KR100887721B1 - Video Vehicle Navigation Apparatus and Method - Google Patents

Abstract

The present invention relates to a video vehicle navigation apparatus and method for superimposing and outputting a point-of-interest on a screen acquired from a camera mounted on a vehicle. The video vehicle navigation apparatus of the present invention displays a point of interest on the screen using the relative coordinates on the map of the point of interest with respect to the coordinate on the map of the traffic light recognized by the camera. In addition, the screen is divided into a plurality of reference areas based on the traffic light, depending on where the position of the map of the point of interest is to the left and right of the traffic light, and whether the position of the point of interest is closer than the vehicle to the position of the map of the traffic light. Or, depending on how far you are, the point of interest corresponds to either reference area. If the 2D image coordinates calculated directly from the location on the map of the point of interest deviate from the reference region, the point of interest coordinates corresponding to the reference region are output on the screen instead of the 2D image coordinates. In addition, the coordinate of the point of interest includes a coordinate representatively representing the point of interest and additional coordinates indicating an entrance and exit of the point of interest.

Description

Image Vehicle Navigation System and Method {IMAGE CAR NAVIGATION SYSTEM AND METHOD}

The present invention relates to a vehicle navigation apparatus and method, and more particularly, to a vehicle navigation apparatus and method for displaying a point of interest (POI) in an image collected in real time by a camera mounted on a vehicle.

The present invention is derived from the research conducted as part of the IT growth engine core technology development project of the Ministry of Information and Communication and the Ministry of Information and Communication Research and Development. [Task Management No .: 2005-S-114-03, Title: Construction of Realistic Content for Telematics / Management skills development].

In a map-based vehicle navigation system for guiding vehicle progress in a two-dimensional map form, points of interest (POIs) are displayed on a map screen in the form of icons or text. POI refers to objects such as buildings, parks, and facilities. POI information includes data consisting of coordinates and text information in the form of points or planes on a map coordinate system.

In addition, the video vehicle navigation apparatus that guides the driving of the vehicle by the image collected in real time by the camera mounted on the vehicle displays the POI superimposed on the front image of the vehicle. However, in order to output POI to an image, the exact camera position and posture are required. In the two-dimensional map-based vehicle navigation system, if the approximate location of the vehicle is identified, there is no big problem in performing functions such as route guidance or map output.However, in the video vehicle navigation system, even a small error in the camera position and attitude is not included in the vehicle navigation function. Great influence For example, driving in one lane of a wide road and driving in four lanes are difficult to distinguish and do not need to be distinguished by the functions of a normal GPS receiver and a two-dimensional vehicle navigation system. It makes a difference.

Conventionally, a technique of correcting the position and attitude information of a camera using an inertial sensor such as a gyroscope has been known in order to obtain accurate camera information. In addition, a technique for detecting an azimuth and an inclination angle of a camera using an inertial sensor such as a gyroscope and an inclinometer is also known in the art.

Another consideration that is not considered in two-dimensional map-based vehicular navigation systems, but also considered in visual vehicular navigation systems is that the building's actual position and the POI's image output position if the building is far from the entrance of the roadside or the building area is very large. Is that a difference can occur. For example, if only the center point of a building is stored in POI coordinates, the entrance for entering the building may actually be visible on the roadside, but the building itself may not be output on the screen as a POI.

The conventional video vehicle navigation apparatus has a problem in that the manufacturing cost increases because an expensive inertial sensor is used to obtain accurate camera information. In addition, since the conventional video vehicle navigation apparatus provides only a single coordinate with respect to the POI, a large building enters the field of view, but the building may not be output as a POI in the image. There is this.

It is therefore an object of the present invention to provide a video vehicle navigation apparatus and method capable of obtaining low cost and accurate camera information.

It is another object of the present invention to use a GPS receiver and a camera without expensive inertial sensors, and a video vehicle navigation apparatus and method that can output POI information superimposed on a real-time video by using a result recognized from an image acquired by the camera. To provide.

Another object of the present invention is to use the additional point data associated with POI coordinates (points or faces), unlike conventional POI data organization, so that even if the building does not appear on the screen, the actual position of the required entrance on the roadside while driving The present invention provides a vehicle navigation apparatus and method for outputting on a screen to help a driver find directions.

The video vehicle navigation apparatus of the present invention for achieving the object as described above is a video vehicle navigation apparatus for displaying a point of interest on the screen, a data input unit for obtaining the screen from a camera mounted on the vehicle, and the screen An image recognizing unit for recognizing a reference object from an electronic map unit, an electronic map unit providing information about the point of interest and a position on a map of the reference object, and a relative position between a position on the map of the reference object and a position on the map of the point of interest And a calculator configured to determine a location of the point of interest on the screen of the point of interest based on the reference object using a relationship, and an output unit to display the point of interest at the point of interest on the screen.

In addition, in order to achieve the above object, the video vehicle navigation method of the present invention is a video vehicle navigation method for displaying a point of interest on a screen, comprising: (a) acquiring the screen by a data input unit from a camera mounted on a vehicle; (B) recognizing, by the image recognition unit, a reference object from the screen, and (c) between a location on the map of the reference object provided by the electronic map unit and a location on the map of the point of interest. Determining a location of the point of interest on the screen of the point of interest based on the reference object by using a relative position relationship, and (d) by the outputting unit, the point of interest on the point of interest on the screen Marking a point.

In this case, the reference object may be a traffic light.

Therefore, according to the present invention, the point of interest may be specified only by the position on the map of the point of interest relative to the reference object without the existing expensive inertial sensor.

In addition, in the video vehicle navigation apparatus and method of the present invention, the operation unit comprises a screen reference area setting unit for dividing the screen into a plurality of screen reference areas on the basis of the reference object, the screen reference area setting unit, The location of the point of interest is determined by corresponding the point of interest to one screen reference area of the plurality of screen reference areas. In this case, the correspondence relationship of the point of interest with respect to the screen reference area is determined by the positional relationship between the vehicle, the reference object, and the point of interest.

In addition, in the video vehicle navigation apparatus and method of the present invention, the output unit calculates the two-dimensional image coordinates from the position on the map of the point of interest, and the two-dimensional image coordinates in the screen reference region to which the position of the point of interest corresponds. If is away, the point of interest is displayed at the point of interest instead of the point of interest in the two-dimensional image coordinates.

Therefore, when there is an error in the 2D image coordinates of the point of interest calculated from the 3D map coordinates, instead of the 2D image coordinates, the point of interest may be displayed at the point of interest point specified in the reference region setting process. Therefore, the point of interest can be displayed at a more accurate position on the screen.

In addition, in the video vehicle navigation apparatus and method of the present invention, the image recognition unit includes a lane recognition unit for recognizing the lane in front of the vehicle from the screen, the operation unit from the information on the lane recognized by the lane recognition unit It may include an azimuth calculation unit for calculating a vehicle azimuth angle of the vehicle.

In this case, the output unit is a vehicle azimuth used to calculate two-dimensional image coordinates from a position on the map of the point of interest, and the vehicle azimuth from one of the vehicle azimuth calculated by the calculating unit and the GPS receiver provided by the GPS receiver. You can choose.

Therefore, the vehicle azimuth from the GPS receiver can be used in a vehicle speed section (for example, 20 km / h) with high reliability for the GPS data, and otherwise, the vehicle azimuth calculated from the recognized lane can be used. It is possible to more accurately specify the vehicle azimuth to be used to calculate the two-dimensional image coordinates from the position.

In addition, in the video vehicle navigation apparatus and method of the present invention, the image recognition unit includes a driving lane recognition unit for recognizing the driving lane of the vehicle from the information on the lane recognized from the screen, the operation unit, the lane recognition unit It may include a position calculation unit for calculating the position of the vehicle from the information on the driving lane recognized by the.

In this case, the data input unit receives position information of the vehicle from a GPS receiver, and the position calculating unit stores the position information of the vehicle received from the GPS receiver on information about the driving lane recognized by the driving lane recognition unit. By calculating by calculating the position of the vehicle.

Therefore, it is possible to eliminate the distance error in the direction perpendicular to the road center line with respect to the position of the vehicle specified as the center line of the road by the information from the GPS receiver.

In addition, in the apparatus and method of the image vehicle navigation system of the present invention, the point of interest is associated with a plurality of point of interest coordinates on a map, and the calculating unit is any one of the plurality of point of interest coordinates to determine the relative positional relationship. A point of interest coordinate of may be specified as a location on the map of the point of interest.

Therefore, the position of the point of interest may be displayed on the screen as needed by a plurality of coordinates including coordinates representing the point of interest and coordinates linked with the coordinates to indicate an entrance and the like of the point of interest. Can be specified precisely.

According to the present invention, there is an effect that the point of interest can be specified only by the position on the map of the point of interest relative to the reference object without the existing expensive inertial sensor.

Further, according to the present invention, when there is an error in the 2D image coordinates of the point of interest calculated from the 3D map coordinates, instead of the 2D image coordinates, the point of interest corresponding to the point of interest specified in the reference region setting process is specified. Since it can be displayed, there is an effect that can display the point of interest in a more accurate position on the screen.

In addition, according to the present invention, since the vehicle azimuth angle from the GPS receiver can be used in the vehicle speed section (for example, 20 km / h) with high reliability for GPS data, otherwise the vehicle azimuth calculated from the recognized lane can be used. For example, the vehicle azimuth angle to be used to calculate the two-dimensional image coordinates from the location of the point of interest on the map can be more accurately specified.

In addition, according to the present invention, there is an effect that can eliminate the distance error in the direction perpendicular to the road centerline with respect to the position of the vehicle specified as the centerline of the road by the information from the GPS receiver.

In addition, according to the present invention, the position of the point of interest may be displayed on the screen as needed by a plurality of coordinates including coordinates representing the point of interest and coordinates linked to the coordinates to indicate the entrance and exit of the point of interest. Therefore, there is an effect that can more accurately specify the point of interest.

Hereinafter, with reference to the accompanying drawings will be described an embodiment of the present invention.

1 is a configuration diagram of a video vehicle navigation apparatus according to an embodiment of the present invention, Figure 2 is a detailed configuration diagram of FIG. The image vehicle navigation apparatus 100 includes a data input unit 10, an electronic map unit 20, an image recognition unit 30, an operation unit 40, and an output unit 50.

The data input unit 10 acquires a current position of the vehicle and an image in front of the vehicle from a GPS receiver and a camera not shown. The electronic map unit 20 includes POI data including a position coordinate value of the POI and text describing the POI (for example, a building name such as an ABC building), traffic light data including a position coordinate value of a traffic light, and Including maps of the electronic road, POI data and traffic light data associated with the current position of the vehicle are retrieved and mapped onto the electronic road map. The image recognition unit 30 recognizes a lane and a traffic light in the road image acquired from the camera and calculates a position of the current driving lane of the vehicle. The calculation unit 40 calculates the vehicle azimuth angle from the GPS signal and calculates the vehicle azimuth angle and the current vehicle position based on the image coordinates of the lanes and the traffic lights received from the image recognition unit 30 and the current driving lane position of the vehicle. The output unit 50 converts the POI coordinates into image coordinates by using the vehicle position and the vehicle azimuth angle and outputs the image superimposed on the image.

In the present specification, an area having an area on which a vehicle travels on a road is referred to as a 'lane', and a line (including a center line and a road boundary line) for dividing it is referred to as a 'lane'. In addition, the driving lane position refers to the number of lanes sequentially given from the center line of the road. For example, if the vehicle is driving on the second lane from the center on the one-way four-way road, the driving lane position = 2. 'Vehicle azimuth' refers to the angle formed by the traveling direction of the vehicle (the same direction that the optical axis of the camera faces) with respect to the N axis of the map coordinate system.

In addition, in the present embodiment, a traffic light is used as a reference object for displaying the image of the POI, but an object other than the traffic light may be used as the reference object as long as the object has a high discrimination power and a high density of arrangement with other objects.

FIG. 2 is a detailed block diagram of the video vehicle navigation apparatus 100 of FIG. 1. The data input unit 10 includes a camera 11 for acquiring a real-time image of the front of the vehicle and a GPS receiver 12 for acquiring GPS data including a vehicle position, a vehicle azimuth angle, and a vehicle speed. The direction of the camera is assumed to be parallel to the direction of travel of the vehicle, and the direction of travel of the vehicle and the direction of the camera are the same. In addition, the camera 11 and the GPS receiver 12 are located so close that the distance between them can be ignored.

The electronic map unit 20 includes an electronic road map unit 21, a map matching processing unit 22, a POI data unit 23, a POI search unit 24, a traffic light data unit 25, and a traffic light search unit 26. . The electronic road map unit 21 has the coordinates of the road.

The map matching processor 22 receives GPS coordinates from the GPS receiver 12 and performs a map matching process. The map matching method is not unique. For example, the current GPS coordinates are compared with the road coordinates of the electronic road map unit 21 to calculate a position on the road closest to the current GPS coordinates. That is, the map matching processing unit 22 maps the position of the vehicle to the center line of the road as the position on the road closest to the GPS coordinate value in order to minimize the error existing in the GPS coordinate value. Therefore, the GPS error in the direction perpendicular to the center line of the road is eliminated. The coordinate values obtained through the map matching process as described above are transmitted to the calculator 40.

The POI data unit 23 has respective POI coordinate values and text attribute values for various objects (buildings, parks, facilities, etc.). In the case of a building, the POI coordinate is configured by linking an additional coordinate value indicating a location of a doorway entrance of the building to an object coordinate value representatively representing the location of the building itself. This data configuration method will be described in more detail with reference to FIG. 3.

3B is an object coordinate value table including coordinate values of the object itself (ie, the viewing itself). Object coordinate values are distinguished from each other by text attribute values such as 'viewing'. 3C is an additional coordinate value table including coordinate values additionally indicating a location of a roadside entrance of a building. Additional coordinate values are distinguished from each other by text attribute values such as 'main gate' and 'east gate'. The object coordinate table and the additional coordinate table are linked by 'name'. In the case of 'viewing', additional coordinate values of 'alumni' and 'preface' are linked to the object coordinates of the city hall itself.

The POI retrieval unit 24 retrieves POI information of the POI data unit 23 according to conditions such as text attribute values and coordinate values. In FIG. 3A, when the vehicle travels in the A direction with the city hall as the destination, the POI search unit 24 searches for additional coordinate values of the 'main gate' rather than the object coordinate value of the city hall itself. In this case, if the object coordinate value of the city hall itself or additional coordinate value of 'alumni' is used, such coordinate value does not appear on the screen. Similarly, when the vehicle travels in the B direction with the city hall as the destination, the POI retrieval unit 24 searches for an additional alumni coordinate value.

The traffic light data unit 25 has traffic light information including coordinate values of traffic lights on the road, and the traffic light search unit 26 retrieves the traffic light information required by the operation unit 40 from the traffic light data unit 25 and calculates the operation unit. To 40.

The association recognition unit 30 includes a lane recognition unit 31, a driving lane recognition unit 32, and a traffic light recognition unit 33.

The lane recognizing unit 31 recognizes the lane from the image acquired by the camera. For example, the lane recognizing unit 31 performs image processing on the image in front of the vehicle, extracts lane data on the left and right sides of the vehicle, and then compares the lane data with previously stored lane recognition pattern data. I can recognize it. The lane recognizing unit 31 transmits the recognized value to the driving lane recognizing unit 32 and the calculating unit 40 in the form of a straight line expressed as a parameter on the image coordinates.

The driving lane recognition unit 32 calculates the position of the current driving lane using the lane recognized from the image acquired by the camera, and transmits the result to the calculation unit 40. For example, if lanes are drawn on the road so that each lane is distinguished from other lanes, that is, the center line is straight, the right lane of the first lane is broken, the right lane of the second lane is dotted, etc. In this case, the recognition pattern data for the lanes which are separated from each other are stored in advance, and the vehicle recognition pattern data corresponding to the lane recognition pattern recognized by the lane recognition unit 31 is retrieved from the stored recognition pattern data. The current driving lane position may be calculated using a known method of determining whether the driving lane is being driven.

The process of the traffic light recognition unit 33 to recognize the traffic light is similar to the process of the lane recognition unit 31 to recognize the lane. That is, the traffic light recognition unit 33 processes the vehicle front image acquired by the camera, and recognizes the image data corresponding to the signal light recognition pattern data stored in advance from the image data obtained by such a process as the traffic light and recognizes the traffic light. The image coordinate value of is transmitted to the calculator 40. The image coordinate value refers to a coordinate value in the image displayed on the screen of the image vehicle navigation apparatus.

The calculation unit 40 calculates the vehicle position and the vehicle azimuth angle from the coordinate values transmitted from the map matching processor 22 and the image recognition result transmitted from the image recognition unit 30.

The position calculating unit 41 corrects the current vehicle position recognized from the map matching data transmitted from the map matching processing unit 22 by the driving lane position information transmitted from the driving lane recognition unit 31. As described above, since the map matching processing unit 22 maps the position of the vehicle to the center line of the road, it is necessary to correct the position of the vehicle in order to determine the exact position of the vehicle. Since the position calculating unit 41 knows the position of the driving lane of the vehicle by the position of the driving lane received from the driving lane detecting unit 32, the position calculating unit 41 determines the position of the vehicle from the road center line from the position of the driving lane and the width of the lane. By calculating the distance away in the direction perpendicular to each other, the position of the vehicle map-matched to the center line of the road can be corrected to the actual vehicle position. At this time, the width of the lane is used when there is precise data indicating the width of each lane, and otherwise, a value standardized according to the region (for example, 3.5 m in the case of urban roads) is used.

The azimuth calculation unit 42 calculates the vehicle azimuth using the lane information transmitted from the lane recognizing unit 32. The lane is almost parallel to the center line of the road, so the angle that the vehicle makes with the road is the same as the angle that the vehicle makes with the lane. However, during actual driving, there are times when the lane and the vehicle are not parallel to form an angle. In this case, the vehicle azimuth is calculated by adding the angle formed by the road with the N-axis of the map and the angle formed by the vehicle with the lane of the road.

The azimuth calculation unit 42 calculates the angle between the vehicle and the lane, for example, as follows. Normal lines from the left lane when a virtual normal line is drawn from the left and right vehicle lanes on the screen recognized by the lane recognizing unit 32 toward the center of both lanes, and a virtual horizontal axis passing through the point on the screen where the two normal lines meet. If the first angle formed by the horizontal axis and the normal angle from the right lane and the second angle formed by the horizontal axis are the same, the angle formed by the vehicle and the lane may be 0 degrees. Therefore, the angle formed by the vehicle and the lane may be calculated from the difference between the first angle and the second angle. As the difference between the first and second angles increases, the angle between the vehicle and the lane will increase proportionally. The vehicle azimuth calculated in this way is selectively used by the output unit 50 together with the vehicle azimuth provided by the GPS receiver 12.

The screen reference area setting unit 43 divides the screen of the video vehicle navigation apparatus into a plurality of reference areas by using the video coordinate values of the traffic lights received from the traffic light recognition unit 33 as the reference coordinate values, and the POI is displayed on the screen. In order to approximate the position to be expressed in the POI, the POI is compared with the position information (coordinate value) of the POI received from the POI search unit 24 with the position information (coordinate value) of the traffic light transmitted from the traffic light search unit 26. It corresponds to the screen reference area divided on the screen. That is, each POI is appropriately displayed on the screen according to the relative position of the POI with the position of the traffic light as the origin.

A method in which the screen reference area setting unit 43 corresponds to the reference area divided on the screen will be described with reference to FIG. 4. The map area is divided into four areas by a dotted line HL connecting the coordinates of the traffic light and the vehicle location on the map of FIG. 4A and a dotted line VL perpendicular to the current road and passing through the coordinates of the traffic light. A, B, C, D, and E on the map represent POIs.

4B illustrates a screen of the video vehicle navigation apparatus. The screen reference area setting unit 43 first displays a traffic light on the screen according to the image coordinate values of the traffic light transmitted from the traffic light recognition unit 33, and displays the four screen reference areas S1, S2, S3, And screen S4.

Subsequently, the screen reference area setting unit 43 matches the POIs of A, C, and E appearing on the map to the left of the traffic light on the map to correspond to the screen reference areas S1 and S3 to the left of the traffic light on the screen. POI of D corresponds to the screen reference areas S2 and S4 on the right side of the traffic light on the screen. In addition, the screen reference area setting unit 43 corresponds to the screen reference areas S1 and S2 above the traffic lights on the screen so that the POIs of A and B closer to the traffic lights when viewed from a vehicle, The POI corresponds to the screen reference areas S3 and S4 below the traffic light on the screen. As a result, each POI of A, B, C, D, and E corresponds to one of four screen reference areas on the screen. In the example of FIG. 4, the POI of E will be placed in the screen reference area of S3, and the POI of B will correspond to the screen reference area of S2.

On the other hand, since the screen reference area setting unit 43 knows the coordinate value of the traffic light and the coordinate value of each POI, the POI is somewhat accurate on the screen by the relative coordinate value of each POI whose coordinate value of the traffic light is the origin. The display position can be determined. Therefore, the screen reference area setting unit 43 can determine the display position of the POI on the screen from the relative coordinate value of each POI with respect to the coordinate value of the traffic light without distinguishing the screen reference area. The reason for dividing the reference area is that the image coordinates of the POI calculated by projecting the three-dimensional map coordinates to the two-dimensional image coordinates by the output unit 50, which will be described later, correspond to the reference region corresponding to the screen reference area setting unit 43. If it does not correspond, it can be confirmed that the image coordinates are not calculated correctly.

The output unit 50 inputs a vehicle position, a vehicle azimuth angle, a known camera parameter, POI data, and a screen reference area, and inputs the image coordinates of the POI calculated by projecting the three-dimensional map coordinates of the output target POI to two-dimensional image coordinates. Output At this time, the output unit 50, the vehicle azimuth angle of the vehicle azimuth angle calculated by the azimuth angle calculation unit 42 and the vehicle azimuth angle provided from the GPS receiver 12 according to the vehicle speed provided from the GPS receiver 12 Calculate the video coordinates of the POI.

Specifically, for a vehicle speed of 20 km / h or more, which is known to be reliable for GPS information, the vehicle azimuth angle provided from the GPS receiver 12 is used, and below 20 km / h, the vehicle azimuth angle calculated by the azimuth calculation unit 42 is used. This is used. In addition, when the lane is not properly recognized due to congestion in front of the vehicle, the vehicle azimuth angle provided from the GPS receiver 12 is used regardless of the speed of the vehicle.

In addition, the output unit 50 checks whether the on-screen area of the calculated video coordinates of the POI coincides with the screen reference area corresponding by the screen reference area setting unit 43. The image coordinates on the screen reference region corresponding to the screen reference region setting 43, not the calculated image coordinates of the POI, are output on the screen as the image coordinates of the corresponding POI.

In addition, the output unit 50, for the objects (buildings, etc.) located on the left side of the screen, the text attribute values (eg, building names, etc.) of the POI data in the form of a three-dimensional signboard with a tail on the left side of the object. For the object located on the right side of the screen, the text attribute value of POI data is output to the image in the form of a 3D sign with a tail on the right side of the object. In addition, the signboard output to the video is configured to some extent so as not to hide other information on the screen.

5 is a flowchart of the operation by the video vehicle navigation apparatus of the present embodiment. When the system starts (S61), the camera 11 of the data input unit 10 acquires the image of the front of the vehicle at a constant frame rate, and the GPS receiver measures the current position coordinate value, the vehicle azimuth angle, and the vehicle speed at regular time intervals. It is detected (S62).

The data input unit 10 transmits an image to the image recognition unit 30 and the output unit 50, and transmits the position coordinate value to the map matching processing unit 22 of the electronic map unit 20. The map matching processing unit 22 performs map matching to approximate the position coordinate value to the nearest point (ie, the center line) on the road in the electronic road map unit 21 (S63) and calculates the map matched position coordinate value. To send).

The lane recognizing unit 32 of the image recognizing unit 30 recognizes the lane in the received image and transmits the result to the driving lane recognizing unit 31, and the driving lane recognizing unit 31 recognizes the lane in the received image. The driving lane position is calculated using the result (S64). The traffic light recognition unit 33 of the image recognition unit 30 recognizes the traffic light in the received image (S65). The lanes are transmitted to the operation unit 40 in the form of image coordinates, the result of the traffic light recognition in the form of image coordinates of the traffic lights positioned in the image, and the position of the driving lane in the form of numbers (that is, '2' in the case of two lanes). .

The calculating unit 40 calculates the vehicle azimuth angle from the video coordinates of the lane in the manner described above, and calculates the correct vehicle position by correcting the vehicle position from the traveling lane position (S66).

  Next, the POI search unit 24 searches for the output target POI from the POI data (S68). The search method is as described above with reference to FIG. 3. The POI retrieval unit 24 transmits the retrieved POI data (coordinate values and text attribute values) to the screen reference area setting unit 43 of the operation unit 40. In addition, the screen reference area setting unit 43 compares the coordinate values of the POI data with the vehicle position and maps the output area of the POI coordinates to one of the screen reference areas.

Finally, the output unit 50 inputs the vehicle position, the vehicle azimuth angle, the known camera parameter, the POI data, and the screen reference area as inputs, and calculates the image of the POI calculated by projecting the three-dimensional map coordinates of the output target POI to the two-dimensional image coordinates. Output the coordinates. At this time, the output unit 50 is calculated by the vehicle azimuth and azimuth calculation unit 42 provided from the GPS receiver 12 according to the vehicle speed provided from the GPS receiver 12 (for example, 20 km / h basis). Image coordinates of the POI are calculated using one of the vehicle azimuths. In addition, the output unit 50 checks whether the on-screen area of the calculated video coordinates of the POI coincides with the screen reference area corresponding by the screen reference area setting unit 43. The image coordinates on the corresponding screen reference region is output by the screen reference region setting unit 43 instead of the calculated image coordinates of the POI as image coordinates of the corresponding POI (S69).

At this time, the output unit 50, for the objects (buildings, etc.) located on the left side of the screen, the text attribute values (eg, building names, etc.) of the POI data in the form of a 3D sign with a tail on the left side of the object. For the object located on the right side of the screen, the text attribute value of POI data is output to the image in the form of a 3D sign with a tail on the right side of the object. In addition, the signboard output to the video is configured to some extent so as not to hide other information on the screen.

The process is repeated for every frame in real time, and terminates when the system receives an end command or the image input is stopped (S70).

On the other hand, the present invention may be implemented by a computer-readable recording medium recording a program for executing the method. In addition, while the embodiments of the present invention described above have been specified by specific configurations and drawings, it is intended to be clear that such specific embodiments do not limit the scope of the present invention. Accordingly, it is to be understood that the invention includes various modifications and equivalents thereof without departing from the spirit of the invention.

1 is a block diagram of a video vehicle navigation apparatus according to an embodiment of the present invention.

FIG. 2 is a detailed configuration diagram of the video vehicle navigation apparatus of FIG. 1. FIG.

3 is a conceptual diagram illustrating the configuration and retrieval of POI data.

4 is a conceptual diagram for explaining setting of a screen reference area.

5 is a flowchart of an image vehicle navigation operation according to an embodiment of the present invention.

Claims (16)

An image vehicle navigation device for displaying a point of interest on a screen, A data input unit for acquiring the screen from a camera mounted on a vehicle; An image recognition unit recognizing a reference object from the screen; An electronic map unit which provides information on a location on the map of the point of interest and the reference object; An operation unit which determines a location of the point of interest on the screen of the point of interest based on the reference object by using a relative positional relationship between a position on the map of the reference object and a position on the map of the point of interest; And an output unit configured to display the point of interest at the point of interest on the screen. The display apparatus of claim 1, wherein the operation unit comprises a screen reference area setting unit dividing the screen into a plurality of screen reference areas based on the reference object, and the screen reference area setting unit is configured to reference the points of interest to the plurality of screen references. And determine the location of the point of interest by corresponding to one screen reference area of the area. The display apparatus of claim 2, wherein the output unit calculates two-dimensional image coordinates from a location on a map of the point of interest and, when the two-dimensional image coordinates deviate from a screen reference area to which the location of the point of interest corresponds. And display the point of interest at the point of interest location instead of the point of interest in dimensional image coordinates. The apparatus of claim 1, wherein the image recognizing unit includes a lane recognizing unit recognizing a lane in front of the vehicle from the screen, and the calculating unit calculates a vehicle azimuth angle of the vehicle from information about the lane recognized by the lane recognizing unit. An imaging vehicle navigation apparatus comprising an azimuth calculator. The apparatus of claim 1, wherein the image recognition unit comprises a driving lane recognizing unit recognizing a driving lane of the vehicle from information on the lane recognized from the screen, and the calculating unit is related to the driving lane recognized by the lane recognizing unit. And a position calculator for calculating the position of the vehicle from the information. The driving apparatus according to claim 5, wherein the data input unit receives position information of the vehicle from a GPS receiver, and the position calculating unit transmits the position information of the vehicle received from the GPS receiver to a driving lane recognized by the driving lane recognition unit. A video vehicle navigation apparatus which calculates the position of the vehicle by correcting the information with respect to the information. The point of interest of claim 1, wherein the point of interest is associated with a plurality of point of interest coordinates on a map, and the operation unit converts the point of interest coordinate of any one of the plurality of point of interest coordinates to determine the relative positional relationship. The video vehicle navigation apparatus which specifies with the position on the map of the. The video vehicle navigation apparatus according to claim 7, wherein the calculator specifies a point of interest coordinate closest to the current position of the vehicle among the plurality of point of interest coordinates as a position on the map of the point of interest. The apparatus of claim 7, wherein the plurality of points of interest coordinates include coordinates of a doorway of the point of interest. The video vehicle navigation apparatus of claim 1, wherein the reference object is a traffic light. An image vehicle navigation method for displaying a point of interest on a screen, (a) acquiring the screen by a data input unit from a camera mounted on the vehicle; (b) recognizing, by the image recognition unit, the reference object from the screen; (c) the location of the point of interest on the screen of the point of interest relative to the reference object using a relative positional relationship between the location on the map of the reference object and the location of the point of interest provided by the electronic mapper; Determining by the operation unit; and (d) displaying the point of interest at the point of interest point on the screen by an output unit. The method of claim 11, wherein the step (c) comprises: dividing the screen into a plurality of screen reference areas based on the reference object, and corresponding the point of interest to one screen reference area of the plurality of screen reference areas. And determining the location of the point of interest, wherein step (d) comprises: calculating a two-dimensional image coordinate from a location on the map of the point of interest; And displaying the point of interest at the point of interest instead of displaying the point of interest in the two-dimensional image coordinates when the two-dimensional image coordinates are out of range. 12. The method of claim 11, wherein the step (b) comprises the step of recognizing the lane in front of the vehicle from the screen, and the step (c) includes calculating the vehicle azimuth angle of the vehicle from the information about the recognized lane. Wherein the step (d) is a vehicle azimuth used for calculating two-dimensional image coordinates from a position on the map of the point of interest, the vehicle azimuth calculated in the step (c) and the vehicle provided from the GPS receiver. And selecting one vehicle azimuth angle based on the current speed of the vehicle. The method of claim 11, wherein the step (b) comprises the step of recognizing the driving lane of the vehicle from the information on the lane recognized from the screen, the step (c) from the information on the recognized driving lane Calculating a position of the vehicle. 12. The method of claim 11, wherein the point of interest is associated with a plurality of point of interest coordinates on a map, wherein step (c) includes the point of interest coordinates of any one of the plurality of point of interest coordinates to determine the relative positional relationship. And a location on the map of the point of interest. The video vehicle navigation method according to claim 11, wherein the step (b) recognizes a traffic light as the reference object from the screen.

Images