JPS62159050A - Measuring device for speed of moving object - Google Patents

Abstract

PURPOSE:To derive a speed of a moving object by a locus of the moving object and an image of a start point and an end point of the moving object, by eliminating an image of a background from a video signal of the moving object. CONSTITUTION:A background image before photographing a moving object is photographed by a TV camera 1 and stored in a background image memory 4. Subsequently, the moving object is photographed, the background image of the memory 4 is eliminated from a moving object video signal by a locus generating circuit 2, and also a locus image signal of the moving object is stored in a locus image memory 3. By such a processing of a background eliminating circuit 9, the difference of video signal of the moving object and a video signal of a background is derived, and an image of the moving object which has eliminated the video signal of the background from the video signal of the moving object is generated. Based on the video signal of this moving object only, an image of a start point and an end point of the moving object are derived by a binary-coding circuit 7 and a superposition processing circuit 8, and stored in start point and end point image memories 5, 6. Subsequently, the binary-coded background video signal, the locus image signal, and the moving object start point and end point video signals are inputted to an image analyzing device 10 through a communication controlling circuit 13, and a speed of the moving object is derived by using these image signals.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a speed measuring device for a moving object, and particularly to a moving object suitable for determining unsteady three-dimensional velocity vectors of a plurality of moving objects having arbitrary shapes. This invention relates to an object speed measuring device.

[Conventional technology]

As a conventional example, there is a device disclosed in Japanese Patent Application No. 59-30281 entitled "Velocity Distribution Measuring Apparatus for a Moving Object." This conventional example consists of a photographing device that captures a moving object, an A/D converter that converts the signal from the photographing device into A/D, a superimposition circuit that superimposes the signal from the A/D converter frame by frame, and A speed measurement device consisting of a speed calculation circuit that calculates the speed of a moving object from superimposed data from the circuit, and a background removal circuit is provided between the A/D converter and the superimposition circuit, and the A/D converter is A distributor is provided that sends the signal from the converter to a speed calculator frame by frame, and the moving object image in the signal from the distributor is used to identify the image of the same moving object in the superimposed data, and its speed and It is characterized by the provision of a speed calculator that can determine the direction of movement. Further, as a background removal method, a signal sequence obtained by taking the difference between two consecutive frames is successively superimposed. This conventional example has one frame memory in front of the two-speed calculator,
Each component of the device is arranged in series.

[Problem that the invention seeks to solve]

In the conventional example described above, a frame memory provided before the speed calculator is used for background removal. In this configuration, there are two zero-order background removal methods.

Can be implemented. (1) Store the image of the measurement starting point including the background in a frame memory, use an inverter and an adder to take the difference from the input video, perform superimposition processing, and remove only the background, which is a static component, In this case, only the image of the moving object is left; (2) background removal is performed between the signal strings by taking the difference between two consecutive frames;

The contents of frame memory are replaced every time.

In method (1), in a trajectory image, if the image at the starting point of a moving object and the image of the moving object in the next video have the same gray level in the overlapping part, even though they are not still images, With the background removal function, it is erased and the 8th
As shown in the figure, the trajectory image is cut off at the position of the starting point image of the moving object, making it difficult to identify it with the starting point image of the moving object and recognize the moving direction of the moving object. There is good luck.

In method (2), background removal is performed between two consecutive frames, so the overlapping part of the moving object image between two consecutive frames is removed in the same way as in method (1). As a result, as shown in FIG. 9, the trajectory image becomes fragmented, making it difficult to identify the end point of the moving object with the image, etc., and to measure the length.

Furthermore, in this conventional technology, each component of the device is arranged in series, and calculations between images cannot be performed freely. Background removal cannot be performed on images such as measurement end points. For this reason, the background image remains as shown in FIGS. 10 and 11, and there is a problem in that the background interferes with identification with the trajectory image.

Furthermore, in this conventional technology, if the speed calculator cannot determine the speed and moving direction of a moving object in real time, it is not possible to send the superimposed data and the data of the measurement start point and measurement end point to the speed calculator. This makes it difficult to rapidly collect time-series image data necessary to determine the unsteadily changing speed of an unsteadily moving object.

SUMMARY OF THE INVENTION An object of the present invention is to provide a speed measuring device for a moving object that can obtain a clear trajectory image without line breaks and can efficiently determine the moving speed.

[Means for solving problems]

The above purpose is to provide a memory that stores a background video signal that does not include the video signal of a moving object output from a photographing device, and to enable a trajectory creation device to store a background video signal that does not include a video signal of a moving object output from a photographing device. removes the background video signal that is
However, this can be achieved by having means for determining the trajectory of the moving object from the video signal from which the background has been removed, as well as determining images of the starting and ending points of the moving object.

[For production]

A background video signal that does not include the moving object outputted from the imaging device is input into the memory in advance, and then the background video signal is removed from the moving object video signal outputted from the imaging device. , images of the starting point and ending point of the moving object are obtained based on the video signal from which the trace is obtained and the background is removed, and the speed of the moving object is obtained based on the trajectory of the moving object and the images of the starting point and the ending point of the moving object. In addition, by connecting the image storage medium provided in the trajectory creation device in parallel with the mechanism that creates the trajectory of the moving object, the process of subtracting the background from the image of the measurement start point, the image of the measurement end point, etc. of the moving object is performed. In some cases, the calculation mechanism used by the trajectory creation mechanism can be shared without providing a dedicated calculation mechanism for this processing, and calculations can be freely performed between input images from each image storage medium and imaging device. .

Furthermore, by providing a plurality of image storage media for storing the trajectory of a moving object provided in the trajectory creation device and a plurality of image storage media for storing images of the moving object at arbitrary times, it is possible to It is now possible to rapidly collect the time-series image data necessary to determine the speed of a moving object, and an analysis device that analyzes the trajectory of a moving object to determine its speed can now calculate the speed of a moving object in real time. Even in cases where this is not possible, it is possible to obtain the unsteadily changing speed of an unsteadily moving object using this analysis device.

〔Example〕

DESCRIPTION OF THE PREFERRED EMBODIMENTS A moving object speed measuring device, which is a preferred embodiment of the present invention, will be described below with reference to FIGS. 1 to 3. The moving object speed measuring device of this embodiment is a TV left camera that captures an image of a moving object, and the output of the TV left camera. A video input circuit 14 that inputs video signals, a trajectory creation circuit 2, a trajectory image memory 3, a background image memory 4, a starting point image memory 5. End point image memory 6, communication control circuit 131 image analysis device 10
, a video output circuit 15 for outputting the created image, and a monitor 16. The trajectory creation circuit 2 includes a binarization circuit 71, a superimposition processing circuit 8, and a background removal circuit 9. And a video input circuit 14, a video output circuit 15,
Binarization circuit 71 Superimposition processing circuit 8. Background removal circuit 9. trajectory image memory 3, background image memory 4, starting point image memory 5,
The end point image memory 6 and the communication control circuit 13 are each connected in parallel to a bus 12 connected to an arithmetic processing circuit (CPU) 11. Transmission control of video signals and image signals through the bus 12 is performed by the CPU 11. Also, a display device 40 for outputting or recording the results of image analysis. It has a printer 41, a plotter 42, and a disk device 43.

Next, the operation of this embodiment will be explained. That is, process the video signal that is the output of the TV left camera using the following steps,
Create a trajectory image of a moving object.

(a) A background image before photographing a moving object is previously photographed using the TV left camera, and this background image is input to the background image memory 4 and stored. (b) Take an image of the moving object using the TV left camera.

(Q) The trajectory creation circuit 2 removes the background image stored in the background image memory 4 from the moving object video signal and performs superimposition processing with the stored contents of the trajectory image memory 3 to generate a new trajectory image signal of the moving object. Output to the trajectory image memory 3.

By repeating the processes in (b) and (c) at predetermined time intervals during a predetermined measurement period, a moving object trajectory image signal to which the moving object trajectory is sequentially added is stored in the trajectory image memory 3. At this time, the CPU II stores the first video signal of the moving object after the start of the measurement in the starting point image memory 5 as the starting point video signal among the images of the moving object in the specified measurement period, and The video signal of the moving object is stored in the end point image memory 6 as the end point image signal. The video signal captured by the TV left camera and input from the video input circuit 14 is once input into the CPU 11.
be done.

The CPU II selects the starting point image signal and the ending point image signal and inputs them into each image memory 5.6. Also.

The CPU 11 sends the video signal during the measurement period to the background removal circuit 9.
Enter.

The CPU II causes the background image memory 4 to input a background video signal before photographing the moving object. The CPU 11 also controls signal transmission between the memories connected to the bus 12, the trajectory creation circuit 2, the communication control circuit 13, and the video output circuit 15.

Next, the procedure for creating a trajectory image signal of a moving object will be explained in more detail based on FIG. Among the video signals 47 output from the TV left camera and input to the bus 12 via the video input circuit 14, a background video photographed before photographing the moving object is first stored in the background image memory 4. A moving object video signal 47 output from the TV left camera in response to an instruction to start measuring a moving object and a background video signal stored in the background image memory 4 are input to the background removal circuit 9.

That is, the background video signal 4 is bit-inverted by the bit inverter 46, and then converted into the moving object video signal 4 by the adder 45.
7 is added. Through such processing of the background removal port N9, the difference between the video signal of the moving object and the video signal of the background is determined, and an image of the moving object is created by removing the background video signal from the video signal of the moving object. . The image signal of only the moving object created here is binarized by the binarization circuit 7, and then sent to the superimposition processing circuit 8.
An OR operation circuit 4 performs a logical sum operation between the output signal of the binarization circuit 7 and the trajectory image signal stored in the trajectory image memory 3.
4, and a new trajectory image signal, which is the output of the OR calculation circuit 44, is stored in the trajectory image memory 3. This new trajectory image signal is obtained by adding an image signal of only the moving object after a predetermined time outputted from the binarization circuit 7 to the trajectory image signal stored in the trajectory image memory 3. The processes in the background removal circuit 9, the binarization circuit 7, and the superimposition processing circuit 8 are repeated at the above-mentioned predetermined time to sequentially store the trajectory image signals of the moving object in the trajectory image memory.

Next, the removal of the background video signal from the starting point video signal and the ending point video signal of a moving object will be explained based on FIG. The start point image signal or end point image signal stored in the start point image memory 5 and end point image memory 6 and the background video signal stored in the background image memory 4 are input to the background removal circuit 8.

After the background video signal is bit-inverted by a bit inverter 46.

The adder 45 adds it to the start point or end point image signal.

Through this processing, the difference between the start point or end point image signal and the background video signal is determined, and an image signal of only the moving object is created by removing the background video signal from the start point or end point image signal. The moving object starting point image signal of only the moving object from which the background video signal has been removed is stored in the starting point image memory 5, and the moving object ending point image signal of only the moving object is stored in the ending point image memory 6.
are stored respectively. Background image memory 4, starting point image memory 5. The image signal stored in the end point image memory 6 can be converted into a binarized output signal 48 using the binarization circuit 7, if necessary.

Further, this embodiment will be explained again using FIG. 1. trajectory image memory 3, background image memory 4, starting point image memory 5,
End point image memory 6, binarization output 4 in the binarization circuit 7
8. The video and image signals in the speed measuring device, such as the video signal 47, can be outputted to the monitor (monitor television) 16 via the video output circuit 15.0 Created arbitrary image signals.

Transferred to the image analysis device 10 through the communication control circuit 13
The image analysis device 10 performs image analysis to determine the speed of the moving object. Information such as shape information, position information, size, amount of movement, speed, vector, etc. of the moving object determined by image analysis is displayed on the display'/device 40. Printer 41, plotter 42, and printer 43 can be used to output or record numerical information or graphical information.

Next is the image analysis bag! ! One method of image analysis in 10 will be explained. Assume that the TV camera 1 captures an image of a moving object 50 moving in the direction of an arrow 51 in a location including a background 49 as shown in FIG. 4(a). T
When the video signal 47 captured by the V-camera 1 is processed by the trajectory processing circuit 2 as described above, an example of the output is the binarized background image signal 5 shown in FIG. 4(b).
2. The trajectory image signal 53 which is binarized with the background removed in FIG. 4(c). A moving object starting point image signal 54, which is binarized with the background removed, shown in FIG. 4(d), and a moving object ending point image signal 55, which is binarized with the background removed, shown in FIG. 4(e), are obtained. These image signals are input to the image analysis device 110 via the communication control circuit 13. A method for determining the velocity of a moving object using these image signals will be described.

First, the moving object starting point image signal 54 and the moving object ending point N image signal 55 are analyzed. In an image containing multiple moving objects, pixels are tracked along the contour constituent points of the image of each moving object, and the image signals of each moving object are distinguished using the coordinate values of the zero-order contour constituent points. The positions of the centers of gravity of the object starting point image signal and the moving object end point image signal are calculated, and the coordinates of each center of gravity are taken as the coordinates of the starting point and ending point of the moving object. An example of the centroid calculation method is as follows.

Here, (Xi, Yi) are the coordinate values of N contour constituent points, and (Xg*Yg) are the coordinates of one center of gravity.

Next, the trajectory image signal 53 is analyzed. Tracking pixels along the contour constituent points of the trajectory image signal 53 of each moving object,
Distinguish and recognize the trajectory image signals of each moving object. Then, the position of the center of gravity is calculated using equations (1) and (2) above. The area surrounded by the outline constituent points of the locus of each moving object is searched to find the center of gravity coordinates of the starting point and end point of the moving object that are within the coordinate values of one outline constituent point. In the trajectory of a moving object, if the number of barycentric coordinates of the starting point and ending point of the moving object is plural, it is recognized that the trajectory is formed by multiple moving objects overlapping, and the starting point and ending point of the moving object are After the centroid coordinate values of the starting point and ending point of the moving object corresponding to the trajectory of the moving object have been determined through the above steps of separation recognition using coordinates, the velocity at the moving average position of the moving object can be calculated as follows. You can ask for it.

Here, U is the velocity component in the X direction, υ is the velocity component in the X direction, and
ge is the coordinate value of the center of gravity in the X direction of the end point of the moving object.

Xgs is the coordinate value of the center of gravity in the X direction of the starting point of a moving object, Yge is the coordinate value of the center of gravity in the Y direction of the end point of a moving object, Ygs is the coordinate value of the center of gravity in the Y direction of the starting point of the moving object, Δt is the arrival of the moving object from the starting point to the ending point This is the time it took to do so.

A normal TV camera has a finite scanning speed for one screen.

For example, the scanning speed is 1/60 seconds/screen for industrial TV cameras and 1/30 seconds/screen for home TV cameras. If the scanning time of one screen of the TV camera is T, and the length of the moving object in the moving direction is L, then if the moving object moves beyond the length L during the scanning time of one screen, T, then the movement Images of the moving object at each time in the predetermined time interval, which is repeated in the process of creating the trajectory of the object (processing in the trajectory creation circuit 2), no longer overlap.

The trajectory image analysis method described above is a method for when images of moving objects at each time overlap continuously, and if they do not overlap continuously and become discontinuous, other analysis methods are required. Become. The conditions for when the trajectory becomes continuous and when it becomes discontinuous are as follows.

If V ≦L/T, continuous trajectory V > L
/T If it is a discontinuous trajectory, V is the magnitude of the velocity of the moving object.

One image analysis device 10 determines whether the trajectory is a continuous trajectory or a discontinuous trajectory. Based on this judgment result, image analysis bag @1
0 selects either the analysis method for continuous trajectories described above or the analysis method for discontinuous trajectories described below, and 1 performs image analysis according to the selected analysis method. FIG. 5 illustrates discontinuous trajectories of a plurality of moving objects. In a discontinuous trajectory, the image signal 56 of the moving object at each time does not overlap with the image of the moving object at the previous or subsequent time, and
A method of analyzing such zero-order discontinuous trajectory image signals, which are images that coexist within one screen, will be described. First, pixels are tracked along contour constituent points of individual discontinuous trajectory image signals to distinguish image signals of each moving object. If the outline of these moving objects includes the barycentric coordinates of the starting point and ending point, the starting point and ending point image signals of each moving object are (
The corresponding memories 5, 6) are stored as described above.

Formulas (1) and (2) are calculated from the coordinate values of the contour constituent points of each moving object.
Calculate and store the coordinates of the center of gravity using A method for identifying the same moving object from image signals will be explained based on FIG. 6. In FIG. 6, the coordinates of the center of gravity of three moving objects A, B and C are A, 58. A engineering 59
, A260, A361, B062, B163, B, 64
, B, 65° and C066, C, 67, C268, C1
There are 69. Each moving object A, B, and C moves from barycenter coordinate A058 to barycenter coordinate A, 61 by one barycenter coordinate B06.
2 to barycenter coordinate B, 65, and from barycenter coordinate 0066 to barycenter coordinate C169. That is, the center of gravity coordinate A
058, B062 and C666 are the barycentric coordinates of the starting points of moving objects A, B and C, respectively, as barycentric coordinates A, 61,
B165 and C169 represent the barycenter coordinates of the end points of moving objects A, B, and C, respectively. In this case, the number of times the superimposition process was performed by the superimposition processing circuit 8 was four times, and four image signals of each of the moving objects A, B, and C were also included. The procedure for identifying the image signal of the moving object A will be described below as an example.

(a) First, examine the barycenter coordinate B163, which is the shortest distance from the starting point's barycenter coordinate A, 58.
7), and in this example, since there is no corresponding point, the search moves to the next point.

(b) Check the next closest center of gravity 41jlB, 62. Since the center of gravity coordinates are the starting point of the moving object B, the search is stopped.

(c) Check the center of gravity coordinate A359. Center of gravity seat 41A□5
9→ Extend the vectors A, A, and search for the neighborhood, barycenter coordinates A, eoi<6 barycenter coordinates A, 60 found barycenter coordinates A, 59. The center of gravity coordinate A159 is the center of gravity coordinate A.

58, and perform operations (a) to (c). By repeating the same operation as many times as the superimposition process, the center of gravity coordinates A161 of the end point of the moving object A can be reached. For moving objects B and C, image signals of the moving objects at each time can be obtained using a similar method. The Euler velocity can be determined from the distance between the start and end points of the moving object identified in this way, and the Lagrange velocity can be determined from the distance between the centers of gravity of the same moving object at each identified time. Further, if the minute radius g57 used as the search range in the above search method is made into a window with sides of εX and εy, processing in an image analysis device or computer becomes easier.

Next, the effects of this embodiment will be described.According to this embodiment, when creating a trajectory image signal, it is possible to obtain a clear trajectory image signal that does not get cut off even if the background is removed. In addition, it is possible to perform processing to remove the background from images of the measurement start point and measurement end point, including image signals of the start and end points of a moving object, without providing a dedicated calculation mechanism for this processing.
The arithmetic mechanisms such as the background removal circuit 9 and the binarization circuit 7 used in the trajectory creation mechanism can be shared. Thereby, it is possible to easily identify the trajectory image signal of the moving object and the moving object start point and end point image signals, and improve speed measurement accuracy and measurement efficiency. FIG. 7 is an example in which the speeds of a plurality of moving objects are measured by the moving object speed measuring device of this embodiment.

Furthermore, by connecting the image storage medium provided in the trajectory creation device and the mechanism for creating the trajectory of a moving object in parallel, the calculation mechanism of the mechanism for creating and printing the trajectory can be shared for calculations between the image storage media. It can be used efficiently without increasing the number of calculation mechanisms.

Furthermore, since the time-series image data necessary to determine the unsteadily changing speed of an unsteadily moving object can be stored at high speed in multiple image storage media, an analysis device that determines the speed of a moving object can Even when the speed of a moving object cannot be determined in real time, it is possible to determine the unsteadily changing speed of an unsteadily moving object.

Next, FIG. 12 shows another embodiment of the present invention. In this embodiment, the moving object speed measuring device having the configuration shown in FIG.
An image memory 72 is provided which can input a video signal 71 from the video output circuit 15 and store a plurality of image signals. If a video signal is used as the video signal 71, the image signal can be transferred to the image memory 72 at a high speed of 1760 seconds per screen.

It becomes possible to quickly collect time-series image data necessary to determine the unsteadily changing speed of an unsteadily moving object.

FIG. 13 shows an embodiment of a speed measuring device for a moving object when measuring three-dimensional speed.

This embodiment includes two TV cameras 1 to stereoscopically capture images of moving objects, including a video input circuit 14, a video output circuit 15, a binarization circuit 7, a superimposition processing circuit 8, and a background removal circuit 9. ．． Two sets each of a trajectory image memory 3, a background image memory 4, a starting point image memory 5, and an end point image memory 6 are connected in parallel to a bus 12 connected to the CPU 1.

By simultaneously processing video signals output from two synchronized TV cameras 1 in parallel, a trajectory image signal stereoscopically captured from two directions, a moving object starting point image signal, and a moving object ending point image signal are created. 1 image analysis device ff1
Analyze with flo. With this, the three-dimensional velocity of the moving object can be determined.

Another embodiment of the present invention is a moving object speed measuring device,
In the six embodiments shown in FIG. 14, the functions of the trajectory creation circuit 2 in the device shown in FIG.
This was achieved using UII. The flowchart in FIG. 14 shows the processing procedure performed within the CPU II. The hardware configuration of this embodiment is such that the locus creation circuit 2 is removed from the embodiment shown in FIG. First, CPU II
Before executing the processing sequence shown in Figure 14, the operator first enters the weight count and binarization level into CPUI 1 as input data in order to set the weight count and binarization level required for the following process. A video signal from a background photographing device, which is the output of the TV camera 1, is inputted, and after being digitized in the CPU II, it is stored in the background image memory 4 as background image data. The video signal input in the case of the first weight processing is digitized as a starting point image signal and stored in the trajectory image memory 3 as starting point image data. The video signal input in the final superimposition process is digitized as an end point image signal and stored in the trajectory image memory 3 as end point image data. T
The video signal including moving objects and background from V camera 1 is sent to CP.
If it is input to UI 1, it will be processed as follows. After this video signal is digitized, it is determined that it does not include only the background video signal, and the background image data stored in the background image memory 4 is removed.

That is, digitized image data input from the TV camera 1 and background image data are subtracted, static components included in both image data are deleted, and background removal is performed to leave only the moving component. and.

The moving object trajectory image data obtained by removing the background in this way is converted into binary image data at a preset binarization level, and this binary image data and the trajectory image memory 3 are stored. A logical OR is performed with the moving object trajectory image data. The moving object trajectory image data after the logical sum is stored in the trajectory image memory 3 again. Then, it is determined whether the superimposition process has ended, and if it has not ended, the process returns to the previous end point input determination part and repeats the above-mentioned process until the number of times of superimposition ends. If completed, image data such as the background, start point, end point, trajectory, etc. is transferred to the image analysis device, and the image is analyzed using the method described above to calculate the speed of the moving object.

Another embodiment shown in FIG. 15 is a color TV camera 73. Video input circuit 14° superposition processing circuit 8
and a background removal circuit 9. A trajectory creation mechanism 2. Trajectory color image memory 74. background color image memory 75, starting point color image memory 76, end point color image memory 77,
Communication control circuit 13, color image analysis device! ! 78 and a monitor 16 for outputting the created image. The moving object speed measuring device of the embodiment shown in FIG. A trajectory image signal, a moving object starting point image signal, a moving object ending point image signal, etc. are created. According to the speed measurement device for a moving object that can process color images of this embodiment, the color of the moving object is recognized by the color image analysis device, and when there are multiple moving objects, it is easy to distinguish between the individual moving objects. , it becomes easier to identify the starting point, end point, and trajectory image. In addition, by using a moving object coated with a temperature-sensitive liquid crystal object or using a temperature-sensitive liquid crystal object itself, by recognizing the color of the moving object, the temperature or temperature distribution of the area where the moving object is present can be determined quickly. Alternatively, it becomes possible to simultaneously measure the velocity distribution.

〔Effect of the invention〕

According to the present invention, since the background image is removed from the moving object's video signal using a background-only video signal that does not include the moving object's video signal, a clear trajectory image is obtained without line breaks in the trajectory image. This improves the accuracy of trajectory image analysis. Furthermore, since an image of a moving object at any time can be stored in an image storage medium and background removal can be performed, the background does not interfere with the identification of the trajectory image and the images of the starting and ending points of the moving object. The moving speed can be determined efficiently.

[Brief explanation of drawings]

FIG. 1 is an embodiment of a configuration diagram of a speed measuring device for a moving object which is a preferred embodiment of the present invention, FIG. 2 is an explanatory diagram showing a signal flow when creating a trajectory image signal in FIG. 1, FIG. 3 is an explanatory diagram showing the signal flow when creating the moving object start point image signal and the moving object end point image signal in FIG. 1, and FIG.
a) is an explanatory diagram of the video signal of a moving object including the background, FIGS. 4(b) to (e) are explanatory diagrams of the image signal output from the trajectory creation circuit, and FIG. 5 is an explanatory diagram of the image signal of a moving object including the background. FIG. 6 is an explanatory diagram of the identification method in the case of a discontinuous trajectory. FIG. 7 is an explanatory diagram showing the measurement results of the velocity of the moving object measured by the device in FIG. 1. , 8th
The figure is an explanatory diagram of a trajectory image from which the background has been removed using the background image of the measurement starting point. FIG. 10 is an explanatory diagram of the starting point image with no background removed, FIG. 11 is an explanatory diagram of the ending point image with no background removed, and 121! FIGS. 1 to 15 are block diagrams of other embodiments of the present invention. 1...TV camera, 2...trajectory creation circuit, 3...
Trajectory image memory, 4...Background image memory, 5...Start point image memory, 6...End point image memory, 7...Z value conversion circuit, 8...Superimposition processing circuit, 9...Background removal circuit, 10... image analysis device, 11... CPU, 12.
...Bus, 13...Tsu゛゛da7'

Claims (1)

[Claims] 1. A photographing device that outputs images of a moving object and a background, a trajectory creation device that determines the trajectory of the moving object based on the video signal output from the photographing device, and a device that analyzes the created trajectory of the moving object and moves it. A device for measuring the speed of a moving object comprising a device for determining the speed of the object, further comprising a memory for storing a background video signal that does not include the video signal of the moving object output from the photographing device, and the trajectory creating device includes:
The background video signal stored in the memory is removed from the video signal output from the photographing device, and the trajectory of the moving object is determined from the video signal from which the background has been removed, and the starting and ending points of the moving object are determined. , and the means for determining the moving speed is a means for determining the speed of the moving object based on a trajectory of the moving object and images of a starting point and an ending point of the moving object. A device for measuring the speed of an object.