JP2009169618A - Roadside interface detection device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a roadside interface detection device for detecting the interface between a road and a roadside by simple configurations. <P>SOLUTION: The roadside interface detection device includes: an imaging means for taking either the front part or rear part of a vehicle or both parts; a feature point detection means for detecting a feature point indicating the shape of an object included in an image obtained by imaging by the imaging means; and an interface specification means for specifying the interface of a road on which the vehicle is traveling and a roadside based on the distribution state of the feature points detected by the feature point detection means. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a roadside boundary surface detection device, and more particularly to a roadside boundary surface detection device that detects a road and a roadside boundary surface from an image captured by a camera or the like.

  In recent years, in order to determine the risk of accidents such as vehicle collisions and deviations from the road, and to automatically avoid these accidents, the vehicle is detected by detecting the interface between the road and the roadside from the captured images. Techniques for recognizing the range of roads that can be driven have been proposed.

For example, in Patent Document 1, the outside of a vehicle is imaged by a stereo optical system including a plurality of cameras, the image captured by the stereo optical system is processed to calculate a distance distribution over the entire image, and the calculated distance distribution A technique is disclosed in which the three-dimensional position of each part of the subject corresponding to the information is calculated, and the shape and side walls of the road are detected using the three-dimensional position information.
JP-A-6-266828

  However, the technique disclosed in Patent Document 1 requires a distance measuring mechanism such as a stereo optical system including a plurality of cameras in order to obtain a distance distribution, and there is a problem that the apparatus configuration becomes complicated.

  The present invention has been made to solve the above-described problems, and an object of the present invention is to provide a road-side boundary surface detection device that can detect a road-road boundary surface with a simple configuration.

  In order to achieve the above object, the invention described in claim 1 is included in the image from an imaging unit that images one or both of the front and rear of the vehicle, and an image obtained by imaging by the imaging unit. A feature point detecting means for detecting a feature point indicating the shape of an object to be detected, and a boundary for identifying a road and a roadside boundary surface on which the vehicle travels based on a distribution state of the feature points detected by the feature point detecting means And surface specifying means.

  According to the first aspect of the present invention, one or both of the front and rear of the vehicle is imaged by the imaging means, and the object included in the image from the image obtained by the imaging by the imaging means by the feature point detection means The feature point indicating the shape of the vehicle is detected, and the boundary surface specifying unit specifies the road surface on which the vehicle travels and the road side boundary surface based on the distribution state of the feature point detected by the feature point detecting unit.

  As described above, according to the first aspect of the present invention, the feature points indicating the shape of the object included in the image are detected from the image obtained by imaging, and based on the distribution state of the detected feature points, Since the boundary between the road on which the vehicle runs and the roadside is specified, the boundary between the road and the roadside can be detected with a simple configuration without providing a distance measuring mechanism such as a stereo optical system.

  The feature point detection means of the present invention performs edge detection on an image obtained by imaging by the imaging means as in the second aspect of the invention, and detects an edge of an object included in the image as the feature point. A point may be detected.

  Further, the present invention, as in the invention of claim 3, further comprises a feature point extracting means for extracting a feature point by a columnar object existing on the road side from the feature points detected by the feature point detecting means, The boundary surface specifying unit may specify the boundary surface based on the distribution state of the feature points extracted by the feature point extracting unit.

  According to a third aspect of the present invention, the feature point extracting means groups the feature points successively arranged in the vertical direction from the feature points detected by the detecting means, as in the fourth aspect of the invention. The feature points by the columnar object may be extracted by extracting the grouped feature points.

  Further, the boundary surface specifying means of the present invention, as in the fifth aspect of the present invention, sets a predetermined position corresponding to a vanishing point at which the road disappears in an image obtained by imaging by the imaging means as an origin. Based on the distribution state of the feature points in a region between the two lines while changing the angle of the two lines extending from the origin within a predetermined angle range from the origin, The boundary surface may be specified.

  According to a fifth aspect of the invention, as in the sixth aspect of the invention, the road area is identified from an image obtained by imaging by the imaging means, and the position of the vanishing point at which the road disappears is estimated. A vanishing point estimating unit may be further provided, and the boundary surface specifying unit may specify the boundary surface using the position of the vanishing point estimated by the vanishing point estimating unit as an origin.

  As described above, according to the present invention, the feature point indicating the shape of the object included in the image is detected from the image obtained by imaging, and the vehicle is detected based on the distribution state of the detected feature point. Since the boundary surface between the road and the road side is specified, it has an excellent effect that the boundary surface between the road and the road side can be detected with a simple configuration.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Hereinafter, a case where the present invention is applied to a driver support device that is mounted on a vehicle and that supports driving of a driver will be described as an example.

  [First Embodiment]

  FIG. 1 shows a schematic configuration of a driver support apparatus 10 according to the present embodiment.

  As illustrated in FIG. 1, the driver support device 10 performs various operations based on a camera 12 that continuously captures a predetermined detection target area, a display 14 that displays various types of information, and an image obtained by imaging with the camera 12. And an apparatus main body 20 that performs the warning.

  The camera 12 according to the present embodiment is attached to the front side of the vehicle, such as a front grill or a bumper of the vehicle, and images the front of the vehicle.

  As shown in FIG. 1, the apparatus main body 20 includes a CPU (Central Processing Unit) 22 that controls the operation of the entire driver support apparatus 10, and a RAM (Random Access Memory) used as a work area when the CPU 22 executes various processing programs. ) 24, a ROM (Read Only Memory) 26 in which various control programs including various boundary surface detection processing programs, which will be described later, various parameters, and the like are stored in advance, an HDD (Hard Disk Drive) 28 in which various information is stored, A camera control unit 30 that controls the shooting operation of the camera 12, a display control unit 32 that controls display of various information such as a screen and a message on the display 14, and a speaker 34 that warns the driver. ing.

  The CPU 22, RAM 24, ROM 26, HDD 28, camera control unit 30, display control unit 32, and speaker 34 are connected to each other via the system bus BUS.

  Accordingly, the CPU 22 accesses the RAM 24, the ROM 26, and the HDD 28, controls the photographing operation of the camera 12 through the camera control unit 30, controls the display of various information on the display 14 through the display control unit 32, and the speaker. The control of the sound output from 34 can be performed respectively.

  FIG. 2 is a functional block diagram showing a functional configuration of the driver support apparatus 10 according to the present embodiment.

  As shown in the figure, the driver support apparatus 10 includes a boundary surface detection unit 50 and a warning display control unit 58.

  The camera control unit 30 is connected to the boundary surface detection unit 50 and the warning display control unit 58, and sequentially outputs image data indicating images obtained by photographing with the camera 12.

  As shown in the figure, the boundary surface detection unit 50 includes a feature point detection unit 52 and a boundary surface specification unit 56.

  The feature point detection unit 52 is connected to the camera control unit 30 and the boundary surface specification unit 56, and image data is sequentially input from the camera control unit 30.

  When the image data is input from the camera control unit 30, the feature point detection unit 52 detects a feature point indicating the shape of the object included in the image from the image indicated by the image data. In the embodiment, edge detection is performed on an image obtained by imaging using a differential filter (for example, a Sobel filter) to detect a vertical edge point of an object included in the image as a feature point. In the present embodiment, the vertical edge point is detected as the feature point, but the present invention is not limited to this as long as it represents the shape and contour of the object.

  The boundary surface specifying unit 56 is connected to the warning display control unit 58.

  The boundary surface specifying unit 56 specifies the road surface on which the vehicle travels and the road side boundary surface based on the distribution state of the vertical edge points detected by the feature point detecting unit 52. In this embodiment, the boundary surface specifying unit 56 performs imaging. With the predetermined position corresponding to the vanishing point at which the road of the image obtained by the above disappears as the origin, the angle of two straight lines extending from the origin within the predetermined angle range from the origin is changed. A boundary surface is specified based on the distribution state of the vertical edge points in the region between the straight lines.

  The warning display control unit 58 is connected to the display 14 and the speaker 34, and image data is sequentially input from the camera control unit 30, and position information indicating the position of the boundary surface is input from the boundary surface specifying unit 56.

  The warning display control unit 58 causes the display 14 to display images indicated by image data sequentially input from the camera control unit 30. The warning display control unit 58 obtains the distance between the road on which the vehicle travels, the road-side boundary surface, and the vehicle based on the position information input from the boundary surface specifying unit 56, and the distance between the boundary surface and the vehicle is determined. When the threshold value is below a predetermined threshold value, the display form of the boundary surface indicated by the position information displayed on the display 14 is changed (for example, the boundary surface is displayed in red), and a warning is issued to the driver. It is supposed to let you. At this time, a warning sound, a warning message, or the like may be output from the speaker 34.

  By the way, the process by each component (the boundary surface detection part 50 (the feature point detection part 52, the boundary surface specific part 56) and the warning display control part 58) of the driver assistance apparatus 10 comprised as mentioned above performs a program. By doing so, it can be realized by a software configuration using a computer. However, the present invention is not limited to realization by a software configuration, and needless to say, it can also be realized by a hardware configuration or a combination of a hardware configuration and a software configuration.

  Below, the case where the driver assistance apparatus 10 which concerns on this Embodiment implement | achieves the process by said each component by executing a boundary surface detection processing program is demonstrated. In this case, the boundary surface detection processing program is installed in advance in the ROM 26 or HDD 28, provided in a state stored in a computer-readable recording medium, or distributed via wired or wireless communication means. The form etc. which can be applied are applicable.

  Next, with reference to FIG. 3, the operation of the driver support apparatus 10 according to the present embodiment will be described. FIG. 3 is a flowchart showing the flow of processing of the boundary surface detection processing program executed by the CPU 22. The boundary surface detection processing program is executed by the CPU 22 when a processing start instruction signal is received from a vehicle control device (not shown), for example, when an engine switch of a vehicle on which the driver assistance device 10 is mounted is turned on.

  In step 100 in the figure, input of image data from the camera control unit 30 is waited.

  In the next step 102, edge detection is performed based on the change in the density value of the image indicated by the input image data, and the vertical edge point of the object included in the image is detected.

  In FIG. 4, vertical edge points detected as a result of performing edge detection on the image indicated by the input image data are indicated by “x” marks.

  In the next step 106, a predetermined position corresponding to the vanishing point where the linear road of the image obtained by imaging disappears is defined as the origin C, and a predetermined boundary surface is predicted from the origin C. Two straight lines extending from the origin C are determined within the specified angle range.

  In the next step 108, the number of edge points and the edge point density are derived as values indicating the distribution state of the vertical edge points in the region between the two straight lines.

  Here, in the present embodiment, as shown in FIG. 4, an angle range in which a boundary surface is expected to exist and two straight lines are defined by a predetermined reference straight line extending from the origin C (in this embodiment, the origin C The angle range that is defined by the angle θ with respect to the vertical line and is predicted to have a boundary surface is represented as {θmin, θmax} (θmin ≦ θmax (for example, θmin = 30 °, θmax = 85 °)). The two straight lines extending from the origin C are represented as a straight line (θb) and a straight line (θt) (θmin ≦ θb <θt ≦ θmax).

  In the present embodiment, the angle between the two straight lines (θb) and (θt) is changed within the angle range {θmin, θmax}, and the region is between the straight lines (θb) and (θt). The number of edge points C (θb, θt) and the edge point density D (θb, θt) are derived. In the present embodiment, for example, first, θb = θmin is first determined by the processing of step 106 and step 108, and θt is determined by changing the angle by a predetermined angle (for example, 1 °) within the range of θb to θmax. Thus, the number of edge points C (θb, θt) and the edge point density D (θb, θt) in the region between the straight line (θb) and the straight line (θt) are derived, and the range between θb and θmax is derived. When derivation of the number of edge points C (θb, θt) and edge point density D (θb, θt) is completed at all the predetermined angles, θb is changed by the predetermined angle and again in the range of θb to θmax. By determining θt and obtaining the number of edge points C (θb, θt) and the edge point density D (θb, θt) until θb = θmax, the predetermined angle is set in the angle range {θmin, θmax}. Edge points C (θb, θt) in all areas circumference is different and the edge point densities D (θb, θt) is derived and.

  In the next step 110, it is determined whether or not the number of edge points C (θb, θt) and the edge point density D (θb, θt) are derived in all regions having different ranges by a predetermined angle, and an affirmative determination is made. In this case, the process proceeds to step 112, while the process proceeds to step 106 where a negative determination is made.

  In the next step 112, an evaluation value F (θb, θt) is calculated from the derived number of edge points C (θb, θt) and edge point density D in each region using the following equation (1), and the evaluation value F .Theta.b and .theta.t at which is maximized.

  F (θb, θt) = α × C (θb, θt) + β × D (θb, θt) (1)

  Where α and β are constants

  Note that α and β may be appropriately determined by experiments using a real machine, computer simulation, or the like.

  Θb and θt at which the evaluation value F is maximum indicate the position of the road and the boundary surface on the road side where the vehicle travels.

  In the next step 114, the distance between the boundary surface and the vehicle is obtained based on θb and θt specified in step 112 above.

  In the next step 116, together with the image indicated by the image data input from the camera control unit 30 on the display 14, when the distance between the boundary surface obtained in step 114 and the vehicle is equal to or smaller than a predetermined threshold value, Generate a warning to the driver.

  Next, in step 120, for example, it is determined whether or not a processing end instruction signal is input from a vehicle control device (not shown) by turning off the engine switch of the vehicle. If the determination is negative, the process proceeds to step 100. On the other hand, if the determination is affirmative, the process of the boundary surface detection processing program ends.

  As described above, according to the present embodiment, feature points indicating the shape of an object included in the image are detected from an image obtained by imaging by the camera 12, and based on the distribution state of the detected feature points. Thus, since the boundary surface between the road on which the vehicle runs and the road side is specified, the boundary surface between the road and the road side can be detected with a simple configuration without providing a distance measuring mechanism such as a stereo optical system.

  [Second Embodiment]

  Since the main configuration of the electric system of the driver assistance apparatus 10 according to the second embodiment is the same as that of the first embodiment (see FIG. 1), the description thereof is omitted.

  FIG. 5 is a functional block diagram showing a functional configuration of the driver support apparatus 10 according to the present embodiment. Note that the same reference numerals as those in FIG. 2 are attached to the same processing portions as those in FIG.

  The boundary surface detection unit 50 according to the present embodiment further includes a feature point extraction unit 54.

  The feature point extraction unit 54 is connected to the feature point detection unit 52 and the boundary surface specification unit 56.

  The feature point extraction unit 54 extracts vertical edge points due to columnar objects existing on the road side from the vertical edge points detected by the feature point detection unit 52. In the present embodiment, the feature point extraction unit 54 detects the feature point detection unit 52. The vertical edge points continuously extracted in the vertical direction from the vertical edge points are grouped, and the vertical edge points by the columnar object are extracted by extracting the grouped vertical edge points.

  The boundary surface specifying unit 56 is connected to the feature point extracting unit 54 and the warning display control unit 58.

  The boundary surface specifying unit 56 specifies the boundary surface based on the distribution state of the vertical edge points extracted by the feature point extracting unit 54.

  Next, with reference to FIG. 6, the flow of processing of the boundary surface detection processing program according to the present embodiment will be described. In the figure, the same processing parts as those in FIG. 3 are denoted by the same reference numerals as those in FIG.

  In step 104, the vertical edge points detected in step 102 are grouped for each vertical edge point continuously arranged in the vertical direction as shown in FIG. 7, and the grouped vertical edge points are columnar objects. Extracted as vertical edge points.

  That is, each vertical edge point detected in step 102 includes a vertical edge point indicating the outline of various objects. Therefore, in the present embodiment, vertical edge points due to columnar objects are specified by grouping vertical edge points that are continuously arranged in the vertical direction (for example, within a range of three pixels).

  In step 108, the number of edge points and the edge point density of the vertical edge points extracted in step 104 in the region between the two straight lines are derived.

  As described above, according to the present embodiment, vertical edge points due to columnar objects are accurately obtained by grouping each vertical edge point continuously arranged in the vertical direction and extracting the grouped vertical edge points. Since it can be detected well, the detection accuracy of the boundary surface between the road and the road is improved.

  In each of the above embodiments, the case where the number of edge points and the edge point density are derived as values indicating the distribution state of the vertical edge points has been described. However, the present invention is not limited to this. Only one of the point densities may be derived, and θb and θt at which the number of edge points or the edge point density becomes the largest value may be specified. Further, the value indicating the distribution state of the vertical edge points is not limited to the number of edge points or the edge point density.

  In each of the above embodiments, the case where the position of the origin C corresponding to the vanishing point is determined in advance has been described. However, the present invention is not limited to this. For example, as shown in FIG. A vanishing point estimation unit 60 that identifies a road region from an image obtained by imaging and estimates the position of the vanishing point at which the road disappears is provided, and the boundary surface identification unit 56 is the vanishing point estimated by the vanishing point estimation unit 60. The boundary surface may be specified using the point position as the origin.

  That is, the vanishing point estimation unit 60 may detect a white line or roadside line of a road from an image obtained by imaging, and obtain a straight line or a curve approximating the detected white line or roadside line to estimate the position of the vanishing point. Good.

  In each of the above embodiments, the case of imaging the front of the vehicle has been described. However, the present invention is not limited to this. For example, it is obtained by imaging the rear of the vehicle or both the front and rear of the vehicle. A feature point indicating the shape of an object included in the image may be detected from the captured image, and a road on which the vehicle travels and a road-side boundary surface may be identified based on the distribution state of the detected feature point. .

  In addition, the main configuration (see FIG. 1) of the electrical system of the driver support apparatus 10 described in the above embodiments and the functional configuration of the driver support apparatus 10 (see FIGS. 2, 5, and 8). ) Is an example, and it is needless to say that changes can be made as appropriate without departing from the gist of the present invention.

  The processing flow of the boundary surface detection processing program (see FIGS. 3 and 6) described in the above embodiments is also an example, and can be changed as appropriate without departing from the gist of the present invention. Needless to say.

It is a block diagram which shows the principal part structure of the electric system of the driver assistance apparatus which concerns on embodiment. It is a block diagram which shows the functional structure of the driver assistance apparatus which concerns on 1st Embodiment. It is a flowchart which shows the flow of a process of the boundary surface detection processing program which concerns on 1st Embodiment. It is a schematic diagram which shows the flow at the time of detecting a boundary surface from the detected vertical edge point which concerns on 1st Embodiment. It is a block diagram which shows the functional structure of the driver assistance apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the flow of a process of the boundary surface detection processing program which concerns on 2nd Embodiment. It is a schematic diagram which shows the flow at the time of detecting a boundary surface from the detected vertical edge point which concerns on 2nd Embodiment. It is a block diagram which shows the other functional structure of a driver assistance apparatus.

Explanation of symbols

10 Driver support device 12 Camera (imaging means)
50 Boundary Surface Detection Unit 52 Feature Point Detection Unit (Feature Point Detection Unit)
54 feature point extraction unit (feature point extraction means)
56 Boundary surface identification part (Boundary surface identification means)
60 Vanishing point estimation unit (vanishing point estimation means)

Claims (6)

Imaging means for imaging one or both of the front and rear of the vehicle;
Feature point detection means for detecting a feature point indicating the shape of an object included in the image from an image obtained by imaging by the imaging means;
Based on the distribution state of the feature points detected by the feature point detection means, boundary surface specifying means for specifying the road surface on which the vehicle travels and the road-side boundary surface;
A roadside boundary surface detection device. The roadside boundary surface detection according to claim 1, wherein the feature point detection means detects an edge point of an object included in the image as the feature point by performing edge detection on an image obtained by imaging by the imaging means. apparatus. A feature point extracting means for extracting a feature point by a columnar object existing on the road side from the feature points detected by the feature point detecting means;
The road-side boundary surface detection device according to claim 1, wherein the boundary surface specifying unit specifies the boundary surface based on a distribution state of feature points extracted by the feature point extraction unit. The feature point extracting unit groups feature points that are continuously arranged in the vertical direction from the feature points detected by the detecting unit, and extracts the feature points by the columnar object by extracting the grouped feature points. The road-side boundary surface detection device according to claim 3. The boundary surface specifying means uses the predetermined position corresponding to the vanishing point at which the road disappears in the image obtained by imaging by the imaging means as the origin, and the origin within a predetermined angle range from the origin. 5. The boundary surface is specified based on a distribution state of the feature points in a region between the two straight lines while changing an angle between the two straight lines extending further. The roadside boundary surface detection apparatus according to claim 1. Further comprising vanishing point estimating means for estimating the position of the vanishing point where the road disappears by specifying the road region from the image obtained by imaging by the imaging means,
The road-side boundary surface detection device according to claim 5, wherein the boundary surface specifying unit specifies the boundary surface with the position of the vanishing point estimated by the vanishing point estimation unit as an origin.

Images