JPWO2013088626A1 - Coordinate conversion table creation system and coordinate conversion table creation method - Google Patents

Abstract

  A coordinate conversion table creation system for creating a coordinate conversion table between an image system coordinate set for a captured image and a world coordinate system set for an immovable object. An image system information acquisition unit that acquires the image system vehicle position at the set image system coordinates and outputs the image system information, and acquires the world system vehicle position of the vehicle with respect to the world system coordinates, as world system information A world system information acquisition unit for outputting, and a coordinate conversion information creation unit for creating a coordinate conversion table of the image system coordinates and the world system coordinates based on the image system information and the world system information.

Description

  The present invention relates to a coordinate conversion table creation system and a coordinate conversion table creation method.

  In recent years, in order to measure traffic flow, to prevent collision accidents at curves and intersections with poor visibility, etc., the vehicle is photographed using a photographing device installed on the roadside, and the position and speed of the vehicle are determined from the photographed image. A safe driving support system for detection has been proposed.

  In such a safe driving support system, TTC (Time-To-Collision) is estimated based on the position and speed of the vehicle acquired from the captured image. Then, based on the estimation result, attention to the driver, brake control of the vehicle, and the like are performed. Therefore, the position and speed of the vehicle need to be acquired with high accuracy.

  In order to obtain the position and speed of a vehicle from a captured image with high accuracy, the position of the vehicle in a coordinate system (hereinafter referred to as an image coordinate system) set in the captured image is set in a real space such as a road. It is necessary to convert to a coordinate system (hereinafter referred to as the world coordinate system). That is, coordinate conversion between the image coordinate system and the world coordinate system is required.

  Therefore, when a new photographing apparatus such as a monitoring camera for monitoring the vehicle is installed, a coordinate conversion table between the image coordinate system and the world coordinate system is created.

  As a technique for creating such a coordinate conversion table, Japanese Patent Application Laid-Open No. 2010-236891 discloses the following method. That is, the vehicle on which the target is mounted is photographed by a roadside camera (photographing device), and the position of the target in the image coordinate system is obtained from the photographed image. On the other hand, the position of the target in the world coordinate system is obtained by using GPS (Global Positioning System). Then, the correspondence table is created by comparing the positions of the target in the world coordinate system and the image coordinate system and associating them.

  However, the technique according to Japanese Patent Application Laid-Open No. 2010-236891 has a problem that a coordinate conversion table cannot be created when a roadside camera is installed in a space such as a tunnel where GPS cannot be used.

  Accordingly, a main object of the present invention is to provide a coordinate conversion table creation system and a coordinate conversion table creation method capable of acquiring a coordinate conversion table between an image coordinate system and a world coordinate system with high accuracy even in an environment where GPS such as a tunnel cannot be used. Is to provide.

  In order to solve the above-described problem, the coordinate conversion table creation system captures a traveling vehicle, acquires an image system vehicle position at an image system coordinate set in the captured image, and outputs the image system information as image system information. An acquisition unit, a world system information acquisition unit that acquires a world system vehicle position of the vehicle with respect to the world system coordinates and outputs it as world system information, and image system coordinates and world system coordinates based on the image system information and the world system information And a coordinate conversion information generation unit for generating the coordinate conversion table.

  In addition, the coordinate conversion table creation method includes a procedure for capturing image system information that captures a traveling vehicle, acquires an image system vehicle position at an image system coordinate set in the captured image, and outputs the image system information; Obtaining the world system vehicle position relative to the world system coordinates and obtaining the world system information to be output as the world system information, and the coordinate conversion between the image system coordinates and the world system coordinates based on the image system information and the world system information And a procedure for creating coordinate conversion information for creating a table.

  According to the present invention, a coordinate conversion table between an image coordinate system and a world coordinate system can be acquired with high accuracy even in an environment where GPS cannot be used such as a tunnel section.

1 is a schematic diagram of a coordinate conversion table creation system according to the present invention. It is a block diagram of a roadside imaging device and an in-vehicle device. It is a flowchart which shows the procedure which produces a coordinate conversion table. It is the figure which illustrated the roadside picked-up image, (a) is the roadside picked-up image in the middle of the vehicle passing the judgment line, (b) is the roadside picked-up image after the vehicle passes the judgment line.

  An embodiment of the present invention will be described. FIG. 1 is a schematic diagram of a coordinate conversion table creation system 2 according to the present invention. The coordinate conversion table creation system 2 includes a roadside imaging device 10 installed on the roadside and an in-vehicle device 20 mounted on the vehicle 30. FIG. 2 is a block diagram of the roadside imaging device 10 and the in-vehicle device 20.

  The roadside photographing apparatus 10 includes a roadside camera 11, a vehicle detection unit 12, an image-based vehicle detection unit 13, and a coordinate conversion table creation unit 14. The roadside camera 11, the vehicle detection unit 12, and the image system vehicle detection unit 13 constitute an image system information acquisition unit 3, and the coordinate conversion table creation unit 14 constitutes a coordinate conversion information creation unit 4.

  The roadside camera 11 is a camera such as a road monitoring camera installed on the roadside. The traveling vehicle 30 is photographed by the roadside camera 11 and is output to the vehicle detection unit 12 and the image system vehicle detection unit 13 as a roadside photographed image. It is assumed that a dotted lane boundary line K is provided on the road (see FIG. 1).

  This lane boundary line K is used as an example of an object that does not move with respect to the roadside photographing apparatus 10 and the in-vehicle apparatus 20 (hereinafter referred to as a reference body). The reference body is not limited to the lane boundary line, and may be a reflector installed on the road. Then, using this reference body K, a reference point for coordinate conversion between the image coordinate system and the world coordinate system is obtained.

  In addition, the roadside camera 11 captures a vehicle tail (vehicle rear) that moves away from the roadside camera 11. An arrow P in FIGS. 1 and 4 indicates the traveling direction of the vehicle 30.

  The vehicle detection unit 12 extracts the vehicle 30 from the roadside photographed image, and determines whether or not the extracted vehicle 30 is within a preset measurement area. This determination is transmitted as area determination information to the global vehicle detection unit 22 by radio means such as radio waves. The measurement area is a range where the position of the vehicle 30 is detected. Even if the vehicle 30 is shown in the roadside photographed image, if the vehicle 30 is small (in the case of a long distance), the accuracy of the vehicle position is low. Therefore, the measurement area is set in advance in consideration of the resolution of the roadside camera 11 and the like.

  Further, the vehicle detection unit 12 determines whether or not the extracted vehicle 30 is approaching the reference body K. When it is determined that the vehicle 30 is approaching the reference body K, the vehicle detection unit 12 transmits vehicle approach information indicating that to the world-based vehicle detection unit 22.

  As shown in FIG. 1, the vehicle boundary line (reference body) K is a line in which a white line K1 having a predetermined length is intermittently connected. Therefore, when the approach of the vehicle 10 is determined, the determination of whether or not the vehicle 10 is approaching differs depending on which position of which white line K1 is used as a reference. Therefore, the end point K2 (K2_i; i is a positive integer) of the white line K1 is set as an approach determination reference position. Since there are many white lines K1, there are also many end points K2, and the approach of the vehicle 30 is determined for each end point K2.

  The image system vehicle detection unit 13 acquires the position of the light source unit 23 from the roadside photographed image. Since the light source unit 23 is installed in the in-vehicle device 20, the position of the light source unit 23 corresponds to the vehicle position. The vehicle position acquired by the image system vehicle detection unit 13 is the vehicle position in the image coordinate system obtained from the roadside photographed image.

  The image system vehicle detection unit 13 sets this vehicle position as the image system vehicle position, sets the acquired time as the image system position acquisition time, and collectively outputs these as image system information to the coordinate conversion table creation unit 14. The image system position acquisition time is obtained from a timer (not shown) provided in the roadside camera 11, the image system vehicle detection unit 13, or the like.

  The coordinate conversion table creating unit 14 coordinates the image coordinate system and the world coordinate system based on the image system information received from the image system vehicle detection unit 13 and the world system information received from the world system vehicle detection unit 22 described later. Create a conversion table.

  Next, the configuration of the in-vehicle device 20 will be described. The in-vehicle device 20 constitutes the world information acquisition unit 5. The in-vehicle device 20 includes an in-vehicle camera 21, a global vehicle detection unit 22, and a light source unit 23 and is mounted on the vehicle 30.

  The in-vehicle camera 21 is a camera that photographs the reference body K. The world-based vehicle detection unit 22 detects the end point K2 of the reference body K based on the image (in-vehicle captured image) captured by the in-vehicle camera 21 and the vehicle approach information received from the vehicle detection unit 12, and with respect to the end point K2. Get the vehicle position at the global vehicle position. In addition, the time when the world system vehicle position is acquired is set as the world system position acquisition time. The world system vehicle position and the world system position acquisition time are transmitted to the coordinate conversion table creation unit 14 as world system information. The world system position acquisition time is obtained from a timer (not shown) provided in the in-vehicle camera 21 or the world system vehicle detection unit 22.

  Further, when the world system vehicle detection unit 22 acquires the world system information, the world system vehicle detection unit 22 outputs a trigger signal to the light source unit 23. The light source unit 23 includes a light source such as an LED, and blinks once every time a trigger signal is received from the world vehicle detection unit 22.

  Next, a procedure for creating a coordinate conversion table using such a coordinate conversion table creation system 2 will be described using the flowchart shown in FIG. For convenience of explanation, it is assumed that the roadside camera 11 is installed in a tunnel, but this embodiment is not limited to use in such an environment.

  Step SA1: The vehicle 30 is traveling on a road in the tunnel. The roadside camera 11 of the roadside photographing apparatus 10 is photographing a road. Therefore, the vehicle 30 entering the shooting area is shot.

  Step SA2: The vehicle detection unit 12 detects the vehicle 30 by performing predetermined image processing on the roadside captured image captured by the roadside camera 11, and acquires the position of the vehicle 30. The vehicle position at this time is a position in the image coordinate system.

  The following method can be illustrated as a detection method of the vehicle 30. That is, an image when the vehicle 30 does not exist is acquired in advance as a background image, and a difference between the roadside captured image captured by the roadside camera 11 and the background image is obtained. Thereby, the vehicle 30 can be extracted. And the vehicle position from the origin set beforehand with respect to the image coordinate system is calculated. The origin can be one point set in the photographing region (for example, one point in the corner of the roadside photographed image). The vehicle position at this time is used to determine whether or not a vehicle 30 described later exists in the measurement area and whether or not the vehicle 30 is approaching. The present embodiment is not limited to such background difference processing, and a known method such as pattern matching can be applied.

  Step SA3: Next, the vehicle detection unit 12 determines whether or not the acquired vehicle position is within a preset measurement area, and transmits the determination result to the global vehicle detection unit 22 as area determination information. .

  Step SA4: If the vehicle detection unit 12 determines that the vehicle 30 is located in the measurement area, the vehicle 30 and the position of the end point K2 of the reference body K in the roadside photographed image are determined according to the procedure described later. Are compared to determine whether or not the vehicle 30 is approaching.

  For example, in FIG. 1, the vehicle 30 is in a state of moving away from the end point K2_4, but is in a state of approaching the end point K2_5. Since the roadside camera 11 is fixed at a fixed position with respect to the road, the roadside camera 11 is also at a fixed position with respect to the end point K2. Therefore, if the position of the end point K2 located in the measurement area is acquired in advance using image system coordinates, it is possible to determine whether the vehicle 30 is approaching each end point K2.

  The vehicle detection unit 12 determines the closest end point K2 from the plurality of end points K2, and determines that the end point K2 is approaching. For example, in FIG. 1, the in-vehicle device 20 is in a state of approaching the end point K2_4 to the end point K2_7, but the end point closest thereto is the end point K2_4. Therefore, the vehicle detection unit 12 determines that the vehicle 30 is approaching the end point K2_4. And when it is judged that it is approaching, it progresses to step SA5, and when it is judged that it is not approaching, it returns to step SA2. If it is determined that the vehicle 30 has not approached the end point K2, it means that the vehicle 30 has moved out of the measurement area.

  The determination as to whether or not the vehicle 30 is approaching is performed as follows. That is, the reference body K is reflected on the roadside photographed image in the form of a white line or the like. Therefore, the vehicle detection unit 12 acquires the reference body K by performing edge extraction processing, high-luminance portion extraction processing, and the like on the roadside photographed image. That is, a reference body K composed of a plurality of white lines K1 is acquired.

  FIGS. 4A and 4B are views showing the reference body K acquired in this way and the vehicle 30 acquired in step SA2. In addition, the dotted line (judgment line) L in the figure is a line that passes through the end point K2 of the reference body K and goes straight to the reference body K. Further, the x mark indicates the position of the in-vehicle device 20 in the vehicle 30. FIG. 4A is a roadside photographed image while the vehicle 30 passes the judgment line L at time t, and FIG. 4B shows the judgment line L at time t + δ (δ> 0). It is the roadside picked-up image after passing through. Thus, when the vehicle 30 passes the determination line L, it is determined that the vehicle 30 is approaching. Setting the determination line L corresponds to specifying the end point K2_4 from among the end points K2_4 to K2_7 that are approaching in FIG.

  Step SA5: When it is determined that the vehicle 30 is approaching, the vehicle detection unit 12 transmits vehicle approach information to the world-based vehicle detection unit 22.

  Note that a wireless LAN or the like can be used for transmission, but other transmission means can be used on condition that the time required for transmission is short. Here, the short time required for transmission means a time when the delay time of information transmission does not become a problem from the viewpoint of required accuracy.

  When the transmission is performed by a packet method, processing is performed so that the global system vehicle detection unit 22 can recognize that the packet is vehicle approach information. For example, a specific 1 bit in the packet data is used as a flag, and this flag is transmitted as “1” indicating that it is a packet of vehicle approach information. Of course, this embodiment is not limited to this method.

  Step SA6: On the other hand, if it is determined in step SA3 that the vehicle 30 is not located within the measurement area, the image-based vehicle detection unit 13 selects a roadside captured image at the moment when the light source unit 23 blinks from the roadside captured image. select. Then, the image system vehicle detection unit 13 acquires the vehicle position (image system vehicle position) from the selected roadside captured image, and acquires the imaging time as the image system position acquisition time. Thus, the image system vehicle detection unit 13 acquires the image coordinate system position and the image system position acquisition time, and outputs them to the coordinate conversion table creation unit 14 as image system information. The acquisition of the image system position information is repeated as many times as the number of blinks of the light source unit 23.

  Whether or not it is a roadside photographed image at the moment when the light source unit 23 blinks can be determined from the luminance of a region including the light source unit 23 in the roadside photographed image, for example. That is, the contour of the vehicle 30 is obtained by performing contour extraction processing on the roadside photographed image. Since the position of the light source unit 23 is known with respect to the contour of the vehicle 30, the region of the light source unit 23 can be specified by obtaining the contour of the vehicle 30. Therefore, when the luminance of the specified area is equal to or higher than the set value, the image-based vehicle detection unit 13 determines that the road-side photographed image is obtained when the light source unit 23 is turned on.

  This set value is appropriately set according to the environment. That is, when the environment where the coordinate conversion table creation system 2 is installed is in a tunnel, the vehicle 30 lights up the headlight and taillight. Therefore, even if the luminance of the light source unit 23 is the same, the set value is set high in order to prevent erroneous recognition by these lights. In this way, it is determined whether or not the road side photographed image at the moment when the light source unit 23 blinks.

  Of course, the present embodiment is not limited to such a method. For example, when a region having a brightness equal to or higher than a preset value is acquired in the roadside photographed image, it is possible to determine that this region is due to the lighting of the light source unit 23. In this case, since the process for obtaining the contour of the vehicle 30 is not required, the process is accelerated.

  Step SA7: The coordinate conversion table creation unit 14 waits for reception of image system position information from the image system vehicle detection unit 13 and world system information from the world system vehicle detection unit 22.

  Step SA8: The coordinate conversion table creation unit 14 associates the image system vehicle position with the world system vehicle position. As described above, the image system vehicle position and the world system vehicle position are vehicle positions in the image coordinate system at the moment when the light source unit 23 is turned on. In other words, the image system vehicle position and the world system vehicle position become the vehicle position at the same time under the condition of “the moment when the light source unit 23 is turned on”. Therefore, a coordinate conversion table between the image coordinate system and the world coordinate system can be created. Note that the coordinate conversion table may be approximated by a function.

  By the way, the image system vehicle detection unit 13 outputs the image system vehicle position and the image system position acquisition time as image system information to the coordinate conversion table creation unit 14, and the world system vehicle detection unit 22 outputs the world system vehicle position and the world. The system position acquisition time is output to the coordinate conversion table creation unit 14 as world system information.

  However, the image system position acquisition time and the world system position acquisition time are not used in creating the coordinate conversion table described above. This is because the image-based vehicle detection unit 13 extracts the image-based vehicle position acquired from the road-side captured image when the light source unit 23 is turned on and sets it as the image-based vehicle position. This is because the position of the vehicle is synchronized.

  For such a method, in the coordinate conversion table creation unit 14, the image system position acquisition time and the world system position acquisition time are converted into a coordinate conversion table using the image system vehicle position and the world system vehicle position at the same time. Is possible. That is, in this case, the image system vehicle position and the world system vehicle position are time-synchronized.

  Whether to employ position synchronization or time synchronization is selected and set in consideration of processing speed, accuracy, and the like. Moreover, you may use both of these. The position synchronization is best detected at the moment when the light source unit 23 is turned on, but the image-based vehicle when the light source unit 23 is not completely coincident with the moment when the light source unit 23 is turned on due to shooting condition accuracy (for example, the number of shooting frames). A position is selected. Therefore, the image system vehicle positions before and after the image system vehicle position when it is determined that the light source unit 23 is turned on are also output as candidates to the coordinate conversion table creation unit 14. The coordinate conversion table creation unit 14 calculates an image system position acquisition time that matches the world system position acquisition time. Then, interpolation processing such as straight line interpolation is performed on a plurality of image system vehicle positions received as candidates, and the image system vehicle position at the calculated time is calculated. This makes it possible to create a coordinate conversion table with high accuracy.

  Next, processing in the in-vehicle device 20 will be described. In the in-vehicle device 20, the above-described world system position information is acquired and transmitted to the coordinate conversion table creating unit 14.

  Step SB1: First, the vehicle-mounted camera 21 images the reference body K.

  Step SB2: The world-based vehicle detection unit 22 detects the end point K2 of the reference body K by performing predetermined image processing on the in-vehicle captured image from the in-vehicle camera 21. Thereby, the position of the own machine (vehicle 30) with respect to the reference body K can be acquired. Since the acquired position of the own aircraft is a position relative to the reference body K formed on the road, it is a position in the world coordinate system.

  As the predetermined image processing, a known method such as an edge extraction method or a high luminance region extraction method can be applied. For example, when the edge extraction method is used, it is assumed that a vehicle-mounted captured image captured by the vehicle-mounted camera 21 is formed from a plurality of pixels. At this time, a luminance difference (differentiation) between adjacent pixels is taken. Thereby, in the area where the luminance changes greatly, such as an edge, the differential value becomes a large value, so that the area can be extracted. Of course, these are examples, and other methods are also applicable.

  Step SB3: Next, based on the area determination information received from the vehicle detection unit 12 in the global vehicle detection unit 22, it is determined whether or not the own device (vehicle 30) is located in the measurement area. If it is outside the measurement area, the process proceeds to step SB10, and if it is within the measurement area, the process proceeds to step SB4.

  Step SB4: World-based vehicle detection unit 22 is waiting to receive vehicle approach information from vehicle detection unit 12.

  Step SB5: Upon receiving the vehicle approach information, world-based vehicle detection unit 22 stops the detection of reference body K and changes the reference body detection parameter so that the detection accuracy is increased.

  For example, in the case of normal accuracy, when 10 frames are used for image processing per second, when the global vehicle detection unit 22 receives the vehicle approach information, 15 frames per second is used for the reference body K. The reference body detection parameter (in this example, the number of frames per second) is changed so as to perform the end point K2. Thereby, the inconvenience that the vehicle 30 passes through the end point K2 of the reference body K can be suppressed between the front and rear frames. That is, the end point K2 can be detected with high accuracy.

  Step SB6: The world vehicle detection unit 22 restarts the detection of the reference body K using the newly set reference body detection parameter.

  Step SB7: The world vehicle detection unit 22 determines whether or not the end point K2 of the reference body K has been detected. If the end point K2 is detected, the process proceeds to step SB8, and if not detected, the process returns to step SB6.

  Step SB8: When the end point K2 of the reference body K is detected, the global vehicle detection unit 22 outputs a trigger signal to the light source unit 23. Thereby, the light source part 23 blinks light sources, such as LED, once.

  Step SB9: The world system vehicle detection unit 22 acquires the time when the trigger signal is output as the world system position acquisition time, and acquires the position of the vehicle at that time as the world system vehicle position. Then, the process returns to step SB2.

  The world vehicle position is acquired as follows. On a highway or the like, since the length of the reference body K is defined as 8 m and the interval is 12 m, the position of the end point K2 can be calculated in the world coordinate system. Further, the world-based vehicle detection unit 22 is, for example, a Tsai camera model (R.Y. Robotics and Automation, Vol. RA-3, No. 4, pp. 323.344, 1999.) and the like are used to calculate the position of the vehicle (vehicle 30) with respect to the end point K2. Thereby, the vehicle position in world system coordinates can be acquired.

  Step SB10: When it is determined in step SB3 that the vehicle 30 is located outside the measurement area (when the vehicle has moved far), the world-based vehicle detection unit 22 stores the stored world-based information. It is transmitted to the coordinate conversion table creation unit 14.

  The coordinate conversion table creation unit 14 creates a coordinate conversion table from the association between the image system vehicle position and the world system vehicle position in accordance with the procedure described above.

  As described above, the coordinate conversion table indicating the correspondence between the vehicle position in the image system acquired from the roadside photographed image and the vehicle position in the world system acquired from the in-vehicle photographed image is in a tunnel where GPS cannot be used. It can be created with high accuracy even in an environment.

  This application claims the priority on the basis of Japanese application Japanese Patent Application No. 2011-272449 for which it applied on December 13, 2011, and takes in those the indications of all here.

2 Coordinate conversion table creation system 3 Image system information acquisition unit 4 Coordinate conversion information creation unit 5 World system information acquisition unit 10 Roadside imaging device 11 Roadside camera 12 Vehicle detection unit 13 Image system vehicle detection unit 14 Coordinate conversion table creation unit 20 In-vehicle device 21 In-vehicle camera 22 World vehicle detection unit 23 Light source unit 30 Vehicle

Claims (10)

A coordinate conversion table creation system for creating a coordinate conversion table between an image system coordinate set for a captured image and a world coordinate system set for a stationary object,
An image system information acquisition unit that captures a traveling vehicle, acquires an image system vehicle position at an image system coordinate set in the captured image, and outputs the image system information;
A world system information acquisition unit that acquires the world system vehicle position of the vehicle relative to world system coordinates and outputs it as world system information;
A coordinate conversion table creation system comprising: a coordinate conversion information creation unit that creates a coordinate conversion table of the image system coordinates and the world system coordinates based on the image system information and the world system information. The coordinate conversion table creation system according to claim 1,
The world information acquisition unit
A vehicle-mounted camera that is mounted on the traveling vehicle and captures an image including a preset reference body as a vehicle-mounted captured image;
A light source unit that blinks the light source when a trigger signal is input;
A global vehicle detection unit that calculates a position of the traveling vehicle with respect to the reference body from the in-vehicle photographed image, acquires a world coordinate system vehicle position using the calculation result, and outputs the trigger signal. A coordinate conversion table creation system characterized by The coordinate conversion table creation system according to claim 1 or 2,
The image system information acquisition unit is installed on the roadside and shoots an image including a traveling vehicle as a roadside captured image; and
The image system information acquisition unit determines whether or not the vehicle is located in a preset measurement area from the roadside photographed image and outputs it to the world vehicle detection unit as area determination information. A coordinate conversion table creation system comprising: an image system vehicle detection unit that determines whether or not the vehicle is approaching the reference body and outputs the vehicle approach information to the world system vehicle detection unit. A coordinate conversion table creation system according to any one of claims 1 to 3,
The image system information acquisition unit is configured to extract the roadside captured image in which the light source unit is lit from a plurality of the roadside captured images, and acquire the image system vehicle position from the extracted roadside captured images. Coordinate conversion table creation system. A coordinate conversion table creation system according to any one of claims 1 to 3,
When the image system information acquisition unit acquires the image system vehicle position, the image system information acquisition unit acquires the acquisition time as an image system position acquisition time, and determines the image system vehicle position and the image system position acquisition time as image system information. Output to the coordinate conversion information creation unit as
When the world system information acquisition unit acquires the world system vehicle position, the world system information acquisition unit acquires the acquisition time as a world system position acquisition time, and sets the world system position and the world system position acquisition time as world system information. Output to the coordinate conversion information creation unit as
The coordinate conversion information creation unit creates the coordinate conversion table based on the image system vehicle position and the world system vehicle position at the same time as the image system position acquisition time and the world system position acquisition time. A coordinate conversion table creation system. A coordinate conversion table creation method for creating a coordinate conversion table between an image system coordinate set for a captured image and a world coordinate system set for an immovable object,
Taking a traveling vehicle, obtaining the image system vehicle position at the image system coordinates set in the captured image, and obtaining image system information to be output as image system information; and
A procedure for acquiring world system information for acquiring the world system vehicle position of the vehicle relative to world system coordinates and outputting it as world system information;
A coordinate conversion table creating method comprising: creating coordinate conversion information that creates a coordinate conversion table of the image system coordinates and the world system coordinates based on the image system information and the world system information. The coordinate conversion table creation method according to claim 6,
The procedure for obtaining the world system information is as follows:
Mounted in the traveling vehicle, and a procedure for in-vehicle shooting for capturing an image including a preset reference body as an in-vehicle captured image;
When the trigger signal is input, the light emission procedure flashes the light source,
Calculating the position of the traveling vehicle with respect to the reference body from the in-vehicle captured image, obtaining a world coordinate system vehicle position using the calculation result, and detecting a world system vehicle that outputs the trigger signal. A coordinate conversion table creation method characterized by the above. A coordinate conversion table creation method according to claim 6 or 7,
The procedure for acquiring the image system information is a procedure for shooting on the roadside, which is installed on the roadside and shoots an image including a traveling vehicle as a roadside shooting image,
The procedure for acquiring the image system information is to determine whether or not the vehicle is located within a preset measurement area from the roadside photographed image and output to the procedure for detecting the world vehicle as area determination information, And a procedure for detecting an image-based vehicle that outputs whether or not the vehicle is approaching the reference body and outputs the vehicle approach information to the procedure for detecting the world-based vehicle. Method. A coordinate conversion table creation method according to any one of claims 6 to 8,
The procedure for acquiring the image system information includes extracting the roadside captured image in which the light emitting procedure is turned on from a plurality of the roadside captured images, and acquiring the image system vehicle position from the extracted roadside captured images. Coordinate conversion table creation method. A coordinate conversion table creation method according to any one of claims 6 to 8,
The procedure for acquiring the image system information includes acquiring the image system vehicle position and the image system position acquisition time by acquiring the acquisition time as an image system position acquisition time when the image system vehicle position is acquired. Output to the procedure to create the coordinate conversion information as information,
When acquiring the world system information, when acquiring the world system vehicle position, the acquisition time is acquired as a world system position acquisition time, and the world system vehicle position and the world system position acquisition time are Output to the procedure to create the coordinate conversion information as information,
The procedure for creating the coordinate conversion information includes creating the coordinate conversion table based on the image system vehicle position and the world system vehicle position at the same time as the image system position acquisition time and the world system position acquisition time. A characteristic coordinate conversion table creation method.

Images