JP5023363B2 - Vehicle travel support device, vehicle, vehicle travel support program - Google Patents

Description

  The present invention relates to an apparatus and the like that supports the traveling of a vehicle based on an image obtained through an imaging device mounted on the vehicle.

A technique has been proposed in which a bright spot pattern of laser light projected toward a road is imaged and a groove present on the road is detected based on the captured image (see Patent Document 1).
JP 05-201298 A

  However, in the case where artificial grooves such as drainage grooves are arranged in parallel at equal intervals on the road, there is a possibility that a false color is generated in the groove portion in the image taken by the in-vehicle camera. For this reason, when this image is processed, there is a possibility that the state of the road is erroneously recognized, such as a large number of wrinkles on the road.

  Therefore, an object of the present invention is to provide a device that can recognize with high accuracy the presence or absence of a plurality of artificial grooves arranged in parallel on a road on which the vehicle is traveling.

A vehicle travel support device according to a first aspect of the present invention is a vehicle travel support device that recognizes the travel environment of the vehicle based on an image representing a situation in a traveling direction of the vehicle obtained through an imaging device mounted on the vehicle. the Represents Wa of the first predicted travel area of the vehicle in the real space in the image, based on the lateral gray variant of the specified image region including the region between the lane mark pair, the first estimated travel area Generating an edge image by executing a first processing element for recognizing the presence or absence of a plurality of parallel linear artificial grooves in the image and an edge extraction process for revealing an edge in the image. to perform the conversion process, based on the execution result of the Hough transform processing, the vehicle and a second processing element recognizes the presence or absence of snow road traveling, the second processing element And recognizes the presence of snow of the road that by the first processing element is recognized that there is no plurality of artificial grooves as a requirement.

According to the vehicle travel support device of the first aspect of the present invention, in the image obtained through the imaging device, the lightness / darkness change mode in the horizontal direction of the designated image region representing the first predicted travel region of the vehicle in real space is recognized. When a plurality of parallel artificial grooves are provided on the road on which the vehicle is traveling, a characteristic shade change mode appears in the lateral direction in the designated image area. Therefore, based on this shade change mode, the presence or absence of a plurality of parallel artificial grooves in the first predicted travel region can be recognized with high accuracy. Furthermore, on the condition that it is recognized that there are not a plurality of parallel artificial grooves on the road, the state of the road (the presence or absence of snow) is recognized based on the execution results of the edge extraction process and the Hough transform process. As a result, a situation in which the state of the road is erroneously recognized due to the presence of a plurality of parallel artificial grooves is avoided.

  Note that the component of the present invention “recognizes” information means that the component retrieves information from a database, reads information from a storage device such as a memory, and measures information based on an output signal from a sensor or the like. It means performing any information processing necessary to prepare or prepare the information for further information processing, such as calculating, estimating, determining, storing the measured information in a memory, and the like.

The vehicle travel support apparatus according to a second aspect of the present invention is the vehicle travel support apparatus according to the first aspect, wherein the first processing element generates a frequency spectrum representing a change in shade in the horizontal direction of the designated image region with respect to the image. Therefore, the first predicted traveling is performed according to the presence or absence of a peak whose intensity is greater than or equal to a threshold value included in a specified frequency range corresponding to the interval between the plurality of artificial grooves in the real space in the frequency spectrum. Recognizing the presence or absence of a plurality of parallel artificial grooves in the region.

According to the vehicle travel support device of the second aspect of the present invention, the frequency spectrum representing the variation in the horizontal direction of the specified image region is generated by performing the Fourier transform process on the image. When a plurality of parallel artificial grooves are present in the first predicted traveling area represented by the designated image area, the frequency spectrum has a designated frequency range corresponding to a horizontal interval or a spatial period of the artificial grooves in real space. An included peak whose intensity is greater than or equal to the threshold appears. Therefore, the presence / absence of a plurality of parallel artificial grooves can be recognized according to the presence / absence of such a peak in the frequency spectrum.

  A vehicle travel support device according to a third aspect of the present invention is the vehicle travel support device according to the first or second aspect, wherein the second processing element is a linear component in a designated region representing the second predicted travel region of the vehicle in the ρ-θ space. The number of votes for the designated vote value is evaluated, and the presence or absence of snow on the road on which the vehicle is traveling is recognized on the condition that the number of votes is equal to or greater than a threshold value.

According to the vehicle travel support device of the third aspect of the present invention, in the designated region representing the second predicted travel region of the vehicle in the real space in the ρ-θ space (Hough space) based on the result of the edge image subjected to the Hough transform process. The number of votes for the designated vote value of the linear component is evaluated. The second predicted travel area and the first predicted travel area may be the same or different. When there is snow on the road, more straight line components appear in the second predicted travel area than when there is no snow on the road, so the number of votes for the designated vote value of the straight line component in the Hough space is greater than or equal to the threshold value. Therefore, the presence or absence of snow is recognized with high accuracy according to whether or not the number of votes for the designated vote value of the linear component is equal to or greater than a threshold value. Further, when there are a plurality of parallel artificial grooves on the road, the presence or absence of snow on the road is not recognized. Therefore, even though there is no snow on the road, there are a plurality of parallel artificial grooves on this road, so the number of votes for the designated vote value of the straight line component in the Hough space exceeds the threshold value, and there is snow on the road. Misidentified situations can be avoided.

  A vehicle according to a fourth aspect of the present invention includes the imaging apparatus and the vehicle travel support apparatus according to the first aspect of the present invention.

  According to the vehicle of the fourth aspect of the present invention, the presence or absence of a plurality of artificial grooves arranged in parallel on the road on which the vehicle is traveling can be recognized with high accuracy by the vehicle travel support device, and further, the state of this road can be recognized with high accuracy. Therefore, the operation of the in-vehicle device can be appropriately controlled from the viewpoint of safe driving of the vehicle based on the recognition result.

  According to a fifth aspect of the present invention, there is provided a driving support program for causing a computer mounted on a vehicle to function as the vehicle driving support device of the first invention.

  According to the driving support program of the fifth aspect of the invention, the in-vehicle computer can function as a vehicle driving support device that recognizes the presence or absence of a plurality of parallel artificial grooves on the road on which the vehicle is driving with high accuracy.

  DESCRIPTION OF EMBODIMENTS Embodiments of a vehicle travel support device and the like of the present invention will be described with reference to the drawings.

  A vehicle (four-wheeled vehicle) 1 shown in FIGS. 1 and 2 is equipped with a camera (imaging device) 12 such as a CCD camera or a near infrared camera, and a vehicle travel support device 10. The camera 12 is attached to the interior space so as to capture an image of the front of the vehicle 1 through the front window. Note that the location of the camera 12 may be changed as appropriate to the front portion of the vehicle 1 or the like. As shown in FIG. 2, the vehicle 1 further includes sensors such as a vehicle speed sensor 122, an acceleration sensor 124 and a yaw rate sensor 126, a steering device 14, and a braking device 16. Each of the vehicle speed sensor 122, the acceleration sensor 124, and the yaw rate sensor 126 outputs signals corresponding to the speed, acceleration, and yaw rate of the vehicle 1, respectively.

  The vehicle travel support device 10 is configured by a computer or an ECU (electronic control unit) (comprising a CPU, ROM, RAM, and electronic circuits such as an I / O circuit and an A / D conversion circuit). Output signals from the camera 12 and the speed sensor 122 are input to the vehicle travel support device 10. The “vehicle driving support program” is read from the memory by the CPU, and various processes described later are executed according to the read program. The program may be distributed or broadcast from the server to the vehicle 1 via a network or satellite at an arbitrary timing, and stored in a storage device such as a RAM of the in-vehicle computer. The vehicle travel support device 10 controls the operation of one or both of the steering device 14 and the braking device 16 to execute travel support control for assisting the travel of the vehicle 1 so that the vehicle 1 does not depart from the travel region. The vehicle travel support device 10 includes a first processing element 110 and a second processing element 120.

  The first processing element 110 performs a Fourier transform process (fast Fourier transform process) on the image obtained through the camera 12 in order to generate a frequency spectrum that represents a change in the horizontal density of the designated image region. The designated image region is a first predicted traveling region of the vehicle 1 in the real space in the image (for example, assuming that a pair of lane marks exist on the left and right sides of the vehicle 1, a part of the region sandwiched between the pair of lane marks or All). The first processing element 110 is based on a frequency spectrum that represents a change in shade in the horizontal direction of the designated image region, and the first predicted traveling region is included in the designated frequency range in this spectrum according to the presence or absence of a peak whose intensity is equal to or greater than a threshold value. Recognizes the presence or absence of artificial grooves, such as a plurality of parallel drainage grooves.

The second processing element 120 generates an edge image by executing an edge extraction process for extracting or revealing an edge in an image obtained through the camera 12. The second processing element 120 executes the Hough transform process on the edge image, and evaluates the number of votes for the designated vote value of the linear component in the ρ-θ space based on the execution result of the Hough transform process. The second processing element 120 recognizes the presence or absence of snow on the road on which the vehicle 1 is traveling, on the condition that the number of votes of the designated vote value in the designated area defined in the ρ-θ space is equal to or greater than a threshold value. The second processing element 120 recognizes the presence or absence of snow on this road on the condition that the first processing element 110 recognizes that there are not a plurality of parallel artificial grooves on the road (specifically, the first predicted travel area). To do. The designated area is the second predicted travel area of the vehicle 1 in the real space in the ρ-θ space (for example, assuming that there are a pair of lane marks on the left and right of the vehicle 1 as in the first predicted travel area) This represents a part or all of a region sandwiched between marks. The boundary of the designated area is set so that the number of votes of the designated voting value in the designated area is less than the threshold value for a road in a snowless state.

  Functions of the vehicle 1 and the vehicle travel support device 10 having the above-described configuration will be described.

First, a digital image representing the situation in front of the vehicle 1 or in the traveling direction is acquired through the camera 12 (FIG. 3 / S002). Thereby, for example, an image of a road extending in front of the vehicle 1 as shown in FIG. 4 (a), FIG. 5 (a) (= FIG. 7 (a)) or FIG. 6 (a) is acquired. 4A is a captured image in a state where there is no snow on the road and a plurality of parallel artificial grooves G are provided on the road, and FIG. 5A is a state in which there is snow on the road. FIG. 6A illustrates a captured image in a state where there is no snow on the road and a plurality of artificial grooves are not provided on the road.

  Further, the first processing element 110 executes a fast Fourier transform process on the digital image (FIG. 3 / S004). As a result, for example, a frequency spectrum as shown in FIG. 4B is generated that represents the variation in the horizontal direction of the rectangular designated image region QA shown in FIG. 4A. Similarly, a frequency spectrum as shown in FIG. 5 (b) is generated, which represents the variation in the horizontal direction of the rectangular designated image area QA shown in FIG. 5 (a). In addition to the rectangular shape, the designated image area may be set to various shapes such as a circular shape, an elliptical shape, a triangular shape, and a trapezoidal shape. Further, instead of the fast Fourier transform process, a normal Fourier transform process or a discrete Fourier transform process may be executed.

  Further, the second processing element 120 executes edge extraction processing on the digital image, thereby generating an edge image in which the edges are made obvious (FIG. 3 / S006). For example, the edge extraction processing is performed on the images shown in FIGS. 6A and 7A, respectively, so that the images shown in FIGS. 6B and 7B are displayed. As shown, an edge image in which edges (outlined portions) are extracted or made visible is generated. Note that an edge means a point or a line segment composed of pixels whose luminance changes beyond a threshold value in a certain scanning direction, and is disclosed in Japanese Patent Laid-Open Nos. 2005-332104 and 2006-012191. Can be recognized according to the image processing method being used.

  Further, the Hough transform process is executed on the edge image by the second processing element 120 (FIG. 3 / S008). For example, the Hough transform process is executed on the edge images shown in FIGS. 6B and 7B, respectively, so that the edge images shown in FIGS. 6C and 7C are shown. As described above, the frequency at which the linear component of the edge subjected to the Hough transform appears at an arbitrary coordinate in the ρ-θ space is evaluated as a vote value.

Further, the first processing element 110 recognizes the presence / absence of a plurality of artificial grooves arranged in parallel in the first predicted travel area represented by the designated image area (S010 in FIG. 3). Specifically, the presence / absence of the artificial grooves arranged in parallel is recognized by recognizing the presence / absence of a peak whose intensity included in the specified frequency range in the frequency spectrum is equal to or greater than a threshold value. The designated frequency range means a spatial frequency range corresponding to a standard artificial groove interval in real space. For example, as shown in FIG. 4B, when there is a peak included in the designated frequency range and having an intensity equal to or higher than a threshold value (one-dot chain line), the first image represented by the designated image region QA is used. It is recognized that there are a plurality of parallel artificial grooves G in the predicted travel region (see FIG. 4A). On the other hand, as shown in FIG. 5B, when there is no peak whose intensity is greater than or equal to the threshold value (one-dot chain line), a plurality of first predicted travel areas represented by the designated image area QA are displayed. It is recognized that there are no parallel artificial grooves G (see FIG. 5A). Incidentally, in addition to the peak intensity is equal to or greater than the threshold is present, this peak is that it is the requirements that exist in the designated frequency range corresponding to a standard lateral spacing of the artificial grooves, a plurality of artificial grooves May be recognized.

When it is determined by the first processing element 110 that there are a plurality of parallel artificial grooves in the first predicted traveling area of the road (FIG. 3 / S010... NO), the second processing element 120 performs edge processing on the digital image. By executing the extraction process or the like, a lane mark is searched as will be described later (FIG. 3 / S016), and it is determined whether or not the travel area can be set based on the search result (FIG. 3 / S018). When set, the operations of the steering device 14 and the braking device 16 are controlled so that the vehicle 1 falls within the travel region (FIG. 3 / S020).

On the other hand, if it is determined by the first processing element 110 that a plurality of parallel artificial grooves are not present in the first predicted travel area of the road (FIG. 3 / S010... YES), the second processing element 120 determines ρ− A histogram expressing the relationship between the vote value in the designated area S defined in the θ space and the number of votes as the frequency of appearance of the vote value is generated (S012 in FIG. 3). Thereby, for example, the first vote area U ₁ on the higher vote value and higher vote side than the threshold line (solid line) shown in FIG. 8 and the second vote on the lower vote value and smaller vote side than the threshold line. The first curve (one-dot chain line) L ₁ or the second curve (two-dot chain line) L ₂ representing the relationship between the vote value and the number of votes is included so that any or all of the areas U ₂ are included. be painted. As the designated region S, a first designated region (enclosed by a one-dot chain line) S ₁ = [delimited by the value of ρ shown in each of FIGS. 6C and 7C. ρ ₁ , ρ ₂ ] and a second designated area (surrounded by a two-dot chain line) delimited by the value of θ S ₂ = [θ ₁ , θ ₂ ] (overlapped area) S ₁ ∩S ₂ is defined. Although voting value in a region deviated from the first specified region S ₁ and the second specified area S ₂ described later with reference to shown in FIG. 6 (c) and FIG. 7 (c) there is a higher pair of points, which is primarily a pair This represents the result of Hough transform of the lane mark or the edge of the ridge. The first designated area S ₁ or the second designated area S ₂ may be defined alone as the designated area S. Further, as the shape of the designated region S, various shapes such as a circular shape, an elliptical shape, a triangular shape, or a trapezoidal shape may be adopted instead of a rectangular shape.

  As for the boundary value of the designated area S, the designated vote value in the designated area S is greater than or equal to the threshold for a snowy road, while the designated vote value in the designated area S is less than the threshold for a road in the no snow condition. It is set to be.

Specifically, while the point voting value is high is relatively small in the first designated area S ₁ as the road in no snow state shown in FIG. 6 (c), a state where there is snow road for Figure 7 the lower limit value [rho ₁ and the upper limit value [rho ₂ of the first specified area S ₁ as voting value is comparatively much higher position in the first designated area S ₁ as shown in (c) is Is set. That is, as described above, the lower limit value ρ ₁ of the first designated region S ₁ is not included so that a pair of high voting values representing the result of Hough transform of edges such as a pair of lane marks or wrinkles is not included. The upper limit value ρ ₂ is set (for example, ρ ₁ = 0, ρ ₂ = 0.3ρ _max ). The first designated area S ₁ in the ρ-θ space passes through the semi-circular first designated image area Q ₁ in the captured image of the camera 12 shown in each of FIGS. 6 (a) and 7 (a). It corresponds to a straight line (line segment) that, in turn, corresponds to a real space region corresponding to the first specified image area Q ₁ (front region near the vehicle 1).

Similarly, while portions vote value is high it is relatively small in the second designated area S ₂ to the road in no snow state shown in FIG. 6 (c), the road state is snow boundary value theta ₁ and theta ₂ of the second specifies that voting value is comparatively much higher point region S ₂ is set in the second designated area S ₂ as shown in FIG. 7 (c) (For example, θ ₁ = π / 6, θ ₂ = 5π / 6). That is, as described above, the boundary value θ ₁ of the second designated region S ₂ is not included so that a pair of high voting values representing the result of the Hough transform of edges such as a pair of lane marks or ridges is not included. And θ ₂ are set. The second designated region S ₂ in the ρ-θ space is a straight line passing through the triangular second designated image region Q ₂ in the captured image of the camera 12 shown in each of FIGS. 6 (a) and 7 (a). Corresponding to the second designated image area Q ₂ (assuming that there is a pair of left and right lane marks, most of them are included between the pair of lane marks). Area).

For this reason, on a road with snow, a vote is made so that a part or the whole is included in the first vote area U ₁ on the higher vote value and higher vote count side than the threshold line shown in FIG. A curve representing the relationship between the value and the number of votes is drawn. On the other hand, on the road without snow cover, the vote is made so that a part or the whole is included in the second vote area U ₂ on the higher vote value and higher vote side than the threshold line shown in FIG. A curve representing the relationship between the value and the number of votes is drawn.

Further, the second processing element 120 recognizes whether or not there is snow on the road on which the vehicle 1 is traveling by recognizing whether or not the number of votes of the designated vote value is equal to or less than a threshold value (FIG. 3 / S014). . For example, when the number of votes N ₁ in the designated vote value shown in FIG. 8 is greater than or equal to the threshold value N _th, it is recognized that there is snow, while when the number of votes N ₂ is less than the threshold value N _th It is recognized that there is no snow. In addition, it is not based on whether the number of votes of one designated vote value is more than a threshold value, but it is the presence or absence of snow depending on whether each vote number is more than a threshold value among several designated vote values. It may be recognized.

  When it is recognized that there is no snow on the road (FIG. 3 / S014... YES), lane marks such as lanes (white line or yellow line) or road fences (botts dots) are displayed based on the execution result of the edge extraction process. Search is performed (FIG. 3 / S016). As a lane mark search method, a method disclosed in Japanese Patent Laid-Open No. 2006-309605, Japanese Patent Laid-Open No. 2006-331193, Japanese Patent Laid-Open No. 2007-018154, Japanese Patent Laid-Open No. 2007-026106, or the like is employed. Can be done. Further, based on the search result of the lane mark, it is determined whether or not a travel region in which left and right are defined by a pair of lane marks can be set (FIG. 3 / S018). When it is determined that the travel region can be set (FIG. 3 / S018... YES), the operation of one or both of the steering device 14 and the braking device 16 is controlled, so that the vehicle 1 deviates from this travel region. In order to prevent this, the driving support control for supporting the driving of the vehicle 1 is executed (FIG. 3 / S020). On the other hand, when it is recognized that there is snow on the road (FIG. 3 / S014... NO), or when it is determined that the travel area cannot be set due to a lane mark search failure (FIG. 3 / S018... NO), setting of the travel area and travel support control are omitted.

According to the vehicle travel support device 10 that exhibits the above function, in the image obtained through the camera (imaging device) 12, the horizontal shading change mode of the designated image region representing the first predicted travel region of the vehicle 1 in the real space. Is recognized. Specifically, a fast spectrum transform process is performed on the digital image, thereby generating a frequency spectrum representing a change in shade in the horizontal direction of the designated image region (FIG. 3 / S004, FIG. 4B) and FIG. 5 (b)). When a plurality of parallel artificial grooves G are provided on the road on which the vehicle 1 is traveling as shown in FIG. 4A, the specified image area QA has a characteristic shade change in the lateral direction. As shown in FIG. 4B, the mode appears as a peak whose intensity included in the designated frequency range in the frequency spectrum is equal to or higher than the threshold. Therefore, based on this shade change mode, the presence or absence of a plurality of parallel artificial grooves in the first predicted travel region can be recognized with high accuracy. Furthermore, on the condition that a plurality of parallel artificial grooves are recognized not to exist on the road, the state of the road is recognized based on the execution results of the edge extraction process and the Hough transform process (FIG. 3 / S010... YES, (See S014). As a result, a situation in which the state of the road is erroneously recognized due to the presence of a plurality of parallel artificial grooves is avoided.

Furthermore, an edge image is generated by extracting or revealing an edge in an image obtained through the camera (imaging device) 12 (see FIG. 3 / S006, FIG. 6B and FIG. 7B). Also, the edge image is subjected to the Hough transform, whereby the voting value of the linear component is evaluated at an arbitrary point in the ρ-θ space (Hough space) (FIG. 3 / S006, FIGS. 6C and 7C). )reference). Then, by recognizing whether or not the number of votes of the designated vote value in the designated region S (see FIG. 6C) in the ρ-θ space is equal to or greater than the threshold value, snow accumulation on the road on which the vehicle 1 is traveling is determined. The presence or absence is recognized (see FIG. 3 / S014, FIG. 8). This is because the designated region S of the ρ-θ space corresponds to a second predicted travel region defined by a pair of lane marks on the left and right sides of the vehicle 1. This is because the number of votes of the designated vote value in the designated area is significantly different depending on the presence or absence of snow. Specifically, as described above, the first designated region S ₁ in the ρ-θ space is the semicircular first designated image region Q ₁ in the captured image of the camera 12 shown in FIG. It corresponds to a straight line (line segment) passing, therefore, corresponds to a real space region corresponding to the first specified image area Q _1. Further, the second designated area S ₂ in the ρ-θ space is a straight line (line segment) passing through the triangular second designated image area Q ₂ in the captured image of the camera 12 shown in FIG. It corresponds to, in turn, corresponds to a real space region corresponding to a second specified image area Q _2. Therefore, regardless of the presence or absence of imaging history from the same position by the camera 12, the characteristics when determining the presence or absence of snow appear in the vote value of the designated area S in FIG. 6C, and the road on which the vehicle 1 is traveling The presence or absence of snow in can be recognized with high accuracy.

Further, when there are a plurality of parallel artificial grooves on the road, the presence or absence of snow on this road is not recognized (see NO in FIG. 3 / S010). Therefore, even though there is no snow on the road, there are a plurality of parallel artificial grooves on this road, so the number of votes for the designated vote value of the straight line component in the Hough space exceeds the threshold value, and there is snow on the road. Misidentified situations can be avoided.

In the above-described embodiment, the horizontal gradation change mode of the designated image area is recognized as the frequency spectrum generated by the fast Fourier transform process. However, as another embodiment, the edge (for example, the brightness in the horizontal direction of the image is low) by the edge extraction process. Negative edge) may be extracted, and the horizontal shading change mode of the designated image area may be recognized as the appearance period of the edge in the image horizontal direction. Then, the presence / absence of an artificial groove may be recognized depending on whether the appearance frequency of the edge in the horizontal direction of the image is equal to or greater than a certain value and the appearance period is included in the specified range.

  In the above embodiment, the presence or absence of snow on the road is recognized as the state of the road (see FIG. 3 / S014, FIG. 6 and FIG. 7). As another embodiment, the presence or absence of fine cracks on the road surface, The presence / absence of scattered objects in the road may be recognized as a road state.

Configuration diagram of the vehicle of the present invention Configuration explanatory diagram of the vehicle travel support device of the present invention The flowchart which shows the function of the vehicle travel assistance device of this invention Explanatory drawing about spectrum generation method by Fourier transform processing Explanatory drawing about spectrum generation method by Fourier transform processing Explanatory drawing about edge extraction processing and Hough transform processing when there is no snow Explanatory drawing about edge extraction processing and Hough transform processing during snowfall Explanatory diagram regarding the relationship between the voting value and the number of votes for linear components

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Vehicle, 10 ... Vehicle travel support apparatus, 12 ... Camera (imaging device), 110 ... 1st processing element, 120 ... 2nd processing element

Claims (5)

A vehicle travel support device for recognizing a travel environment of the vehicle based on an image representing a situation in a traveling direction of the vehicle obtained through an imaging device mounted on the vehicle,
It said to Table Wa standard running region of the vehicle in the real space in the image, based on the lateral gray variant of the specified image region including a region between the pair of lane mark, a plurality of parallel in the standard traveling area A first processing element for recognizing the presence or absence of a linear artificial groove;
An edge image is generated by executing an edge extraction process that reveals an edge in the image, a Hough transform process is performed on the edge image, and the vehicle is running based on an execution result of the Hough transform process A second processing element for recognizing the presence or absence of snow on the road,
The vehicle travel support apparatus according to claim 1, wherein the second processing element recognizes whether there is snow on the road on the condition that the first processing element recognizes that the plurality of artificial grooves are not present . The vehicle travel support device according to claim 1,
The first processing element performs a Fourier transform process to generate a frequency spectrum that represents a change in lightness and shade in the lateral direction of the designated image region with respect to the image, and the plurality of artificial objects in real space in the frequency spectrum A vehicle travel support apparatus that recognizes the presence or absence of a plurality of artificial grooves arranged in parallel in the standard travel region in accordance with the presence or absence of a peak whose intensity is greater than or equal to a threshold value, which is included in a specified frequency range corresponding to a groove interval. . In the vehicle travel support device according to claim 1 or 2,
The second processing element evaluates the number of votes with respect to a designated vote value of a straight line component in a designated area representing the standard running area in the ρ-θ space, and the vehicle has the requirement that the number of votes is equal to or greater than a threshold. A vehicle travel support apparatus for recognizing presence or absence of snow on a traveling road. A vehicle comprising: an imaging device; and the vehicle travel support device according to claim 1. A vehicle driving support program for causing a computer mounted on a vehicle to function as the vehicle driving support device according to claim 1.