TWI590657B - Monitoring system, monitoring method, and computer storage medium - Google Patents

Description

Monitoring system, monitoring method and computer memory medium

The present invention relates to a monitoring system for monitoring a predetermined area, a monitoring method using the monitoring system, and a computer memory medium.

Previously, surveillance systems using surveillance cameras were used for the purpose of prevention and prevention. In such a monitoring system, for example, in a store, a commercial facility, a public facility, or the like, a monitoring camera is installed in a predetermined monitoring target area or a monitoring object, and an abnormal state or a dangerous situation is monitored based on an image captured by a surveillance camera.

In general, the image data captured by the surveillance camera is two-dimensional, so high-level information and depth information cannot be obtained. In this way, for example, even if the image data of two characters of different sizes are captured, it is because the heights of the two people are actually different, or one person is on the side close to the surveillance camera, and the other person is on the far side. Therefore, it seems that the size is different. The computer can only judge based on the image data. That is, it is difficult to correctly grasp a person based on two-dimensional image data, and therefore it is difficult to specify the action of a person.

Therefore, in Patent Document 1, it is proposed to add depth information to the image data. Specifically, the imaging system described in Patent Document 1 includes an irradiation source that irradiates a laser, an imaging unit that images an object, and a measurement unit that measures distance data from the irradiation source to the subject. Then, in the imaging system, image data of the subject imaged by the imaging unit is generated, and the distance data is superimposed on the synthesized data of the image data, and the three-dimensional image of the object is generated. Portrait material.

[Previous Technical Literature] [Patent Literature]

[Patent Document 1] Japanese Patent Laid-Open Publication No. 2013-207415

However, when the imaging system described in Patent Document 1 is used as a monitoring system, it is necessary to measure the distance to the subject during the monitoring period when the subject is to be captured in three dimensions. In addition, it is necessary to generate the above-mentioned composite data of the image data and the distance data, and the three-dimensional image data of the object. In the related situation, the processing performed in the monitoring is very complicated, and the amount of data processed is also large, which imposes a great burden on the computer to be processed. Therefore, there is room for improvement as a monitoring system.

The present invention is invented in view of related problems, the purpose The area is monitored appropriately and easily.

In order to achieve the above object, the present invention is a monitoring system for monitoring a predetermined area, characterized in that the imaging unit is fixedly disposed at a predetermined position, and images the predetermined area from above, and the distance measuring unit measures the predetermined area. The distance from the imaging unit to the measurement target; the model generation unit is based on the background of the predetermined area formed by the standing surface of the predetermined area in the monitoring area during the monitoring period of the predetermined area, a distance from the imaging unit to the background measured by the distance portion, the background is divided in a horizontal direction and a height direction by a grid of a predetermined size, and a mesh model of the background is generated; and the monitoring unit is based on the imaging unit The image data of the image is extracted, and a dynamic monitoring target is extracted, and the mesh model is applied to the background of the predetermined region of the image data, and new monitoring image data for synthesizing the monitoring target to the mesh model is generated, and the monitoring image is monitored. The area specified.

In the monitoring system of the present invention, after the distance from the imaging unit to the background of the predetermined area is measured by the distance measuring unit, the model generation unit generates a mesh model of the background of the predetermined area, and further applies the mesh model to the imaging unit. The background of the predetermined area of the image is monitored by the monitoring unit.

Here, the mesh model of the present invention includes distance information from the imaging unit to each of the meshes measured by the distance measuring unit, that is, position information (three-dimensional information) including the horizontal direction and the height direction of each mesh. In this way, it can be used to grasp which grid the monitoring object in the specified area is located, and take Get the 3D information of the monitored object. In other words, once the mesh model of the background of the predetermined region is generated, it is not necessary to measure the distance of the monitoring target as often as described in Patent Document 1 above, and the target can be monitored only by imaging the predetermined region by the imaging unit. region. Therefore, according to the present invention, the predetermined area can be monitored appropriately and easily.

The model generating unit may be configured to overlap the image of the background of the image data captured by the imaging unit by the mesh model of the monitoring image data.

The monitoring system further includes a database for storing information of objects in the predetermined area, and the monitoring unit may specify the object based on the database and monitor the predetermined area.

In the mesh model described above, the mesh having the predetermined size may be divided into a space surrounded by the bottom surface of the predetermined area and the standing object in a three-dimensional region.

Further, the monitoring system further includes a person setting unit that divides a person who enters the predetermined area into a plurality of areas, and the monitoring unit monitors the action of the person based on a rate of change of the person in each area set by the person setting unit. Also.

The monitoring system further includes a sound detecting unit that detects sound generated in the predetermined area, and the monitoring unit sets an imaging direction of the imaging unit in a direction of a sound detected by the sound detecting unit. And monitor the area where the sound occurs.

The present invention is a monitoring method in which an imaging unit captures and monitors a predetermined area, and is characterized in that it has a distance measuring project and a needle. The distance from the imaging unit to the background is measured by the distance measuring unit on the bottom surface of the predetermined area and the background of the predetermined area formed by the standing object standing in the monitoring period in the predetermined area; model generation engineering According to the distance measured in the foregoing ranging engineering, the background is divided in the horizontal direction and the height direction by a grid of a certain size, and the grid model of the background is generated; the camera engineering is performed by the aforementioned camera unit. The imaging is performed in the predetermined area, and the monitoring project is based on the image data captured in the imaging project, and the dynamic monitoring object is extracted, and the mesh model is applied to the background of the predetermined region of the image data to generate the monitoring. The object is synthesized into a new monitoring image data of the mesh model, and the predetermined area is monitored.

In the above-described model generation project, an image of the background of the image data captured by the imaging unit may be superimposed on the mesh model of the image data for monitoring.

The information of the object in the predetermined area is stored in the database; in the monitoring project, the object may be specified according to the database, and the predetermined area may be monitored.

In the above-described model generation project, in the mesh model, the space of the predetermined size may be defined by the bottom surface of the predetermined area and the space surrounded by the permanent object.

In the above-described monitoring project, the person entering the predetermined area is divided into a plurality of areas, and the action of the person is monitored based on the rate of change of the person in each of the divided areas.

In the aforementioned imaging project, occurring in the aforementioned predetermined area When the sound is detected by the sound detecting unit, the imaging direction of the imaging unit is set in the direction of the sound, and the area where the sound is generated is captured. In the monitoring process, the area where the sound is generated may be monitored.

Moreover, according to the present invention, a readable computer memory medium is provided for storing a program by means of a monitoring system executing the aforementioned monitoring method, the program being used to enable a computer controlling the monitoring system to function A program that moves on a computer.

According to the present invention, the predetermined area can be monitored appropriately and easily.

1‧‧‧Monitoring system

10‧‧‧ shop

11‧‧‧Floor surface

12‧‧‧

20‧‧‧ camera

21‧‧‧ frame

22‧‧‧Semicircular cover

23‧‧‧Ranging sensor

23a‧‧‧Environment source

23b‧‧‧Light-receiving components

24‧‧‧ surveillance cameras

25‧‧‧Support components

26‧‧‧Drive mechanism

27‧‧‧Communication Department

30‧‧‧Monitor

31‧‧‧ Input Department

32‧‧‧Model Generation Department

33‧‧‧Monitor

34‧‧‧Output Department

35‧‧‧Control Department

36‧‧‧Memory Department

40‧‧‧ Character Setting Department

50‧‧‧ upper area

51‧‧‧Intermediate area

52‧‧‧ Lower area

60‧‧‧concentrator

61‧‧‧Sound Detection Department

A‧‧‧ surveillance area

D‧‧‧ mesh model

M‧‧ Grid

N‧‧‧ grid

P (P1, P2) ‧ ‧ characters

Fig. 1 is an explanatory view showing a schematic structure of a monitoring system according to the present embodiment.

Fig. 2 is an explanatory view showing a schematic structure of a monitoring system according to the present embodiment.

Fig. 3 is a flowchart showing a monitoring method according to the embodiment.

Fig. 4 is a perspective view showing the inside of a shop.

FIG. 5 is an explanatory diagram showing a state in which the distance between the monitoring camera and the background of the monitoring area is measured.

Fig. 6 is an explanatory diagram showing a state in which the distance between the monitoring camera and the background of the monitoring area is measured.

[Fig. 7] An explanatory diagram showing a mesh model.

FIG. 8 is an explanatory diagram showing a monitoring image data.

Fig. 9 is an explanatory diagram showing a mesh model according to another embodiment.

FIG. 10 is an explanatory diagram showing a schematic configuration of a monitoring system according to another embodiment.

FIG. 11 is an explanatory diagram showing a state in which a person is divided into a plurality of regions.

FIG. 12 is an explanatory diagram showing a schematic configuration of a monitoring system according to another embodiment.

Fig. 13 is a flow chart showing a monitoring method according to another embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present specification and the drawings, constituent elements having substantially the same functional configurations are denoted by the same reference numerals, and the description thereof will not be repeated.

<1. Construction of monitoring system>

1 and 2 show the schematic structure of the monitoring system 1 of the present embodiment. In the present embodiment, the state in which the inside of the store 10 such as a supermarket or a convenience store is monitored by the use monitoring system 1 will be described.

As shown in FIG. 1, the monitoring system 1 has an imaging device 20 fixed to the ceiling of the store 10, and a transmission network (not shown) and a camera. A monitoring device 30 connected to the device 20. The network is not particularly limited as long as it can communicate with the imaging device 20 and the monitoring device 30, and is configured by, for example, an Internet, a wired LAN, or a wireless LAN.

In the imaging device 20, the monitoring area A in the shop 10 is imaged from above, and the distance to the measurement target (the background of the monitoring area A to be described later) of the monitoring area A is measured. The monitoring area A is identical to the imaging area of the imaging device 20. Further, in the monitoring device 30, a three-dimensional mesh model is generated for the background of the monitoring area A, and the mesh model is applied to the background of the monitoring area A imaged by the imaging device 20, and the monitoring area A is monitored. The structure and operation of the imaging device 20 and the monitoring device 30 will be described in detail below.

<2. Structure of camera device>

As shown in FIG. 2, the imaging device 20 has a structure in which a semi-circular cover 22 having a transparent or semi-transparent hemispherical shape is provided in a lower portion of the casing 21. Inside the semicircular cover 22, a distance measuring sensor 23 as a distance measuring unit, a monitoring camera 24 as an imaging unit, and a support member 25 that suspends and supports the monitoring camera 24 are provided. Further, inside the casing 21, a drive mechanism 26 for controlling the swing operation of the monitoring camera 24 via the support member 25 and a communication unit 27 for transmitting the data acquired by the imaging device 20 to the monitoring device 30 are provided. . Furthermore, the shape of the imaging device 20 is not limited to this, and can be arbitrarily designed.

The distance measuring sensor 23 includes a light receiving element 23a that emits, for example, infrared rays, and a light receiving element 23b that receives light reflected from the infrared light. The illumination source 23a is, for example, an LED. The light receiving element 23b is, for example, a PSD, a CMOS or the like. A lens (not shown) for focusing the light is provided on the monitoring area A side of the illumination source 23a and the light receiving element 23b, respectively. Further, a plurality of the illumination source 23a and the light receiving element 23b may be provided separately.

In the distance measuring sensor 23, the infrared ray is irradiated to the measurement target (monitoring area A) from the irradiation source 23a, and the reflected light of the infrared ray reflected by the measurement target is received by the light receiving element 23b, and the measurement target is measured. distance. The method of measuring the distance to the measurement target based on the reflected wave of the infrared ray, for example, the time and phase difference from the irradiation of the infrared ray to the return of the reflected wave, the position on the light receiving element where the reflected wave of the infrared ray is received, and the reflection of the infrared ray The method of calculating the intensity of the wave or the like can be arbitrarily selected by the practitioner from known methods. Then, the distance data measured by the distance measuring sensor 23 is output to the communication unit 27.

The distance measuring sensor 23 is close to the monitoring camera 24 and is fixedly disposed directly below it. Therefore, the distance measured by the distance measuring sensor 23 can be regarded as the distance from the monitoring camera 24 to the measurement target.

In addition, the distance measuring sensor 23 of the present embodiment uses infrared rays for measuring the distance to the measurement target. However, the distance measuring sensor 23 is not limited thereto. For example, ultrasonic waves or lasers can be arbitrarily selected.

The surveillance camera 24 is, for example, any camera such as a CCD camera or a CMOS camera. The surveillance camera 24 is suspended from the support member 25 and supported. Further, the monitoring camera 24 can be rotated in the horizontal direction (the X-axis direction, the Y-axis direction, the left-right direction) and the height direction (the Z-axis direction, the vertical direction) by the drive mechanism 26, and can be zoomed. Composition. The drive mechanism 26 is, for example, a stepping motor or a direct drive motor. Then, the monitoring camera 24 images the monitoring area A through the semicircular cover 22 of the imaging window, and can obtain an image of the monitoring area A. Further, the image data captured by the surveillance camera 24 is output to the communication unit 27.

The communication unit 27 is a communication interface for communication between the medium and the network, and performs data communication with the input unit 31 of the monitoring device 30 to be described later. Specifically, the communication unit 27 outputs the distance data measured by the distance measuring sensor 23 and the image data captured by the monitoring camera 24 to the monitoring device 30.

<3. Construction of monitoring device>

The monitoring device 30 is constituted by, for example, a computer, and is configured by, for example, a central processing unit such as a circuit (hardware) or a CPU, and a program (software) for performing such functions. The monitoring device 30 includes an input unit 31, a model generation unit 32, a monitoring unit 33, an output unit 34, a control unit 35, and a storage unit 36.

The input unit 31 is an interface for communication between the medium and the network, and performs data communication with the communication unit 27 of the imaging device 20. Specifically, the input unit 31 inputs the distance data measured by the distance measuring sensor 23 and the image data captured by the monitoring camera 24.

The model generation unit 32 generates a mesh model of the background of the monitoring area A based on the distance data of the input unit 31. Further, the monitoring unit 33 monitors the monitoring area A based on the image data and the mesh model. The specific operations of the model generating unit 32 and the monitoring unit 33 will be described later.

The output unit 34 outputs the monitoring result of the monitoring unit 33. The method of outputting the monitoring result is not particularly limited. For example, it may be displayed on a display, or an alarm may be issued when an abnormal state or a dangerous situation occurs, and an arbitrary method may be selected.

The control unit 35 controls each operation of the imaging device 20. That is, the control unit 35 controls, for example, the timing and position at which the distance measuring sensor 23 measures the distance, and controls the timing and position of the imaging of the monitoring camera 24.

The memory unit 36 stores a program for monitoring the monitoring area A by the monitoring system 1. Furthermore, the program may be stored in the memory unit 36 as such, or may be stored in a computer-readable hard disk (HD), a flexible disk (FD), a compact disk (CD), a magneto-optical disk (MO), and various memories. A computer-readable memory medium such as a body can also be used. Further, the program may be downloaded from a communication network such as the Internet or stored in the aforementioned memory medium.

<4. Action of monitoring system>

Next, a monitoring method of the monitoring area A by the monitoring system 1 configured as described above will be described. Figure 3 is a flow chart showing an example of the main engineering of the related monitoring method.

Hereinafter, the situation of monitoring the inside of the shop 10 shown in FIG. 4 will be described as an example. Here, in the monitoring area A in the store 10, the person who does not move during the monitoring period is defined as the background of the monitoring area A. In the present embodiment, the floor surface 11 of the store 10 and the plurality of objects 12 standing as permanent objects in the store 10 constitute the background of the monitoring area A. Furthermore, the device 12 is intentionally moved due to a layout change or the like in the store 10. The situation is not the monitoring period during the move. At this time, it is assumed that the monitoring period is started after the new position setting device 12 is set. Therefore, in the present embodiment, the object 12 is regarded as a permanent object.

First, the distance between the monitoring camera 24 and the background of the monitoring area A is measured using the distance measuring sensor 23 of the imaging device 20 (step S1 of FIG. 3). Specifically, as shown in FIG. 5 and FIG. 6 , the distance measurement (the broken line in FIG. 5 ) is started immediately below the imaging device 20 , and the measurement direction is rotated from the imaging sensor 23 to the measurement direction from the imaging device 20 . The bottom side is moved to the outside to measure the distance (the solid line portion in Fig. 5). Then, the distance between the monitoring camera 24 and the background of the monitoring area A is measured over the entire area of the monitoring area A. The distance data measured by the distance measuring sensor 23 is output to the model generating unit 32 of the monitoring device 30 via the communication unit 27 and the input unit 31.

In the model generation unit 32, a mesh model of the background of the monitoring area A is generated based on the distance data measured by the distance measuring sensor 23 (step S2 of FIG. 3). Specifically, as shown in FIG. 5, the mesh M is stacked from directly below the imaging device 20 toward the outside. The size of the mesh M is arbitrarily set, for example, set to 50 cm × 50 cm. The position of the horizontal direction (X-axis direction and Y-axis direction) of each mesh M can be calculated by the number of stacked meshes M. Further, the position of the height direction (Z-axis direction) of each mesh M can be calculated from the distance data measured by the distance measuring sensor 23.

As described above, when the mesh M having the three-dimensional position information in the horizontal direction and the height direction is stacked, as shown in FIG. 7, a three-dimensional grid reflecting the floor surface 11 and the object 12 is generated for the background of the monitoring area A. Model D. In other words, in step S2, based on the distance data measured by the distance measuring sensor 23, the background of the monitoring area A is three-dimensionally partitioned by the complex mesh M to generate the mesh model D. Further, in FIG. 7, for the sake of easy explanation, the mesh model D of the floor surface 11 between the two objects 12 is illustrated, but the mesh model D is actually generated for all of the background of the monitoring area A. Further, in Fig. 7, hatching is added to the floor surface 11 for the sake of easy understanding.

Steps S1 to S2 up to this point are used to monitor the preparation of the monitoring area A, and the actual monitoring is started from there. That is, the monitoring area A of the imaging device 20 is used to image the monitoring area A (step S3 of FIG. 3). The image data captured by the monitoring camera 24 is output to the monitoring unit 33 of the monitoring device 30 via the communication unit 27 and the input unit 31.

The monitoring unit 33 analyzes the image data, and extracts the person in the monitoring area A by, for example, the background difference. This background difference technique is a technique for obtaining a dynamic monitoring target by taking the difference between the image data acquired by the monitoring camera 24 and the background image of the monitoring area A acquired in advance. In the present embodiment, the monitoring of the store 10 is performed. Therefore, the object to be monitored is described as a person. However, the object to be monitored is not limited thereto.

On the other hand, in the monitoring unit 33, the mesh model D generated by the model generating unit 32 is applied to the background of the monitoring area A in the image data. That is, as shown in FIG. 8, the character P is synthesized in the mesh model D, and new monitoring image data is generated. Then, the monitoring area A is monitored based on the monitoring image data (step S4 of FIG. 3). Furthermore, the monitoring node of the monitoring unit 33 The result is output to the output unit 34.

Here, the advantages of using the monitoring image data in this manner will be described. For example, as shown in FIG. 8, in the monitoring image data, it is assumed that the characters P1 and P2 of two people having different sizes are displayed in the monitoring area A. Hereinafter, the side close to the monitoring camera 24 (the Y-axis negative direction side) is referred to as "front side", and the side away from the monitoring camera 24 (the Y-axis positive direction side) is referred to as "deep side". If it is the previous portrait material, the computer cannot judge whether the two people are different in height, or one person's character P1 is in front and the other person's character is on the deep side, so it looks different in size.

On the other hand, in the monitoring image data of the present embodiment, each mesh M of the mesh model D has three-dimensional information. In this way, it is possible to grasp which grid M of the persons P1 and P2 is located on the floor surface 11 by recognizing the feet of the persons P1 and P2, for example. Then, since it is known that the lengths of the persons P1 and P2 on the image data are monitored in the height direction, the heights (heights) of the persons P1 and P2 can be calculated. In other words, by grasping which grid M the characters P1 and P2 are respectively located, the actual heights of the characters P1 and P2 can be grasped. In this way, the characters P1 and P2 can be grasped three-dimensionally based on the monitoring image data. Further, even if the monitoring target is not a person, the shape of the monitoring target can be grasped three-dimensionally.

In addition, when the characters P1 and P2 are grasped three-dimensionally in this way, for example, even if the motion of the person P1 in front of the image data is large, it is understood that there is not such a large operation. On the other hand, even if the movement of the person P2 located on the deep side is small, it is understood that a large operation is actually performed. Therefore, the actions of the characters P1 and P2 can be correctly grasped. Again, for example Even if the characters P1 and P2 overlap in the monitoring image data, it can be recognized that the characters P1 and P2 do not actually collide.

Further, when the mesh model D of the background of the monitoring area A is generated in steps S1 to S2, the monitoring area A can be monitored by repeating steps S3 to S4. In other words, in the method described in Patent Document 1, when the persons P1 and P2 are monitored, it is necessary to constantly measure the distances of the persons P1 and P2. In the present embodiment, it is not necessary to measure the distances to the persons P1 and P2. Therefore, the processing performed during monitoring is very simple, and the processing of the data is small, so that the burden on the computer can be greatly reduced.

Further, even if the layout of the store 10 is changed, or the arrangement of the imaging device 20 is changed, and the background of the monitoring area A imaged by the imaging device 20 is changed, the mesh model D can be automatically generated by performing steps S1 to S2. Therefore, the monitoring system 1 can flexibly respond to changes in the background of such a monitoring area A.

As described above, according to the present embodiment, the monitoring area A can be appropriately and easily monitored.

<5. Other Embodiments>

Next, other embodiments of the present invention will be described. In the following description, the description of the points overlapping with the above embodiment will be omitted.

<5-1. Other Embodiments>

When the mesh model D is generated in step S2 of the above embodiment, the mesh model D composed of the complex mesh M is superimposed in advance to monitor the image. The image data of the background of the monitoring area A of the camera 24 may be used. Then, the mesh model D is composed of the complex mesh M and the image data of the background of the monitoring area A. In the relevant situation, in step S4, the monitoring area A can be more appropriately monitored.

<5-2. Other Embodiments>

In the above embodiment, the storage unit 36 of the monitoring device 30 may store a database storing information of objects in the monitoring area A. The object in the monitoring area A is intended to be an object that should exist in the monitoring area A. In the present embodiment, when the store 10 is monitored, information such as a representative product cabinet, a table, a chair, and the like, which are related objects, is stored in the database. Further, in addition to the above-described device 12, information such as representative products and carts are also stored in the database.

In the related situation, when the monitoring area A is monitored in step S4, the shape of the object in the monitoring area A can be grasped by using the mesh model D. Therefore, by referring to the information of the above-mentioned database, it is possible to specify what the object is. In this way, even the specific actions of the character P can be mastered. For example, if the character P wants to enter the forbidden entry area, it can be grasped, and the character P can grasp it if he wants to steal a certain product from a commodity cabinet. As described above, according to the present embodiment, the dynamics of the monitoring target can be specifically grasped, and the monitoring area A can be more appropriately monitored.

<5-3. Other Embodiments>

When the mesh model D is generated in step S2 of the above embodiment, as shown in FIG. 9, the floor surface 11 and the object 12 of the monitoring area A are surrounded. The space (hereinafter referred to as the monitoring space) may be divided into three dimensions by a plurality of grids N division. The mesh N formed in the monitoring space has the same size as the mesh M of the floor surface 11 and the object 12. Then, the mesh N of the monitoring space is three-dimensionally formed so as to fill the space between the floor surface 11 and the mesh M of the object 12. Further, in Fig. 9, the mesh M of the floor surface 11 and the object 12 is shown by a broken line for the sake of easy understanding.

In the related situation, the mesh N of the monitoring space has three-dimensional position information in the horizontal direction and the height direction, similarly to the floor surface 11 and the mesh M of the object 12. Therefore, when the monitoring area A is monitored in step S4, the person P can be grasped more accurately and easily in three dimensions.

<5-4. Other Embodiments>

In the above embodiment, as shown in FIG. 10, the monitoring device 30 may further include a person setting unit 40 that divides the person P entering the monitoring area A into a plurality of areas. As shown in FIG. 11, the person setting unit 40 divides the person P into a plurality of areas 50 to 52 in the height direction. The upper region 50 is formed at the position of the head of the person P, the intermediate region 51 is formed at the position of the body of the person P, and the lower region 52 is formed at the position of the foot of the person P. Specifically, the person setting unit 40 first recognizes the foot of the person P and recognizes the height of the person P from the mesh model D. In this way, the approximate position of the head and body of the character P can be grasped.

In the related situation, when the monitoring area A is monitored in step S4, the person P is monitored based on the rate of change of the person P in each of the areas 50 to 52. In this way, for example, when the rate of change of the upper region 50 is large, the person P is known. We perform action such as shaking the head to the left and right and peeing around the look of the surroundings. Further, for example, when the rate of change of the intermediate portion 51 is large, it is understood that the person P is performing an operation of moving the body in the lateral direction and being restless. Further, for example, when the rate of change of the lower region 52 is large, it is understood that the person P is performing an operation such as squatting. In this way, when the monitoring area A is monitored, the specific operation of the person P can be grasped.

<5-5. Other Embodiments>

In the above embodiment, as shown in FIG. 12, the imaging device 20 further has a sound collector 60 that collects sound generated in the monitoring area A, and the monitoring device 30 further has a sound collection by the sound collector 60. The sound detecting unit 61 of the sound may be used. The sound collector 60 is a microphone, and has a plurality of, for example, three inside the semicircular cover 22.

Figure 13 is a flow chart showing an example of a main project using a sound detection monitoring method. Steps S1 to S4 in Fig. 13 are the same as the steps S1 to S4 shown in Fig. 3 of the above embodiment.

Then, in parallel with the generation of the mesh model D in steps S1 to S2, the specific sound to be detected in the monitoring area A is collected and stored in the memory unit 36 of the monitoring device 30 (step T1 of FIG. 13). The specific sound is a sound that occurs when an abnormal state or a dangerous situation occurs in the monitoring area A, such as the sound of the character P and the sound of the broken thing.

These steps S1 to S2 and T1 are used to monitor the preparation of the monitoring area A in advance. Then, during the monitoring, for example, the sound data collected by the sound collector 60 is transmitted to the sound detector through the communication unit 27 and the input unit 31. Measuring unit 61. In the sound detecting unit 61, when the sound data is matched with the specific sound stored in the memory unit 36, it is detected that a specific sound is generated in the monitoring area A (step T2 in Fig. 13).

The information that the specific sound is detected by the sound detecting unit 61 is output to the monitoring unit 33. The monitoring unit 33 sets the imaging direction of the monitoring camera 24 in the direction of the specific sound detected by the sound detecting unit 61, and moves the monitoring camera 24 through the control unit 35. Then, in step S3, the surveillance camera 24 is used to image an area in the monitoring area A where a specific sound occurs. Thereafter, in step S4, the area where the specific sound is generated is monitored.

In the related situation, when an abnormal state or a dangerous situation occurs in the monitoring area A, the sound can be specified, and attention is paid to the area where the sound is generated and monitored. Further, even in the case where the sound is moved, the direction in which the monitoring camera 24 follows the sound can be used, and the area where the sound is generated can be appropriately monitored.

<5-6. Other Embodiments>

In the above embodiment, the plurality of imaging devices 20 may be provided in the store 10. In the related situation, the monitoring of the complex monitoring area A can be used to monitor the entire interior of the store 10. Further, when the plurality of imaging devices 20 monitor one monitoring area A, the monitoring area A can be monitored with higher precision.

Further, in the above embodiment, the situation in which the monitoring system 1 is used to monitor the store 10 has been described. However, the location of the monitoring is not limited thereto. The monitoring system 1 of the present invention can monitor, for example, shopping Centers, department stores, complex facilities, and commercial facilities for commercial activities such as exhibitions and fairs, public facilities such as airports and railways, and amusement facilities such as amusement parks and stadiums, hospitals and care facilities, Offices and factories, single-family buildings, condominiums, parking lots, etc., various places.

Although the preferred embodiments of the present invention have been described above with reference to the drawings, the present invention is not limited to the related examples. It is obvious that as long as it is a practitioner, various modifications and corrections are conceivable within the scope of the invention described in the scope of the patent application, and the examples are of course also within the technical scope of the present invention.

[Industry use possibility]

The present invention is useful for monitoring, for example, a predetermined area.

1‧‧‧Monitoring system

20‧‧‧ camera

21‧‧‧ frame

22‧‧‧Semicircular cover

23‧‧‧Ranging sensor

23a‧‧‧Environment source

23b‧‧‧Light-receiving components

24‧‧‧ surveillance cameras

25‧‧‧Support components

26‧‧‧Drive mechanism

27‧‧‧Communication Department

30‧‧‧Monitor

31‧‧‧ Input Department

32‧‧‧Model Generation Department

33‧‧‧Monitor

34‧‧‧Output Department

35‧‧‧Control Department

36‧‧‧Memory Department

Claims (13)

A monitoring system is a monitoring system for monitoring a predetermined area, characterized in that the imaging unit is fixedly disposed at a predetermined position, and images the predetermined area from above; and the distance measuring unit measures the imaging unit from the predetermined area. a distance to the measurement target; the model generation unit is configured to determine the background of the predetermined region formed by the permanent object standing in the monitoring period in the predetermined region from the bottom surface of the predetermined region, and based on the distance measuring portion a distance from the imaging unit to the background, the background is divided in a horizontal direction and a height direction by a grid of a predetermined size, and a mesh model of the background is generated; and the monitoring unit is based on image data captured by the imaging unit. The dynamic monitoring target is extracted, and the mesh model is applied to the background of the predetermined region of the image data, and new monitoring image data for synthesizing the monitoring target to the mesh model is generated, and the predetermined region is monitored. The monitoring system according to the first aspect of the invention, wherein the model generating unit is configured to superimpose the image of the background of the image data captured by the imaging unit in the mesh model of the monitoring image data. The monitoring system described in claim 1 of the patent application, further comprising: a database for storing objects in the predetermined area The monitoring unit identifies the object according to the database and monitors the predetermined area. The monitoring system according to claim 1, wherein the model generating unit is configured to surround the bottom surface of the predetermined area and the standing object in a three-dimensional region by the mesh of the predetermined size. Space. The monitoring system according to the first aspect of the invention, further comprising: a person setting unit that divides a person who enters the predetermined area into a plurality of areas; and the monitoring unit is configured according to each of the person setting units The rate of change of the aforementioned characters in the area monitors the action of the character. The monitoring system according to claim 1, further comprising: a sound detecting unit that detects a sound generated in the predetermined area; and the monitoring unit detects the sound detecting unit In the direction of the sound, the imaging direction of the imaging unit is set, and the area where the sound is generated is monitored. A monitoring method is a monitoring method in which an imaging unit captures and monitors a predetermined area, and is characterized in that: a distance measuring project is performed on a bottom surface of the predetermined region, The background of the predetermined area formed by the standing object standing in the monitoring period in the predetermined area, and the distance from the imaging unit to the background is measured by the distance measuring unit; the model generation engineering is determined according to the distance measurement project The distance is defined by a grid of a predetermined size, the background is divided in the horizontal direction and the height direction, and a mesh model of the background is generated; the camera engineering is to image the predetermined area by the camera unit; and the monitoring project is based on The image data captured in the image capturing project extracts a dynamic monitoring target, and applies the mesh model to the background of the predetermined region of the image data, thereby generating a new monitoring that combines the monitoring target into the mesh model. Image data, monitor the aforementioned area. The monitoring method according to claim 7, wherein in the model generation project, an image of the background of the image data captured by the imaging unit is superimposed on the mesh model of the monitoring image data. The monitoring method according to claim 7, wherein the information of the object in the predetermined area is stored in a database; and in the monitoring project, the object is specified based on the database, and the predetermined area is monitored. . The monitoring method described in claim 7 of the patent application, In the above-described model generation project, in the mesh model, the bottom surface of the predetermined area and the space surrounded by the standing object are three-dimensionally divided by the mesh of the predetermined size. The monitoring method according to claim 7, wherein in the monitoring project, the person entering the predetermined area is divided into a plurality of areas, and the person is monitored according to the rate of change of the person in each of the divided areas. action. The monitoring method according to claim 7, wherein in the imaging project, when the sound generated in the predetermined region is detected by the sound detecting unit, the imaging unit is set in the direction of the sound. The imaging direction is used to image the area where the sound is generated. In the above monitoring project, the area where the sound is generated is monitored. A computer memory medium is a readable computer memory medium for storing a program by a monitoring system that executes the monitoring method described in any one of claims 7 to 12, wherein the program is used to make A program that controls the computer of the monitoring system to operate on the computer.