JP4257219B2 - Traveling locus recording apparatus and traveling locus recording method - Google Patents

Description

  The present invention relates to an apparatus for recording a travel locus of a vehicle and a method for recording a travel locus of a vehicle.

  For example, Patent Document 1 discloses a navigation device that uses two-dimensional map data and GPS in order to display the current position of a vehicle on a map or perform route guidance to a destination. ing. In this navigation device, the current position of the vehicle is recorded in time series according to the travel of the vehicle, whereby the travel locus of the vehicle is displayed on the map. Further, in this apparatus, information such as the vehicle speed and altitude is further recorded, and information such as the vehicle speed and altitude that changes in accordance with the travel is displayed in addition to the travel locus of the vehicle.

Patent Document 2 discloses a technique for recording a three-dimensional shape of a road on which a vehicle has traveled by using a monocular camera and GPS. According to this method, a white line on the road surface is detected using a captured image obtained from a monocular camera, and the detected white line is associated with the longitude, latitude, and altitude measured by the GPS, thereby obtaining a three-dimensional road. The shape is recorded.
JP-A-10-253369 JP 2002-81941 A

  However, since the method disclosed in Patent Document 1 uses map data that is fixedly prepared in advance, the travel locus cannot be displayed when there is no map data corresponding to the road on which the vehicle has traveled. Inconvenience arises. Further, in this method, although the position of the vehicle is detected using GPS, it is only specified macroscopically on which road on the map the vehicle is traveling. For this reason, there is a problem that the travel locus cannot be recorded from a microscopic viewpoint of how the vehicle traveled on the road. Moreover, since the method disclosed in Patent Document 2 recognizes a road shape by detecting a white line, there is a problem that the road shape cannot be recognized on a road without a white line.

  The present invention has been made in view of such circumstances, and an object thereof is to record a traveling locus of a vehicle on a road on which the vehicle is traveling.

  In order to solve such a problem, the first invention provides an apparatus for recording a travel locus of a vehicle. The travel locus recording apparatus calculates distance data using stereo matching based on a stereo camera that outputs a pair of image data and a pair of image data by capturing a scene including a road ahead of the vehicle. A road model that defines the road shape by recognizing the position of the road ahead of the vehicle in a three-dimensional space based on the position of the vehicle based on the stereo image processing unit and the distance data calculated by the stereo image processing unit A recognizing unit for calculating the vehicle model, a recording unit for storing the calculated road model in time series according to the travel of the vehicle, and a detecting unit for detecting a vehicle parameter indicating the state of the vehicle. The recording unit stores the detected vehicle parameter in association with the calculated road model.

  Here, in the first invention, the recognition unit preferably detects a feature existing along the road and calculates a road model based on the position of the feature. In addition, the travel locus recording apparatus may further include a calculation unit that calculates a current position of the vehicle by receiving radio waves emitted from a satellite. In this case, it is preferable that the recording unit stores the calculated current position of the vehicle in association with the calculated road model.

  In the first invention, the traveling locus recording apparatus includes a control unit that determines the content to be displayed based on information stored in the recording unit, and a display that is controlled by the control unit and displays the determined content. And a device. In this case, the control unit controls the display device so as to display the road shape of the road on which the vehicle has traveled by connecting the stored road models in time series in consideration of the amount of movement of the vehicle. At the same time, it is preferable to control the display device so as to display the position of the vehicle on the road. Further, the control unit controls the display device to display the road shape and the position of the vehicle on the road in a two-dimensional manner with the upper side of the road as a viewpoint, and the road shape and the position of the vehicle on the road It is preferable to control the display device so that it is displayed three-dimensionally with the upper side of the screen as a viewpoint.

  In the first invention, the travel locus recording apparatus may further include an information recording device for writing the information stored in the recording unit to the information recording medium, and the information stored in the recording unit. In addition, an information transmission device that transmits to an external device by communication may be further included.

  The second invention provides a method for recording a travel locus of a vehicle. In this traveling locus recording method, as a first step, a pair of image data output by capturing a scene including a road ahead of the vehicle using a stereo camera is acquired, and as a second step, a pair of images is acquired. Based on the data, the distance data is calculated using stereo matching, and as a third step, the position of the road ahead of the vehicle in the three-dimensional space based on the position of the vehicle is recognized based on the distance data. Thus, a road model that defines the road shape is calculated, and as a fourth step, the calculated road model is stored in time series according to the travel of the vehicle, and as a fifth step, the state of the vehicle is indicated. Get vehicle parameters. In this case, the fourth step includes a step of storing the detected vehicle parameter in association with the calculated road model.

  Here, in the second invention, it is preferable that the third step detects a feature existing along the road and calculates a road model based on the position of the feature. In addition, the traveling locus recording method may further include a step of calculating the current position of the vehicle by receiving radio waves emitted from the satellite. In this case, it is preferable that the fourth step includes a step of storing the calculated current position of the vehicle in association with the calculated road model.

  In the second invention, the display device is controlled so as to display the road shape of the road on which the vehicle has traveled by connecting the stored road models in time series in consideration of the movement amount of the vehicle. In addition, it is preferable to further include a step of controlling the display device so as to display the position of the vehicle on the road.

  As described above, according to the present invention, a pair of image data in which a road on which the host vehicle is traveling is projected from the viewpoint of the vehicle is output by capturing a scene in front of the vehicle using a stereo camera. By storing the road model calculated based on the distance data obtained from the pair of image data in time series, the trajectory of the vehicle traveling on the road can be recorded.

(First embodiment)
FIG. 1 is a block diagram of a travel locus recording apparatus according to the first embodiment. A stereo camera 1 that captures a landscape including a road ahead of the vehicle is attached in the vicinity of a room mirror, for example. The stereo camera 1 is composed of a pair of cameras 2a and 2b, and an image sensor (for example, a CCD or CMOS sensor) is built in each of the cameras 2a and 2b. The main camera 2a captures a reference image necessary for performing stereo image processing in time series, and the sub camera 2b captures a comparative image in time series. In a state where they are synchronized with each other, each analog image output from the cameras 2a and 2b is converted into a digital image of a predetermined luminance gradation (for example, a gray scale of 256 gradations) by the A / D converters 3 and 4. Is converted to

  A pair of digitized image data is subjected to brightness correction, image geometric conversion, and the like in the image correction unit 5. Usually, there is an error in the mounting position of the pair of cameras 2a and 2b, although there is a difference in degree. Therefore, a shift caused by the error occurs in the left and right images. In order to correct this deviation, geometrical transformation such as image rotation or translation is performed using affine transformation or the like.

  Through such image processing, reference image data is obtained from the main camera 2a, and comparison image data is obtained from the sub camera 2b. These image data are a set of luminance values (0 to 255) of each pixel. Here, the image plane defined by the image data is expressed in the ij coordinate system, with the lower left corner of the image as the origin, the horizontal direction as the i coordinate axis, and the vertical direction as the j coordinate axis. Stereo image data corresponding to one frame is output to the subsequent stereo image processing unit 6 and stored in the image data memory 8.

  The stereo image processing unit 6 calculates distance data related to a captured image corresponding to one frame based on the reference image data and the comparison image data. Here, the “distance data” is a set of parallax d calculated for each small area on the image plane defined by the image data, and each parallax d corresponds to a position (i, j) on the image plane. It is attached. Each parallax d is calculated for each pixel block of a predetermined area (for example, 4 × 4 pixels) constituting a part of the reference image.

  FIG. 2 is an explanatory diagram of pixel blocks set in the reference image. For example, when the reference image is composed of 200 × 512 pixels, a parallax group corresponding to the maximum number of pixel blocks PBij (50 × 128) is calculated from a captured image corresponding to one frame. As is well known, the parallax d is the amount of horizontal displacement with respect to the pixel block PBij that is the calculation unit, and has a large correlation with the distance to the object projected in the pixel block PBij. That is, the closer the object projected in the pixel block PBij is to the cameras 2a and 2b, the larger the parallax d of the pixel block PBij is, and the farther the object is, the smaller the parallax d is. d becomes 0).

  When calculating the parallax d regarding a certain pixel block PBij (correlation source), a region (correlation destination) having a correlation with the luminance characteristic of the pixel block PBij is specified in the comparison image. As described above, the distance from the cameras 2a and 2b to the object appears as a horizontal shift amount between the reference image and the comparison image. Therefore, when searching for the correlation destination in the comparison image, it is only necessary to search on the same horizontal line (epipolar line) as the j coordinate of the pixel block Pij as the correlation source. The stereo image processing section 6 shifts the correlation between the correlation source and the correlation destination candidates while shifting one pixel at a time on the epipolar line within a predetermined search range set based on the i coordinate of the correlation source. Sequential evaluation (stereo matching). In principle, the amount of horizontal deviation of the correlation destination (one of the correlation destination candidates) determined to have the highest correlation is defined as the parallax d of the pixel block PBij.

The correlation between two pixel blocks can be evaluated, for example, by calculating a city block distance CB. Formula 1 shows the basic form of the city block distance CB. In the equation, p1ij is the luminance value of the ijth pixel of one pixel block, and p2ij is the ijth luminance value of the other pixel block. The city block distance CB is the total sum of the differences (absolute values) of the luminance values p1ij and p2ij corresponding to each other in the entire pixel block, and the smaller the difference, the greater the correlation between both pixel blocks. .
(Formula 1)
CB = Σ | p1ij−p2ij |

  Basically, among the city block distances CB calculated for each pixel block existing on the epipolar line, the pixel block having the smallest value is determined as the correlation destination. The amount of deviation between the correlation destination specified in this way and the correlation source is the parallax d. Note that the hardware configuration of the stereo image processing unit 6 for calculating the city block distance CB is disclosed in Japanese Patent Laid-Open No. 5-1114099, so refer to it if necessary. The distance data calculated through such processing, that is, a set of parallax d associated with the position (i, j) on the image is stored in the distance data memory 7.

  The microcomputer 9 includes a CPU, a ROM, a RAM, an input / output interface, and the like. The microcomputer 9 is inputted with various sensors including the sensors 13a to 13d and signals obtained from the GPS position detecting unit 13e in order to specify vehicle parameters indicating the current vehicle state. The vehicle speed sensor 13a detects the vehicle speed of the vehicle, and the steering angle sensor 13b detects the steering angle of the wheels. The rate sensor 13c detects the amount of change (for example, yaw rate) of the rotational motion of the vehicle such as yawing, rolling, and pitching. The vehicle orientation sensor 13d is a sensor that detects the traveling direction of the vehicle, and a geomagnetic orientation sensor, a gyro, or the like can be used. The GPS position detection unit 13e receives radio waves emitted from GPS satellites and differential information from fixed stations installed at known points. Although not explicitly shown in FIG. 1, in addition to these detected values, the operation state such as the operation amount of the accelerator, the brake, the steering wheel, etc., the vehicle operation such as the engine speed, the boost pressure, and the transmission gear position. The state is also detected as a vehicle parameter. In the present specification, the term “detection unit 13” is used to collectively refer to various sensors that detect these vehicle parameters and the GPS position detection unit 13e.

  The microcomputer 9 includes a recognition unit 10, a calculation unit 11, and a control unit 12 when this is viewed functionally. The recognition unit 10 recognizes the position of the road ahead of the vehicle in the three-dimensional space based on the vehicle based on the distance data calculated by the stereo image processing unit 6. A road model that defines the road shape is calculated based on the recognized road position. For calculation of the road model, the image data stored in the image data memory 8 is also referred to as necessary. The calculation unit 11 further calculates vehicle parameters such as the posture of the vehicle and the current position based on the detection signal obtained from the detection unit 13. Then, the calculated road model and the vehicle parameters (the detected value obtained from the detecting unit 13 and the calculated value calculated by the calculating unit 11) are associated with each other in the subsequent recording unit 14 as travel locus data. Stored. The control unit 12 refers to the travel locus data stored in the recording unit 14 and controls the display device 15 to display the travel locus of the vehicle. Further, the control unit 12 stores the travel locus data stored in the recording unit 14 in the information recording medium via the information recording device 16 or transmits it to an external device (not shown) by communication through the information transmission device 17. can do.

  FIG. 3 is a flowchart showing a procedure for recording the travel locus of the vehicle. The routine shown in this flowchart is called at predetermined intervals and executed by the microcomputer 9. First, in step 1, the recognition unit 10 reads image data corresponding to one frame from the image data memory 8 and reads distance data corresponding to this data from the distance data memory 7.

  In step 2, the recognition unit 10 calculates a road model. This road model is expressed by a linear expression in the horizontal direction and the vertical direction in the coordinate system of the real space, and can be calculated by setting the parameters of this linear expression to values that match the actual road shape. . Plants that exist along the road, solid objects such as pylons and guardrails, or features such as white lines (or yellow lines) that define lanes drawn on the road surface are effective in recognizing road shapes. . Therefore, the recognizing unit 10 recognizes the positions in the real space of these feature objects existing along the road, and calculates the road model by connecting these positions. The position (x, y, z) of the feature in the real space is uniquely determined from a well-known coordinate conversion formula based on the position (i, j) on the distance data and the parallax d calculated with respect to this position. Calculated. The three-dimensional coordinate system that defines the real space is set on the basis of the vehicle, with the road surface directly below the center of the stereo camera 1 as the origin, the vehicle width direction is the x axis, the vehicle height direction is the y axis, Let (distance direction) be the z-axis. Therefore, the calculated road model defines the road shape in the three-dimensional space with the vehicle position as a reference.

  In the road model calculation based on the three-dimensional object recognition, a three-dimensional object in front of the vehicle is detected based on the distance data, and the detected three-dimensional object includes a group of objects (preceding vehicle or obstacle) and a wall surface (for example, , Guardrails and planting). Along with this classification, a series of three-dimensional objects existing along the road are detected as wall surfaces. A wall surface model is calculated by correcting a wall surface model representing the contour of the wall surface by connecting a plurality of nodes based on the position of the detected wall surface in real space. Since the wall surface model substantially defines the shape of the road, it can be handled equivalently to the road model.

  In the road model calculation based on white line recognition, image data is referred to based on the knowledge that the white line is brighter than the road surface. Based on this image data, the position of the left and right white lines on the image plane is specified by evaluating the luminance change in the width direction of the road. The position of the white line is detected based on the position (i, j) on the image plane of the identified white line and the parallax d of the distance data corresponding to this position. The road model can be calculated by dividing the white line on the road into multiple sections in the distance direction, approximating the position of the left and right white lines in each section with a three-dimensional straight line, and connecting them in a polygonal line. .

  For example, the recognition unit 10 calculates a road model based on a white line when a white line is present in front of the host vehicle, and calculates a road model based on a solid object when the white line is not present. In addition to this, a road model may be calculated by combining both recognition methods by recognizing the center line drawn on the road surface and the guard rail existing on the road shoulder side. The details of white line detection are disclosed in Japanese Patent Laid-Open No. 2001-92970, and details of solid object detection are disclosed in Japanese Patent Laid-Open No. 11-213138.

  In step 3, the calculation unit 11 reads the detection signal from the detection unit 13. And based on the detection signal of the detection part 13, the attitude | position and present position of a vehicle are calculated (step 4). Specifically, the attitude of the vehicle is calculated based on sensor signals obtained from the sensors 13a to 13d. Further, the current position of the vehicle is calculated based on the GPS signal obtained from the GPS position detector 13e. As is well known, the calculation of the self-position using only the radio wave emitted from the GPS satellite has a large error. Therefore, the calculation unit 11 observes the position of this point based on the differential information obtained from the fixed station in order to remove the error of the calculated value. Then, by feeding back correction information obtained based on this position observation (so-called D-GPS control), the absolute position of the vehicle can be accurately calculated.

  In step 5, the road model calculated by the recognition unit 10 is stored in the recording unit 14 for a predetermined distance (for example, 5 m) in front of the host vehicle. At the same time, the posture and current position of the vehicle calculated by the calculation unit 11 and the vehicle parameters detected by the detection unit 13 are stored in the recording unit 14, and the routine is exited.

  By repeating such a cycle, the road model is stored in the recording unit 14 in time series according to the traveling of the vehicle. At the same time, vehicle parameters corresponding to the road model are stored in the recording unit 14 in time series. The travel locus data stored in the recording unit 14 is written to an information recording medium via the information recording device 16, or is transmitted to an external device via the information transmission device 17 through the Internet or a wireless / wired LAN. Can be transmitted.

  Further, the control unit 12 can display the traveling locus data on which the vehicle has traveled on the display device 15 based on the traveling locus data stored in the recording unit 14. For example, when a road model is calculated on a white line basis, a plurality of road models such as a first road model R1, a second road model R2, and a third road model R3 are stored in the recording unit 14 in time series. Stored. FIG. 4A is a two-dimensional schematic diagram of a road model represented by a linear equation. In FIG. 6A, points C1 to C3 indicate the position of the vehicle (reference position when calculating the road model), and the horizontal viewing angle (illustrated by a dotted line) with reference to the position C of the vehicle. Inside, the road shape defined by the road model is indicated by a solid line.

  As a premise for displaying the road model, the control unit 12 associates a position on the display screen of the display device 15 with position information by GPS in advance. Then, the control unit 12 displays the stored road models connected in time series in consideration of the amount of movement of the vehicle. Specifically, the first road model R1 is displayed at a position P1 on the display screen corresponding to the current position C1 of the vehicle in consideration of the posture of the vehicle. Further, the second road model R2 is displayed at a position P2 on the display screen corresponding to the current position C2 of the vehicle in consideration of the posture of the vehicle. In this case, the first road model offset ahead of the second road model R2 is not displayed. This process is similarly performed for the third road model R3 (or the subsequent road model R), so that only the road models stored in the recording unit 14 are displayed (FIG. 4B). )reference). In this connected road model, a set of reference positions C when the road model is calculated is displayed as a travel locus of the vehicle.

  FIG. 5 is an explanatory diagram of travel locus data displayed on the display screen. In the figure, for example, the travel locus and road shape of the vehicle when the vehicle travels on an oval course are shown, and the road shape on which the vehicle has traveled is indicated by a solid line and the travel locus is indicated by a dotted line. The control unit 12 controls the display device 15 so that the road shape and the position of the vehicle on the road according to the traveling of the vehicle are two-dimensionally displayed with the upper side as a viewpoint. Along with this, the traveling locus and the road shape are displayed in a state viewed from directly above (see (a) of the figure). In addition, the control unit 12 may control the display device 15 so that the road shape and the position of the vehicle on the road according to the traveling of the vehicle are three-dimensionally displayed with the upper side as a viewpoint. Accordingly, the travel locus and the road shape are displayed in a state viewed from an oblique rear side of the vehicle (a so-called bird view) (see FIG. 5B). In FIG. 5B, a symbol corresponding to the vehicle is displayed, and this symbol may be displayed so as to correspond to the posture of the vehicle. For example, vehicle parameters such as vehicle speed and engine speed may be displayed on the display screen of the display device 15 from the viewpoint of enhancing the display contents. From the same viewpoint, for example, the display form shown in FIG. 5A and the display form shown in FIG. 5B may be displayed in parallel on one display screen. In other words, the control unit 12 controls the display device 15 to perform two-dimensional display, and controls the display device to perform three-dimensional display in parallel with the display device 15.

  As described above, according to the present embodiment, a pair of image data in which a road on which the host vehicle is traveling is projected from the viewpoint of the vehicle by capturing a scene in front of the vehicle using the stereo camera 1. Is output. A road model that defines the road shape is calculated based on the distance data calculated from the image data. The calculated road model is stored in the recording unit 14 in time series according to the traveling of the host vehicle. Since this road model defines the road shape in a three-dimensional space based on the position of the vehicle, the recording unit 14 stores the vehicle on the road based on the position of the host vehicle along with the change in the road shape. A relative change in the width direction is recorded in time series. In other words, since the relative change in the vehicle width direction of the road is a change in the vehicle width direction position of the host vehicle based on the road, the vehicle travels on the road by recording this road model. Recorded trajectory can be recorded.

  Moreover, according to this embodiment, since a road model can be calculated using either a white line or a three-dimensional object as a feature object, a travel locus can be recorded in a wide range of situations. For example, even in a course such as a circuit field without a map, a travel locus can be recorded by calculating a road model in real time. Further, even on a temporary road (course) where pylons are installed side by side in a large parking lot, it is possible to record a travel locus in the same manner.

  In addition, since the current position of the vehicle is calculated by the calculation unit 11, for example, when a travel locus is displayed on the display device 15, the travel locus is accurately obtained by connecting road models based on this position. Can be displayed. Further, by storing the travel locus data in an information recording medium that is easy to carry or transmitting it to an external device, processing such as data analysis and storage can be executed using the external device. Thereby, traveling locus data can be used more effectively. For example, not only the travel locus by the actual driving operation in a certain course is displayed, but also the travel locus by the driving operation by the theoretical optimal solution is compared and displayed. In this case, by displaying the vehicle parameters on the display device 15, it is possible to perform a more detailed comparison of traveling tracks.

(Second Embodiment)
FIG. 6 is a block diagram of a travel locus recording apparatus according to the second embodiment. The second embodiment is different from the first embodiment in that the GPS position detection unit 13e is not provided. Note that in the second embodiment, the same components as those described in the first embodiment are denoted by the same reference numerals, and description thereof is omitted. In the case where the GPS position detection unit 13e is provided, the road model stored in time series according to the traveling of the host vehicle is related to each other by using the absolute position by GPS as a reference. Can do. On the other hand, in the second embodiment in which the GPS position detection unit 13e is not provided, the road models stored in time series are correlated with each other by estimating the movement amount of the host vehicle. There is a need. The movement amount of the vehicle can be estimated by using a method of estimating using dead reckoning or a method of estimating from the image data and the distance data.

  In the movement amount estimation method using dead reckoning, the calculation unit 11 calculates the movement distance of the vehicle after elapse of a predetermined time (for example, routine call interval) based on the vehicle speed obtained from the vehicle speed sensor 13a. At the same time, the direction change amount of the vehicle obtained from the vehicle direction sensor 13d is calculated. Based on the calculated vehicle travel distance and vehicle azimuth change amount, the calculation unit 11 calculates the vehicle travel position as the current position. Then, the moving position of the vehicle is recorded in the recording unit 14 in time series. The amount of movement of the vehicle is calculated from the movement position of the vehicle recorded in time series.

  According to the present embodiment, the same effects as those of the first embodiment described above can be achieved by estimating the amount of movement of the vehicle. Since the amount of movement of the vehicle is estimated, if an error occurs between the actual amount of movement of the vehicle and the estimated amount of movement, the error may accumulate by repeating this over time. There is sex. For example, when the vehicle is traveling on an oval course as shown in FIG. 5A, the start position and the goal position may not match. For this reason, when the GPS position detection unit 13e is not provided, it is preferable to partially display the change over time in the travel locus by using, for example, a display form as shown in FIG. However, although there is a possibility that the reproducibility of the travel locus may be reduced as compared with the first embodiment, according to the second embodiment, the configuration of the detection unit 13 is simplified, and the cost can be reduced. it can.

1 is a block diagram of a travel locus recording apparatus according to a first embodiment. Explanatory drawing of the pixel block set to the reference image Flowchart showing a procedure for recording a vehicle travel locus Explanatory diagram of road model connection processing Explanatory drawing of running track data displayed on the display screen Block diagram of a travel locus recording apparatus according to the second embodiment

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Stereo camera 2a Main camera 2b Sub camera 3,4 A / D converter 5 Image correction part 6 Stereo image processing part 7 Distance data memory 8 Image data memory 9 Microcomputer 10 Recognition part 11 Calculation part 12 Control part 13 Detection part 13a Vehicle speed Sensor 13b Rudder angle sensor 13c Rate sensor 13d Vehicle direction sensor 13e GPS position detection unit 14 Recording unit 15 Display device 16 Information recording device 17 Information transmission device

Claims (11)

In an apparatus for recording the traveling locus of a vehicle,
A stereo camera that outputs a pair of image data by imaging a landscape including a road ahead of the vehicle;
A stereo image processing unit that calculates distance data using stereo matching based on the pair of image data;
Based on the distance data calculated by the stereo image processing unit, a road model that defines the road shape is calculated by recognizing the position of the road ahead of the vehicle in a three-dimensional space based on the position of the vehicle. A recognition unit;
A recording unit that stores the calculated road model in time series according to the traveling of the vehicle;
A detection unit for detecting a vehicle parameter indicating a running state of the vehicle,
The recording unit stores the detected vehicle parameter in association with the calculated road model.   The travel locus recording apparatus according to claim 1, wherein the recognition unit detects a feature existing along the road and calculates the road model based on a position of the feature. . By further receiving a radio wave emitted from a satellite to calculate a current position of the vehicle;
The travel locus recording apparatus according to claim 1, wherein the recording unit stores the calculated current position of the vehicle in association with the calculated road model. A control unit that determines the content to be displayed based on the information stored in the recording unit;
A display device controlled by the control unit and displaying the determined content;
The control unit is configured to display the road shape of the road on which the vehicle has traveled by connecting the stored road models in time series in consideration of the amount of movement of the vehicle. The travel locus recording apparatus according to claim 1, wherein the display device is controlled so as to display a position of the vehicle on the road.   The control unit controls the display device to display the road shape and the position of the vehicle on the road in a two-dimensional manner with the upper side of the road as a viewpoint, and also controls the road shape and the vehicle on the road. The travel locus recording apparatus according to claim 4, wherein the display device is controlled so that the position is three-dimensionally displayed with the upper side of the road as a viewpoint.   The travel locus recording apparatus according to any one of claims 1 to 5, further comprising an information recording apparatus that writes information stored in the recording unit to an information recording medium.   The travel locus recording apparatus according to any one of claims 1 to 6, further comprising an information transmission device that transmits information stored in the recording unit to an external device through communication. In a method of recording a travel locus of a vehicle,
A first step of acquiring a pair of image data output by imaging a landscape including a road ahead of the vehicle using a stereo camera;
A second step of calculating distance data using stereo matching based on the pair of image data;
A third step of calculating a road model that defines a road shape by recognizing a position of a road ahead of the vehicle in a three-dimensional space based on the position of the vehicle based on the distance data;
A fourth step of storing the calculated road model in time series according to the traveling of the vehicle, and a fifth step of acquiring a vehicle parameter indicating a traveling state of the vehicle,
The fourth step includes a step of storing the detected vehicle parameter in association with the calculated road model.   9. The travel locus according to claim 8, wherein the third step detects a feature existing along the road and calculates the road model based on the position of the feature. Recording method. A step of calculating a current position of the vehicle by receiving radio waves emitted from a satellite;
The travel locus recording method according to claim 8 or 9, wherein the fourth step includes a step of storing the calculated current position of the vehicle in association with the calculated road model.   In consideration of the amount of movement of the vehicle, the display device is controlled to display the road shape of the road on which the vehicle has traveled by connecting the stored road models in time series, and The travel locus recording method according to any one of claims 8 to 10, further comprising a step of controlling the display device so as to display a position of a vehicle on a road.

Images