JP2012181063A - Calculation device, calculation method and calculation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a calculation technique by which an installation height and an installation angle of a camera may be accurately calculated without much time and effort.SOLUTION: A calculation device comprises a first acquiring part, a second acquiring part and a calculating part. The first acquiring part acquires a plurality of images of one object captured by one camera when the object is in various different positions. The second acquiring part acquires a height of the object. The calculating part calculates an installation angle and an installation height of the camera on the basis of the plurality of images and the height acquired by the second acquiring part.

Description

  The present invention relates to a calculation device, a calculation method, and a calculation program.

  2. Description of the Related Art Conventionally, there is a technique for calculating a distance from a target object to a camera, a height of the target object, and a camera installation angle using an image photographed by the camera ( For example, see Patent Documents 1 to 3).

JP 09-318351 A JP 2003-329411 A JP 2010-245628 A

  In recent years, for example, it has been required to calculate the actual height of a person by calculating the position and height of the person in the actual space from the position of the person captured in the image taken by the surveillance camera. . In this case, it is necessary to measure the installation height and installation angle of the camera in advance, but there is a risk that the measurement may be time consuming and the accuracy may change greatly due to the measurement method and human error. .

  The present invention has been made in view of the above, and an object thereof is to provide a calculation device, a calculation method, and a calculation program capable of calculating the installation height and the installation angle of a camera with high accuracy without taking time and effort. .

  In order to solve the above-described problems and achieve the object, the present invention is a calculation device, and acquires a plurality of images in which the same object is photographed by the same camera at different positions. A first acquisition unit; a second acquisition unit configured to acquire a height of the object; and a calculation unit configured to calculate an installation angle and an installation height of the camera using the plurality of images and the height. It is characterized by.

  Moreover, this invention is a calculation method performed with a calculation apparatus provided with a 1st acquisition part, a 2nd acquisition part, and a calculation part, Comprising: When the said 1st acquisition part exists in a respectively different position, it is the same A first acquisition step of acquiring a plurality of images each of which is captured by the same camera, a second acquisition step in which the second acquisition unit acquires the height of the target, and the calculation unit And a calculation step of calculating an installation angle and an installation height of the camera using the plurality of images and the height.

  Further, the present invention is a calculation program for causing a computer to execute the above calculation method.

  According to the present invention, it is possible to calculate the installation height and the installation angle of the camera with high accuracy without taking time and effort.

FIG. 1 is a diagram illustrating a functional configuration of a computing device 50 according to an embodiment. FIG. 2 is a diagram illustrating two images G1 and G2. FIG. 3 is a flowchart showing a procedure of calculation processing performed by the calculation device 50. FIG. 4 is a diagram showing the positional relationship between the positions where the same person appears in two images and the camera installation positions in the XYZ space. FIG. 5 is a diagram showing the positional relationship between the position of the same person in one image and the installation position of the camera on the XZ plane. FIG. 6 is a diagram illustrating an interface. FIG. 7 is a diagram for explaining an application example. FIG. 8 is a diagram for explaining an application example.

  Exemplary embodiments of a calculation device, a calculation method, and a calculation program according to the present invention will be explained below in detail with reference to the accompanying drawings.

  Here, the hardware configuration of the computing device of this embodiment will be described. The computing device includes a control unit such as a CPU (Central Processing Unit) that controls the entire device, a main storage unit such as a ROM (Read Only Memory) and a RAM (Random Access Memory) that stores various data and various programs, and various types It is equipped with an auxiliary storage unit such as an HDD (Hard Disk Drive) or CD (Compact Disk) drive device that stores data and various programs, and a bus that connects them, resulting in a hardware configuration using a normal computer. ing. In addition, a display unit that displays information, an operation input unit such as a keyboard and a mouse that accepts user input, and a communication interface (I / F) that controls communication with an external device are wired or wireless. Are connected to each other. In addition, a camera that captures an image may be connected to the calculation device, and an image captured by the camera may be stored in, for example, an auxiliary storage unit. In addition, a reception unit that receives broadcast waves is connected to the computing device as a communication I / F so that an image carried by the broadcast waves is received by the reception unit and stored in the main storage unit or the auxiliary storage unit. Anyway. In addition, a communication I / F that controls communication via a network is connected to the computing device as a communication I / F, and an image transmitted from an external device is received via the communication I / F, and the main storage unit Alternatively, it may be stored in the auxiliary storage unit. The network is, for example, a local area network (LAN), an intranet, Ethernet (registered trademark), or the Internet. In the present embodiment, how the image is stored in the main storage unit and the auxiliary storage unit is not limited, but is an image taken by a camera such as a surveillance camera disposed at a predetermined location. Suppose that images stored in the main storage unit and the auxiliary storage unit are handled. The image is information indicating a pixel value for each pixel in pixels. When handling a moving image, for example, for each frame image (referred to as a frame image), a plurality of continuous or discontinuous frame images are handled.

  Next, various functions realized by the computing device in such a hardware configuration will be described. FIG. 1 is a diagram illustrating a functional configuration of the computing device 50. The calculation device 50 includes an image acquisition unit 51, a height acquisition unit 52, a calculation unit 53, and an output unit 54. The functions of these units are realized by the CPU of the computing device 50 executing various programs stored in the main storage unit and the auxiliary storage unit.

  The image acquisition unit 51 acquires a plurality of images in which the same object is photographed by the same camera at different positions. The image acquisition unit 51 acquires the image by reading it from the main storage unit or auxiliary storage unit stored as described above.

  FIG. 2 is a diagram illustrating two images G1 and G2 captured by the same camera when the object is a person and the person is at different positions. The image G1 is an image when the position of the head which is the position of one end in the vertical direction in the three-dimensional space is Q1, and the position of the foot which is the position of the other end in the vertical direction is Q2. G2 is an image when the position of the head of the person is Q3 and the position of the foot is Q4.

  The height acquisition unit 52 acquires the height of the object shown in the image acquired by the image acquisition unit 51. The height value is input by a user via an operation input unit connected to the calculation device 50, for example, and the height acquisition unit 52 acquires the height by receiving the input of the value.

  The calculation unit 53 uses the plurality of images acquired by the image acquisition unit 51 and the height acquired by the height acquisition unit 52 to calculate a camera installation angle (a depression angle) and an installation height as the camera installation status. . A specific calculation method will be described later. The output unit 54 outputs the installation angle (the depression angle) and the installation height of the camera calculated by the calculation unit 53.

  Next, a calculation processing procedure performed by the calculation device 50 according to the present embodiment will be described with reference to FIG. The calculation device 50 acquires one image captured by one camera by the function of the image acquisition unit 51 (step S1). Further, the calculation device 50 acquires the height (height) of the person as the object shown in the image by the function of the height acquisition unit 52 (step S2). Then, the computing device 50 analyzes the image acquired in step S1, and performs a human body detection process for detecting an area in which a person is captured (referred to as a human body area) (step S3). Since the human body detection process can be performed using a known technique, the description thereof is omitted here. Next, the computing device 50 determines whether or not the human body region has been detected (step S4). When the determination result is negative (step S4: NO), the process returns to step S1, and the calculation device 50 acquires a new image taken by the same camera.

  If the determination result in step S4 is affirmative (step S4: YES), the computing device 50 is a person shown in a predetermined area (referred to as a measurement area) in a plurality of images with respect to the image acquired in step S1. A person tracking process for identifying the image is performed (step S5), and it is determined whether or not the same person is shown in the measurement region of the image (step S6). Since the person tracking process can be performed using a known technique, the description thereof is omitted here. When step S5 is performed for the first time after the calculation device 50 performs the calculation process, the person captured in the human body region detected in step S4 is set as the person to be identified for the image acquired in step S1 after the next time. The person tracking process in step S5 is performed, and in step S6, it is determined whether or not the person to be identified is shown in the measurement region of the image. When the determination result is negative (step S6: NO), the process returns to step S1, and the calculation device 50 acquires a new image taken by the same camera. On the other hand, when the determination result of step S6 is affirmative (step S6: YES), the calculation device 50 acquires coordinates of the human body region detected in step S4 and stores them in the main storage unit (step S7). . Then, the calculation device 50 adds “1” to the number of times the coordinates of the human body region are acquired from different images for the same person.

  Next, the calculation device 50 determines whether or not the number of times that the coordinates of the human body region are acquired from different images for the same person is N (N: an integer equal to or greater than 2) (step S8). When the determination result is negative (step S8: NO), the process returns to step S1, and the calculation device 50 acquires a new image taken by the same camera. At this time, the calculation device 50 may acquire an image in which a person different from the person shown in the image acquired in the previous step S1 is shown, or is shown in the image acquired in the previous step S1. An image in which the same person as the person is captured as a new object may be acquired.

  On the other hand, when the determination result of step S8 is affirmative (step S8: YES), the calculation device 50 uses the coordinates of the human body region stored in the main storage unit in step S7 and the height acquired in step S2, A camera installation angle (a depression angle) is calculated (step S9). In addition, the calculation device 50 resets the number of times the coordinates of the human body region are acquired from different images for the same person to “0”. Here, a method for calculating the depression angle will be described with reference to FIGS. Here, it is assumed that the images G1 and G2 in FIG. 2 are acquired in step S1, the coordinates of positions Q1 and Q2 are acquired from the image G1, and the coordinates of positions Q3 and Q4 are acquired from the image G2 in step S7. .

FIG. 4 is a diagram showing the positional relationship between the positions where the same person appears in two images and the installation positions of the cameras that captured these images in an XYZ space, which is a three-dimensional space. FIG. 5 is a diagram showing a positional relationship on the XZ plane between the position where the same person appears in one image and the installation position of the camera that captured these images. Here, the vertical direction is the Z axis, and the horizontal plane with respect to the Z axis is the XY plane composed of the X axis and the Y axis. The XZ plane is a plane having two axes in the vertical direction and the horizontal direction. The camera installation height corresponding to the coordinates on the Z axis is H _cam (m), the height, which is the height of the person, is H _man (m), and the camera installation angle (a depression angle) is α. The person's height _Hman is acquired by the function of the height acquisition unit 52 in step S2, and is known. In the image G1, the distance from the installation position of the camera to the position Q2 of the person's foot is D ₂ (m), the angle of the position Q2 with respect to the optical axis projected on the XZ plane from the camera is ρ _z2, and the angular position Q1 with respect to the optical axis which is projected on a plane and [rho _z1, vanishing point Qvp (Xvp, Yvp) on the XY plane and then, the apparent person in the image G1 length, i.e., from the position Q1 The length up to the position Q2 is P ₁₂ (pixels), and the length of the person from which the influence of the depression angle on the images G1 and G2 is removed is P ′ ₁₂ (pixels). In the image G2, the distance from the camera installation position to the foot position Q4 of the person is D ₄ (m), the angle of the position Q4 with respect to the optical axis projected from the camera onto the XZ plane is ρ _z4, and The angle of the position Q3 with respect to the optical axis projected on the XZ plane is _ρz3 , the apparent length of the person on the image G2, that is, the length from the position Q3 to the position Q4 is P ₃₄ (pixels), On the other hand, the length of the person from which the influence of the depression angle on the images G1 and G2 is removed is defined as P ′ ₃₄ (pixels). At this time, the following formulas 1 and 2 are derived from the relationship between the distances D ₂ and D ₄ and the installation height with H _cam .

Further, since the distances D ₂ and D ₄ and the lengths P ′ ₁₂ and P ′ _{34 of the} person have an inversely proportional relationship, the following Expression 3 is established.

The lengths P ′ ₁₂ and P ′ ₃₄ of the persons on the images G1 and G2 are obtained by removing the effect of reduction due to the depression angle from the apparent lengths of the persons on the images G1 and G2, respectively. It is obtained by the following formulas 4-5.

The angle ρ _z1 of the position Q1 relative to the optical axis projected from the camera onto the XZ plane, the angle of the position Q2 relative to the optical axis ρ _z2 , the angle of the position Q3 relative to the optical axis ρ _z3, and the position Q4 relative to the optical axis The angle ρ _z4 is obtained by the following equations 6 to 9, respectively. Note that imgHeight is the vertical width of the image, βv is the vertical angle of view, and these are known. y _i is the y coordinate of the position Qi (i = 1 to 4).

  By using the above formulas 1 to 9, the following formula 10 is derived, and the depression angle α can be obtained.

Returning to the description of FIG. The calculation device 50 calculates the installation height of the camera using the depression angle calculated in step S9 and the height acquired in step S2 (step S10). Here, if the x coordinate of the above-mentioned position Qi (i = 1 to 4) is X _i and the y coordinate is Y _i , the camera installation height H _cam can be obtained by the following Expression 11. That is, the installation height H _cam camera, the height of the camera on the image G1 obtained by using the depression angle α in the image G1, were obtained in a ratio and step S2 and the length P ₁₂ of the person in the image G1 It is obtained using the height H _man of the person. More specifically, the camera installation height H _cam is obtained by using the depression angle α, the vanishing point on the XY plane, and the height H _{man of} the person acquired in step S2. Note that the y-coordinate Yvp of the vanishing point is obtained by the following equation 12. That is, the y-coordinate Yvp of the vanishing point is the x-coordinate and y-coordinate on the XY plane for each of the positions Q1, Q3 at one end and the positions Q2, Q4 at the other end of the person shown in the images G1, G2, respectively. It is calculated using.

As described above, the calculation device 50 calculates the depression angle and installation height of the camera for each identical person. Next, the calculation device 50 outputs the depression angle calculated in step S9 and the installation height calculated in step S10 by the function of the output unit 54 (step S11). Here, an example of an interface for outputting the depression angle and the installation height in step S11 will be described. FIG. 6 is a diagram illustrating a screen in which an interface for outputting the depression angle and the installation height is integrally formed with an interface for a user to input the height of a person. The calculation device 50 displays the screen illustrated in FIG. 6 on the display unit for a plurality of images in which the same object is photographed by the same camera at different positions, and inputs on the screen. When the height (height) of the object is input to the item K1 via the operation input unit, the input of the height is accepted in step S2 in FIG. 3, and steps S3 to S10 are performed. In step S11, step S9 is performed. The camera installation angle (the depression angle) calculated in step S10 is displayed in the output item K2, and the installation height calculated in step S10 is displayed in the output item K3. Further, the calculation device 50 may display the distance from the object to the camera (the example D ₂ or D ₄ described above) at the position closest to the camera among the different positions in the output item K4. good.

  According to the configuration as described above, it is possible to easily calculate using the image photographed by the camera without taking the trouble of actually measuring the installation angle and the installation height of the camera. In addition, since the error in accuracy due to the difference between the measurers is less likely to occur than when the installation angle and the installation height are actually measured, the installation angle and the installation height can be calculated with high accuracy.

Here, an application example of the installation angle and the installation height of the camera calculated as described above will be described. As described above, in the image G1, the distance D ₂ from the installation position of the camera to the position Q2 at the foot of the person is determined by Equation 1. Thus, the horizontal distance D _xy from the position on a horizontal plane which is installed in the camera to the position Q2 of the feet of a person can be easily obtained. Further, the direction θ in which the person is present with respect to the camera can be obtained by the following Expression 13. Note that imgWidth is the horizontal width of the image, and β _H is the horizontal angle of view. x _i is the x coordinate of the position Qi (i = 1 to 4).

  As described above, the position of the person on the map in the real space with the camera as the origin and the ground on which the person is present can be known. By the way, when tracking a person on the image, even if the person in the foreground and the person in the back are moving at the same speed, the apparent amount of movement on the image is to differ greatly. Therefore, it has been necessary to change the tracking range of the person depending on the length of the person on the image. If the position of the person on the map in the real space with the ground on which the person is present is known according to the present embodiment, the apparent length of the person on the image depends on the apparent length as illustrated in FIGS. Without being done, the range for tracking the person can be determined.

[Modification]
Note that the present invention is not limited to the above-described embodiment as it is, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. Moreover, various inventions can be formed by appropriately combining a plurality of constituent elements disclosed in the embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, constituent elements over different embodiments may be appropriately combined. Further, various modifications as exemplified below are possible.

  In the above-described embodiment, various programs executed by the computing device 50 may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. The various programs are recorded in a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, and a DVD (Digital Versatile Disk) in a file in an installable or executable format. May be configured to be provided.

  In the above-described embodiment, a person is treated as the same object shown in a plurality of images used when calculating the installation angle and installation height of the camera. However, the present invention is not limited to this, and an object having a certain length. Or a mobile object.

50 Calculation Device 51 Image Acquisition Unit 52 Height Acquisition Unit 53 Calculation Unit 54 Output Unit

Claims (9)

A first acquisition unit that acquires a plurality of images each of which is captured by the same camera when the same object is in a different position;
A second acquisition unit for acquiring the height of the object;
A calculation apparatus comprising: a calculation unit that calculates an installation angle and an installation height of the camera using the plurality of images and the height. The calculation unit includes a positional relationship in a three-dimensional space between each position where the object is reflected in each of the plurality of images and the installation position of the camera, and each distance from the installation position of the camera to each position. The calculation apparatus according to claim 1, further comprising an installation angle calculation unit that calculates the installation angle based on a ratio of the two. The installation angle calculation unit, each of the plurality of images, each angle of the object at each position relative to the optical axis projected on a plane having two vertical and horizontal directions from the camera, The calculation apparatus according to claim 2, wherein the installation angle is calculated based on a ratio of the distances obtained by using the lengths of the objects on each of a plurality of images. The installation angle calculation unit includes a position of one end and a position of the other end in the vertical direction of the object with respect to an optical axis projected from the camera on a plane having two axes of a vertical direction and a horizontal direction in each of the plurality of images. The installation angle based on a ratio of the distances obtained using each angle of the position and each length from the position of the one end of the object to the position of the other end on each of the plurality of images. The calculation device according to claim 3, wherein: The calculation unit uses a ratio between the height of the camera on the image and the length of the object on the image, and the height obtained using the installation angle in at least one of the plurality of images. The calculation apparatus according to claim 2, further comprising an installation height calculation unit that calculates the installation height. The calculation unit is configured to obtain the installation angle and the position of one end and the position of the other end in the vertical direction of each of the plurality of images in the plurality of images using the position coordinates on the horizontal plane. The calculation apparatus according to claim 5, further comprising: an installation height calculation unit that calculates the installation height using the vanishing point of and the height. The calculation apparatus according to claim 1, further comprising an output unit that outputs the installation angle and the installation height. A calculation method executed by a calculation device including a first acquisition unit, a second acquisition unit, and a calculation unit,
A first acquisition step in which the first acquisition unit acquires a plurality of images each of which is captured by the same camera when the same object is in a different position;
A second acquisition step in which the second acquisition unit acquires the height of the object;
The calculation method includes a calculation step of calculating an installation angle and an installation height of the camera using the plurality of images and the height.   A calculation program for causing a computer to execute the calculation method according to claim 8.

Images