1 and make a right turn. However, when the vehicle 10 receives a notification indicating the approach of the rear vehicle 100 and changes the lane from the overtaking lane L1 to the traveling lane L2 in order to avoid the rear vehicle 100, the vehicle 10 changes to the overtaking lane L1 depending on the distance to the intersection. There is a risk of failing to return and making a right turn.

  Therefore, when the vehicle 10 needs to make a right turn from the overtaking lane L1 at the intersection 50 where the vehicle 10 is approaching, the situation determination unit 6c determines that the condition “approaching the intersection to be turned right” is satisfied. Specifically, first, the situation determination unit 6c is based on the coordinates of the travel position based on the position information of the vehicle 10 and the position coordinates of the node N1 indicating the intersection 50 on the electronic map data of the map information 7a. The distance which is the length between each coordinate is calculated.

  When the calculated distance is equal to or less than the predetermined distance d1 (for example, 300 m or less), the situation determination unit 6c determines that the condition “below the predetermined distance to the intersection” is satisfied. Then, the notification unit 6e receives the determination result and stops outputting the notification information 7c, so that the vehicle 10 changes lanes to avoid the rear vehicle 100, so that the intersection cannot be turned right. Can be prevented.

  The situation determination unit 6c may set the predetermined distance d1 to a distance in consideration of the driving level of the driver in addition to the prohibited lane change section defined by law. Thereby, it can notify appropriately according to a driving level of a driver.

  Moreover, the determination method by the above-mentioned situation determination part 6c is applicable not only when turning right at the intersection 50 but also when the vehicle 10 makes a U-turn at the intersection 50. In such a case, the same determination process can be performed by replacing the above-mentioned “right turn” with “U-turn”.

<Peripheral situation no. 2: Close to the intersection with a right turn lane>
Next, a case where the vehicle 10 approaches the intersection 51 where the right turn exclusive lane L3 (an example of a turn exclusive use lane) is located will be described with reference to FIG. FIG. 7 shows a case where the vehicle 10 travels straight on the passing lane L1 at the intersection 51 where the right turn exclusive lane L3 is located.

  At the intersection 51 where the right turn lane L3 is in front of the vehicle 10, the rear vehicle 100 may approach the vehicle 10 in an attempt to change the lane to the right turn lane L3. However, since the notification of the approach of the rear vehicle 100 is originally unnecessary to the driver of the vehicle 10, the driver may feel annoying on the contrary.

  Therefore, when the vehicle 10 is approaching the intersection 51 where the right turn exclusive lane L3 is located, the situation determination unit 6c determines that the condition “approaching the intersection where there is a right turn exclusive lane” is satisfied. Specifically, the situation determination unit 6c first determines the coordinates of the travel position based on the position information of the vehicle 10 (the lower vehicle 10 in FIG. 7) and the intersection 51 on the electronic map data of the map information 7a. Based on the position coordinates of the indicated node N2, a distance that is the length between the coordinates is calculated.

  When the calculated distance is equal to or less than the predetermined distance d2, the situation determination unit 6c determines that the condition “below the predetermined distance to the intersection” is satisfied. The starting point of the predetermined distance d2 is preferably set to a point where the branching of the right turn dedicated lane L3 starts based on the information related to the right turn dedicated lane included in the node N2.

  Then, when the rear vehicle 100 passes through a position (for example, the position of the node N2) that can be estimated that the rear vehicle 100 does not turn right at the intersection 51, that is, the vehicle 10 continues to follow the rear of the vehicle 10, the situation determination unit 6c Re-determine if the condition is not met. And the notification part 6e will output the notification information 7c, if the result of this redetermination is received.

  That is, the notification unit 6e temporarily stops the output of the notification information 7c in the section of the right turn exclusive lane L3, thereby suppressing unnecessary notifications and making it difficult for the driver of the vehicle 10 to feel annoyance. it can.

<Peripheral situation no. 3: Rear vehicle changes lane>
Next, with reference to FIG. 8, a case will be described in which the rear vehicle 100 traveling on the same lane as the vehicle 10 changes lanes to the adjacent traveling lane L2. FIG. 8 shows a case where the rear vehicle 100 approaching the vehicle 10 is going to change the lane to the travel lane L2.

  In this case, when the driver of the vehicle 10 receives a notification of the approach of the rear vehicle 100 and changes the lane to the travel lane L2, both the vehicle 10 and the rear vehicle 100 travel in the travel lane L2, and the travel lane L2 The vehicle 10 and the rear vehicle 100 may approach again.

  Therefore, the situation determination unit 6c determines that the condition “the rear vehicle changes lane” is satisfied when a predetermined operation such as taking out the winker W is detected in order for the rear vehicle 100 to change the lane. .

  The situation determination unit 6c is a condition when, for example, the blinker W blinks rapidly, such as the luminance of a pixel in a region where the blinker W is in the frame image captured by the camera 2 exceeds a predetermined change rate. It is determined that “the rear vehicle satisfies the lane change operation”.

  The lane change operation is not limited to blinking of the blinker W, and may include a change in the turning angle of the front wheel of the rear vehicle 100, an operation in which the front wheel of the rear vehicle 100 straddles the lane marking 22, and the like. Thereby, the vehicle recognition apparatus 1 can prevent the own vehicle 10 from making an unnecessary lane change and approaching the rear vehicle 100 again in the traveling lane L2.

<Peripheral situation no. 4: There is a vehicle ahead>
Next, with reference to FIG. 9, a case where the front vehicle 102 is traveling in front of the vehicle 10 will be described. FIG. 9 shows a case where the forward vehicle 102 is traveling in front of the vehicle 10 in the overtaking lane L1.

  In this case, even if the lane is changed to the traveling lane L2 in order to avoid the rear vehicle 100 approaching by the vehicle 10, the rear vehicle 100 cannot pass the front vehicle 102 and is behind the rear vehicle 100. Traffic jams occur, and as a result, there is often no need to change lanes.

  Therefore, the situation determination unit 6c determines that the condition “detect the preceding vehicle” is satisfied when the preceding vehicle 102 exists in front of the vehicle 10 traveling on the overtaking lane L1. The forward vehicle 102 is detected, for example, by image analysis using pattern matching or the like from a frame image acquired from the camera 2 that captures the front of the vehicle 10.

  Thereby, the vehicle recognition apparatus 1 can reduce performing an unnecessary lane change. In addition, the vehicle recognition apparatus 1 may detect the presence of another forward vehicle ahead of the forward vehicle 102 using image analysis based on a frame image or millimeter wave radar, and confirm the degree of congestion ahead. Good.

  In addition, when the situation determination unit 6c detects an operation of changing the lane such as the forward vehicle 102 issuing a turn signal, the situation determination unit 6c determines that the condition “the vehicle is ahead” is not satisfied, and the notification unit 6e In response, the notification information 7c may be output.

<Peripheral situation no. 5: Approaching a branch point>
Next, a case of approaching a branch point in front of the vehicle 10 will be described. A branch point is, for example, a junction on a highway, and is a point where a running road branches into a plurality of roads.

  When the vehicle 10 needs to travel on the overtaking lane L1 at the junction of the expressway and enter the branch road, the lane is changed to the driving lane L2 in order to avoid the rear vehicle 100, and then to the overtaking lane L1. If you fail to return, you may not be able to enter the branched road.

  Therefore, when the vehicle 10 is approaching the branch point on the highway, the situation determination unit 6c determines that the condition “approaching the branch point” is satisfied. Such a case can be realized by using a calculation method similar to the calculation of the distance d1 (see FIG. 6) between the intersection and the vehicle 10 and replacing the “intersection” node N1 with a “branch point” node.

  When the distance from the branch point to the vehicle 10 is less than or equal to the predetermined distance, the situation determination unit 6c determines that the condition “below the predetermined distance to the branch point” is satisfied. In this case, the predetermined distance is preferably set longer than the distance d1 and the distance d2 described above in consideration of the traveling speed on the highway. This can prevent the vehicle 10 from failing to enter the desired road at the branch point.

  Note that the above-described specific example of the “surrounding situation” is an example, and the present invention is not limited to this. If the situation is unnecessary.

  Thereby, the vehicle recognition apparatus 1 according to the embodiment can prevent the driver from being notified in a situation where it is difficult to change the lane.

<2.2.6. Route Setting Unit 6d>
Returning to FIG. 2, the description of the control unit 6 will be continued. The route setting unit 6d receives the signal indicating the destination designated by the driver received from the input unit 4, and from the departure point (for example, the current location of the vehicle 10) to the destination in the electronic map data of the map information 7a. Set the guide route. Then, the route setting unit 6d notifies the status determination unit 6c of the set guide route as guide route information.

  The route setting unit 6d notifies guide route information to a navigation device (not shown), and the navigation device guides driving of the vehicle 10 by outputting characters and voice for guidance according to the guide route of the guide route information. And guide the route to the destination.

<3. Flowchart of vehicle recognition device 1>
Next, a processing procedure of notification processing executed by the vehicle recognition device 1 according to the embodiment will be described with reference to FIG. FIG. 10 is a flowchart illustrating a processing procedure of notification processing executed by the vehicle recognition device 1 according to the embodiment.

  As illustrated in FIG. 10, the rear vehicle detection unit 6a detects, for example, the rear vehicle 100 approaching the vehicle 10 from the rear on the same lane as the vehicle 10 based on the frame image acquired from the camera 2 (step S101). ).

  Subsequently, the lane determination unit 6b specifies, for example, the type of lane based on the frame images 30 and 31 acquired from the camera 2, so that the lane in which the vehicle 10 is traveling is the overtaking lane L1. It is determined whether or not (step S102).

  When the lane determining unit 6b determines that the lane is the overtaking lane L1 (step S102, Yes), the situation determining unit 6c determines whether or not the surrounding situation of the vehicle 10 satisfies a condition included in the surrounding situation information 7b. (Step S103).

  When the situation determination unit 6c determines that the condition included in the surrounding situation information 7b is not satisfied (No at Step S103), the notification unit 6e outputs the notification information 7c to the output unit 5 (Step S104), and performs processing. finish.

  On the other hand, in the determination process of step S102, when it is determined that the vehicle is traveling on the traveling lane L2, in other words, the vehicle is not traveling on the overtaking lane L1 (step S102, No), the notification unit 6e outputs the notification information 7c. Is terminated (step S105), and the process is terminated.

  On the other hand, in the determination process of step S103, when it is determined that the condition included in the surrounding state information 7b is satisfied (step S103, Yes), the notification unit 6e stops outputting the notification information 7c (step S105), and the process Exit.

  As described above, the vehicle recognition device 1 according to the embodiment includes the rear vehicle detection unit 6a, the lane determination unit 6b, the situation determination unit 6c, the route setting unit 6d, and the notification unit 6e. The rear vehicle detection unit 6 a detects the rear vehicle 100 approaching the vehicle 10 from the rear on the same lane as the vehicle 10. The lane determination unit 6b determines whether or not the lane in which the vehicle 10 is traveling is the overtaking lane L1. The situation determination unit 6c determines whether or not the surrounding situation of the vehicle 10 satisfies a predetermined condition. The route setting unit 6d sets a guide route from the departure point of the vehicle 10 to the destination. The notification unit 6e outputs notification information 7c for notifying the rear vehicle 100 detected by the rear vehicle detection unit 6a only when the lane determination unit 6b determines that the vehicle is the overtaking lane L1. Moreover, the notification part 6e stops the output of the notification information 7c, when the condition determination part 6c determines with satisfy | filling predetermined conditions.

  Thereby, according to the vehicle recognition device 1 according to the embodiment, the approaching rear vehicle 100 can be appropriately notified to the driver of the vehicle 10.

  In the above-described embodiment, other vehicles such as the rear vehicle 100 and the front vehicle 102 are detected using the frame image by the camera 2, but the present invention is not limited to this. For example, the other vehicle is detected by a millimeter wave radar. May be.

  When the millimeter wave radar is used, a radio wave is transmitted to a range of a predetermined angle in front of or behind the vehicle 10, and the transmitted radio wave is reflected by another vehicle to be detected and detected as a received wave. For example, a speed difference from another vehicle, whether or not the vehicle is in the same lane, an inter-vehicle distance, and the like are detected based on a time difference between a transmission radio wave and a reception radio wave, an angle formed, an intensity of the reception radio wave, and the like.

  Further, the time interval of the detection process of the rear vehicle 100 by the rear vehicle detection unit 6 a may be changed according to the vehicle speed of the vehicle 10. For example, when the vehicle speed of the vehicle 10 acquired from the vehicle speed sensor is faster than a predetermined speed, the detection process time interval is lengthened, and when it is slow, the detection process time interval is shortened.

  This considers the speed difference with the rear vehicle 100. When the vehicle speed of the vehicle 10 is faster than the predetermined speed, the speed difference with the rear vehicle 100 is relatively small, and when the vehicle speed is lower than the predetermined speed. This is because the speed difference is relatively large.

  Thereby, when the speed difference between the vehicle 10 and the rear vehicle 100 is large, the rapid approach of the rear vehicle 100 can be detected earlier, and when the speed difference is small, the time interval of the detection process is increased. Thus, the processing load on the CPU can be reduced and the power consumption can be reduced.

  In the above-described embodiment, as an example of a country where left-hand traffic is adopted, the right lane L1 and the left lane L2 in the traveling direction of the vehicle 10 in the one-side multiple lane have been described. On the other hand, if the country in which the vehicle 10 travels is a country where right-hand traffic is adopted, the positional relationship described above may be switched between the left and right. For example, in the above description, the turn to the overtaking lane (the side where the oncoming lane is present) has been described as a right turn, but in the case of a country where right-hand traffic is adopted, the turn may be read as a left turn.

  Further effects and modifications can be easily derived by those skilled in the art. Thus, the broader aspects of the present invention are not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications can be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and their equivalents.

DESCRIPTION OF SYMBOLS 1 Vehicle recognition apparatus 6a Rear vehicle detection part 6b Lane determination part 6c Situation determination part 6d Route setting part 6e Notification part 7c Notification information 100 Back vehicle

Claims (9)

A rear vehicle detection unit for detecting a rear vehicle approaching the host vehicle from the rear on the same lane as the host vehicle;
A lane determination unit that determines whether the lane in which the host vehicle is traveling is an overtaking lane;
A notification unit that outputs notification information for notifying the rear vehicle detected by the rear vehicle detection unit only when it is determined by the lane determination unit that the vehicle is the overtaking lane. Vehicle recognition device. A situation determination unit for determining whether or not the surrounding situation of the host vehicle satisfies a predetermined condition;
The notification unit
The vehicle recognition device according to claim 1, wherein when the condition determination unit determines that the predetermined condition is satisfied, the output of the notification information is stopped. A route setting unit for setting a guide route from the departure point of the host vehicle to the destination;
The situation determination unit
The vehicle recognition apparatus according to claim 2, wherein the predetermined condition is determined when it is necessary to bend from the overtaking lane at an intersection where the host vehicle is approaching on the guide route. The situation determination unit
4. The vehicle recognition device according to claim 2, wherein, when a turn-only lane exists at an intersection where the host vehicle is approaching, it is determined that the predetermined condition is satisfied. 5. The situation determination unit
5. The method according to claim 2, wherein the predetermined condition is determined when a predetermined operation for changing a lane to a traveling lane adjacent to the overtaking lane is detected in the rear vehicle. Vehicle recognition device. The situation determination unit
6. The vehicle according to claim 1, wherein when the vehicle ahead is traveling in the same lane as the vehicle, the predetermined condition is determined to be satisfied. Vehicle recognition device. The situation determination unit
The vehicle recognition device according to any one of claims 2 to 6, wherein when the host vehicle is approaching a branch point that branches to a plurality of roads, the vehicle satisfies the predetermined condition. The rear vehicle detection unit is
Based on an optical flow generated by connecting the same feature points in a plurality of frame images captured at a predetermined time interval in the host vehicle, the approach of the rear vehicle included in the frame image is detected. The vehicle recognition device according to any one of claims 1 to 7, wherein: A rear vehicle detection step of detecting a rear vehicle approaching the host vehicle from the rear on the same lane as the host vehicle;
A lane determination step of determining whether the lane in which the host vehicle is traveling is an overtaking lane;
A notification step of outputting notification information for notifying the rear vehicle detected by the rear vehicle detection step only when it is determined by the lane determination step that the vehicle is the overtaking lane. Vehicle recognition method.

Images