WO2019013253A1

WO2019013253A1 - Detection device

Info

Publication number: WO2019013253A1
Application number: PCT/JP2018/026192
Authority: WO
Inventors: 章伸酒井; 謙二岡野
Original assignee: 株式会社デンソー
Priority date: 2017-07-14
Filing date: 2018-07-11
Publication date: 2019-01-17
Also published as: JP2019020957A

Abstract

This detection device (30) is mounted on a vehicle (70). The detection device is provided with an image acquisition unit (S100), a candidate extraction unit (S110), a brightness determination unit (S160), a plurality determination unit (S190), a recognition unit (S210) and an output unit (S40). If the plurality determination unit has determined that there is a plurality of demarcation candidates, the recognition unit (S210) recognizes the demarcation line candidate nearest to the vehicle as a lane marking, that is, a demarcation line that demarcates the lane in which the vehicle is traveling. The output unit (S40) outputs the result of recognition by the recognition unit.

Description

Detection device

Cross-reference to related applications

This international application claims priority based on Japanese Patent Application No. 2017-137854 filed with the Japanese Patent Office on July 14, 2017, and the Japanese Patent Application No. 2017-137854 The entire contents are incorporated by reference into this international application.

The present disclosure relates to a technique for recognizing a lane mark from an image.

In the following Patent Document 1, when a plurality of line candidates serving as lane mark candidates are detected from an image captured by a camera mounted on a vehicle, the line candidate having the highest luminance among the plurality of line candidates is selected. A technique has been proposed which recognizes as a lane mark.

JP, 2015-197829, A

However, the lane mark may include a line having lower luminance than the white line, such as a yellow line, for example. As a result of the inventor's detailed examination, when the lane mark is detected, the technique described in Patent Document 1 always detects only the white line if a plurality of line candidates having different luminances, such as a white line and a yellow line, are detected. A problem was found that there is a possibility that the vehicle may be recognized as a lane mark. That is, with the technique described in Patent Document 1, it has been found that there is a possibility that lane marks can not be detected properly.

One aspect of the present disclosure provides a technique for appropriately detecting a lane mark that defines a traveling path on which a vehicle travels.
One aspect of the present disclosure is a detection device mounted on a vehicle. The detection device includes an image acquisition unit, a candidate extraction unit, a luminance determination unit, a multiple determination unit, a recognition unit, and an output unit.

The image acquisition unit is configured to repeatedly acquire an image captured by at least one camera mounted on the vehicle and including a travel path which is a road on which the vehicle travels. The candidate extraction unit determines at least one line candidate which is a candidate for a division line that divides the lane from the captured image based on the feature point at which the luminance changes by a predetermined change threshold or more between adjacent pixels in the captured image. It is configured to extract

The luminance determination unit is configured to acquire the luminance of the line candidate for each of the line candidates, and determine whether the luminance of the line candidate is equal to or more than a predetermined luminance threshold. The multiple determination unit is configured to determine whether there is a plurality of section candidates that are line candidates and the luminance determination unit determines that the luminance of the line candidate is equal to or higher than the luminance threshold.

The recognition unit is a travel division line that is a division line that divides the lane where the vehicle travels, which is the division candidate closest to the vehicle among the plurality of division candidates when it is determined by the multiple determination unit that there are a plurality of division candidates. It is configured to recognize as. The output unit is configured to output the recognition result by the recognition unit.

According to such a configuration, when a plurality of section candidates are detected, the section candidate closest to the vehicle is recognized as a traveling section line, so the traveling section line is appropriately selected regardless of the difference in the luminance of the section line. Can be detected.

In addition, the reference numerals in parentheses described in the claims indicate the correspondence with specific means described in the embodiments described later as one aspect of the present disclosure, and the technical scope of the present disclosure is limited. It is not something to do.

FIG. 2 is a block diagram showing the configuration of a driving support system. Explanatory drawing which shows an example of the arrangement position of a camera. Explanatory drawing which shows the function of ECU. Schematic diagram of the bird's eye view image. Explanatory drawing which shows the luminance of the dividing line in the area | region A of FIG. 4, and a repair mark. 6 is a flowchart of detection processing. The flowchart of recognition processing. Explanatory drawing explaining a brightness | luminance threshold value. Explanatory drawing which shows the other example of the arrangement position of a camera.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.
[1. Constitution]
[1-1. overall structure]
The driving support system 1 shown in FIG. 1 is mounted on a vehicle 70. The driving support system 1 recognizes lane markings of a road from an image obtained by photographing the surroundings of the vehicle 70, estimates traveling path parameters, and executes various driving assistances based on the estimated traveling path parameters. In addition, a demarcation line is what is called a lane mark, and is a white line and a yellow line drawn on the road surface so that the lane of a traveling path may be divided. The travel path is a road on which the vehicle travels. The travel path parameters represent the state of the travel path for the vehicle 70 and the shape of the travel path.

The driving support system 1 includes an ECU 30. The driving support system 1 may include a camera 10, a sensor group 20, and a vehicle control device 50.
The camera 10 includes a front camera 11, a left side camera 12, a right side camera 13, and a rear camera 14. Each of the cameras 11 to 14 can be configured using a CCD image sensor, a CMOS image sensor, or the like.

As shown in FIG. 2, the front camera 11 is installed, for example, on a bumper at the front end of the vehicle such that the road surface in front of the vehicle is a shooting range. The left side camera 12 is installed, for example, on the left side mirror so that the road surface on the left side of the vehicle is in the shooting range. The right side camera 13 is installed, for example, on the right side mirror such that the road surface on the right side of the vehicle is the shooting range. The rear camera 14 is installed, for example, on a bumper at the rear end of the vehicle such that the road surface on the rear side of the vehicle is in the shooting range.

Each of the cameras 11 to 14 repeatedly captures images at preset time intervals, for example, intervals of several tens of msec, and outputs camera images to the ECU 30.
The sensor group 20 is a sensor that measures the behavior of the vehicle 70. Specifically, the sensor group 20 includes a vehicle speed sensor that measures the vehicle speed of the vehicle 70, a yaw rate sensor that measures the yaw rate of the vehicle 70, and the like. The sensor group 20 is a GPS sensor that detects the position of the vehicle 70, a radar sensor that detects the distance and relative speed with a target present around the vehicle 70, and an illuminance sensor that detects the brightness around the vehicle 70 Etc. may be provided. The sensor group 20 outputs detection results such as sensor values to the ECU 30.

The vehicle control device 50 includes a microcomputer having a semiconductor memory such as a CPU, a ROM, a RAM, and a flash memory. The vehicle control device 50 controls steering of the vehicle 70, a brake, an engine, and the like so that the vehicle 70 travels in the lane based on the recognition result of the dividing line output from the ECU 30. The recognition results of the lane markings may include roadway parameters.

The ECU 30 includes a microcomputer having a CPU 41 and a semiconductor memory (hereinafter, memory 42) such as a RAM, a ROM, and a flash memory. The various functions of the ECU 30 are realized by the CPU 41 executing a program stored in a non-transitional tangible storage medium. In this example, the memory 42 corresponds to a non-transitional tangible storage medium storing a program. Also, by executing this program, a method corresponding to the program is executed. The ECU 30 may include one microcomputer or may include a plurality of microcomputers.

As shown in FIG. 3, the ECU 30 includes an input processing unit 31, a combining processing unit 32, a recognition processing unit 33, and an output processing unit 34 as a configuration of functions realized by the CPU 41 executing a program. The recognition processing unit 33 also includes an output unit image acquisition unit, a candidate extraction unit, a luminance determination unit, a multiple determination unit, a recognition unit, an accumulation unit, an update unit, an environment determination unit, and an output unit. The method for realizing these elements is not limited to software, and some or all of the elements may be realized using hardware combining logic circuits, analog circuits, and the like.

[1-2. Characteristics of the Road in the Photographed Image]
FIG. 4 is a schematic view of a bird's-eye view image generated by the combination processing unit 32. As shown in FIG. An area indicated by a broken line at the center of the figure is a vehicle area in which the vehicle 70 is present. The synthesis processing unit 32 synthesizes the camera images captured by the four cameras 11-14 and converts it into a bird's-eye view to generate a bird's-eye view image surrounding the vehicle area. In the bird's-eye view image shown in FIG. 4, a solid yellow line and a solid white line, and a repair mark are present on the traveling path.

Here, solid yellow lines and solid white lines are dividing lines. Usually, the brightness of the white line is greater than the brightness of the yellow line. Therefore, if it is assumed that a division line with the highest luminance in the photographed image is always detected as a traveling division line, there is a possibility that a yellow line may not be detected as a traveling division line. In addition, a traveling division line is a division line which divides the lane which a vehicle drive | works.

On the other hand, a repair mark is a mark which repaired the crack of the road surface. The repair marks may include, for example, a mark obtained by repairing a crack in the asphalt road surface with tar, a mark formed by repairing a crack in the concrete road surface with asphalt, and the like. Cracks on the road surface often occur along the dividing line due to tire pressure, particularly in snowy areas such as North America, and the repair marks often become linear along the dividing line.

Usually, the brightness of the repair marks is smaller than the brightness of the dividing lines such as white and yellow lines. In addition, the luminance of the repair mark is smaller than the luminance of the road surface. Also, in general, a straight line obtained by performing processing such as Hough transformation on a feature point extracted from a photographed image is recognized as a dividing line. The feature points referred to here are edge points. An edge point is a point at which the luminance changes by at least a change threshold which is a predetermined threshold between adjacent pixels in a captured image.

Therefore, for example, as shown in FIG. 4 and FIG. 5, a plurality of repair marks extending substantially parallel to the dividing line are positioned across the road surface, and the intervals of the plurality of repair marks are substantially the same as the width of the dividing line. In some cases, there is a risk that a road surface sandwiched by a plurality of repair marks may be erroneously detected as a dividing line. If there is a portion whose luminance is lower than the road surface, such as a repair mark, the low luminance portion is erroneously recognized as the road surface, and the original road surface is erroneously recognized as the dividing line.

The low luminance regions referred to below are each of a plurality of linear regions located on the road surface so as to be parallel to the division lines, and are separated from each other by the same extent as the width of the division lines. Is a low area. The low luminance region may include the above-described repair marks. In addition, the low luminance region may include cracks of the road surface, tire marks, and the like.

The term "parallel" as used herein is not limited to being strictly parallel, and may not be strictly parallel as long as misrecognition may occur as described above. Further, the line referred to here is not limited to the line in the strict meaning, and may not be the line strictly as long as there is a possibility that the same may be misrecognized. Further, the same as the width of the dividing line mentioned here is not limited to the same width as the dividing line in a strict sense, and if there is a possibility of misrecognition as above, the dividing line strictly It does not have to be the same width as.

The non-section line area mentioned below is an area sandwiched between a plurality of low luminance areas on the road surface, and is an area substantially parallel to the section line which may be erroneously recognized as a section line.
Such a characteristic is present in the photographed image of the traveling road. Therefore, in the present embodiment, the ECU 30 is configured to appropriately detect a traveling lane line regardless of the difference in the luminance of the lane line by executing a detection process described later. Further, the ECU 30 is configured to determine a non-section line area and a section line due to a repair mark or the like by executing detection processing.

[2. processing]
[2-1. Detection process]
Next, the detection process executed by the ECU 30 will be described using the flowchart of FIG. The detection processing represents a processing procedure for recognizing and outputting a traveling lane line based on the feature in the photographed image of the traveling road described above. This detection process is repeatedly executed at shooting time intervals of the camera 11-14.

First, in step (hereinafter, referred to as S) 10, the ECU 30 acquires a camera image captured by the camera 11-14, and converts the acquired camera image into a digital signal by sampling.

In S20, the ECU 30 converts the four camera images converted into digital signals into a bird's-eye view seen from a preset virtual viewpoint and combines them, and generates a bird's-eye view image of the surroundings of the vehicle 70.

In S30, the ECU 30 recognizes a traveling division line from the bird's-eye view image generated in step S20 by executing recognition processing. Details of the recognition process will be described later.
In S40, the ECU 30 estimates traveling path parameters of the traveling lane lines recognized in the recognition process. Then, the ECU 30 outputs traveling path parameters to the vehicle control device 50 via the in-vehicle network as a recognition result of the traveling lane lines. The travel path parameters may include, for example, the curvature of the dividing line, the width of the lane, the angle between the traveling direction of the vehicle 70 and the tangential direction of the dividing line, and the like. The ECU 30 ends the present recognition process as described above.

In the above embodiment, S10 corresponds to the processing by the input processing unit 31, S20 corresponds to the processing by the combining processing unit 32, S30 corresponds to the processing by the recognition processing unit 33, and S40 by the output processing unit 34. It corresponds to processing.

[2-2. Recognition processing]
Next, the processing procedure of the recognition process executed by the ECU 30 in S30 of the detection process will be described using the flowchart of FIG. 7.

First, in S100, a photographed image is acquired. The photographed image referred to here is an image photographed by at least one camera 10 mounted on the vehicle 70 and is an image including a traveling path. Specifically, the ECU 30 acquires the bird's-eye view image generated in S20 as a photographed image.

In S110, the ECU 30 extracts line candidates from the captured image based on the edge points in the captured image. The line candidate is a candidate for a dividing line that divides the lane. The change threshold when extracting an edge point is stored in advance in the memory 42.

Specifically, the ECU 30 applies the sobel filter or the like to the bird's-eye view image acquired in S100 to detect an edge point. Then, the ECU 30 applies a Hough transform or the like to the detected edge point to detect a straight line, and extracts the detected straight line as a line candidate. The ECU 30 extracts line candidates on each of the left side and the right side of the vehicle 70. As the extracted line candidate, a line candidate existing in a predetermined range may be extracted from the vehicle 70. Specifically, since line candidates existing outside the predetermined range from the vehicle 70 have a high probability of being adjacent lanes, the processing load can be reduced by excluding such line candidates. .

In S120, the ECU 30 acquires the luminance of the line candidate. The luminance of the line candidate is the luminance value of the line candidate extracted in S110. Specifically, in the bird's-eye view image, the ECU 30 calculates the average value of the luminance values for all the pixels included in the line candidate, and acquires the average value as the luminance of the line candidate. However, the method of calculating the luminance of the line candidate is not limited to this. The ECU 30 may be configured to calculate an average value of luminance values for any of a plurality of pixels included in the line candidate, and acquire the average value as the luminance of the line candidate. When there are a plurality of line candidates on each of the left side and the right side of the vehicle 70, the ECU 30 acquires the luminance of the line candidate for each of the plurality of line candidates.

In S130, the ECU 30 acquires a luminance threshold. The luminance threshold is a predetermined value, and is a value used to discriminate between the dividing line and the non-dividing line area. The luminance threshold is stored in the memory 42 as described later.

In S140, the ECU 30 determines whether the brightness of the traveling path around the vehicle 70 (hereinafter, the periphery of the vehicle) satisfies a predetermined condition. Here, the brightness of the traveling path around the vehicle may include the brightness around the vehicle 70 in addition to the brightness of the traveling path itself around the vehicle 70. Below, the brightness of the traveling path around the vehicle is simply referred to as the brightness of the traveling path. The ECU 30 shifts the processing to S150 when the brightness of the travel path satisfies the predetermined condition, and shifts the processing to S160 when the brightness of the travel path does not satisfy the predetermined condition.

The present S140 is a process for determining whether or not S160-S180 and S240-S250 described later are not to be executed. The processes of S160 to S180 are processes for excluding line candidates which are line candidates and whose luminance is less than the luminance threshold, from the section candidates, as described later. The processes of S240 to S250 are processes for updating the luminance threshold as described later.

In the present embodiment, the brightness of the traveling road is such brightness that the difference between the brightness of the dividing line and the brightness of the road surface is less than a predetermined threshold (hereinafter referred to as bright threshold) (hereinafter referred to as bright condition). It is taken as a predetermined condition. For example, a concrete running path at the time of clear weather may be mentioned as an example where the brightness of the running path satisfies the bright condition. In this case, due to the influence of sunlight, the brightness of the road surface may have the same size as the brightness of the dividing line such as a white line or a yellow line. That is, the difference between the luminance of the road surface and the luminance of the dividing line such as a white line or a yellow line can be less than the bright threshold. The bright threshold referred to here may be a value sufficiently smaller than, for example, the brightness of the road surface or the brightness of the dividing line, such as close to zero.

Furthermore, in the present embodiment, the brightness of the road is such that the difference between the brightness of the low brightness area and the brightness of the road surface is less than a predetermined threshold (hereinafter referred to as dark threshold) (hereinafter referred to as dark condition) ,) As the above predetermined condition. For example, a traveling path at night, a traveling path in a tunnel, etc. may be mentioned as an example where the brightness of the traveling path satisfies the dark condition. In this case, the road surface may have the same brightness as the repair mark. That is, the difference between the brightness of the road surface and the brightness of a low brightness area such as a repair mark can be less than the dark threshold. The dark threshold referred to here may be, for example, a value close to 0, which is sufficiently smaller than the brightness of the road surface and the brightness of a repair mark. The bright threshold and the dark threshold may be the same value. The light threshold and the dark threshold may be confirmed by experiment or the like.

Specifically, in this step, the ECU 30 determines that the brightness of the traveling path does not satisfy the predetermined condition if the brightness threshold value acquired in S130 is a value within the predetermined range in this step. In other words, as shown in FIG. 8, when the acquired luminance threshold is equal to or higher than the predetermined upper threshold or when the acquired luminance threshold is less than the predetermined lower threshold smaller than the upper threshold, It is determined that the brightness of the travel path satisfies the predetermined condition.

As will be described later, the luminance threshold is a value proportional to a value based on the luminance of a travel lane line recognized in the past. That is, the brightness threshold is a large value when the brightness of the traveling path is sufficiently bright to satisfy the light condition. In addition, the brightness threshold is a small value when the brightness of the traveling path is sufficiently dark to satisfy the dark condition.

Therefore, in this step, the ECU 30 determines whether the brightness of the traveling path satisfies the predetermined condition based on whether the luminance threshold is within the predetermined range. That is, when the luminance threshold is equal to or higher than the upper threshold, it is determined that the brightness of the travel path satisfies the bright condition. That is, it is determined that the brightness of the travel path satisfies the predetermined condition. When the brightness threshold is less than the lower limit threshold, it is determined that the brightness of the travel path satisfies the dark condition. That is, it is determined that the brightness of the travel path satisfies the predetermined condition. The upper limit threshold and the lower limit threshold for representing the predetermined range here are predetermined by experiments or the like, and are stored in the memory 42.

At S150, the ECU 30 sets all line candidates detected at S110 as section candidates to be described later, as an exception to the processing at S160-S180. Then, the ECU 30 shifts the process to S190.

In S160, the ECU 30 obtains the luminance of the line candidate for each of the line candidates, and determines whether the luminance of the line candidate is equal to or greater than the luminance threshold. Here, the ECU 30 shifts the processing to S170 when the luminance of the line candidate is equal to or higher than the luminance threshold. Then, in S170, the ECU 30 sets a line candidate determined to be equal to or higher than the luminance threshold in S160 as a section candidate, and shifts the processing to S180. On the other hand, when the luminance of the line candidate is less than the luminance threshold, the ECU 30 shifts the processing to S180.

As will be described later, the luminance threshold is a value proportional to a value based on the luminance of a travel lane line recognized in the past. In addition, the brightness threshold value is a value close to the brightness of the travel lane lines recognized in the past, and is a value smaller than the brightness of the travel lane lines recognized in the past.

For this reason, as shown in FIG. 8, that the luminance of the line candidate is equal to or higher than the luminance threshold means that it is more likely to be a traveling section line. That is, the section candidate is more likely to be a running section line. In other words, the fact that the luminance of the line candidate is equal to or greater than the luminance threshold means that it is not a non-section line area. The process of S160 is a process for determining a non-partitioning line area from among a plurality of line candidates by comparing the brightness of the line candidate with the brightness threshold.

In S180, the ECU 30 repeats the processing of S160 to S180 until the determination of S160 is performed for each of all the line candidates detected in S110. The ECU 30 shifts the processing to S190 when the determination of S160 is performed for all the line candidates detected in S110.

In S190, the ECU 30 determines in S150 or S170 whether a plurality of section candidates are set. The ECU 30 shifts the processing to S200 when one segment candidate is set, and shifts the processing to S210 when a plurality of segment candidates are set.

In S200, when one section candidate is set, the ECU 30 determines the section candidate as a traveling section line. Then, the ECU 30 shifts the process to S220.
In S210, when a plurality of section candidates are set, the ECU 30 determines a section candidate closest to the vehicle 70 among the plurality of section candidates as a travel section line. Then, the ECU 30 shifts the process to S220. The ECU 30 determines travel division lines on the right and left sides of the vehicle 70, respectively. That is, the ECU 30 determines a pair of travel division lines estimated to represent the left and right boundaries of the travel path of the vehicle 70. However, the ECU 30 is not limited to this, and may be configured to determine the travel division line on at least one of the right side and the left side of the vehicle 70.

The ECU 30 stores the traveling division line luminance in the memory 42 at S220. The traveling parting line luminance is the luminance of the traveling parting line determined in S200 or S210. Specifically, among the luminances of the line candidates acquired in S120, the luminances of the line candidates determined as the traveling division lines are used as the traveling division line luminances.

In S230, the ECU 30 determines whether the brightness of the travel path satisfies the predetermined condition, as in S140. The ECU 30 ends the recognition process when the brightness of the travel path satisfies the predetermined condition, and shifts the process to S240 when the brightness of the travel path does not satisfy the predetermined condition.

However, unlike the step S140 in this step, the ECU 30 does not satisfy the predetermined condition when the brightness of the traveling path satisfies the predetermined condition when the traveling division line luminance stored in the memory 42 in S220 is within the predetermined value. to decide. Specifically, the ECU 30 determines that the brightness of the traveling path satisfies the predetermined condition when the traveling division line luminance is equal to or higher than a predetermined first threshold. Further, the ECU 30 determines that the brightness of the traveling path satisfies the predetermined condition when the traveling lane line luminance is less than a second threshold smaller than the first threshold.

The first threshold and the second threshold are predetermined by experiment or the like, and are stored in the memory 42. The first threshold is a value corresponding to the upper limit threshold, and the second threshold is a value corresponding to the lower limit threshold.

The ECU 30 calculates an average brightness at S240. The average luminance is an average value of a plurality of past luminances. The past luminance is the traveling part line luminance accumulated in the memory 42 in the past. Here, an average value of a plurality of past luminances accumulated in the memory 42 in the most recent predetermined past period is calculated as the average luminance.

The ECU 30 calculates a reference value in S250. The reference value is a value obtained by multiplying the average luminance by a predetermined multiple α. The multiple α is a value less than 1 and may be set to a value such as 0.7 to 0.8. However, the multiple α is not limited to this, and may be appropriately set based on an experiment or the like. Then, the ECU 30 re-stores the calculated reference value in the memory 42 as a new brightness threshold. The ECU 30 ends the present recognition process as described above.

[3. effect]
According to the first embodiment described above, the following effects can be obtained.
(3a) The ECU 30 repeatedly acquires the captured image, and in S110, extracts at least one line candidate from the captured image based on the edge point in the captured image. In S160, the ECU 30 determines, for each of at least one line candidate, whether or not the brightness of the line candidate is equal to or greater than the brightness threshold, and sets one having the brightness of the line candidate equal to or greater than the brightness threshold as a section candidate. In step S210, the ECU 30 recognizes a section candidate closest to the vehicle 70 as a traveling section line when there are a plurality of section candidates. The ECU 30 outputs a recognition result in S40.

As a result, when a plurality of section candidates are detected, the section candidate closest to the vehicle 70 is identified as a traveling section line, so that the traveling section line is properly detected regardless of the difference in the luminance of the section line. be able to.

In addition, since the line candidate whose luminance is less than the luminance threshold is not set as a section candidate, the non-section line area and the section line can be discriminated. That is, it is suppressed that a non-section line area is mistakenly extracted as a section candidate. As a result, it is possible to appropriately detect a traveling division line from among the division candidates.

(3b) The ECU 30 stores the traveling division line luminance in the memory 42 in S220 each time the traveling division line is recognized in S210. The ECU 30 calculates an average luminance, which is an average value of a plurality of past luminances, and calculates a reference value smaller than the average luminance every time the traveling lane line luminance is stored in the memory 42 at S250. The value is stored back in the memory 42 as a new luminance threshold. In S160, the ECU 30 acquires the luminance threshold value thus stored in the memory 42, and makes a determination using the luminance threshold value.

That is, since the luminance threshold is set based on the luminances of a plurality of travel markings recognized in the past, an appropriate luminance threshold is set that reflects the change in the brightness of the environment around the vehicle 70 which changes from moment to moment. Be done. In addition, since the luminance threshold is appropriately set, it is possible to suppress that a non-section line area due to a repair mark or the like is erroneously extracted as a section candidate. As a result, it is possible to properly detect the traveling lanes.

(3c) In S140 or S230, the ECU 30 is configured to determine whether the brightness of the travel path around the vehicle satisfies the predetermined condition. As a result, processing can be performed according to the brightness of the travel path around the vehicle.

(3d) In S250, when it is determined in S250 that the brightness of the traveling path satisfies the predetermined condition in S250, the ECU 30 stops storing the reference value in the memory 42 as a new brightness threshold.

That is, for example, when the bright condition is satisfied and the irradiation light by the sun is strong and the travel route is very bright, or when the dark condition is satisfied and the travel route is very dark in the tunnel or at night, etc. , The brightness threshold is not updated using the reference value. The reference value is, as described above, a value based on the luminance of the travel lane lines recognized in the past. The reference value is a large value when the brightness of the travel path is bright, and is a small value when the brightness of the travel path is dark.

Here, if the brightness threshold is updated using the reference value when the travel path is bright enough to satisfy the bright condition, the brightness threshold may be set to a value larger than the brightness of the normal yellow line. On the other hand, when the brightness threshold is updated using the reference value when the travel path is dark to the extent that the dark condition is satisfied, the brightness threshold is set to a value smaller than the brightness of a low brightness area such as a repair mark There is a fear. In the former case, the yellow line may not be extracted as a section candidate. In the latter case, the low luminance region may be extracted as a section candidate.

In the present embodiment, when it is determined that the brightness of the travel path satisfies the predetermined condition, the brightness threshold is not updated using the reference value. As a result, it is possible to suppress that the yellow line is not extracted as a section candidate based on the luminance threshold. Further, based on the luminance threshold value, extraction of a low luminance area as a section candidate can be suppressed.

(3e) In S210, when it is determined that the brightness of the traveling path satisfies the predetermined condition in S210, the ECU 30 is at least one line candidate extracted in S110 and among all the line candidates The line candidate closest to the vehicle 70 is recognized as a travel division line.

That is, when it is determined that the brightness of the traveling path satisfies the predetermined condition, the division candidate extraction based on the luminance threshold is not performed, and the line candidate closest to the vehicle 70 among all the line candidates is traveled. Recognized as a dividing line. As described above, when it is determined that the brightness of the traveling path satisfies the predetermined condition, the luminance threshold is not appropriately set, and therefore, there is a possibility that the section candidate may not be appropriately extracted. Therefore, in this embodiment, extraction of a section candidate is stopped in such a case. As a result, erroneous recognition of the travel lane lines based on the lane candidates is suppressed.

(3f) The ECU 30 determines in S140 or S230 that the predetermined condition is that the brightness of the traveling road is such that the difference between the brightness of the dividing line and the brightness of the road surface is less than a predetermined bright threshold. , Is configured to make a decision.

That is, when the difference between the luminance of the dividing line and the luminance of the road surface is smaller than the bright threshold, for example, processing such as stopping extraction of a section candidate or stopping updating of the luminance threshold can be performed. In addition, when the difference between the luminance of the demarcation line and the luminance of the road surface is less than the bright threshold, it is possible to stop the output of the recognition result. As a result, it is possible to suppress misrecognition of the travel lane lines. In addition, it is possible to suppress the output of an erroneous recognition result.

(3g) In S140 or S230, the ECU 30 determines that the brightness of the traveling path is such that the difference between the brightness of the low brightness area and the brightness of the road surface is less than a predetermined dark threshold. As, it is configured to make a decision.

That is, when the difference between the brightness of the low brightness area and the brightness of the road surface is less than the dark threshold, for example, processing such as stopping extraction of a section candidate or stopping updating of the brightness threshold can be performed. In addition, when the difference between the brightness of the low brightness area and the brightness of the road surface is less than the dark threshold, it is possible to stop the output of the recognition result. As a result, it is possible to suppress misrecognition of the travel lane lines. In addition, it is possible to suppress the output of an erroneous recognition result.

(3h) In S140, the ECU 30 determines that the brightness of the traveling path satisfies the predetermined condition when the luminance threshold is equal to or higher than the predetermined upper limit threshold in S140. Further, in S140, the ECU 30 determines that the brightness of the traveling path satisfies the predetermined condition in S140 if the brightness threshold is less than the predetermined lower limit threshold smaller than the upper limit threshold. As a result, in order to detect the brightness of the traveling path, it is easily determined whether the brightness of the traveling path satisfies the predetermined condition without providing a new configuration such as an illuminance sensor or the like. Can.

(3i) In S230, the ECU 30 determines that the brightness of the traveling path satisfies the predetermined condition when the traveling lane line luminance is equal to or higher than a predetermined first threshold value in S230. Further, in step S230, the ECU 30 determines that the brightness of the traveling path satisfies the predetermined condition when the traveling division line luminance is less than a second threshold smaller than the first threshold. As a result, the same effect as the above (3h) can be obtained.

In the above embodiment, the ECU 30 corresponds to a detection device, and the memory 42 corresponds to a storage unit. Also, S40 corresponds to the processing by the output unit, S100 corresponds to the processing by the image acquisition unit, S110 corresponds to the processing by the candidate extraction unit, S140 and S230 correspond to the processing by the environment judgment unit, and S160 represents the luminance. It corresponds to the processing by the judgment unit. Further, S190 corresponds to the processing by the multiple judgment unit, S210 corresponds to the processing by the recognition unit, S220 corresponds to the processing by the storage unit, and S250 corresponds to the processing by the updating unit.

Further, a bird's-eye view image corresponds to a photographed image, and an edge point corresponds to a feature point. Further, each of the bright condition and the dark condition corresponds to a predetermined condition.
[4. Other embodiments]
As mentioned above, although embodiment of this indication was described, this indication can be variously deformed and implemented, without being limited to the above-mentioned embodiment.

(4a) In the above embodiment, based on whether or not the brightness threshold value is within the predetermined range in S140, based on whether or not the travel division line degree is within the predetermined range in S230, It has been determined whether the brightness satisfies the predetermined condition. However, the present disclosure is not limited to this.

For example, in the vehicle 70, an illuminance sensor that detects ambient brightness may be mounted as a sensor of the sensor group 20. The ECU 30 may be configured to determine that the brightness of the traveling path satisfies the predetermined condition when the sensor value of the illuminance sensor is equal to or greater than the predetermined first illuminance threshold. Further, when the sensor value of the illuminance sensor is less than a second illuminance threshold which is a value smaller than the first illuminance threshold, the ECU 30 assumes that the brightness of the traveling path satisfies the predetermined condition. It may be configured to make a decision.

For example, in the vehicle 70, a GPS device may be mounted as a sensor of the sensor group 20, and a map database storing map data may be mounted. When the ECU 30 determines that the current position of the vehicle 70 is in the tunnel based on the detection result of the GPS device and the map data, it is assumed that the brightness of the traveling path satisfies the predetermined condition. It may be configured to make a decision.

(4b) As described above, when it is determined that the brightness of the travel path satisfies the predetermined condition, the brightness threshold is not appropriately set, and there is a possibility that the travel division line may not be properly determined. Therefore, the ECU 30 may be configured to stop the output of the recognition result when it is determined in S40 that the brightness of the traveling path satisfies the predetermined condition in S40. As a result, it is possible to suppress output of an erroneous recognition result. In addition, it is possible to suppress erroneous vehicle control from being performed based on an erroneous traveling path parameter.

(4c) In the above embodiment, the ECU 30 is configured to recognize the traveling division line from the bird's-eye view image using the bird's-eye view image generated based on the camera image by the camera 11-14 as the shot image. The image is not limited to a bird's eye view image. For example, as shown in FIG. 9, one camera 10 may be mounted on a vehicle so as to capture a road surface ahead of the vehicle 70. Specifically, the camera 10 is mounted on the center front side of the vehicle 70, and as shown in FIG. 9, it is configured to photograph an area extending in a predetermined angle range toward the front of the vehicle 70 It is also good. And ECU30 detects an edge point from the photography picture photoed with the camera 10 like the above-mentioned embodiment, and based on an edge point, it may be constituted so that a run division line may be recognized from the photography picture. good.

(4d) The plurality of functions of one component in the above embodiment may be realized by a plurality of components, or one function of one component may be realized by a plurality of components . Also, a plurality of functions possessed by a plurality of components may be realized by one component, or one function realized by a plurality of components may be realized by one component. In addition, part of the configuration of the above embodiment may be omitted. In addition, at least a part of the configuration of the above embodiment may be added to or replaced with the configuration of the other above embodiment. In addition, all the aspects contained in the technical thought specified from the wording described in the claim are an embodiment of this indication.

(4e) In addition to the above-described ECU 30 and the driving support system 1, a program for causing the ECU 30 to function, a non-transient actual recording medium such as a semiconductor memory recording this program, a dividing line detection method, etc. Disclosure can also be realized.

Claims

A detection device (30) mounted on a vehicle (70),
An image acquisition unit configured to repeatedly acquire an image captured by at least one camera (10) mounted on the vehicle, the captured image including a travel path being a road on which the vehicle travels (S100 )When,
At least one line candidate which is a candidate of a dividing line for dividing a lane is extracted from the photographed image based on a feature point which is a point at which luminance changes by a predetermined change threshold or more between adjacent pixels in the photographed image. A candidate extraction unit (S110) configured as
A luminance determination unit (S160) configured to acquire the luminance of the line candidate for each of the line candidates and determine whether the luminance of the line candidate is equal to or greater than a predetermined luminance threshold;
A plurality of judgment units (S190) configured to judge whether there are a plurality of division candidates which are the line candidates and the luminance judgment unit judges that the luminance of the line candidate is equal to or higher than the luminance threshold;
When it is determined by the plurality of determination units that there is a plurality of the section candidates, a running section that is a section line that divides a lane in which the vehicle travels is a section candidate closest to the vehicle among the plurality of section candidates A recognition unit (S210) configured to recognize as a line;
An output unit (S40) configured to output a recognition result by the recognition unit;
A detection device comprising:
The detection device according to claim 1, wherein
A storage unit (S220) configured to store, in the storage unit (42), the traveling division line luminance that is the luminance of the traveling division line recognized by the recognition unit;
An average luminance which is an average value of a plurality of past luminances, which is the traveling division line luminance accumulated in the storage section in the past, is acquired, and a value smaller than the average luminance based on the average luminance The update unit (S250) further calculates a reference value and stores the reference value as a new brightness threshold in the storage unit (S250), and the brightness determination unit acquires the brightness threshold from the storage unit, Detection device configured to determine.
The detection device according to claim 2,
An environment determining unit (S140, S230) configured to determine whether the brightness of a traveling path around the vehicle satisfies a predetermined condition;
A detection device further comprising
The detection device according to claim 3,
The updating unit uses the reference value as the new brightness threshold in the storage unit when the environment determining unit (S230) determines that the brightness of the traveling path around the vehicle satisfies the predetermined condition. A detection device configured to stop storing.
A detection device according to claim 3 or claim 4, wherein
The recognition unit is configured to select all the at least one extracted by the candidate extraction unit when it is determined by the environment determination unit (S140) that the brightness of the traveling path around the vehicle satisfies the predetermined condition. A detection device configured to recognize a line candidate closest to the vehicle among line candidates as the travel division line.
The detection device according to any one of claims 3 to 5, wherein
The environment determining unit may set the predetermined condition that the brightness of the traveling path around the vehicle is such that the difference between the brightness of the dividing line and the brightness of the road surface is less than a predetermined bright threshold. Detection device configured to determine.
A detection device according to any one of claims 3 to 6, wherein
The environment determining unit may set the predetermined condition that the brightness of the traveling path around the vehicle is such that the difference between the brightness of the low brightness area and the brightness of the road surface is less than a predetermined dark threshold. Configured to make decisions,
The low luminance region is each of a plurality of linear regions positioned on the road surface so as to be parallel to the division line, and is a region having lower luminance than the road surface. apparatus.