JP5190970B2 - Monitoring camera placement position evaluation device - Google Patents

Description

  The present invention relates to a monitoring camera arrangement position evaluation apparatus that evaluates the arrangement positions of a plurality of monitoring cameras arranged in a monitoring target area.

Conventionally, position analysis using a so-called Voronoi diagram has been performed.
For example, Patent Document 1 below discloses a technique for creating a Voronoi diagram with the placement position of each radar device as a generating point and optimizing the coverage area to be detected by each radar device.

Here, a general Voronoi diagram will be described.
FIG. 16 is a schematic diagram showing an example of a general Voronoi diagram.
A general Voronoi diagram is divided into a plurality of points (mother points) arranged at arbitrary positions in a metric space according to which mother point is close to other points in the same metric space. Is. The example shown in FIG. 16 shows an example in which five generating points 1601 to 1605 are arranged in a certain distance space, and is divided into five Voronoi regions 1611 to 1615 belonging to each generating point. A Voronoi boundary occurs at the boundary of the Voronoi region, and the intersection of the Voronoi boundaries is a Voronoi point.

JP 2007-212299 A

In recent years, the demand for surveillance cameras has increased due to the need to ensure social security.
However, in the surveillance camera arranged in the monitoring target area, a blind spot area that does not appear in the surveillance camera occurs depending on the arrangement location or the like. And it is a very important subject to reduce the blind spot area as much as possible and arrange the monitoring camera in the monitoring target area from the above-described needs for ensuring social security.

  In this regard, in the past, with regard to the arrangement of the monitoring camera, most are based on the subjectivity of the installer who arranges the monitoring camera, evaluation of the arrangement position of the monitoring camera arranged in the monitoring target area, It is difficult to determine the optimum arrangement position.

  Here, as a method of evaluating the arrangement position of the monitoring camera, it is conceivable to perform evaluation using the above-described general Voronoi diagram. This example will be described with reference to FIG.

FIG. 17 is a schematic diagram illustrating an example of a monitoring target region using a general Voronoi diagram as a generating point of the monitoring camera arrangement position.
A plurality of obstacles 1710-1 to 1710-3 and a plurality of monitoring cameras 1720-1 to 1720-3 are arranged in the monitoring target area 1700 shown in FIG. In the method using a general Voronoi diagram, the Voronoi region is set depending on which generating point is close to other points on the same distance space with the arrangement position of each monitoring camera as the generating point. In this example, a Voronoi region 1731 having a monitoring camera 1720-1 as a generating point, a Voronoi region 1732 having a monitoring camera 1720-2 as a generating point, and a Voronoi region 1733 having a monitoring camera 1720-3 as a generating point are monitored. It is formed in the target area 1700.

  However, in the method using the general Voronoi diagram, for example, in the Voronoi region 1732 having the monitoring camera 1720-2 as a generating point, the blind spot region of the obstacle 1710-1 viewed from the monitoring camera (generating point) 1720-2. Since the region belongs to the monitoring camera (base point) 1720-2, there is a problem that it is difficult to appropriately evaluate the arrangement position of the monitoring camera.

  The present invention has been made in view of such problems, and provides a monitoring camera arrangement position evaluation apparatus that can appropriately evaluate the arrangement positions of a plurality of monitoring cameras arranged in a monitoring target area where an obstacle exists. The purpose is to provide.

  The monitoring camera arrangement position evaluation apparatus of the present invention is a monitoring camera arrangement position evaluation apparatus that evaluates the arrangement positions of a plurality of monitoring cameras arranged in a monitoring target area where an obstacle exists, and the arrangement position information of the obstacle Information acquisition means for acquiring monitoring target area information relating to the monitoring target area including information and monitoring camera information relating to the plurality of monitoring cameras including arrangement position information of the plurality of monitoring cameras, the monitoring target area information, and Using the monitoring camera information, for each area of the monitoring target area, the Voronoi area related to each generating point is expanded for each area of the monitoring target area with each monitoring camera's arrangement position in the plurality of monitoring cameras as each generating point. Using the non-diffracting Voronoi diagram creating means for creating a non-diffracting Voronoi diagram for non-diffracting the blind spot area of the obstacle viewed from the above, and using the non-diffracting Voronoi diagram, And a evaluation means for evaluating process in the deployed position of said plurality of surveillance cameras in the object area viewed.

  ADVANTAGE OF THE INVENTION According to this invention, the evaluation of the arrangement position in the some monitoring camera arrange | positioned in the monitoring object area | region where an obstruction exists can be performed appropriately.

It is a block diagram which shows an example of the hardware constitutions of the surveillance camera arrangement position evaluation apparatus which concerns on embodiment of this invention. It is a block diagram which shows an example of a function structure of the surveillance camera arrangement position evaluation apparatus which concerns on embodiment of this invention. It is a flowchart which shows an example of the process sequence of the monitoring camera arrangement position evaluation method by the monitoring camera arrangement position evaluation apparatus which concerns on embodiment of this invention. It is a flowchart which shows an example of the detailed process sequence of the preparation process of the non-diffraction Voronoi diagram in step S305 of FIGS. It is a schematic diagram which shows an example of the image of the information acquired by the information acquisition means of FIG. 2 in step S301 shown in FIG. It is a schematic diagram which shows an example of the image of the discrete space group ensured on the memory in step S303 and S304 shown to FIGS. It is a schematic diagram which shows an example of the creation method of the non-diffraction Voronoi diagram created in step S323 shown in FIG. 3-2. It is a schematic diagram which shows another example of the non-diffraction Voronoi diagram produced in step S323 shown to FIGS. 3-2. It is a schematic diagram which shows another example of the non-diffraction Voronoi diagram produced in step S323 shown to FIGS. 3-2. It is a schematic diagram which shows an example of the production method of the 1st non-diffracting Voronoi diagram produced in step S324 shown in FIG. 3-2. It is a schematic diagram which shows an example of the production method of the 2nd non-diffracting Voronoi diagram produced in step S324 shown in FIG. 3-2. FIG. 9 is a schematic diagram illustrating an example of a method for creating the second-order non-diffracting Voronoi diagram created in step S324 illustrated in FIG. FIG. 6 is a schematic diagram when a first-order non-diffracting Voronoi diagram is created for the monitoring target region 400 shown in FIG. 4 in step S324 of FIG. 3-2. FIG. 3C is a schematic diagram when a non-diffractive Voronoi diagram of 1st to 3rd (kth) positions is created for another monitoring target region 1100 in step S324 of FIG. 3-2. It is a schematic diagram which shows an example of the threshold value table used in the judgment process of step S308 shown in FIG. It is a schematic diagram which shows the embodiment of this invention and shows the example of a display of the image which shows the optimal arrangement position of the surveillance camera displayed on the display part of FIG. It is a schematic diagram which shows the modification 1 in embodiment of this invention, and shows an example of the process image at the time of preparation of the non-diffraction Voronoi diagram which makes the surveillance camera which has a predetermined angle of view a generating point. FIG. 10 is a schematic diagram illustrating a first non-diffracting Voronoi diagram created in step S305 illustrated in FIG. 3A according to the first modification of the embodiment of the present invention. It is a schematic diagram which shows an example of a general Voronoi diagram. It is a schematic diagram which shows an example of the monitoring object area | region which made the arrangement | positioning position of the surveillance camera the generating point using a general Voronoi diagram.

  Hereinafter, embodiments (embodiments) for carrying out the present invention will be described with reference to the drawings.

  FIG. 1 is a block diagram showing an example of a hardware configuration of a monitoring camera arrangement position evaluation apparatus 100 according to an embodiment of the present invention.

  1 has a hardware configuration including a CPU 101, a RAM 102, a ROM 103, an external memory 104, an input device 105, a display unit 106, a communication interface (communication I / F) 107, and a bus 108. Configured.

  The CPU 101 controls the entire surveillance camera arrangement position evaluation apparatus 100 using, for example, programs and data stored in the ROM 103 or the external memory 104.

  The RAM 102 includes SDRAM, DRAM, and the like, and includes an area for temporarily storing programs and data loaded from the ROM 103 or the external memory 104 and a work area necessary for the CPU 101 to perform various processes. .

  The ROM 103 stores information such as programs that do not need to be changed and various parameters.

  The external memory 104 stores, for example, an operating system (OS), a program executed by the CPU 101, information known in the description of the present embodiment, and the like. In the present embodiment, the program for executing the processing of the flowchart shown in FIG. 3 to be described later is stored in the external memory 104. However, for example, the program stored in the ROM 103 is also applicable. Is possible.

  The input device 105 includes, for example, a mouse, a keyboard, and the like. For example, the input device 105 is operated when the user gives various instructions to the monitoring camera arrangement position evaluation apparatus 100, and inputs the instructions to the CPU 101 or the like. To do.

  The display unit 106 includes, for example, a monitor and outputs various data and various information to the monitor based on the control of the CPU 101.

  The communication I / F 107 controls transmission / reception of various data and various information performed between the monitoring camera arrangement position evaluation apparatus 100 and the external apparatus G.

  The bus 108 connects the CPU 101, the RAM 102, the ROM 103, the external memory 104, the input device 105, the display unit 106, and the communication I / F 107 so that they can communicate with each other.

  FIG. 2 is a block diagram illustrating an example of a functional configuration of the monitoring camera arrangement position evaluation apparatus 100 according to the embodiment of the present invention. Here, in FIG. 2, the same reference numerals as those in FIG. 1 are assigned to the functional configurations similar to those shown in FIG.

  The monitoring camera arrangement position evaluation apparatus 100 in FIG. 2 has functional configurations of an information acquisition unit 201, a non-diffracting Voronoi diagram generation unit 202, a selection unit 203, an evaluation unit 204, an arrangement position determination unit 205, and a display unit 106. Configured.

  In the present embodiment, for example, the information acquisition unit 201 shown in FIG. 2 is configured from the CPU 101 and the program stored in the external memory 104, the RAM 102, and the communication I / F 107 shown in FIG. Further, for example, from the CPU 101 and the external memory 104 shown in FIG. 1 and the RAM 102, the non-diffractive Voronoi diagram creation means 202, the evaluation means 204, and the arrangement position determination means 205 shown in FIG. It is configured. Also, for example, the selection unit 203 shown in FIG. 2 is configured from the CPU 101 and the program stored in the external memory 104 shown in FIG. 1 and the input device 105.

  2 will be described together with the flowcharts of FIGS. 3A and 3B to be described later.

  Next, the processing procedure of the monitoring camera arrangement position evaluation method by the monitoring camera arrangement position evaluation apparatus 100 according to the embodiment of the present invention will be described.

FIG. 3A is a flowchart illustrating an example of a processing procedure of the monitoring camera arrangement position evaluation method by the monitoring camera arrangement position evaluation apparatus 100 according to the embodiment of the present invention.
Through the processing of the flowchart illustrated in FIG. 3A, the monitoring camera arrangement position evaluation apparatus 100 evaluates the arrangement positions of a plurality of monitoring cameras arranged in a monitoring target area where an obstacle exists. Hereinafter, the flowchart of FIG. 3A will be described with reference to FIG.

  First, in step S301 in FIG. 3A, the information acquisition unit 201 in FIG. 2 receives, from the external device G, monitoring target area information related to the monitoring target area including obstacle arrangement position information, and arrangement of a plurality of monitoring cameras. A process of acquiring surveillance camera information related to a plurality of surveillance cameras including position information is performed. Here, the information acquired in step S301 will be described with reference to FIG.

FIG. 4 is a schematic diagram illustrating an example of an image of information acquired by the information acquisition unit 201 of FIG. 2 in step S301 illustrated in FIG.
In the example illustrated in FIG. 4, the information acquisition unit 201 includes monitoring target area information regarding the monitoring target area 400 including the arrangement position information of the obstacles 410-1 and 410-2 and a plurality of monitoring cameras 420-1 and 420-. Monitoring camera information including the arrangement position information of 2 is acquired.

  Here, the information acquisition unit 201 acquires, for example, coordinate information of the monitoring target area 400, coordinate information related to the arrangement positions of the obstacles 410-1 and 410-2, and the like as the monitoring target area information. Also, the information acquisition unit 201 acquires, for example, coordinate information related to the arrangement positions of the monitoring cameras 420-1 and 420-2, information related to the shooting direction, information related to the angle of view of shooting, and the like as the monitoring camera information. To do.

  As the coordinate information, not only two-dimensional coordinates but also three-dimensional coordinates can be applied. In the following description of the present embodiment, two-dimensional coordinates are used for the sake of simplicity. The case will be described. Further, various shooting directions and various shooting angles of view can be applied to the shooting direction and the shooting angle of view of the surveillance camera. However, in the following description of the present embodiment, the description will be simplified. Therefore, the case where the camera is an omnidirectional camera in which the shooting direction is omnidirectional and the shooting field angle is 360 ° will be described.

  Further, in the above-described example, the aspect in which the information acquisition unit 201 directly acquires the monitoring target area information and the monitoring camera information to be processed from the external device G has been described. However, the present embodiment is limited to this aspect. It is not something. For example, the information acquisition unit 201 acquires an image related to the monitoring target area 400 including the obstacle and the monitoring camera from the external device G, analyzes the image, and acquires the monitoring target area information and the monitoring camera information. Alternatively, the monitoring target area information and the monitoring camera information are acquired by displaying the image on the display unit 106 and detecting the monitoring target area 400, the obstacle, and the monitoring camera designated by the user via the input device 105. The aspect to apply is also applicable.

  Here, it returns to description of FIG.2 and FIG.3-1 again.

  When the process in step S301 in FIG. 3A is completed, for example, in step S302 in FIG. 3A, for example, the information acquisition unit 201 sets 1 to a variable A indicating the number of processes. Thereby, 1 is set to the processing count A.

  Subsequently, in step S303 of FIG. 3-1, for example, the non-diffracting Voronoi diagram creation unit 202 (or information acquisition unit 201) of FIG. 2 monitors the monitoring target area information acquired in step S301 and the monitoring acquired in step S301. Based on the camera information (or the monitoring camera information updated in step S309 based on the monitoring camera information acquired in step S301), the monitoring target area, the obstacle, and the monitoring camera are discretely secured on the memory (for example, the RAM 102). Processing to arrange in the space P (1) is performed.

  Subsequently, in step S304 of FIG. 3-1, for example, the non-diffracting Voronoi diagram creation means 202 (or information acquisition means 201) of FIG. 2 uses the discrete space P (1) obtained in step S303 as the total number of surveillance cameras. (In this example, the total number is assumed to be “k”). The process is performed by duplicating the number obtained by subtracting 1 and securing the discrete spaces P (2) to P (k) on the memory (for example, the RAM 102). Through the processing in steps S303 and S304, k discrete spaces P (1) to P (k) are secured on the memory.

  Here, the discrete space group secured in steps S303 and S304 will be described with reference to FIG.

FIG. 5 is a schematic diagram showing an example of an image of the discrete space group secured on the memory in steps S303 and S304 shown in FIG.
In FIG. 5, a discrete space P (1) indicates the discrete space secured in step S303 in FIG. 3-1, and the discrete spaces P (2) to P (k) are in step S304 in FIG. Shows a discrete space secured by duplicating the discrete space P (1) by the number obtained by subtracting 1 from the total number k of surveillance cameras.

  Here, it returns to description of FIG.2 and FIG.3-1 again.

  When the process of step S304 in FIG. 3A is completed, then, in step S305 in FIG. 3A, the non-diffracting Voronoi diagram creating unit 202 in FIG. 2 performs each discrete space (steps in step S303 and S304). Using the monitoring target area information acquired in step S301 and the monitoring camera information acquired in step S301 (or the monitoring camera information updated in step S3309 based on the monitoring camera information acquired in step S301), And each discrete space in which surveillance cameras are arranged) for each region of the monitored area with each surveillance camera's placement position as each mother point, and expanding the Voronoi region related to each mother point and seeing from each mother point Create a non-diffracting Voronoi diagram that makes the blind spot area of the object non-diffracting. Here, “non-diffraction” in the present embodiment refers to a phenomenon that does not go around the geometric shadow (dead angle) of an obstacle.

  Specifically, in step S305, the non-diffracting Voronoi diagram creation unit 202 in FIG. 2 sets k as the total number of each monitoring camera (each generating point) arranged in the monitoring target region, and targets the generating point of k. When the non-diffracting Voronoi diagram in which the Voronoi region of the maximum order k is expanded and the blind spot region of the obstacle viewed from each generating point at the generating point of the k is non-diffracting is used as the non-diffracting Voronoi diagram of the k-th order, 1 Create a non-diffractive Voronoi diagram from position to k. Here, when an integer i (1 ≦ i ≦ k) is assumed, the i-th non-diffracting Voronoi diagram is a non-diffracting i-order Voronoi diagram divided by a set of points that are simultaneously close to i generating points.

Here, a method of creating the non-diffracting Voronoi diagram created in step S305 will be described with reference to FIG.
FIG. 3B is a flowchart illustrating an example of a detailed processing procedure of the non-diffraction Voronoi diagram creation processing in step S305 in FIG.

  First, in step S321 in FIG. 3-2, the non-diffracting Voronoi diagram creation unit 202 in FIG. 2 stores the monitoring target area and the obstacle on the memory (for example, the RAM 102) based on the monitoring target area information acquired in step S301. The process of ensuring as a discrete space D is performed. Specifically, in step S321, the discrete space D (1) to (d) obtained by replicating the discrete space in which the monitoring target area and the obstacles based on the monitoring target area information acquired in step S301 are arranged for k monitoring cameras. D (k) is secured on the memory.

  Subsequently, in step S322, the non-diffracting Voronoi diagram creating means 202 in FIG. 2 has one surveillance camera (base point) for each of the discrete spaces D (1) to D (k) obtained in step S321. Are assigned and arranged, and each discrete space D is associated with each surveillance camera (each mother point). Specifically, the total number k of surveillance cameras (base points) are assigned serial numbers from 1 to k, and in step S322, the i-th (i is an integer between 1 and k) surveillance cameras ( A process of arranging the mother point) in association with the discrete space D (i) is performed.

  Subsequently, in step S323, the non-diffracting Voronoi diagram creating means 202 in FIG. 2 sets the position of each monitoring camera to each mother space with respect to the discrete spaces D (1) to D (k) obtained in step S322. For each area of the monitored area, a non-diffractive Voronoi diagram is created in which the Voronoi area is expanded from each mother point and the blind spot area of the obstacle viewed from each mother point is non-diffracted. Hereinafter, a method for creating the non-diffractive Voronoi diagram created in step S323 will be described with reference to FIG.

FIG. 6 is a schematic diagram illustrating an example of a method for creating a non-diffracting Voronoi diagram created in step S323 shown in FIG. 3-2.
Here, FIG. 6 shows the monitoring target region 600 arranged in one of the discrete spaces D (1) to D (k) obtained in step S322, and the monitoring target region. An obstacle 610 and a mother point (monitoring camera) 620 are shown. In the example shown in FIG. 6, a monitoring target area 600 different from the monitoring target area 400 shown in FIG. 4 is shown. FIG. 6 shows an example of a discrete Voronoi diagram, and in FIG. 6, the process proceeds with the monitoring target areas 600-1, 600-2, 600-3, 600-4,. I will go. Further, in FIG. 6, a case where one obstacle 610 is set in the monitoring target area 600 is shown for easy explanation. Further, in each monitoring target area 600 shown in FIG. 6, the white area indicates an unprocessed area.

  First, in the monitoring target region 600-1 in FIG. 6, a region near the mother point 620 where the obstacle 610 does not exist is set as the Voronoi region 631 of the mother point 620. Thereafter, the process of expanding the Voronoi region concentrically around the generating point 620 is sequentially performed.

  Here, consider the region to which the processing target region (discrete point) T1 of the monitoring target region 600-1 belongs. In the present embodiment, when the region to which the processing target region T1 belongs is set, a plurality of discrete points adjacent to the processing target region T1 (in the example illustrated in FIG. 6, It is set in consideration of the region to which the adjacent discrete points below belong.

  Specifically, in the example shown in FIG. 6, since the discrete points adjacent to the left and below the processing target region T1 indicated by arrows are both regions belonging to the Voronoi region 631 of the generating point 620, the processing target region T1 Is set as the Voronoi region 631 of the generating point 620 (Voronoi region 631a of the monitoring target region 600-2 in FIG. 6).

Thereafter, it is assumed that the process of expanding the Voronoi region concentrically around the generating point 620 is sequentially performed and the state of the monitoring target region 600-2 is reached.
Here, consider the region to which the processing target region (discrete point) T2 of the monitoring target region 600-2 belongs. Specifically, in the example shown in FIG. 6, the discrete points indicated by the arrows adjacent to the left of the processing target area T2 are areas belonging to the obstacle 610, and are indicated by the arrows adjacent below the processing target area T2. The discrete points are regions belonging to the Voronoi region 631 of the generating point 620. In this case, in this embodiment, since the region to which the discrete points adjacent to the left and below the processing target region T2 belong is different from the obstacle 610 and the Voronoi region 631, a straight line 641 connecting the processing target region T2 and the mother point 620. A region to which the processing target region (discrete point) T2 belongs is set depending on whether or not the obstacle 610 exists on the straight line 641. In the example shown in FIG. 6, since the obstacle 610 does not exist on the straight line 641, the processing target region T2 is set as the Voronoi region 631 of the generating point 620 (the Voronoi region 631b of the monitoring target region 600-3 in FIG. 6). ). Although different from the example illustrated in FIG. 6, if the obstacle 610 exists on the straight line 641, the processing target area T <b> 2 is set as a blind spot area of the obstacle 610.

Thereafter, it is assumed that the process of expanding the Voronoi region concentrically around the generating point 620 is sequentially performed, and the state of the monitoring target region 600-3 is obtained.
Here, consider the region to which the processing target region (discrete point) T3 of the monitoring target region 600-3 belongs. Specifically, in the example shown in FIG. 6, the discrete points indicated by the arrows adjacent to the left of the processing target region T3 are the regions belonging to the obstacle 610, and are indicated by the arrows adjacent below the processing target region T3. The discrete points are regions belonging to the Voronoi region 631 (631b) of the generating point 620. In this case, in the present embodiment, processing similar to that in the case of the processing target region T2 described above is performed. That is, a straight line 642 connecting the processing target region T3 and the generating point 620 is drawn, and the region to which the processing target region (discrete point) T3 belongs is set depending on whether or not the obstacle 610 exists on the straight line 642. In the example shown in FIG. 6, since the obstacle 610 exists on the straight line 642, the processing target area T3 is set as the blind spot area of the obstacle 610 (the blind spot area 632 of the monitoring target area 600-4 in FIG. 6). .

Thereafter, it is assumed that the process of expanding the Voronoi region concentrically around the generating point 620 is sequentially performed and the state of the monitoring target region 600-4 is reached.
Here, consider the region to which the processing target region (discrete point) T4 of the monitoring target region 600-4 belongs. Specifically, in the example shown in FIG. 6, the discrete points indicated by the arrows adjacent to the left of the processing target area T4 are areas belonging to the obstacle 610, and are indicated by the arrows adjacent below the processing target area T4. The discrete points are the blind spot area 632 of the obstacle 610. In this case, since the Voronoi region 631 of the generating point 620 is not adjacent to the processing target region T4, the processing target region T4 is set as a blind spot region of the obstacle 610, which is not illustrated in FIG. Become.

  Thereafter, a non-diffracting Voronoi diagram in which the blind spot region of the obstacle 610 is non-diffracted is created by sequentially performing the above-described processing on the unprocessed region shown in white of the monitoring target region 600-4.

In the example shown in FIG. 6, for the sake of simplicity, a case where one obstacle 610 is set in the monitoring target area 600 is shown, but this embodiment is limited to this. Instead, for example, as shown in FIGS. 7-1 and 7-2 to be described later, the present invention is also applicable when a plurality of obstacles 610 are set in the monitoring target area.
FIGS. 7-1 and FIGS. 7-2 are schematic diagrams showing another example of the non-diffracting Voronoi diagram created in step S323 shown in FIG. 3-2. In the example illustrated in FIGS. 7A and 7B, a monitoring target area different from the monitoring target area 400 illustrated in FIG. 4 and the monitoring target area 600 illustrated in FIG. 6 is illustrated.

  Here, FIG. 7-1 shows, for example, the monitoring target region 710 arranged in the discrete space D (1) among the discrete spaces D (1) to D (k) obtained in step S322, and the monitoring. The obstacles 611 and 612 and the mother point (monitoring camera) 621 arranged in the target area are shown. A generating point (monitoring camera) 621 represents the first generating point (monitoring camera). When the non-diffracting Voronoi diagram creation processing described in FIG. 6 is performed on the monitoring target region 710-1 illustrated in FIG. 7A, the non-diffracting Voronoi based on the discrete space D (1) illustrated in the monitoring target region 710-2 is performed. A diagram is created. In the monitoring target area 710-2 in FIG. 7A, a Voronoi area 631 at the generating point 621 and a blind spot area 632 of the obstacles 611 and 612 at the generating point 621 are shown. In FIG. 7A, numerical values are described inside each Voronoi region 631, and this represents a square value of the distance from the generating point 621. In the present embodiment, the non-diffracting Voronoi diagram creation means 202 of FIG. 2 is a Voronoi region 631 in addition to information on whether each region of the monitoring target region 710 is the Voronoi region 631 or the blind spot region 632. In FIG. 7A, information related to the square value of the distance from the generating point 621 is stored in a memory (for example, the RAM 102).

  7-2 shows, for example, the monitoring target region 720 arranged in the discrete space D (2) among the discrete spaces D (1) to D (k) obtained in step S322, and the monitoring target. Obstacles 611 and 612 and a mother point (monitoring camera) 622 arranged in the area are shown. A generating point (monitoring camera) 622 indicates a second generating point (monitoring camera). When the non-diffracting Voronoi diagram creation processing described in FIG. 6 is performed on the monitoring target region 720-1 illustrated in FIG. 7B, the non-diffracting Voronoi based on the discrete space D (2) illustrated in the monitoring target region 720-2 is performed. A diagram is created. 7-2, a Voronoi region 631 at the generating point 622 and a blind spot region 632 of the obstacles 611 and 612 at the generating point 622 are shown. Similarly to the case shown in FIG. 7A described above, in this embodiment, the non-diffracting Voronoi diagram creating means 202 in FIG. 2 is the Voronoi region 631 or the blind spot region 632 for each region of the monitoring target region 720. In addition to such information, in the case of the Voronoi region 631, information related to the square value of the distance from the generating point 622 shown in FIG. 7B is stored in a memory (for example, the RAM 102).

  In this way, the non-diffracting Voronoi diagram creating means 202 of FIG. 2 performs non-diffracting based on each discrete space for each discrete space in the discrete spaces D (1) to D (k) obtained in step S322. Create a Voronoi diagram.

  Here, it returns to description of FIG. 3-2 again.

  When the process of step S323 in FIG. 3-2 is completed, then, in step S324 in FIG. 3-2, the non-diffracting Voronoi diagram creating unit 202 in FIG. 2 performs the discrete spaces D (1) to D created in step S323. Using the non-diffracting Voronoi diagram based on (k), the first to k-th non-diffracting Voronoi diagrams based on the discrete spaces P (1) to P (k) are created. Hereinafter, a method for creating the first to k-th non-diffractive Voronoi diagrams created in step S324 will be described with reference to FIG. 8, and FIGS. 9-1 and 9-2.

FIG. 8 is a schematic diagram showing an example of a method for creating the first-order non-diffracting Voronoi diagram created in step S324 shown in FIG. 3-2.
In FIG. 8, a monitoring target area 710-2 is a non-diffractive Voronoi diagram based on the discrete space D (1) shown in FIG. 7-1, and a monitoring target area 720-2 is a discrete pattern shown in FIG. 7-2. It is a non-diffracting Voronoi diagram based on the space D (2). In this example, the non-diffracting Voronoi diagram creating means 202 in FIG. 2 uses the non-diffracting Voronoi diagrams relating to the monitoring target regions 710-2 and 720-2 to perform the first non-diffracting based on the discrete space P (1). Create a Voronoi diagram. Specifically, in this example, the information on the obstacles 611 and 612 is acquired in the monitoring target area information acquired in step S301, and the monitoring camera information acquired in step S301 (or acquired in step S301). In the monitoring camera information updated in step S309 based on the monitoring camera information), an example is shown in which the generating points 621 and 622 are acquired as the arrangement positions of the monitoring cameras (k = 2). This first-order non-diffracting Voronoi diagram is a non-diffracting Voronoi diagram showing the Voronoi region of the nearest generating point.

  Specifically, the monitoring target area 810 is a monitoring target area arranged in the discrete space P (1). Then, the non-diffracting Voronoi diagram creating means 202 in FIG. 2 has the distance from the mother point 621 in the Voronoi region 631 of the mother point 621 in the monitoring target region 710-2 in each region of the monitoring target region 810. A region closer than the distance from the point 622 is set as the Voronoi region 811 of the generating point 621, and the distance from the generating point 622 of the Voronoi region 631 of the generating point 622 in the monitoring target region 720-2 is the mother point. A region closer than the distance from the point 621 is set as the Voronoi region 812 of the generating point 622. At this time, in this example, the distance from each generating point uses the numerical values shown in FIGS. 7-1 and 7-2 stored in the memory. A region where the distance from the generating point 621 is equal to the distance from the generating point 622 is set as the Voronoi region of the generating point having a small serial number (the generating point 621 in this example). In addition, the non-diffracting Voronoi diagram creating means 202 in FIG. 2 includes, in each region of the monitoring target region 810, both of the monitoring target regions 710-2 and 720-2 belong to any generating point. It is set as a blind spot area 813 of no obstacle 611,612.

  By performing the processing shown in FIG. 8, a first-order non-diffracting Voronoi diagram is created for the monitoring target region 810 in the discrete space P (1).

9A and 9B are schematic diagrams illustrating an example of a method for creating the second-order non-diffracting Voronoi diagram created in step S324 illustrated in FIG. 3B.
9A, a monitoring target area 710-2 is a non-diffracting Voronoi diagram based on the discrete space D (1) shown in FIG. 7-1, and a monitoring target area 720-2 is shown in FIG. 7-2. FIG. 3 is a non-diffractive Voronoi diagram based on the discrete space D (2).

  When creating the second-order non-diffracting Voronoi diagram, first, the non-diffracting Voronoi diagram creating means 202 in FIG. 2 newly performs a process of securing the monitoring target area 900 in the memory (for example, the RAM 102). 2 uses the non-diffracting Voronoi diagram in the monitoring target region 710-2 and the non-diffracting Voronoi diagram in the monitoring target region 720-2 as shown in FIG. In addition, an area distribution map indicating the second closest area from the generating point is created in the monitoring target area 900. Specifically, in the region distribution chart shown in FIG. 9A, the region 911 where the generating point 621 is the second closest region, the region 912 where the generating point 622 is the second closest region, the generating points 621 and A region 921 in which one of the mother points 622 is an obstruction blind spot and a region 922 in which both the mother point 621 and the mother point 622 are obstruction blind spots are shown.

Subsequently, the process proceeds to 9-2.
9-2, the monitoring target area 810 is a first-order non-diffracting Voronoi diagram based on the discrete space P (1) shown in FIG. 8, and the monitoring target area 900 is a generating point shown in FIG. FIG. In this example, the non-diffracting Voronoi diagram creating means 202 in FIG. 2 uses the first-order non-diffracting Voronoi diagram in the monitoring target region 810 and the region distribution diagram in the monitoring target region 900 to create the discrete space P (2). Create a second non-diffracting Voronoi diagram based on it. This second-order non-diffracting Voronoi diagram shows a set of points simultaneously close to the two generating points for the two generating points, and the obstacles viewed from each generating point in the two generating points. The blind spot area is not diffracted.

  Specifically, in this example, the non-diffracting Voronoi diagram creating unit 202 in FIG. 2 is a region 2 based on the regions 911 and 912 of the region distribution map in the monitoring target region 900 and targets both the generating points 621 and 622. Is set as the first Voronoi region 821. 2 sets the area based on the areas 921 and 922 of the area distribution diagram in the monitoring target area 900 as the blind spot area 822 of the obstacles 611 and 612.

By performing the processing shown in FIGS. 9A and 9B, a second-order non-diffracting Voronoi diagram is created for the monitoring target region 820 in the discrete space P (2).
In the example illustrated in FIGS. 7-1 to 9-2, the case where the total number of surveillance cameras is 2 has been described. However, when this is generalized, the total number of surveillance cameras (base points) is k. Following the above description, the non-diffracting Voronoi that expands the k-th position Voronoi region for the k generating point and makes the blind spot region of the obstacle viewed from each generating point in the k generating point non-diffracting The figure is a k-th non-diffracting Voronoi diagram, and in this case, the first to k-th non-diffracting Voronoi diagrams are created.

  FIG. 10 is a schematic diagram when a first-order non-diffracting Voronoi diagram is created for the monitoring target region 400 shown in FIG. 4 in step S324 of FIG. 3-2. In FIG. 10, the same components as those in FIG. 4 are denoted by the same reference numerals.

  In the first non-diffracted Voronoi diagram of the monitoring target region 400 shown in FIG. 10, the Voronoi region 431 is a Voronoi region with the monitoring camera 420-1 as a generating point, and the Voronoi region 432 has the monitoring camera 420-2 as a generating point. It is a Voronoi region to be. Further, the blind spot area 433 is a blind spot area of the obstacles 410-1 and 410-2 that does not belong to any generating point.

  FIG. 11 is a schematic diagram when a non-diffractive Voronoi diagram of 1st to 3rd (kth) positions is created for another monitoring target region 1100 in step S324 of FIG. 3-2. In the example shown in FIG. 11, the monitoring target area 400 shown in FIGS. 4 and 10 and the monitoring target area 1100 different from the monitoring target areas shown in FIGS. 7-1 to 9-2 are shown. This shows a case where the total number k of surveillance cameras (base points) is 3.

  In the monitoring target area 1100 shown in FIG. 11, one obstacle 1110 and three monitoring cameras 1120-1 to 1120-3 are arranged.

  Here, Fig.11 (a) makes each arrangement | positioning position of each monitoring camera 1120-1 to 1120-3 be each mother point about each area | region of the monitoring object area | region 1100-1 arrange | positioned in discrete space P (1), It is a first-order non-diffracting Voronoi diagram in which the Voronoi region is expanded from each generating point and the blind spot region of the obstacle 1110 viewed from each generating point is non-diffracting. The first non-diffractive Voronoi diagram shown in FIG. 11A includes a Voronoi region 1131 having a monitoring camera 1120-1 as a generating point, a Voronoi region 1132 having a monitoring camera 1120-2 as a generating point, and a monitoring camera. A Voronoi region 1133 having 1120-3 as a generating point and a blind spot region 1134 of an obstacle 1110 that does not belong to any generating point are formed.

  FIG. 11 (b) expands the second Voronoi region for two generating points and expands the two generating points for each region of the monitoring target region 1100-2 arranged in the discrete space P (2). FIG. 6 is a second non-diffracted high-order Voronoi diagram in which the blind spot area of the obstacle 1110 viewed from each generating point in FIG. That is, the second non-diffracting high-order Voronoi diagram shown in FIG. 11B is a non-diffracting Voronoi diagram showing a set of points that are simultaneously close to two generating points. In the second non-diffracting high-order Voronoi diagram shown in FIG. 11B, the second-order Voronoi region 1141 having two of the monitoring cameras 1120-1 and 1120-2 as a generating point, the monitoring camera 1120-1, and A second-place Voronoi region 1142 centering on two of 1120-3 and a blind spot region 1143 of an obstacle 1110 viewed from each generating point are formed.

  In addition, FIG. 11 (c) expands the third-place Voronoi region for the three generating points for each region of the monitoring target region 1100-3 arranged in the discrete space P (3), and It is a 3rd-order non-diffracting high-order Voronoi diagram in which the blind spot area of the obstacle 1110 viewed from each generating point at the generating point is non-diffracting. That is, the third non-diffracting high-order Voronoi diagram shown in FIG. 11C is a non-diffracting Voronoi diagram showing a set of points that are simultaneously close to the three generating points. The third-order non-diffracted high-order Voronoi diagram shown in FIG. 11C includes a third-order Voronoi region 1151 having three monitoring cameras 1120-1, 1120-2, and 1120-3 as mother points, and each mother A blind spot area 1152 of the obstacle 1110 viewed from the point is formed.

  Here, it returns to description of FIG.2 and FIG.3-1 again.

  When the process of step S305 in FIG. 3A is completed, subsequently, in step S306 of FIG. 3A, the selection unit 203 is created in step S305 in accordance with an input instruction from the user via the input device 105, for example. The non-diffracting Voronoi diagram to be evaluated is selected from the non-diffracting Voronoi diagrams of the 1st to kth positions. As described above, according to the present embodiment, the evaluation target non-diffracting Voronoi diagram for evaluating the arrangement position of the monitoring camera can be selected according to the security level desired by the user.

  Subsequently, in step S307 of FIG. 3-1, the evaluation unit 204 of FIG. 2 uses the evaluation target non-diffracting Voronoi diagram selected in step S306 to arrange the positions of a plurality of monitoring cameras arranged in the monitoring target region. Perform the evaluation process.

  Specifically, the evaluation unit 204 calculates, as an evaluation value, a ratio between the total Voronoi region combined with (totaled) each Voronoi region and the monitoring target region in the non-diffracting Voronoi diagram selected in Step S306. Perform the evaluation process.

More specifically, referring to the example of FIG. 11, consider the case where the first-order non-diffracting Voronoi diagram shown in FIG. 11A is selected as the evaluation target non-diffracting Voronoi diagram in step S306. In this case, a ratio obtained by dividing the area Sb1 of all the Voronoi regions including the Voronoi regions 1131 to 1133 by the area Sk of the monitoring target region 1100 is calculated as an evaluation value H (this evaluation value H is referred to as “H1”). The calculation formula of this evaluation value H1 is shown in the following formula (1).
H1 = Sb1 / Sk (1)

In addition, when the second non-diffracting Voronoi diagram shown in FIG. 11B is selected as the evaluation target non-diffracting Voronoi diagram in step S306, the area Sb2 of all Voronoi regions including the Voronoi regions 1141 and 1142 is calculated. A ratio divided by the area Sk of the monitoring target region 1100 is calculated as an evaluation value H (this evaluation value H is “H2”). The formula for calculating the evaluation value H2 is shown in the following formula (2).
H2 = Sb2 / Sk (2)

In addition, when the first non-diffracting Voronoi diagram shown in FIG. 11C is selected as the evaluation target non-diffracting Voronoi diagram in step S306, the Voronoi region 1151 becomes the entire Voronoi region. The ratio divided by the area Sk of the monitoring target region 1100 is calculated as an evaluation value H (this evaluation value H is set to “H3”). The formula for calculating the evaluation value H3 is shown in the following formula (3).
H3 = Sb3 / Sk (3)

  Then, the evaluation unit 204 performs an evaluation process at the arrangement positions of the plurality of monitoring cameras arranged in the monitoring target area according to the magnitude of the calculated evaluation value H. In this case, as the evaluation value H is larger, that is, as the area of the Voronoi region is larger, it is evaluated that the arrangement positions of the plurality of monitoring cameras arranged in the monitoring target region are better (appropriate). At this time, the evaluation means 204 may perform the evaluation process by classifying, for example, excellent / good / good / impossible according to the magnitude of the evaluation value H.

  Subsequently, in step S308 in FIG. 3A, for example, the arrangement position determining unit 205 in FIG. 2 determines that the evaluation value H obtained in the evaluation process in step S307 is equal to or greater than a predetermined threshold or satisfies the end condition. Determine whether.

  Here, an example of the determination process in step S308 will be described below.

FIG. 12 is a schematic diagram illustrating an example of a threshold table used in the determination process of step S308 illustrated in FIG.
FIG. 12 shows the evaluation target non-diffracting Voronoi diagram selected in step S306 and the threshold value when the evaluation processing is performed using the non-diffracting Voronoi diagram. For example, when the first non-diffracting Voronoi diagram is selected as the evaluation target non-diffracting Voronoi diagram in step S306, the threshold value of the evaluation value H (H1) calculated based on the above-described equation (1) is 0.9. Is selected, and the determination process of step S308 is performed.

  Further, as an end condition in the determination process in step S308, in this example, it is determined whether the current number of processes has reached 100. That is, it is determined whether the current process is A = 100.

  In the present embodiment, the determination process in step S308 is performed as described above.

  As a result of the determination in step S308 in FIG. 3A, if the evaluation value H obtained in the evaluation process in step S307 is not equal to or greater than a predetermined threshold and does not satisfy the end condition (A = 100), step The process proceeds to S309.

  When the process proceeds to step S309 in FIG. 3A, the arrangement position determination unit 207 updates the arrangement positions of the plurality of monitoring cameras based on the evaluation value H obtained in the evaluation process of step S307.

  Specifically, the arrangement position determination unit 207 changes all items of the monitoring camera information (coordinate information about the arrangement position, information about the shooting direction, information about the angle of view of shooting, etc.) acquired in step S301 as variables. In addition, the evaluation value H obtained in the evaluation processing in step S307 is used as the fitness of the surveillance camera system, for example, by using a meta-heuristic technique such as a so-called annealing method or a genetic algorithm. The placement position of the surveillance camera is updated by correcting the placement position. Note that the update of the arrangement position of the monitoring camera is not limited to the update by the correction of the arrangement position of each monitoring camera, but the update of the arrangement position of the monitoring camera including the increase / decrease of the monitoring camera can also be included.

  Subsequently, in step S <b> 310 of FIG. 3A, for example, the information acquisition unit 201 updates the processing count A by adding 1 to the variable A indicating the processing count. When the process in step S310 is completed, the process returns to step S303, and the processes after step S303 are performed again.

  On the other hand, as a result of the determination in step S308 in FIG. 3A, when the evaluation value H obtained in the evaluation process in step S307 is equal to or greater than a predetermined threshold, or when the end condition (A = 100) is satisfied. Advances to step S311.

  When the process proceeds to step S311 in FIG. 3A, the arrangement position determination unit 207 performs a process of determining the optimum arrangement positions of the plurality of monitoring cameras in the monitoring target area based on the result of the evaluation process by the evaluation unit 204. Specifically, the arrangement position determination unit 207 determines the optimum arrangement position of each monitoring camera in the monitoring target area by setting the arrangement position of each monitoring camera set in the determination process of step S308 immediately before the transition to step S311. It is determined as an arrangement position.

  Thereafter, the arrangement position determination unit 207 performs processing for displaying an image indicating the optimum arrangement position of the monitoring camera in the monitoring target area on the display unit 106 based on the determination of the optimum arrangement position of the plurality of monitoring cameras. Thereby, the monitoring camera arrangement position evaluation apparatus 100 can notify the user of the optimum arrangement position of the monitoring camera. An example of displaying an image on the display unit 106 will be described with reference to FIG.

  FIG. 13 is a schematic diagram illustrating a display example of an image showing the optimal arrangement position of the monitoring camera displayed on the display unit 106 of FIG. 2 according to the embodiment of the present invention. Here, in FIG. 13, the same components as those shown in FIG.

  In the image of the monitoring target area 400 shown in FIG. 13, from the viewpoint of the blind spot area of the obstacle 410, the monitoring cameras 420-1 and 420-2 in the arrangement state shown in FIG. This indicates that it is optimal to arrange the position 2. Note that FIG. 13 is merely an example of the optimal placement position of the monitoring camera, and depending on the evaluation result of the evaluation unit 204, the placement is not limited to the placement position shown in FIG. There may also be embodiments.

  As described above, the processing of the monitoring camera arrangement position evaluation method by the monitoring camera arrangement position evaluation apparatus 100 according to the present embodiment is performed through the processing of steps S301 to S311 of FIG.

  Next, a modified example in the present embodiment will be described.

(Modification 1)
First, Modification 1 in the present embodiment will be described.
In the description of the present embodiment described above, for the sake of simplicity, the monitoring camera is described as being an omnidirectional camera with a shooting angle of view of 360 °. It is also possible to apply a surveillance camera having an angle of view. Therefore, as a first modification in the present embodiment, a case where a surveillance camera having a predetermined angle of view (not 360 °) is applied will be described. In the following description of the first modification, only the portions different from the description of the present embodiment described above will be described.

  In the case of the first modification, first, in step S301 in FIG. 3A, as the monitoring camera information, the coordinate information regarding the arrangement positions of the monitoring cameras 420-1 and 420-2, the information regarding the imaging direction, and the captured image are displayed. Get information about corners.

  Further, when creating a non-diffracting Voronoi diagram in step S305 of FIG. 3A, for example, the processing is performed as shown in FIG.

FIG. 14 is a schematic diagram illustrating an example of a processing image when creating a non-diffractive Voronoi diagram having a surveillance camera having a predetermined angle of view as a generating point, in a first modification of the embodiment of the present invention.
As shown in FIG. 14, when a surveillance camera 1420 having a predetermined angle of view θ is used as a base point, an obstacle 1410 is set in a region other than the predetermined angle of view θ to create a non-diffracting Voronoi diagram. As a result, a Voronoi region is set in the monitorable region based on the predetermined angle of view θ, and a blind spot region is set around the obstacle 1410.

  FIG. 15 is a schematic diagram illustrating a first non-diffracting Voronoi diagram created in step S305 illustrated in FIG. 3A according to the first modification of the embodiment of the present invention. In the example shown in FIG. 15, the monitoring target area 400 shown in FIGS. 4 and 10, the monitoring target area shown in FIGS. 7-1 to 9-2, the monitoring target area 1100 shown in FIG. An area 1500 is shown.

  In the monitoring target area 1500 shown in FIG. 15, an example is shown in which obstacles 1510 and monitoring cameras 1520-1 and 1520-2 having a predetermined angle of view (not 360 °) are arranged.

  In the non-diffracting Voronoi diagram of the monitoring target area 1500 shown in FIG. 15, obstacles 1511 and 1512 are set in areas other than the predetermined angle of view θ in the monitoring cameras 1520-1 and 1520-2, respectively. The case where the first-order non-diffracting Voronoi diagram is created is shown. In the first non-diffractive Voronoi diagram of the monitoring target area 1500 shown in FIG. 15, the Voronoi area 1531 having the monitoring camera 1520-1 as a generating point, the Voronoi area 1532 having the monitoring camera 1520-2 as the generating point, A blind spot area 1533 due to an obstacle viewed from each generating point is configured.

  As described above, the first-order non-diffracting Voronoi diagram is generated with the monitoring camera having a predetermined angle of view as a generating point.

  The example shown in FIG. 14 shows the processing for creating the first-order non-diffracting Voronoi diagram, but the creation of the second-order or more non-diffracting Voronoi diagram in step S305 in FIG. As in the case of creating a diffractive Voronoi diagram, an obstacle is set in a region other than the predetermined angle of view θ in the surveillance camera, and a non-diffracted Voronoi diagram of the second or higher position is created.

  By performing the above processing, it is possible to evaluate the arrangement position of the monitoring camera having a predetermined angle of view that is not 360 ° and to determine the optimum arrangement position.

(Modification 2)
Next, a second modification of the present embodiment will be described.
In the above description of the present embodiment, the case where the monitoring target area is two-dimensional has been described in order to simplify the description. However, not only two-dimensional monitoring but also a three-dimensional monitoring target area can be applied. is there. Therefore, as a second modification in the present embodiment, a case where the monitoring target area is three-dimensional will be described. Note that in the following description of the second modification, only portions different from the description of the present embodiment described above will be described.

  In the case of the second modification, first, in step S301 in FIG. 3A, the monitoring target area information and the monitoring camera information related to three dimensions are acquired.

  In steps S303 and S304 in FIG. 3A, the monitoring target area, the obstacle, and the monitoring camera are arranged in the three-dimensional discrete space based on the monitoring target area information and the monitoring camera information related to the three dimensions described above. Perform the process.

  In step S305 of FIG. 3A, each of the three-dimensional discrete spaces obtained in steps S303 and S304 (monitoring target area information obtained in step S301 and monitoring camera information obtained in step S301 (or step S301). The monitoring camera information acquired in step S3309 is used to determine the monitoring camera area, the obstacles, and the discrete spaces in which the monitoring cameras are arranged). A process of creating a 1st to kth non-diffracting Voronoi diagram in which the blind spot area of the obstacle viewed from each generating point is non-diffracting is performed.

  In the above-described embodiment, when the first-order non-diffracting Voronoi diagram is selected as the evaluation target non-diffracting Voronoi diagram in the evaluation process in step S307 of FIG. 3A, the evaluation shown in the expression (1) is performed. Although the value H1 is calculated, in the second modification, for example, the volume Vb1 of all the Voronoi regions including the Voronoi regions in the first non-diffracting Voronoi diagram is divided by the volume Vk of the monitoring target region. The ratio (Vb1 / Vk) is calculated as the evaluation value H1.

Similarly, in the evaluation process in step S307 of FIG. 3-1, when the second-order non-diffracting Voronoi diagram is selected as the evaluation target non-diffracting Voronoi diagram, the evaluation value H2 shown in equation (2) is calculated. However, in the second modification, for example, the ratio (Vb2 / Vk) obtained by dividing the volume Vb2 of the entire Voronoi region by combining the Voronoi regions in the second non-diffracting Voronoi diagram by the volume Vk of the monitoring target region. ) As the evaluation value H2.
Also, in the evaluation process in step S307 in FIG. 3A, when the third-order non-diffracting Voronoi diagram is selected as the evaluation target non-diffracting Voronoi diagram, the evaluation value H3 shown in the equation (3) is calculated. However, in the second modification, for example, the ratio (Vb3 / Vk) obtained by dividing the volume Vb3 of all Voronoi regions by combining the Voronoi regions in the third-order non-diffracting Voronoi diagram by the volume Vk of the monitoring target region. Is calculated as an evaluation value H3.

  By performing the above processing, it is possible to evaluate the arrangement position of the monitoring camera and determine the optimum arrangement position even in the three-dimensional monitoring target region.

  According to the monitoring camera arrangement position evaluation apparatus 100 of the present embodiment described above, it is possible to appropriately evaluate the arrangement positions of a plurality of monitoring cameras arranged in a monitoring target area where an obstacle exists. Furthermore, it is possible to determine the optimum arrangement position of the surveillance camera based on the appropriate evaluation of the arrangement position of the surveillance camera.

-Other embodiments-
The present invention can also be realized by executing the following processing.
That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, or the like) of the system or apparatus reads the program. It is a process to be executed. This program and a computer-readable recording medium storing the program are included in the present invention.

  Note that the above-described embodiments of the present invention are merely examples of implementation in practicing the present invention, and the technical scope of the present invention should not be construed as being limited thereto. It is. That is, the present invention can be implemented in various forms without departing from the technical idea or the main features thereof.

  In recent years, the demand for surveillance cameras has been increasing due to the need to ensure social security, and the network camera market including surveillance cameras has been constantly expanding at an average of about 150% since 2002. Under such a background, the present invention determines the optimum arrangement position based on the evaluation of the arrangement position of the surveillance camera and the evaluation result, and is very useful for improving the security. is there.

100: monitoring camera arrangement position evaluation apparatus, 201: information acquisition means, 202: non-diffracting Voronoi diagram creation means, 203: selection means, 204: evaluation means, 205: arrangement position determination means, 106: display unit 106, G: external apparatus

Claims (4)

A monitoring camera arrangement position evaluation apparatus for evaluating the arrangement positions of a plurality of monitoring cameras arranged in a monitoring target area where an obstacle exists,
Information acquisition means for acquiring monitoring target area information relating to the monitoring target area including the arrangement position information of the obstacle, and monitoring camera information relating to the plurality of monitoring cameras including arrangement position information of the plurality of monitoring cameras; ,
Using the monitoring target area information and the monitoring camera information, the Voronoi area related to each mother point is expanded for each area of the monitoring target area with each monitoring camera arrangement position in each of the plurality of monitoring cameras as a generating point. And a non-diffracting Voronoi diagram creating means for creating a non-diffracting Voronoi diagram for non-diffracting the blind spot area of the obstacle viewed from each generating point,
A monitoring camera arrangement position evaluation apparatus comprising: an evaluation unit that performs an evaluation process at an arrangement position of the plurality of monitoring cameras arranged in the monitoring target region using the non-diffracting Voronoi diagram.   In the non-diffracting Voronoi diagram, the evaluation means calculates the ratio of the total Voronoi region combining the Voronoi regions related to the respective generating points and the monitoring target region as an evaluation value, and performs the evaluation processing. The monitoring camera arrangement position evaluation apparatus according to claim 1. The non-diffracting Voronoi diagram creation means sets the total number of the respective generating points to k, expands the k-th place Voronoi region for the generating point of the k, and the obstacle viewed from the generating points of the generating point of the k When a non-diffracting Voronoi diagram that makes the blind spot region of an object non-diffracting is a non-diffracting Voronoi diagram at the k-th position, a non-diffracting Voronoi diagram at the first to k-th positions is created.
A selecting means for selecting a non-diffracting Voronoi diagram to be evaluated from the non-diffracting Voronoi diagrams of the 1st to kth positions;
The monitoring camera arrangement position evaluation apparatus according to claim 1, wherein the evaluation unit performs the evaluation process using an evaluation target non-diffracting Voronoi diagram selected by the selection unit.   4. The apparatus according to claim 1, further comprising an arrangement position determination unit that determines an optimum arrangement position of the plurality of monitoring cameras based on a result of the evaluation process performed by the evaluation unit. Monitoring camera placement position evaluation device.

Images