JPH01211100A - Traffic flow measuring system - Google Patents

Abstract

PURPOSE:To improve the operability of the title system by setting an area to be measured and a command in a conversational format, confirming the setting by a human being in a graphic presentation, and further changing algorithm interactively by building in a tuning table. CONSTITUTION:A method for operating a measuring routine for extracting a traffic flow parameter stored in the system is made into the one to be interactively instructed by the human being by command inputting according to the conversational format in a teaching mode. Further, the command format is made into a system composition control setting command, a measured area setting command, a coordinate system setting command, a system executing control setting command, and a tuning data setting command (the command to execute the tuning of the algorithm of the measuring routine). Moreover, mainly the system composition control setting command can correspond to the change of weather and the change of circumferential brightness, and mainly the coordinate system setting command and the measured area setting command can correspond to the change of a place as the object of the measurement. Thus, the operability of the system can be improved.

Description

[Detailed description of the invention]

[Industrial Application Field] The present invention relates to a man-machine inch face of a traffic flow measurement system that extracts traffic flow parameters from image information such as ITV that photographs a road surface to be measured. [Prior art] A traffic flow measurement system using an ITV camera measures traffic flow from images obtained by photographing the road surface with an ITV camera, but since the measurement target is outdoors, the following Various problems occur. (1) Changes in weather (sunny weather, rainy weather, snowfall, etc.) affect images. (2) The constantly changing brightness (morning, noon, dusk, night, etc.) affects images. (3) Road surface condition (straight road, curved road,
(number of lanes, etc.) differs depending on location. The above problems directly affect the measurement algorithm, but in the conventional system, the measurement target,
These problems were covered by the positioning of the device as a specialized device that had limited usage conditions to a certain extent and was equipped with only measurement algorithms suitable for those conditions. [Problems to be solved by the invention] The above-mentioned prior art lacks tools to deal with all of the problems (1) to (3) above. In other words, the traffic flow measurement system of the above-mentioned conventional technology detects the above-mentioned change when there is (1) a change in the weather, (2) a change in brightness, or (3) a change in the measurement target location with respect to the initially set usage conditions. There was a problem in that it was not possible to measure according to the An object of the present invention is to provide a universal traffic flow measurement system that can address the problems (1) to (3) above. [Means for Solving the Problem] The above purpose is to allow a human to interactively instruct the operation method of a measurement routine for extracting traffic flow parameters stored in a traffic flow measurement system by inputting commands in a conversational manner in a teaching mode. Furthermore, this command format is converted into the five commands shown in FIG. 1, namely (1) system configuration control setting command; setting the weather, ambient brightness, etc. (2) Measurement area setting command: Extracts measurement target areas such as lanes from the road surface image captured by the ITV camera. (3) Coordinate system setting command Correlates the distance between the actual road surface and the image of the road surface captured by the ITV camera. (4) System execution control setting command; controls the execution method of the measurement routine and the output method of the measurement results. (5) Tuning data setting command: Tunes the algorithm of the measurement routine. This is achieved by doing this. [Function] 1. By allowing humans to freely set the operation method of the measurement routine in the teaching mode, even if changes occur in the measurement environment, it is possible to respond to changes in real time. 26 By providing the commands (1) to (5) above, (a) Changes in weather 2 Changes in ambient brightness:
Mainly due to the system configuration control setting command, and also. (b) Changes in the location to be measured can be handled mainly by coordinate system setting commands and measurement area setting commands. With 1 and 2 above, the target traffic flow measurement system becomes resistant to changes in the measurement environment, and one system can be made into a general-purpose system that can be used in various environments. [Example] Examples of the present invention are shown below. First, the hardware configuration of the traffic flow measurement system of the present invention will be explained.

[Hardware configuration]

The traffic flow measurement system of the present invention is composed of the following modules as shown in FIG. (1) ITV camera 100 A device that takes an overhead view of the road surface and captures an image of the target surface for extracting traffic flow parameters. (2) Image processing unit 200 Processes the image obtained by the ITV camera 100. , a device that removes noise, extracts vehicles, and converts traffic flow parameters into images that are easy to calculate. Note that the image processing section 200 is composed of the following. i) Address processor 210 Performs address management such as input/output of image data. This processor also has a graphic processing function that generates straight lines, arcs, etc. n) Image memory 220 A two-dimensional memory that stores target images and the results of image processing. It consists of a binary image memory where each pixel has 1 bit, and a gray scale image memory where each pixel has multiple bits. (2) Image processor 230 An image processor that processes images from the ITV camera 100 and image memory 220 at high speed. Its functions include binarization, geometric shape conversion, labeling, convolution, inter-image calculations, and histograms. (3) Image monitor 300 Displays images stored in the ITV camera 1002 image memory 220 and graphic images generated by the address processor 210 in a superimposed manner. (4) CPU 400 1) Vehicle images extracted by the image processing unit 200. Extract traffic flow parameters using image features, etc. ii) Control the man-machine interface between humans and the one-text flow measurement system. 1■) Performs overall control of this traffic flow measurement system. (5) Floppy disk 500 Saves traffic flow parameters etc. obtained by this traffic flow measurement system. (6) I10 controller 600: keyboard, which is a device for man-machine interface;
(7) Keyboard 700 Man-machine interface device for controlling input/output of mouse, etc. For inputting commands and various data. (8) Mouse 800 A device for man-machine interface. Interactively input coordinates within the displayed image. (9) Console monitor 900 A device for man-machine interface. Displays command menus for operating this system, traffic flow parameters resulting from calculations, etc. Next, the operation of the traffic flow measurement system of the present invention will be described.

[System operation]

This traffic flow measuring system consists of two operating modes, a teaching mode 31 and a measuring mode 32, as shown in FIG. In the teaching mode 31, a measurement area is set by teaching, various parameters are set, etc. by command input, and various tables that define the operation of the present traffic flow measurement system are created. This mode is implemented by the man-machine interface of the present invention. FIG. 1 shows the rough 1-ware module configuration of this man-machine interface section. Details about each module will be described later. The measurement mode 32 is a mode in which online measurement is performed according to the operation mode set in the teaching mode. After the main measurement mode ends, the mode returns to the teaching mode, and the resulting traffic flow parameters are displayed on the console monitor. An overview of the operation of the entire system will be described below using FIG. 2. (1) In the teaching mode 31, the console monitor 9
00, follow the menu screen displayed on the keyboard 700. Using mouse 800, a human enters commands and parameters. and I10 controller 60
0, commands and parameters are sent to the CPU 400. (2) The CPU 400 interprets the command and creates a table to be described later based on the set parameters. After this process is completed, the system shifts to measurement mode 32. (3) At this time, the ITV camera 100 photographs the road and displays the image on the image monitor 300. (4) The image processing unit 200 transmits the image captured by the ITV camera 100 to the image memory 220 or the image processing processor 230 in response to activation from the CPU 400, and executes a series of image processing. (5) The CPU 400 analyzes the final image obtained by the 1-image processing unit 200 and the feature amounts, and calculates traffic flow parameters such as the number of vehicles and average vehicle speed in congestion. (6) After the measurement mode ends, the mode shifts to the teaching mode again, and the resulting traffic flow parameters are displayed on the console monitor 900, saved on the floppy disk 500, etc. by human command input. Among the operations (1) to (6) above, the operation (1), which is the man-machine interface section of the present invention, will be described in detail below. (Details about the man-machine interface The single man-machine interface is based on five commands, as shown in FIG. All you have to do is input it into the system. Below (1) to (5)
) describes the details of each command. (1) System configuration control setting This command is used to create tables for determining the basic operation of this traffic flow measurement system, that is, the following four tables shown in FIG. 4. (a) Algorithm selection table A table for selecting the most suitable one suited to usage conditions and environmental conditions from among several types of traffic flow parameter extraction algorithms built into the system. Setting value O; Algorithm 1 selected 1; 〃 2 〃 2; n 3n (b) Environmental condition setting table A table that stores the ambient environmental conditions on the measurement date. The table structure consists of the following. i) Time...Measurement time setting value O; Measurement during the day 1; At dusk 〃 2; At night 〃 3; At dawn ■) Weather... Weather setting value on the measurement day 0~3; Sunny 4~ 7; Cloudy 8-11; Rain 12-15; Fog 1ii) Shadow direction... Vehicle shadow direction setting value 0; Shadow appears upwards 1; Directs upward to the right! ! 2; Rightward II 3; Downward right 〃 4; Downward 〃 5; Downward left! ! 6; Leftward 7; Upper leftward (C) Road condition setting table A table that stores the condition of the road surface to be measured. The table structure consists of the following. i) Number of lanes... set value for the number of lanes on the road to be measured n,
n = 1 to 5 (lane) if) Lane width... Length setting value of actual lane width m (c
m) m) Lane condition setting value 0; Straight road & no merging 1; Straight road & vessel flow 2; Curved road & no merging 3; Curved road & merging iv) Vehicle correction coefficient...ITV camera For correcting left and right road surface distortion due to viewing angle. Setting values w, 0, 1 < w < 10, the above n) to N) are set for each lane. In this embodiment, a maximum of five lanes are provided. (d) Vehicle type condition setting table A table that stores vehicle type conditions. The table structure consists of the following. i) Number of vehicle type discrimination... main text Number of wheels that the fine measurement system distinguishes Setting value 1; No discrimination of vehicle type 2; Distinction into two, large and small cars 3; Three discrimination between large, medium and small cars i ) Vehicle width: Minimum width length setting value for one vehicle type P(
C1l) m) Vehicle length...minimum length setting value for one vehicle type Q(■
) iv) Tail lamp width: Minimum tail lamp interval length for one vehicle type (used for nighttime measurement) setting value R (CIl
l) The above items (■) to iv) are prepared for each large, medium, and small vehicle. (2) Measurement area setting This command extracts the area to be measured from the image of the road surface captured by the ITV camera, and creates the lane label image and lane area table described below. The processing procedure of this command will be explained below using FIG. First, a person points to the road surface painter (FIG. 6(a)) using the keyboard 700 or mouse 800 to roughly measure the area to be measured, and then points to the image position address (point coordinates). ) is input into this traffic flow measurement system. Figure 6 (,) shows lanes #1 to #3.
This is an example of a lane road. In this traffic flow measuring system, a loss cursor is displayed on the image monitor 300 at a position corresponding to the point coordinates as shown in FIG. 6(b). This allows a person to confirm whether pointing has been performed correctly. The cross cursor and the original image are displayed superimposed. In FIG. 6(b), POL"P3L is a point coordinate point specifying the left boundary of lane #1, and POR"P4R is a point coordinate point specifying the right boundary. Lane #2. Similar processing is performed for #3 as well. After inputting the above point coordinates, the text flow measurement system performs the measurement area extraction process described below in Figures 7(i) to 7(i).
Perform step (iii). (i) Points located at point coordinates are connected by vectors using graphic processing to create a lane contour image as shown in (a) (
A binary image) is created on the image memory 220. (ii) Next, the lane axis contour image created in (i) is inverted by the image processing processor 230, that is, the image data is converted from O to 1 and from 1 to 0, and (b
) Create the inverted image shown in (). In the figure, the hatched area is 1, and the other areas (blank) are 0. (甫) Then, for the inverted image in (ii), the image processing processor 230 performs labeling processing on one connected component, and a lane label image (shaded image) as shown in (c) is stored in the image memory 220. can be obtained. In (C), label 1 indicates the background, labels 2 and 3.4 indicate lanes #1 to #3, respectively, and label 0 indicates the boundary between the lane and the background. The area to be measured by this traffic flow measurement system can be extracted using this lane label image. For example, in measurement for lane #1, from the lane label image, perform binarization processing to set only label 2 to 1 and the others to 0 to create a mask image for lane #1 shown in (d). Good. Using this mask image, traffic flow can be measured by limiting the area of lane #1 from the image shown in FIG. 6(a). The same applies to other lanes. After the measurement area extraction process described above, the lane area table shown in FIG. 8 is created. The single lane area table will be described below. The main lane area table stores the position information on the image of the lane to be measured, and has the following configuration. i) Flag: Determines whether or not the following components are updated. The user sets the following values. Setting value: O: Table not updated 1: Table updated ii) Number of right line points...For the right side of the lane. An entry that stores the number of point coordinates specified by the user. In the example of FIG. 6(b), the number of POR to P4R is five. ■) Number of left line points...for the left side of the lane,
An entry that stores the number of point coordinates specified by the user. In the example of the sixth ffi (b), Pot, ~P3L
, that is, 4. iv) Measurement upper limit Y coordinate: Entry that stores the upper limit position of the lane measurement area. That is, the smallest Y coordinate among the point coordinates specified by the user is stored. Said sixth
In the example of Figure (b), it is the smallest Y coordinate of POL and FOR. ■) Measurement lower limit Y coordinate: Entry that stores the upper limit position of the lane measurement area. That is, the maximum Y coordinate among the point coordinates specified by the user is stored. In the example of FIG. 6(b), this is the maximum Y coordinate of P3L and P4R. vi) Screen limit Y coordinate: An entry that stores the Y coordinate of the limit when the lane measurement area set by the user deviates from the screen. In the example of FIG. 6, this is the Y coordinate of P2L. If the measurement area does not fall off the screen, such as in the center lane, 0 is stored. ∖) Left side line X, Y coordinates... relative to the left side of the lane,
Coordinates of all points specified by the user from top to bottom (x, y
) Stored by model number. In the example of FIG. 6(b), P O
From L (X + Y), Pa (X, Y) is stored. vi) Right side line X, Y coordinates: Coordinates of all points specified by the user for the right side of the lane, in order from the top. Store in (x, y) format. In the example of FIG. 6(b), P4R(X, Y) is stored from PoR(x, Y). The above i) to vii) are prepared as many as the number of lanes. In this embodiment, there are a maximum of five sets. (3) Coordinate system setting This command associates the distance between the actual passage surface and the image taken by the ITV camera 100, and consists of the following processing procedure. 1) Straight path depth distance setting mode In this mode, a person points directly on the image of the path surface displayed on the image monitor 300 using the keyboard 700 or the mouse 800 to set the position corresponding to the standard distance. This is to teach the system. This will be explained in detail using FIG. 9. First, as shown in FIG. 9(a), a person finds road information, such as a center line, guardrail, etc., that is an index of standard distance from an image of the road surface, and points the location. In this example, it is the break point A-E of the white line of the center line. Since the distance between center lines is stipulated to be 20 m (white line length 8 m), humans can
, B.C. Teach the system that the distance between cD and DE is 20 m. If the road information does not exist on the road surface, a person places markers or the like on the road in advance at intervals of, for example, 20 m, photographs the markers, and performs the same processing as described above. In addition, in the above pointing, vectors Q^ to QE are displayed using graphic processing on a horizontal line passing through the point A-E that has been pointed. This is shown in FIG. 9(b). FIG. 9(b) shows an image of a road surface and a vector image obtained by graphic processing superimposed and displayed on the single-image monitor 300. This allows you to check whether or not the pointing was done correctly.
Humans can check it in real time. 2) Table work mode In this mode, the following ( Four tables a) to (d) are created (shown in FIG. 10). (a) Lane depth table 1 This table is a table for setting the depth (distance) of lanes. It consists of the following: i) Flag: Determines whether or not the following components are updated. The user sets the following values. Setting value O: Do not update the table 1: Update the table ii) Depth from the reference point... Based on the road distance information taught by the road depth distance setting mode described above, the following values (from the reference point) depth distance). When a road surface is photographed in an overhead view using the ITV camera 100, as shown in FIGS. 9(a) and 9(b), the distance (the upper part of the screen) gradually becomes smaller. That is, the distance between the center lines in FIG. 9(a) is 20 m as shown in FIG. 9(a), but when viewed as an image, the distance becomes narrower as shown in FIG. 9(b). Therefore, since the vertical length of one pixel differs for each line (scanning line) of one image, it is necessary to perform interpolation processing as shown in FIG. 10. I will discuss this. The horizontal axis in FIG. 10 indicates the number of pixels in the vertical direction (address in the Y direction) of the image. In this example, it is an image of n+1 pixels (
Figure 9(a),(b)). In the figure, i, j, Q, m are points E, D, and
Corresponds to the Y coordinates of C, B, and A. Further, the vertical axis in FIG. 13 represents the actual distance 1 (m). At this time, if Q (Y coordinate (pixel) of point B) is taken as the reference point, and the upper direction of the image is positive and the lower direction is negative, then Q
The distance from l*J, + and the distance from Q to m are known (2
0 m interval) and are plotted as shown in FIG. From O to n in the vertical direction of the image, 1+ J+ k
In order to make the unknown Y coordinate other than r Qt m correspond to the actual distance, approximation is performed using linear interpolation in the example of FIG. 13. Of course, in this interpolation process, if more precision is required, it can be handled by using a quadratic function or the like. Further, the designated reference point is the first point pointed at in the above teaching. The “depth from the base point” of main lane depth table 1 is:
The interpolated values shown in FIG. 13 are stored corresponding to Y coordinates 0 to n. (b) Lane depth table 2 This table is basically the same as the lane depth table 1 described above, but there are differences in the following points. That is, the "depth from the reference point" of the lane depth table 1 is further divided by the number of pixels to store the vertical length of one pixel (unit length of one pixel, CI+/pixel). For example, in Fig. 13, the unit length of one pixel located at k is (20X100)/CQ-+1) (an/
pixels). (c) Lane Width Table This table stores the number of pixels corresponding to the lane width of the lane captured as an image for each line (Y coordinate), and consists of the following. i) Flag: Determines whether or not the following components are updated. The user sets the following values. Setting value: O; Table is not updated 1; Table is updated The image processor 230 extracts a horizontal projection histogram, and stores this projection histogram in this table. The "number of pixels in the horizontal direction of the lane" corresponds to the projection histogram value. The above i) and ii) are prepared depending on the number of lanes. (d) Vehicle determination table This table is used to determine whether or not an object on the lane to be measured is a moving vehicle (for example, garbage, dirt on the road surface, etc.) when it is captured as an image. The table consists of the following: i) Flag: Determines whether or not the following components are updated. The user sets the following values. Setting value O: Do not update the table 1: Update the table it) Minimum number of pixels for small cars...In order to judge whether or not it is a vehicle, the smallest widest small car (image) on the market is set in the measurement area. For the lane mask image extracted in the settings, the width in pixels is extracted and stored. The minimum width is obtained by reading the vehicle type condition setting table created by the system configuration control setting command. Here, if the setting value of this table, "minimum number of pixels for small cars", is ωN (Y) (Y=O-N), then it is expressed as ωN (Y) = -・ωR(Y) ・δ (pixels). It will be done. Here, P: Minimum width of a small vehicle (am) m: Lane width of the lane to be measured (an), obtained by reading the road condition setting table created by the system configuration control setting command. ωR(Y): Number of pixels in the horizontal direction of the lane to be measured. Said (
C) is obtained by leading the lane width table. 58 weighting factors, typically 0.8 for tuning. If the width of the object on the measurement lane (on the image) is ω, (y) (pixel) on line Y, then if (IIX(Y)n(LIN(Y) then)
It can be determined that the vehicle is not a vehicle. The above i) and n) are prepared as many as the number of lanes. (4) System execution control setting This command is used to create a table for determining the execution method of the measurement routine of this traffic flow measurement system and the output method of measurement results, that is, the following (a) and (b) shown in FIG. )
This will create two tables. (a) Execution mode table A table that determines the execution method of the measurement routine. The table structure consists of the following. i) Execution mode...Specifies execution control Setting value O: Online execution 1; Executing in step units (algorithm evaluation of measurement routine, device ii) Loop count...Repetition number of measurement routine execution LC Setting value LC ( (times) However, when LC<O input, it is an infinite loop (b) Output control table A table that controls the output of measurement results. The table configuration is
It consists of the following: i) Output timer... Interval setting value for outputting measurement results 'l, Ts 'l Outputs results every (minute) Ts (second). If T, < O, no output. ii) Output device...Device setting value for transfer destination of measurement results 0; Device 1 connected to R52322#O; Device 2 connected to R52322#1; Device 3 connected to R82322#2 ; Connected to R52322 #2; 4; Floppy disk ■) Output display...Measurement result display method setting value 0; Measurement results are not displayed) 1; Measurement results are displayed on the console monitor 900 for 10 seconds. 2; Negative value to display the measurement result on the console monitor 900 for 20 seconds; measurement result to always be displayed on the console monitor 900 (5) Tuning data setting This command is used to create a table for tuning the algorithm of the measurement routine. The following tuning table shown in FIG. 12 is created.・Tuning table This table is used to store threshold values for binarization processing, initial data of histogram memory, etc. when depacking measurement routines.
This is an interactive system that can be changed by humans. The data necessary for tuning the algorithm is stored in this table, and the data set in this table is taken in during the measurement routine, and the binarization processing, initial processing of the histogram memory, etc. are performed. The commands (1) to (5) above have been described, but as mentioned in the main text, these commands and parameter settings can be executed in the form of a conversation with a human using the man-machine interface of the main text flow measurement system. It is now possible to do so. Further, the measurement routine described in this embodiment operates based on the tables set in (1) to (5) above. [Effects of Example 1 1. Improved operability i) It is possible to set the measurement area and input commands and parameters in a conversational manner ii) After the measurement area is set, the original image and graphics are displayed, such as a cross cursor display in the point coordinate area Superposition of. (It also improves visibility.) The provision of a tuning table makes it easier to develop measurement algorithms. 2. Reduction of memory (miniaturization of the system) i) Since the measurement area is managed using lane label images, image memory for storing mask images equal to the number of lanes is not required. n) A lane area table is provided to manage the measurement area (memorize the point coordinates and the shape of the measurement area → reduce the amount of information), reducing the main memory and external storage such as floppy disks. It is possible to reduce the memory occupation rate of the element. 3. Direction of recognition rate Fi) Changes in the road environment for 2 hours according to the table created by the system configuration control setting command. It can also respond to changes in weather, changes in the type of vehicle being measured, etc. ii) Since the table created by the coordinate system setting command allows correspondence between real space distance and distance on the image,
The accuracy of vehicle recognition is improved. [Effects of the Invention] According to the present invention, measurement areas can be set in a conversational manner. Data such as commands and parameters can be set, which can be checked by humans using graphical displays, etc.
The built-in tuning table allows for interactive algorithm changes, which has the effect of improving the operability of the traffic flow measurement system.

[Brief explanation of the drawing]

FIG. 1 is a command configuration diagram of the present invention, FIG. 2 is a hardware configuration diagram of an embodiment of the present invention, and FIGS. 3 to 13 are detailed explanatory diagrams of the present invention. 100... ITV camera, 200... Image processing unit,
300--Image monitor, 400--CPU
(CemtralProcessing Umit),
500...floppy disk, 600...I1
0 controller, 700...keyboard, 800...
・Mouse, 900...Console monitor 1:j, :,
゛- Day 5 Figure 6 Figure 9 Figure 10

Claims (1)

[Claims] 1. A photographing device for photographing a road surface with a wide field of view, and determining the number of vehicles, average speed, etc. from images obtained from the photographing device.
A traffic flow measurement system equipped with a computing unit that extracts traffic flow parameters such as the degree of road congestion, a display device that displays images obtained from the photographing device, and coordinates, data, etc. on the screen of the display means. A data input device that can interactively input data is provided, and the area to be measured can be roughly determined from the screen of the display device using the data input device.
By being taught by a human, the system is able to finely extract the measurement area on the target image, and at the same time, based on the taught data, it creates a first table that associates at least the road surface and the image, and A traffic flow measurement system characterized by being able to automatically generate a second table for detecting road surface conditions. 2. In the traffic flow measuring system according to claim 1, the area of each lane to be measured roughly taught by a human being is determined using graphic processing by pointing input of coordinate data using the data input device. Interpolate between point coordinates to create a contour image for each lane.
Create an inverted image of the contour image by converting 1 to 0 and 0 to 1, label the connected components of the inverted image to create a label image, and apply only a specific label to the label image. A binary image is created by a binarization process in which the area is set to 1 and the other areas are set to 0, and the 1 area of this binary image is set as the measurement area corresponding to the lane to be measured, and the calculation unit is A traffic flow measuring system characterized in that the binary image can be displayed on the display device by superimposing it on the target image as an original image. 3. The first table recited in claim 1 uses the binary image extracted as the measurement area recited in claim 2 to calculate each of the images handled by the arithmetic unit. A feature is that a conversion is performed to associate the vertical and horizontal lengths of one pixel for each scanning line with the actual depth and width distances of the road surface on each lane, and this converted value is stored. traffic flow measurement system. 4. The first table as set forth in claim 1 stores at least point coordinates of the upper limit, lower limit, left side, and right side positions of the measurement area designated by the teaching. Traffic flow measurement system. 5. The second table set forth in claim 1 indicates that the road surface is straight based on the shape of region 1 of the binary image extracted as the measurement area set forth in claim 2. A traffic flow measurement system characterized by determining whether there is a curve or not, and storing the determination result. 6. In the traffic flow measuring system according to claim 1, environmental data at the time of measurement, such as weather (rainy, sunny, cloudy, snowy, etc.), night, day, twilight, etc., is input from the data input device. A traffic flow measurement system characterized in that a third table is provided for storing the data. 7. In the traffic flow measuring system according to claim 1, the length and width of the vehicle can be inputted for each vehicle type (for example, large vehicle, medium-sized vehicle, small vehicle, etc.) from the data input device, A traffic flow measurement system characterized by providing a fourth table for storing these. 8. In the traffic flow measurement system as set forth in claim 1, a fifth device is configured to allow tuning data such as binarization threshold values for vehicle extraction to be inputted from the data input device, and to store these data. A traffic flow measurement system featuring a table. 9. The traffic flow measurement system according to claim 1, wherein data for execution control of a routine for measuring traffic flow parameters can be inputted from the data input device, and a sixth table for storing these data is provided. A traffic flow measurement system characterized by the following: 10. A traffic flow measurement system, wherein the display device according to claim 1 is capable of displaying at least traffic flow parameters as measurement results and measured time.