JP2008014825A - Method and program for measurement - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To measure a distance to an image or an object displayed in a screen image highly precisely. <P>SOLUTION: A method for measuring a distance from a predetermined position in a photographing means to an object included in an image obtained by the photographing means, comprises a following distance measuring step for solving a problem. When assuming that the pixel number corresponding to a predetermined width of the object included in the image is F; the distance of the reference that is preset is Ls; and the pixel number of the reference that is set Fs corresponding to the distance Ls, the distance L from the predetermined position in the photographing means to the object is calculated by L=(Ls ×Fs)/F and then the distance is measured. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a measurement method and a measurement program, and more particularly, to a measurement method and a measurement program for measuring a distance to an object shown in an image or video with high accuracy.

  2. Description of the Related Art Conventionally, a distance measuring device that takes an object such as a person using an imaging unit such as a camera and measures the distance between the camera and the object from the taken image has been put into practical use. Here, as a conventional distance measuring device, for example, a device using a stereo camera is known (see, for example, Patent Document 1).

  As shown in Patent Document 1, the measurement method of the distance measuring device using a stereo camera first images an object at the same time with two cameras installed at different positions, and two captured images. The point (corresponding point) which shows the same places, such as a person, is specified. Thereafter, the distance to the object is measured in consideration of the distance between the cameras and the focal length of the camera lens.

As another method, a distance measuring function including a light emitting unit that emits laser light to the camera and a light receiving unit that receives reflected light reflected from the object by laser light is provided, and reflection characteristics by the laser light are used. There is a method for measuring the distance to an object.
JP 2005-91173 A

  However, as described above, in the conventional distance measurement method, when measuring a distance using a stereo camera, images and videos taken simultaneously with a plurality of cameras are required, and a distance measurement function using a laser beam is required. For this reason, there are problems such as an increase in cost (price) of the apparatus and a complicated system configuration. Further, there has been no method for measuring the position of the object at the same time as measuring the above-mentioned distance with high efficiency and high accuracy.

  The present invention has been made in view of the above-described problems, and provides a measurement method and a measurement program for measuring the distance to an object and the position of the object reflected in an image or video with high accuracy. Objective.

  In order to solve the above problems, the present invention employs means for solving the problems having the following characteristics.

  The invention described in claim 1 is a measuring method for measuring a distance from a predetermined position of the imaging unit to an object included in an image obtained from the imaging unit. When the number of pixels corresponding to a predetermined width is F, the reference distance set in advance is Ls, and the reference pixel number set corresponding to the distance Ls is Fs, the predetermined distance of the imaging unit is It has a distance measuring step of measuring the distance by calculating the distance L to the object by L = (Ls × Fs) / F.

  According to a second aspect of the present invention, there is provided a measurement method for measuring a distance from a predetermined position of the imaging unit to an object included in the image obtained from the imaging unit. The number of pixels corresponding to a predetermined width of the object is set to F, the angle of view of the image pickup means when the number of pixels F is measured is set to α, a predetermined reference distance is set to Ls, and the distance Ls is set. When the number of reference pixels is Fs and the angle of view of the imaging unit when the number of pixels Fs is measured is αs, the distance L from the predetermined position of the imaging unit to the object is expressed as L = (Ls It is characterized by having a distance measuring step of measuring the distance by calculating by * tan (αs / 2) * Fs) / (tan (α / 2) * F).

  According to a third aspect of the present invention, there is provided a measurement method for measuring a distance from a predetermined position of the imaging unit to an object included in the image obtained from the imaging unit. F is the number of pixels corresponding to a predetermined width of the object, α is the angle of view of the imaging means when the number of pixels F is measured, β is the inclination with respect to the shooting direction of the object, and the distance is a preset reference. Ls, where Fs is the reference pixel number set corresponding to the distance Ls, and αs is the angle of view of the imaging unit when the pixel number Fs is measured, the object from the predetermined position of the imaging unit A distance measuring step of measuring the distance by calculating the distance L to the object by L = (Ls × tan (αs / 2) × Fs) / (tan (α / 2) × F × cosβ) And

According to a fourth aspect of the present invention, the number of pixels in the horizontal direction of the imaging unit is N, the horizontal field angle of the imaging unit is αh, and the horizontal coordinate of the center of the object is x. Then, the horizontal angle θ of the object is calculated by θ = tan ⁻¹ (((2 × x / N) −1) × tan (αh / 2)), and the calculated result and the distance measurement And a position measuring step of measuring the position of the object based on a distance from the predetermined position of the imaging means obtained by the step to the object.

  The invention described in claim 5 further includes a screen generation step of generating a screen including at least a result obtained by the distance measurement step and the position measurement step.

  The invention described in claim 6 causes a computer to execute the measurement method described in any one of claims 1 to 5.

  According to the first aspect of the present invention, it is possible to measure the distance from the predetermined position of the imaging unit that has captured an image or video to the object reflected in the image or video with high accuracy.

  According to the second aspect of the present invention, even when the angle of view is changed by the zoom function of the camera, it is possible to measure the exact distance between the imaging means and the object.

  According to the third aspect of the present invention, the distance can be measured with high accuracy even when the object is not facing the image pickup means.

  According to the invention of claim 4, the position of the object can be measured with high accuracy.

  According to the invention described in claim 5, by generating and outputting a screen including at least the distance measurement result and the position measurement result, the user or the like can obtain an image from a predetermined position of the imaging unit that has captured the image or video. It is possible to easily grasp the distance to the object and the position of the object shown in the video.

  According to the invention described in claim 6, the distance from the predetermined position of the image pickup means for capturing an image or video to the target object shown in the image or video and the position of the target object are measured efficiently and with high accuracy. be able to. Moreover, the measurement process can be easily realized by installing the execution program in the computer.

  Hereinafter, preferred embodiments of the measurement method and the measurement program according to the present invention will be described with reference to the drawings. In the embodiment described below, for a person as an object photographed in an image or video photographed by an imaging means such as a camera, a configuration for measuring a distance from the camera and position information of the person However, the present invention is not limited to this, for example, a configuration for measuring only the distance of a person from the camera, and a configuration for measuring the position of the photographed person. Can be configured differently.

  In the following embodiments, an example in which the imaging unit is configured as a separate body and the measurement apparatus acquires image information such as images and videos via a communication network (which may be wired or wireless) is shown. It may have a function of an imaging device.

<Measuring device: functional configuration>
FIG. 1 is a diagram illustrating an example of a schematic configuration of a measurement apparatus according to the present invention. 1 includes an input unit 11, an output unit 12, a storage unit 13, a distance measurement unit 14, a position measurement unit 15, a screen generation unit 16, a transmission / reception unit 17, and a control unit 18. It is comprised so that.

  The input unit 11 measures an instruction for receiving image information such as an image or a video captured by the subject from a camera or the like from the transmission / reception unit 17 described later, and a distance of the target from the acquired image or video. Or input of various instruction information such as a measurement instruction for measuring a position. The input unit 11 includes, for example, a touch panel, a group of operation buttons, a keyboard, a pointing device such as a mouse, a microphone for inputting instructions by voice, and the like.

Here, the type of camera for taking an image or video is not particularly limited. For example, a high-definition camera, a telephoto camera, or the like can be used, and any commercially available camera having a general resolution can be used. Good. In addition to images and video, image information obtained from the camera includes shooting time information indicating the date and time of shooting, camera identification information for identifying the camera, and voice input from the camera or a microphone installed around the camera. In addition, the output unit 12 includes instruction information input by the input unit 11, images and videos obtained from a camera or a predetermined external memory device, and captured images. The distance measurement unit 14 outputs the distance measurement result from the predetermined position of the camera to the person and the position measurement result of the object obtained by the position measurement unit 15 using a display or the like. Note that the display contents generated by the screen generation means 16 are output as the distance measurement and position measurement results.

  Here, the output unit 12 includes an audio output unit such as a speaker in addition to the display. For example, after the distance measurement or the position measurement is completed, the output unit 12 is notified to the user or the like by voice, or is installed around the camera or the camera. Voice data obtained from voice input means such as a microphone can be output.

  The storage means 13 includes image information obtained by the camera (including images, video, shooting time information, camera identification information, sound, etc.), distance measurement results obtained by the distance measurement means 14, and positions obtained by the position measurement means 15. Accumulate various information such as measurement results.

  Various data stored in the storage means 13 can be read out as necessary based on a control signal from the control means 18, and data can be updated, added, etc. written and deleted. it can.

  The distance measuring means 14 is based on the image information received via the transmission / reception means 17 or the image or video included in the image information stored in advance in the storage means 13 from a predetermined position preset by the camera to the object. Measure the distance. A specific distance measuring method will be described later.

  Further, the position measuring unit 15 measures the position of the object based on the image information received via the transmission / reception unit 17 or the image or video included in the image information stored in advance in the storage unit 13. A specific position measurement method will be described later.

  In addition, the screen generation unit 16 includes the image information received via the transmission / reception unit 17, the image or video included in the image information stored in advance in the storage unit 13, the distance measurement result measured by the distance measurement unit 14, A screen for outputting the position measurement result measured by the position measuring means 15 from the output means 12 is generated. A specific generation screen example will be described later.

  The transmission / reception means 17 includes an antenna, a communication line, etc., and transmits / receives data or control signals to / from a predetermined camera or an external storage device by wireless or wired communication, and receives images and videos taken from the camera or the like. I do.

  Further, the control means 18 controls the entire components of the measuring apparatus 10. Specifically, when the control unit 18 receives an image or video captured by the camera, the control unit 18 stores the image or video in the storage unit 13, causes the distance measurement unit 14 to measure the distance to the person included in the image, or the like. Control of processing such as measuring the position of a person included in an image or the like by the measurement unit 15 or generating a screen for displaying the measurement result on a display or the like by the screen generation unit 16 is performed.

<Distance Measuring Method in Distance Measuring Means 14>
Next, the distance measuring method in the distance measuring means 14 will be described with reference to the drawings.
<Principle of distance measurement>
First, the principle of distance measurement in this embodiment will be described. FIG. 2 is a diagram for explaining the principle of distance measurement in the present embodiment. Here, FIG. 2A is an image obtained by photographing a person 0.5 m away from a predetermined position (for example, the center position of the lens, the center of gravity position of the camera body, etc.) preset for each camera. b) is an image of a person photographed 1.0 m away from a predetermined position of the camera.

  In general, as shown in FIGS. 2 (a) and 2 (b), the size of a person's face reflected on the camera differs depending on the distance, and is larger when closer to the camera and smaller when far away. In other words, if the size of the face is known, it is possible to measure the distance to a person without using a plurality of stereo cameras or a measurement method using reflection characteristics by laser as in the prior art.

  In the present invention, based on the above-described contents, the distance is obtained from information on the size (width, length, etc.) of the face shown in each frame image of the image or video. Specifically, a reference value indicating the relationship between the size of the face reflected on the camera and the distance from the camera is set, and the distance is measured using the reference value. For example, as shown in FIG. 2C, the distance is 1 m when the number of pixels corresponding to a predetermined predetermined width (distance) of the face is 100 pixels, based on the width and length of the face. Based on the relationship between the number of pixels and the distance. In FIG. 2C, the distance from the tip of the head to the jaw is used as a reference for the size (width) of the face. Note that the reference face size is not limited to this for the present invention. For example, from the eyebrows to the mouth, from the eyes to the chin, etc., both eyes, both eyebrows, nose, mouth, both ears, jaw, and head contour. At least one distance serving as a predetermined reference is selected from the facial feature such as, and a pixel corresponding to the selected distance is set.

  It should be noted that the predetermined width as a reference may be set according to the application. For example, as shown in FIG. 2 (a), considering the case where the chin portion protrudes from the image, the reference predetermined width is set at a relatively short distance, for example, from the eyes to the mouth or from both eyes. It is better to set it. On the other hand, the smaller the distance from the camera to the person, the smaller the person appears. Therefore, the accuracy can be improved by setting a predetermined reference width longer. The reference for these pixels depends on the number of pixels of an image or video obtained from a camera or the like.

  As described above, in this method, the distance can be measured based on at least one reference value set as described above. In other words, as in the past, a distance measurement function using laser light, etc., a person's position in an image is converted to an actual space position, and a table for converting image information into distance is stored in advance in the memory. There is no need to prepare, and the distance can be obtained according to the number of pixels occupied by the face.

  Therefore, the distance measuring unit 14 extracts the number of pixels corresponding to the width of the face from the image, and accurately calculates the distance from the predetermined position to the object shown in the image or video based on the preset reference value. Can be measured. Note that there are various conventional methods for detecting a face included in an image. For example, it can be measured by the feature points of both eyes, nose, mouth, etc. included in the face and the positional relationship between the feature points. . A face detection method is disclosed in, for example, Japanese Patent Application Laid-Open No. 11-281661.

  Next, an embodiment based on the above-described principle will be described.

<First embodiment>
First, as a first embodiment, a method for measuring the distance of a person facing the front of the camera will be described.

  FIG. 3 is a diagram for explaining a first example of distance measurement. As shown in FIG. 3, it is assumed that a camera (imaging means) 21 is installed at a certain predetermined position and the vertical angle of view of the camera 21 is α °.

  Here, a person is placed on an image frame 22-1 at a predetermined distance L (m) from a predetermined position of the camera 21 and an image frame 22-2 at a position 2L (m) away from the predetermined position of the camera 21, respectively. Suppose that 23 is photographed. At this time, as shown in FIG. 3, when the distance from the camera 21 is doubled, the vertical imageable range is also doubled. In addition, since the number of pixels of the camera 21 is constant regardless of the distance, when the distance from the camera 21 is doubled, the actual range included in one pixel of the camera 21 in the vertical direction is doubled. However, since the actual size of the face is constant (x) regardless of the distance from the camera 21, the number of pixels corresponding to the width of the face (vertical direction) is 1/2 when the distance is doubled in the vertical direction. Doubled.

  From the above, if the width of the face relative to the reference distance and the number of pixels corresponding to the width are known from the relationship between the distance from the camera and the number of pixels corresponding to the width of the face, for example, the following formula is used: Thus, the distance from the predetermined position of the camera 21 (the center position of the lens, the gravity center position of the camera body, etc.) to the person can be derived from the number of pixels corresponding to the width of the photographed person's face.

  Here, if the number of pixels corresponding to a predetermined width of the person included in the image is F, the reference distance set in advance is Ls, and the reference pixel number set corresponding to the distance Ls is Fs, the camera The distance L from the predetermined position 21 to the person can be obtained by L = (Ls × Fs) / F.

  For example, if the reference value is a distance of 1 m and the number of pixels corresponding to the width of the face is given as 100 pixels, when the face of a person detected from an image reflected on the camera is 70 pixels, The distance is human distance L = (1 m × 100 pixels) / 70 pixels = 1.43 m.

  Thereby, it is possible to measure the distance of the object with high accuracy using one image or video.

<Second embodiment>
Next, a second embodiment of the present invention will be described. In the second embodiment, a distance measuring method corresponding to camera zoom will be described.

  FIG. 4 is a diagram for explaining a second embodiment of distance measurement. As shown in FIGS. 4A and 4B, the optical zoom function by the lens optical system of a general camera 21 can photograph a distant position by changing the distance between the lenses. Actually, as shown in FIGS. 4 (a) and 4 (b), the camera 21 projects a far frame (L <L ′) 22-3 by narrowing the angle of view (α> α ′). ing. That is, as shown in FIG. 4, even when the vertical size of the projected range is the same y (m), the distance to the camera 21 varies depending on the angle of view.

  From the above, from the relationship between the distance from the camera and the face width, the relationship between the camera angle of view, the number of pixels corresponding to the face width at the reference distance, and the camera angle of view at that time If there is, for example, the following formula can be used to derive the distance from the predetermined position of the camera 21 to the person from the number of pixels corresponding to the width of the face of the person whose distance is to be measured.

  Here, the number of pixels corresponding to a predetermined width of the person included in the image is F, the angle of view of the camera 21 when the number of pixels F is measured is α, the preset reference distance corresponds to Ls, and the distance Ls. When the reference pixel number set in this way is Fs, and the angle of view of the camera 21 when the pixel number Fs is measured is αs, the distance L from the predetermined position of the camera 21 to the person is L = (Ls × tan (αs / 2) × Fs) / (tan (α / 2) × F).

  Thus, according to the second embodiment, the distance to the object (person) can be calculated even when the angle of view changes due to the zoom function of the camera.

  For example, if the reference value is a distance of 1 m and the number of pixels corresponding to the width of the face is 100 pixels, and the angle of view at that time is given as 40 °, When the face is 70 pixels and the angle of view is 20 °, the distance between the camera and the person is the distance L of the person L = (1 m × tan (40 ° / 2) × 100 pixels) / (tan (20 ° / 2) ) × 70 pixels) = 2.95 m, and the distance can be obtained even if the angle of view changes due to zooming.

  In the second embodiment described above, the distance can be obtained on the basis of the telephoto magnification and the like using not only zoom but also a similar method.

<Third embodiment>
Next, a third embodiment of the present invention will be described. In the third embodiment, a distance measurement method corresponding to the inclination of the face will be described. FIG. 5 is a diagram for explaining a third embodiment (third embodiment) in distance measurement.

  In the embodiments so far, as shown in FIG. 5A, for the face facing the front in the shooting direction of the camera, the relational expression between the face size and the distance is obtained, and the distance is measured. It was. In this method, the distance to the front face can be accurately measured. However, for example, when the face is moved up and down (left and right) as shown in FIG. is there. Specifically, when the actual front face width is F pixels, the photographed face width is Fcos β ° pixels. Therefore, in the third embodiment, in order to improve this, the difference in face size (width) depending on the angle of the photographed face is obtained by a relational expression, and the distance is corrected.

  Specifically, the distance of the person is corrected according to the inclination of the face, using a formula for deriving the distance from the number of pixels with respect to the measured current face length. The face inclination detection method can be obtained by a conventional detection method (for example, the above-mentioned Japanese Patent Application Laid-Open No. 11-181661).

  Here, the number of pixels corresponding to a predetermined width of the person included in the image is F, the angle of view of the camera when the number of pixels F is measured is α, the inclination with respect to the shooting direction of the person is β, and a predetermined reference is used. When the distance is Ls, the reference number of pixels set corresponding to the distance Ls is Fs, and the angle of view of the camera when the number of pixels Fs is measured is αs, the person object from the predetermined position of the camera to be corrected Can be obtained by L = (Ls × tan (αs / 2) × Fs) / (tan (α / 2) × F × cosβ).

  For example, when the reference value is given as 100 pixels occupied by the face when the distance is 1 m and the angle of view at that time is 40 °, the face of the person detected from the image captured by the camera is 70 pixels, When the tilt of the face is 30 ° and the angle of view of the camera at that time is 25 °, the distance L between the camera and the person is L = (1 m × tan (40 ° / 2) × 100 pixels) / (tan (20 ° / 2) × 70 pixels × cos 30 °) = 3.41 m.

  This makes it possible to measure the distance with high accuracy even when the person is not facing the shooting direction of the camera and the face is tilted. Note that these tilt corrections can be applied not only to the top and bottom of the face but also to the left and right of the face.

  Here, Examples 1 to 3 described above are based on the vertical width of the face. However, in the present invention, the width is not limited to this and may be a horizontal width.

<Position Measurement Technique in Position Measuring Unit 15>
Next, the position measuring method in the position measuring means 15 will be described with reference to the drawings. In the present invention, as a position measurement method, a deviation angle from the center of the photographing range of the camera is measured.
<Principle of position measurement>
First, the principle of position measurement in this embodiment will be described. FIG. 6 is a diagram for explaining the principle of position measurement in the present embodiment. As shown in FIGS. 6A and 6B, the coordinates of the person's face reflected on the camera vary on the image depending on the angle of deviation from the center of the shooting range of the camera (dotted line in FIG. 6). That is, if the coordinates on the face image are known, it is possible to measure the deviation angle of the person from the center of the camera. Using this principle, the face in the image is detected by image processing or the like, and the coordinates of the center of the detected face are obtained to obtain the angle of the person from the camera.

  Here, FIG. 7 is a diagram illustrating an example for measuring the angle of the person from the camera. As shown in FIG. 7, the angle from the camera 21 matches the coordinates on the image regardless of the distance. That is, the angle per pixel can be found by using the horizontal angle of view of the camera 21 to be used and the horizontal coordinate of the image. Therefore, if the coordinates of the center position of the face of the person 23 are given to this information, the angle of the person 23 from the camera 21 can be measured.

  For example, as shown in FIG. 7, in frames 22-4 to 22-6 of images at different distances (1.0 m, 2.0 m, 3.0 m) from the camera 21, the person 23 is in the horizontal direction. If the total number of pixels in the horizontal direction is 320 pixels when the image is shifted by 5 ° from the center (0 °) of the image, the pixel on the left side is 118 pixels from the position shifted by 5 ° when viewed from the camera 21. The pixels on the right side are 202 pixels (320-118 pixels).

Therefore, the horizontal angle from the person's camera is obtained by the following procedure. FIG. 8 is a diagram illustrating an example of a specific method for measuring the angle in the horizontal direction. In FIG. 8, when the horizontal pixel angle of the camera 21 is N, the horizontal angle of view of the camera 21 is αh °, and the horizontal coordinate of the center of the person (object) is x, the horizontal direction of the person The angle θ can be obtained by θ = tan ⁻¹ (((2 × x / N) −1) × tan (αh / 2)).

  As for the center coordinates of the human face, one of the corners of the image frame is set to the origin coordinate (0, 0), and the horizontal and vertical coordinates are extracted with the origin as a reference. In the example of FIG. 7, regarding the base angle, the center of the camera in the horizontal direction is 0 °, the sign of one angle is positive (+: plus), and the other is negative (−: minus).

For example, if the number of pixels in the horizontal direction of the camera is 320 pixels, the horizontal angle of view is 40 °, and the horizontal coordinate of the person's face is 60, the horizontal angle of the person is θ ° = tan ⁻¹ ((( (2 × 60/320 pixels) −1) × tan (40 ° / 2) = − 12.8 °.

<Conversion to two-dimensional planar coordinates>
Next, when outputting the distance and angle obtained as described above, it is converted into coordinates on a two-dimensional plane so that the user can visually understand it. Here, FIG. 9 is a diagram illustrating an example of coordinate transformation on a two-dimensional plane.

  As shown in FIG. 9, when the distance obtained by the person is L and the angle is θ with respect to the coordinates (X, Y) of the entire two-dimensional plane, the coordinates (x, y) on the two-dimensional plane are x = L × sin θ, y = L × cos θ. In this case, the origin is set at a reference position previously set in the camera.

  As described above, the position information of the object (person) can be efficiently acquired by the present invention.

<Screen generation example>
Here, an example of the screen generated by the screen generation means 16 in the present invention will be described with reference to the drawings. FIG. 10 is a diagram showing an example of a screen generated in the present invention. The measurement result display screen 30 shown in FIG. 10 is configured to have a menu display area 31, an image display area 32, a measurement result display area 33, and a position display area 34.

  The menu display area 31 reads an image to be displayed on the measurement result display screen 30, displays distance and position information measured according to the present invention, and displays the displayed result in another storage area as a file name. And processing such as recording. The image display area 32 displays an image to be measured. At this time, information on the face feature point 41 for measuring which part of the screen is the face, the center of the face, and the size (width, length) of the face is also displayed.

  In the measurement result display area 33, the actual measurement result is displayed. Here, the data shown in the measurement result display area 33 are, for example, the size of the face, the distance between the camera and the person, the center coordinates of the face, the angle between the camera and the person, and the like. The size of the face indicates a ratio when a certain reference is set to 100, and the center coordinates of the face are set based on the resolution (320 × 240) of the image display area 32.

  The position display area 34 indicates the position of the camera 42 on the two-dimensional plane, the position of the person (object) 43 corresponding to the camera 42, and the direction of the person 43 corresponding to the shooting direction of the camera 42. An arrow 44 is displayed together with a distance from a predetermined position of the camera 42. In the present invention, the content displayed in the position display area 34 is not limited to this, and any display content may be used as long as the distance and positional relationship between the camera and the person can be understood.

  The items displayed on the measurement result display screen 30 are not limited to the above-described contents, and may include at least distance measurement and position measurement results. For example, time information when an image is acquired may be displayed, The acquired measurement results may be displayed side by side.

  In this way, by generating the measurement result display screen 30 and displaying it on the display or the like, the user or the like can move the distance from the predetermined position of the imaging means that captured the image or video to the object shown in the image or video. And the position of the object can be easily grasped.

  As described above, according to the present invention, it is possible to measure the distance from the predetermined position of the imaging unit that has captured an image or video to the object shown in the image or video with high accuracy. Specifically, since the distance and position between the camera and the person can be measured using the above-described formulas for distance and position measurement, the measurement process can be performed by one camera.

<Execution program>
Here, the above-described measurement apparatus can perform the measurement process according to the present invention using the dedicated apparatus configuration described above, but generates an execution program for causing the computer to execute the process in each configuration. The measurement processing according to the present invention can be realized by installing the program in a personal computer, a server, or the like.

<Hardware configuration>
Here, a hardware configuration example of a computer capable of executing the measurement process according to the present invention will be described with reference to the drawings. FIG. 11 is a diagram illustrating an example of a hardware configuration capable of realizing the measurement process according to the present invention.

  11 includes an input device 51, an output device 52, a drive device 53, an auxiliary storage device 54, a memory device 55, a CPU (Central Processing Unit) 56 that performs various controls, and a network connection device. 57 are connected to each other by a system bus B.

  The input device 51 has a keyboard and a pointing device such as a mouse operated by a user, a voice input device, and the like, and inputs various operation signals and voice signals such as a program execution instruction from the user. The output device 52 has a display, a speaker, and the like that display various windows and data necessary for operating the computer main body for performing the processing in the present invention. Display or audio output is possible.

  Here, in the present invention, the execution program installed in the computer main body is provided by a recording medium 58 such as a CD-ROM. The recording medium 58 on which the program is recorded can be set in the drive device 53, and the execution program included in the recording medium 58 is installed in the auxiliary storage device 54 from the recording medium 58 via the drive device 53.

  Further, the drive device 53 can record the execution program according to the present invention in the recording medium 58. As a result, the recording medium 58 can be used for easy installation on a plurality of other computers, and the measurement processing in the present invention can be easily realized.

  The auxiliary storage device 54 is a storage means such as a hard disk, and can store an execution program according to the present invention, a control program provided in a computer, etc., and perform input / output as necessary. The auxiliary storage device 54 can also be used as a storage unit that stores distance information and position information of an object included in the above-described image, image information captured by the camera 21, the above-described output image, and the like.

  Based on a control program such as an OS (Operating System) and an execution program read from the auxiliary storage device 54 and stored in the memory device 55, the CPU 56 inputs various calculations and data with each hardware component. Each process in the measurement process can be realized by controlling processes of the entire computer such as output. Various information necessary during the execution of the program can be acquired from the auxiliary storage device 54 and stored.

  The network connection device 57 obtains an execution program from another terminal connected to the communication network or executes the program by connecting to a communication network such as a telephone line or a LAN (Local Area Network) cable. The execution result obtained in this way or the execution program in the present invention can be provided to other terminals or the like.

  With the hardware configuration as described above, the measurement process can be realized at a low cost without requiring a special device configuration. In addition, measurement processing can be easily realized by installing a program.

<Measurement procedure>
Next, the measurement processing procedure in the present invention will be described using a flowchart. FIG. 12 is a flowchart illustrating an example of a measurement processing procedure. In FIG. 12, the object is a person as an example, and the distance and position are measured when the person is included in the image. However, the present invention is not limited to this, and distance measurement and position measurement are not limited thereto. May be performed as separate measurement processes.

  In FIG. 12, first, image information is input from an imaging means such as a camera (S01), and it is determined whether or not a person (face) is included in the image (S02). Here, the face detection process of the person in S02 can use the conventional face detection method as described above.

  Next, in the process of S02, when there is a person in the image (YES in S02), the distance of the person is measured (S03). Specifically, as shown in the first to third embodiments described above, based on the relationship between the camera and the person photographed by the camera (face size, camera angle of view, face orientation, etc.), The distance from a predetermined position of the camera to the person is measured. Further, the position of the person is measured based on the distance information (S04). After the processes of S03 and S04 are completed, a screen for displaying the measurement result is generated (S05), and the generated screen is output (S06).

  Here, after the process of S06 is completed or when it is determined in the process of S02 that there is no person in the image (NO in S02), it is determined whether or not there is still an uninput image to be subjected to the measurement process ( S07). Specifically, for example, when a moving image is input, the above-described processing is repeated.

  Therefore, if there is an uninput image in the process of S07 (YES in S07), the process returns to S01 and the above-described processes are repeated. If there is no uninput image (NO in S07), the process is terminated.

  By the measurement process described above, the distance to the object and the position of the object shown in the image or video can be measured with high accuracy. In addition, by installing a program for performing the above-described measurement process, it is possible to easily measure the distance and position of a person.

  As described above, according to the present invention, it is possible to measure the distance from the predetermined position of the imaging unit that has captured an image or video to the object reflected in the image or video with high accuracy. Specifically, since the distance and position between the camera and the person can be measured using the above-described formulas for distance and position measurement, the measurement process can be performed by one camera.

  Further, the distance between the camera and the person can be measured using the second embodiment corresponding to the change in the angle of view of the camera. In other words, since the zoom function of a camera normally projects far away objects by narrowing the angle of view, the distance from the camera varies depending on the angle of view even if the size of the projected range is the same. Therefore, even when the angle of view is changed by the zoom function of the camera, the accurate distance between the camera and the person can be measured.

  If the face of a person included in the photographed image is tilted, the distance between the camera and the person can be measured using the third embodiment corresponding to the tilt of the person's face. That is, when measuring the distance between the camera and the person based on the size of the person's face, the size of the person's face differs depending on the inclination of the person's face with respect to the camera, and an error occurs in the distance between the camera and the person. Therefore, it is possible to eliminate the error of the distance due to the inclination of the person's face by the above formula and to measure the exact distance between the camera and the person.

  Further, the position of the person relative to the camera can be measured by combining the angle between the camera and the person with the distance measured in the first to third embodiments described above. Furthermore, by generating and outputting a screen including at least the distance measurement result and the position measurement result, the user or the like can go from the predetermined position of the imaging means that captured the image or video to the object reflected in the image or video. It is possible to easily grasp the distance and the position of the object.

  Note that the measurement method according to the present invention can detect a suspicious person with higher accuracy by applying it to, for example, a monitoring system in a bank, department store, supermarket, convenience store, hospital, house periphery, or the like. In addition, the measurement method according to the present invention is also applied to a case where the attention object is a certain product, an advertisement, a signboard, or the like, thereby checking the attention level or interest level of a passerby or customer for the product. be able to.

  Although the preferred embodiment of the present invention has been described in detail above, the present invention is not limited to the specific embodiment, and various modifications, within the scope of the gist of the present invention described in the claims, It can be changed.

It is a figure which shows an example of schematic structure of the measuring apparatus in this invention. It is a figure for demonstrating the principle of the distance measurement in this embodiment. It is a figure for demonstrating the 1st Example in distance measurement. It is a figure for demonstrating the 2nd Example in distance measurement. It is a figure for demonstrating the 3rd Example in distance measurement. It is a figure for demonstrating the principle of the position measurement in this embodiment. It is a figure which shows an example for measuring the angle from the camera of a person. It is a figure of an example which shows the specific measuring method of the angle of a horizontal direction. It is a figure which shows an example of the coordinate transformation on a two-dimensional plane. It is a figure which shows an example of the screen produced | generated in this invention. It is a figure which shows an example of the hardware constitutions which can implement | achieve the measurement process in this invention. It is a flowchart which shows an example of a measurement processing procedure.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Measuring apparatus 11 Input means 12 Output means 13 Accumulation means 14 Distance measurement means 15 Position measurement means 16 Screen generation means 17 Transmission / reception means 18 Control means 21, 42 Camera 22 Frame 23, 43 Person 30 Measurement result display screen 31 Menu display area 32 Image display area 33 Measurement result display area 34 Position display area 41 Feature point 44 Arrow 51 Input device 52 Output device 53 Drive device 54 Auxiliary storage device 55 Memory device 56 CPU
57 Network connection device 58 Recording medium

Claims (6)

In a measurement method for measuring a distance from a predetermined position of the imaging unit to an object included in an image obtained from the imaging unit,
When the number of pixels corresponding to a predetermined width of the object included in the image is F, the reference distance set in advance is Ls, and the reference pixel number set corresponding to the distance Ls is Fs, The distance L from the predetermined position of the imaging means to the object is
L = (Ls × Fs) / F
A measurement method comprising a distance measurement step for calculating a distance by measuring the distance. In a measurement method for measuring a distance from a predetermined position of the imaging unit to an object included in an image obtained from the imaging unit,
F is the number of pixels corresponding to a predetermined width of the object included in the image, α is the angle of view of the imaging means when the number of pixels F is measured, Ls is a preset reference distance, and Ls is the distance Ls. The distance L from the predetermined position of the imaging means to the object is Fs, where Fs is the number of reference pixels set corresponding to, and αs is the angle of view of the imaging means when the number of pixels Fs is measured. The
L = (Ls × tan (αs / 2) × Fs) / (tan (α / 2) × F)
A measurement method comprising a distance measurement step for calculating a distance by measuring the distance. In a measurement method for measuring a distance from a predetermined position of the imaging unit to an object included in an image obtained from the imaging unit,
The number of pixels corresponding to a predetermined width of the object included in the image is F, the angle of view of the imaging unit when the number of pixels F is measured is α, and the inclination of the object with respect to the shooting direction is β, When the reference distance is Ls, the reference number of pixels set corresponding to the distance Ls is Fs, and the angle of view of the imaging means when the number of pixels Fs is measured is αs, the imaging means A distance L from the predetermined position to the object,
A measurement method comprising a distance measurement step of measuring a distance by calculating L = (Ls × tan (αs / 2) × Fs) / (tan (α / 2) × F × cosβ). When the number of pixels in the horizontal direction of the imaging unit is N, the horizontal field angle of the imaging unit is αh, and the horizontal coordinate of the center of the target is x, the horizontal angle θ of the target is ,
θ = tan ⁻¹ (((2 × x / N) −1) × tan (αh / 2))
And a position measurement step of measuring the position of the object based on the calculated result and the distance from the predetermined position of the imaging means obtained by the distance measurement step to the object. The measurement method according to any one of claims 1 to 3.   The measurement method according to claim 4, further comprising a screen generation step of generating a screen including at least a result obtained by the distance measurement step and the position measurement step.   A measurement program for causing a computer to execute the measurement method according to any one of claims 1 to 5.

Images