JP2020053840A - Surveillance system and camera - Google Patents

Abstract

To sufficiently obtain feature information of a person by creating a 3D model of the person using information obtained from a captured image looking down a space.SOLUTION: The surveillance system includes: an imaging unit, installed on a ceiling, for acquiring a captured image looking down a space below the ceiling in a direction of gravity from the ceiling; a determination unit for determining whether a person is captured in the captured image; a creating unit for creating a 3D model of the person captured in the captured image using information obtained from the captured image when the determination unit determines that the person is captured in the captured image; and a display unit for displaying the 3D model.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a surveillance system and a camera.

  Surveillance cameras are used for monitoring intrusion into offices and condominiums. Among such surveillance cameras, there is one that monitors a space to be monitored from an obliquely upward direction (for example, Patent Document 1).

JP 2013-229044 A

  In the case where the surveillance camera as described in Patent Document 1 monitors the space obliquely from above, the side of the person being photographed that is opposite to the side on which the surveillance camera is arranged is not shown. There is a possibility that the feature information of the person cannot be obtained sufficiently. For this reason, a technique capable of sufficiently obtaining characteristic information of a person passing through a monitored space is desired.

  SUMMARY An advantage of some aspects of the invention is to solve at least a part of the problems described above, and the invention can be implemented as the following embodiments.

  (1) According to one aspect of the present invention, a monitoring system is provided. The monitoring system is installed on a ceiling, an imaging unit that obtains a captured image of the space below the gravitational direction from the ceiling, and a determination unit that determines whether a person is included in the captured image, A creating unit that creates a 3D model of the person appearing in the captured image using information obtained from the captured image when the determining unit determines that the person is present in the captured image. According to the monitoring system of this aspect, a captured image of the space below the gravitational direction from the ceiling where the imaging unit is installed is obtained. From the captured image, information obtained by capturing the body of the person who has been captured from multiple viewpoints can be obtained. Since a 3D model of a person is created using such information obtained from a captured image of the space, feature information of the person can be sufficiently obtained.

  (2) In the monitoring system according to the aspect, the creation unit may create the 3D model using information obtained from the captured images acquired at different times. With such an embodiment, a 3D model can be created with high accuracy.

  (3) According to another aspect of the present invention, there is provided a camera. The camera is a camera installed on a ceiling, and an imaging unit that acquires a captured image of the space below the ceiling in the direction of gravity from the ceiling, and a determination that determines whether a person is included in the captured image. And a creating unit that creates a 3D model of the person captured in the captured image using information obtained from the captured image, when the determination unit determines that a person is captured in the captured image, A communication unit that sends information of the 3D model to a display unit that displays the 3D model. According to the camera of this embodiment, a captured image is obtained from the ceiling where the camera is installed, while looking down at the space below the camera in the direction of gravity. From the captured image, information obtained by capturing the body of the person who has been captured from multiple viewpoints can be obtained. Since a 3D model of a person is created using such information obtained from a captured image of the space, feature information of the person can be sufficiently obtained.

  The embodiment of the present invention is not limited to the form of a camera or a monitoring system, and for example, causes a computer to realize functions of the monitoring system and the management apparatus in addition to a management apparatus that manages the camera and the monitoring system. It is also possible to apply to various forms such as a program for the purpose. Further, the present invention is not limited to the above-described embodiments at all, and it goes without saying that the present invention can be implemented in various embodiments without departing from the spirit of the present invention.

It is an explanatory view showing a monitoring system. FIG. 3 is an explanatory diagram illustrating a state in which a person is imaged by an imaging unit. FIG. 4 is an explanatory diagram illustrating a state in which an upper body of a person on the front side is imaged by an imaging unit; FIG. 4 is an explanatory diagram illustrating a state in which the top of a person is imaged by an imaging unit. FIG. 8 is an explanatory diagram illustrating a state in which the upper body of the back side of the person is imaged by the imaging unit; FIG. 5 is an explanatory diagram illustrating an example of a display image displaying a 3D model. FIG. 3 is an explanatory diagram showing a camera. It is an explanatory view showing a monitoring system.

A. First embodiment:
FIG. 1 is an explanatory diagram showing a monitoring system 10 according to the present embodiment. The monitoring system 10 monitors an area AR around the door DR for entering the security area SC. The monitoring system 10 includes an imaging unit 110, a determination unit 120, a creation unit 130, and a display unit 140.

  The imaging unit 110 is installed on the ceiling of the area AR and acquires a captured image of the space below the ceiling in the direction of gravity. Here, the ceiling is a concept including not only a portion of a surface on the upper side in the gravitational direction in a closed room, but also an upper side in the gravitational direction of the area AR. In the present embodiment, the imaging unit 110 is a range image camera (depth camera) equipped with a color filter. In another embodiment, the imaging unit 110 may be a depth camera of only a grayscale image or a stereo camera using a stereo ranging method, as long as the imaging unit 110 can obtain information necessary for creating a 3D model. Good. Further, when infrared rays are used for the distance measurement as the imaging unit 110, the distance can be stably measured even in a dark place. In the present embodiment, the imaging unit 110 constantly captures an image of the area AR. In another embodiment, the imaging unit 110 may perform imaging only when a moving object enters the area AR.

  The determination unit 120 determines whether a person is included in the captured image. The determination unit 120 makes a determination at each preset time interval using the captured images accumulated during the interval. The captured images are stored in a memory included in the monitoring system 10.

  When the determination unit 120 determines that a person is present in the captured image, the creating unit 130 creates a 3D model of the person who was captured in the captured image using information obtained from the captured image. The information obtained from the captured image includes irregularity information on the surface of the target person, distance information to the person as an absolute value with the imaging unit 110 as the origin, a luminance value, an RGB value, and the like.

  The display unit 140 displays the 3D model created by the creating unit 130. In the present embodiment, the display unit 140 is a liquid crystal display of a personal computer included in the monitoring system 10. In another embodiment, the display unit 140 may be a smartphone or a liquid crystal display provided on a wall surface in a building where the area AR exists. Further, the display unit 140 may be configured to perform display using AR (Augmented Reality), VR (Virtual Reality), and MR (Mixed Reality).

  FIG. 2 is an explanatory diagram illustrating a state in which the image capturing unit 110 captures an image of a person FG that has entered the area AR. In FIG. 2, the person FG enters the area AR from the right side of the drawing and is heading toward a door DR (not shown) arranged on the left side of the drawing. The persons FG1 to FG5 represent the positions of the persons FG that move from the right side of the drawing to the left side of the drawing. The imaging unit 110 arranged on the ceiling of the area AR captures a series of motions of the person FG passing through a range that the imaging unit 110 can image. The imaging unit 110 captures the body of the person FG in accordance with the positions of the people FG1 to FG5 as indicated by the arrows in FIG. 2, and thus can capture the characteristics of the person FG at each position.

  FIG. 3 is an explanatory diagram illustrating a state in which the upper body on the front side of the person FG is imaged by the imaging unit 110 at the position of the person FG2. FIG. 4 is an explanatory diagram illustrating a state in which the top of the person FG is imaged by the imaging unit 110 at the position of the person FG3. FIG. 5 is an explanatory diagram illustrating a state in which the upper body on the back side of the person FG is imaged by the imaging unit 110 at the position of the person FG4. Further, at the position of the person FG1, the lower body of the front side of the person FG is imaged by the imaging unit 110. At the position of the person FG5, the lower body on the back side of the person FG is imaged by the imaging unit 110. The creating unit 130 creates a 3D model of the person FG by using information obtained from the images captured at the positions of the people FG1 to FG5. Therefore, a 3D model of the person FG can be created with high accuracy.

  FIG. 6 is an explanatory diagram illustrating an example of a display image displaying a 3D model. The display image Vi shown in FIG. 6 is an image showing a 3D model of the person FG. The display image Vi is displayed on the display unit 140. In the display image Vi, a person FG viewed from five sides is displayed. The display image is not limited to such a display format. For example, when the display unit 140 is a touch panel, the 3D model of one person FG displayed on the display image is rotatably displayed by operating the touch panel. May be.

  According to the first embodiment described above, a captured image of the area AR, which is a space below the gravitational direction, is obtained from the ceiling where the imaging unit 110 is installed. From the captured image, information obtained by capturing the body of the person FG from multiple viewpoints can be obtained. Since the 3D model of the person FG is created using such information obtained from the captured image of the area AR, the feature information of the person FG can be sufficiently obtained. In the monitoring system 10, by modeling the person FG as a 3D model, it is possible to reproduce a state when the person FG is viewed from a viewpoint that was not obtained when the area AR was imaged obliquely from above. In other words, information that can identify not only the person FG viewed from one viewpoint but also the person FG viewed from various viewpoints is obtained. For this reason, when the user who sees the 3D model of the person FG displayed on the display unit 140 actually encounters the person FG, it is possible to increase the possibility that the person is recognized as the person FG.

  In the case where the area AR is imaged from an obliquely upward direction, the side of the person FG being photographed that is opposite to the side where the imaging unit is arranged is not shown, and thus information on the side is missing. Model is likely to be created. In the first embodiment, since the area AR is imaged downward from the ceiling in the direction of gravity, the side of the person FG that is not visible from the imaging unit 110 can be easily reduced. The possibility of forming a 3D model with many objects can be increased. Therefore, it is possible to increase the possibility of forming a 3D model including information on the back and side surfaces of the person FG that is likely to be blind spot.

  When an attempt is made to create a 3D model with a large amount of information, the imaging unit that captures the area AR from an obliquely upward direction has image capturing units arranged at a plurality of positions to reduce the area AR in order to reduce portions that are not captured in the person FG. It is necessary to take an image. On the other hand, in the first embodiment, since the imaging unit 110 captures the area AR from a position where the area AR is overlooked, the information amount of the person FG obtained from one imaging unit is lower than that of the imaging unit that captures an image from an obliquely upward direction. Therefore, the information on the person FG can be sufficiently acquired by the smaller number of imaging units 110. Therefore, the device cost of the monitoring system 10 can be reduced.

  Further, as compared with the imaging unit that images the area AR from an obliquely upward direction, the imaging unit 110 that images the area AR from a bird's-eye view position can easily image the front side and the back side of the person FG. For this reason, in the monitoring system 10, since the amount of information on the front side and the back side of the person FG is unlikely to be insufficient, a 3D model with a large amount of information on the front side and the back side can be created.

  In addition, since the imaging unit 110 captures an image of the person FG that moves to the positions of the people FG1 to FG5, the imaging unit 110 can acquire characteristics of an operation such as a walking operation of the person FG. By applying such feature information to the 3D model, the motion of the person FG can be reproduced in the 3D model.

  Further, in the first embodiment, since the information obtained from the captured image includes a luminance value, an RGB value, and the like, the creating unit 130 can create a 3D model with color information. For this reason, the height and the physique of the person FG can be grasped visually easily from the created 3D model. Further, from the 3D model with the color information, it is possible to know in detail the information on the clothes and decorations of the person FG.

  Further, in the first embodiment, since the imaging unit 110 is installed on the ceiling, wiring is easier than in a mode in which the imaging unit 110 is installed on a side wall of a room. Specifically, when wiring to the imaging unit 110 installed on the ceiling, wiring may be performed in the space behind the ceiling, but wiring to the imaging unit installed on the side wall of the room. In such a case, complicated work such as embedding wiring in the wall is likely to occur. For this reason, in the first embodiment, the installation of the imaging unit 110 can be simplified.

B. Other embodiments:
FIG. 7 is an explanatory diagram showing a camera 10a according to another embodiment. The camera 10a includes an imaging unit 110, a determination unit 120, a creation unit 130, and a communication unit 150. The functions of the imaging unit 110, the determination unit 120, and the creation unit 130 are the same as those of the monitoring system 10 according to the first embodiment. In other words, the camera 10a executes the functions of the imaging unit 110, the determination unit 120, and the creation unit 130 included in the monitoring system 10 in the camera 10a.

  The communication unit 150 sends the information of the 3D model created by the creating unit 130 to a display unit provided outside the camera 10a. The display unit here is a screen of a digital signage, a smartphone, or a personal computer. According to such an embodiment, the same effect as in the first embodiment can be obtained.

  In the first embodiment described above, the determination unit 120 performs the determination at each preset time interval using the captured images accumulated during the interval, but the present invention is not limited to this. . For example, the determination unit 120 may make the determination only when a preset condition is satisfied.

  An example of a preset condition will be described with reference to FIG. The door DR is a door that is unlocked by an authentication operation. When there is an authenticated person AT who performs the authentication operation and unlocks the door DR to enter the security area SC, the suspicious individual PR who has not performed the authentication operation is required to perform authentication before the door DR opened by the authenticated person AT is closed. After that, a situation of entering the security area SC is referred to as tailgating. When the occurrence of the tailgating is set as a preset condition, the determination unit 120 includes the suspicious individual PR as a person in a captured image acquired at a certain time before the tailgating occurs. It may be determined whether or not there is.

  The present invention is not limited to the above-described embodiments, examples, and modified examples, and can be realized with various configurations without departing from the spirit thereof. For example, the technical features in the embodiments, examples, and modifications corresponding to the technical features in each embodiment described in the Summary of the Invention section are for solving some or all of the above-described problems, or In order to achieve some or all of the above-described effects, replacement and combination can be appropriately performed. Unless the technical features are described as essential in the present specification, they can be deleted as appropriate.

    DESCRIPTION OF SYMBOLS 10 ... Monitoring system, 10a ... Camera, 110 ... Imaging part, 120 ... Judgment part, 130 ... Creation part, 140 ... Display part, 150 ... Communication part, AR ... Area, AT ... Authentication person, DR ... Door, FG ... Person , PR: suspicious person, SC: security area, Vi: display image

Claims (3)

A monitoring system,
An imaging unit that is installed on the ceiling and acquires a captured image that overlooks the space below the gravitational direction from the ceiling,
A determining unit that determines whether a person is captured in the captured image,
A creating unit that creates a 3D model of a person that is captured in the captured image using information obtained from the captured image, when the determination unit determines that a person is captured in the captured image;
A display unit for displaying the 3D model. The monitoring system according to claim 1, wherein
The monitoring system, wherein the creating unit creates the 3D model using information obtained from the captured images acquired at different times. A camera installed on the ceiling,
An imaging unit that acquires a captured image of the space below the gravitational direction from the ceiling,
A determining unit that determines whether a person is captured in the captured image,
A creating unit that creates a 3D model of a person that is captured in the captured image using information obtained from the captured image, when the determination unit determines that a person is captured in the captured image;
A communication unit that sends information of the 3D model to a display unit that displays the 3D model.

Images