Information processing device, information processing method and program

Abstract

To evaluate an area that can be monitored by monitoring cameras.SOLUTION: An evaluation result obtained by evaluating the degree of shielding of a visual field caused by an object is generated about monitoring cameras arranged in a prescribed space on the basis of structure data about a structure existing in the prescribed space and object data about the object moving within the prescribed space.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a surveillance camera. [Background technology]

[0002] Systems for optimizing surveillance by surveillance cameras are known. For example, Patent Literature 1 discloses an invention related to a system for changing or correcting a surveillance area of ​​a surveillance camera based on structure information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-225108 A [Patent Document 2] JP 2021-010069 A Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure aims to evaluate areas that can be monitored by surveillance cameras. [Means for solving the problem]

[0005] One aspect of the present disclosure is to The information processing device has a control unit that generates an evaluation result that evaluates the degree of obstruction of the view caused by an object for a surveillance camera placed in a specified space based on structure data regarding a structure existing in the specified space and object data regarding an object moving within the specified space.

[0006] One aspect of the present disclosure is to This is an information processing method in which an information processing device executes the steps of acquiring structure data relating to structures existing in a specified space, acquiring object data relating to objects moving within the specified space, and generating an evaluation result that evaluates the degree of obstruction of the view caused by the objects for a surveillance camera placed in the specified space based on the structure data and the object data.

[0007] Another aspect of the present invention is a program for causing a computer to execute the above-described method, or a computer-readable storage medium non-transitoryly storing the program. Effect of the Invention

[0008] According to the present invention, it is possible to evaluate an area that can be monitored by a surveillance camera. [Brief description of the drawings]

[0009] [Figure 1] Schematic diagram for explaining the space to be monitored. [Diagram 2] FIG. 2 is a diagram for explaining a module configuration of the evaluation device 1. [Diagram 3] FIG. 2 is a diagram for explaining data stored in a storage unit 12. [Figure 4] FIG. 4 is a diagram for explaining motion information included in object data. [Diagram 5] 4 is a flowchart of a process executed in the first embodiment. [Figure 6] 4 is a flowchart of a process executed in the first embodiment. [Figure 7] 1 is a diagram illustrating the average occlusion rate for each camera. [Figure 8] 13 shows an example of material data used in the second embodiment. [Figure 9] 13 shows an example of ambient light data used in the second embodiment. [Figure 10] 10 is a flowchart of a process executed in a second embodiment. [Figure 11] 10 is a flowchart of a process executed in a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] In order to monitor a given space, such as the inside of a commercial facility, it is common to use multiple surveillance cameras. When monitoring a facility using multiple surveillance cameras, it is preferable to determine the locations of the cameras so as to minimize blind spots.

[0011] As a related technology, for example, there is a system that uses information on the positions of structures placed in a space to calculate the area that each of multiple surveillance cameras can capture, and determines the placement of surveillance cameras to minimize blind spots. This makes it possible to minimize the occurrence of areas that cannot be monitored, such as the shadows of pillars.

[0012] However, because such systems do not utilize information other than that of the structure, there may be cases where the area that can be monitored cannot be properly estimated. For example, consider a case where there are dynamic objects such as people and cars in the monitored space. When the dynamic object comes in front of the surveillance camera, it may block the field of view of the surveillance camera, resulting in an area where sufficient surveillance cannot be performed.

[0013] For example, consider placing multiple surveillance cameras in a store for the purpose of automatically settling items. In order to determine when a customer has picked up an item from a shelf, it is necessary to capture the customer's hand on the video. However, as the number of customers increases, the target's hand may be obscured by a shadow.

[0014] To solve this problem, it is preferable to evaluate the field of view of a surveillance camera taking into account the presence of moving objects. The information processing device according to the present disclosure solves such a problem.

[0015] An information processing device according to one embodiment has a control unit that generates an evaluation result that evaluates the degree of obstruction of the view caused by an object for a surveillance camera placed in a specified space based on structure data relating to a structure existing in the specified space and object data relating to an object moving within the specified space.

[0016] The predetermined space is a space to be monitored, and is typically an indoor space. The structure data is data related to fixed structures in the space. The structure data may be, for example, data related to the shape, size, location, etc. of one or more structures. The structure data may also include information on openings (e.g., windows, etc.) provided in the structure. The structure data may be data representing the location of multiple structures in a three-dimensional space.

[0017] The object data is data about an object moving within a given space. The object data may include, for example, data about the type and size of the object, the time period when the object appears within the given space, and the movement within the given space.

[0018] By using the structure data, the control unit can determine the physical blind spot from a specific position and can identify the field of view from a certain surveillance camera. Furthermore, by using the object data, the control unit can simulate the movement of an object, such as a person, within a space. This makes it possible to determine when an object causes part of the field of view of the surveillance camera to be obstructed (i.e., the area that can be monitored becomes narrower than expected). Also, by using the object data, the control unit can determine when an object causes the field of view of the surveillance camera to be obstructed (i.e., the area that can be monitored becomes narrower than expected). It is possible to determine to what extent the field is blocked.

[0019] The control unit may calculate an evaluation value that is higher as the proportion of the area blocked by the object in the field of view of the surveillance camera decreases. In other words, the control unit may generate an evaluation value that is higher as the blocked area becomes smaller and that is lower as the blocked area becomes larger.

[0020] The control unit may also calculate an evaluation value that is higher the smaller the proportion of the time during which at least a part of the field of view of the surveillance camera is blocked by the object relative to a predetermined time width. In other words, the control unit may generate an evaluation value that is higher the shorter the time during which the blocking occurs, and that is lower the longer the time during which the blocking occurs.

[0021] Furthermore, the control unit may integrate a plurality of evaluation values ​​corresponding to the plurality of surveillance cameras, respectively, and may evaluate the layout pattern of the plurality of surveillance cameras. Also, the control unit may determine a layout pattern of the plurality of surveillance cameras such that the sum of the plurality of evaluation values ​​exceeds a predetermined value.

[0022] Furthermore, the object data may further include data regarding a time period during which the dynamic object exists in a predetermined space, and the control unit may calculate the evaluation value for each time period.

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The configurations of the following embodiments are merely examples, and the present disclosure is not limited to the configurations of the embodiments.

[0024] First Embodiment An overview of an evaluation device according to a first embodiment will be described below. The evaluation device according to this embodiment is a device that determines optimal placement positions of multiple surveillance cameras within a given space.

[0025] First, the optimal placement of the surveillance cameras will be described. Fig. 1 is a plan view illustrating a space to be monitored by multiple surveillance cameras. The space to be monitored may be, for example, the inside of a commercial facility such as a store.

[0026] In Fig. 1, there are structures inside the store that obstruct visibility, such as walls and pillars. For example, there are pillars indicated by reference numerals 102A and 102B inside the store. In addition, there are shelves for displaying products and a cash register counter inside the store. The shelves and counters can also be considered as part of the structures.

[0027] Here, we consider an example in which the interior of such a store is monitored by multiple surveillance cameras. Reference numeral 101 denotes a surveillance camera installed in one corner of the store. The surveillance camera has a predetermined field of view. Here, the surveillance camera 101 is capable of capturing an image of the range indicated by reference numeral 103. In the following description, the three-dimensional area that each camera can capture without any physical barriers is referred to as the capture area. In order to thoroughly monitor the inside of such a store, it is preferable to arrange a plurality of surveillance cameras so that the imaging areas of the surveillance cameras can cover the entire area of ​​the store.

[0028] However, there are cases where this alone results in areas that cannot be monitored by any of the surveillance cameras. For example, in the example of FIG. 1, assume that a person is standing at the position indicated by reference numeral 104. In such a case, part of the shelf is hidden by the shadow of the person, and the person cannot be captured by the surveillance camera 101. In the illustrated example, the area indicated by reference numeral 105 temporarily becomes invisible. If this situation continues for a long time, another surveillance camera must be placed to monitor the area 105. The occurrence of such a phenomenon cannot be predicted based on the location information of the structure alone.

[0029] The evaluation device 1 in this embodiment evaluates the visibility of multiple surveillance cameras by simulating human movement in addition to the position information of structures. It also evaluates the placement positions of the surveillance cameras in multiple patterns and determines the optimal placement positions of the surveillance cameras based on the evaluation results.

[0030] [Device configuration] FIG. 2 is a diagram showing an example of the configuration of the evaluation device 1. As shown in FIG. The evaluation device 1 is, for example, a computer such as a server device, a personal computer, a smartphone, a mobile phone, a tablet computer, a personal information terminal, etc. The evaluation device 1 includes a control unit 11, a storage unit 12, and an input / output unit 13.

[0031] The evaluation device 1 can be configured as a computer having a processor (CPU, GPU, etc.), a main storage device (RAM, ROM, etc.), and an auxiliary storage device (EPROM, hard disk drive, removable media, etc.). The auxiliary storage device stores an operating system (OS), various programs, various tables, etc., and by executing the programs stored therein, various functions (software modules) that match a predetermined purpose, as described below, can be realized. However, some or all of the functions may be realized as hardware modules by hardware circuits such as ASICs and FPGAs.

[0032] The control unit 11 is a calculation unit that executes a predetermined program to realize various functions of the evaluation device 1. The control unit 11 can be realized by a hardware processor such as a CPU. The control unit 11 may also be configured to include a RAM, a ROM (Read Only Memory), a cache memory, and the like.

[0033] The control unit 11 is configured to have three software modules: a data acquisition unit 111, a simulation unit 112, and a result output unit 113. Each software module may be realized by causing the control unit 11 (CPU) to execute a program stored in the storage unit 12, which will be described later.

[0034] The data acquisition unit 111 acquires data for evaluating the installation positions of the surveillance cameras in a given space. In this embodiment, the data acquisition unit 111 acquires data on structures existing in the target space (hereinafter, structure data) and data on virtual dynamic objects moving in the space (hereinafter, object data).

[0035] The simulation unit 112 simulates an area that can be captured by each of the multiple surveillance cameras, based on the data acquired by the data acquisition unit 111. The simulation includes the simulation of a dynamic object.

[0036] The result output unit 113 generates and outputs information regarding an optimal arrangement of multiple surveillance cameras based on the results of the simulation performed by the simulation unit 112.

[0037] The storage unit 12 is a means for storing information, and is configured with storage media such as RAM, a magnetic disk, a flash memory, etc. The storage unit 12 stores programs executed by the control unit 11, data used when the programs are executed, etc.

[0038] The storage unit 12 stores structure data and object data acquired by the data acquisition unit 111. The project data is stored.

[0039] An example of the structure data will now be described. Fig. 3(A) shows an example of the structure data. The structure data is data related to the shape and size of a structure existing in a space. The structure data includes, for example, fields for a structure ID, a type, and location information. The structure ID field stores an identifier assigned to each structure. The type field stores the type of the structure (e.g., pillar, wall, window, etc.). The location information field stores data related to the position of the structure in the space. Examples of such data include a three-dimensional model of the structure, information about the size of the structure, and information about the placement position of the structure. By referring to the location information, the control unit 11 can identify the position of the structure in the monitored space. The structure data is stored in the BIM (Building Information Modeling) model and 3D- The structure data may be a CAD model, or may include data regarding the structure of the building itself.

[0040] Next, an example of the object data will be described below. Fig. 3(B) shows an example of the object data. The object data is data that defines a plurality of virtual objects that move within a space to be monitored. Examples of the virtual objects include a person, a car, a bicycle, and a personal mobility device. In this embodiment, the virtual object is a person. Each record of the object data is defined for each object. In the example of Fig. 3(B), three people are defined as objects. The object data includes fields for object ID, type, shape information, time information, and movement information.

[0041] The object ID field stores an identifier of a virtual object. The type field stores a type of object, such as a person or a car. The shape information field stores data (shape information) related to the shape, size, etc. of the object. If the object is a person, the shape information may be information related to height, sex, etc. If the object is a car, the shape information may be information related to the class, shape, size, etc. of the car. The shape information may also be three-dimensional modeling data.

[0042] The time information field stores information about the time period and time when the corresponding object visits the monitored store, etc. For example, a certain virtual person may have information such as "visits the store between 12:00 and 13:00 from Monday to Friday and stays for 15 minutes."

[0043] The movement information field stores information about the movement of the corresponding object. For example, if the monitoring target is a store, the movement information may be data that defines the movement (time-series change in position) of customers from entering the store to leaving the store. The movement information may be automatically generated based on typical behavior patterns of customers.

[0044] The movement information may be a combination of information (position information) that indicates the position of an object in a space and information (pose information) that indicates the pose of the object (person). For example, as shown in FIG. 4, the movement information may be data in which the position information and the pose information are defined for each time. Here, time t1 is the time when the target object enters (or moves into) the monitored space, and time t2 is the time when the target object leaves (or moves out of) the monitored space. It's time to leave.

[0045] In this embodiment, an object is typically a moving virtual object such as a human, an automobile, a bicycle, personal mobility, etc. The object may be a living thing or an inorganic object. The object data may be prepared by a user of the evaluation device 1, or may be generated based on the movements of objects observed in the past. Furthermore, the object data may be generated using a machine learning model or the like.

[0046] Returning to Figure 2, we will continue with the explanation. The input / output unit 13 is a means for receiving an input operation performed by an operator and presenting information to the operator. Specifically, the input / output unit 13 includes devices for input such as a mouse and a keyboard, and devices for output such as a display and a speaker. The input / output devices may be integrally configured with, for example, a touch panel display.

[0047] The specific hardware configuration of the evaluation device 1 may include omissions, substitutions, and additions of components as appropriate depending on the embodiment. For example, the control unit 11 may include multiple hardware processors. The hardware processor may be configured with a microprocessor, FPGA, GPU, etc. Also, input / output devices other than those exemplified (for example, an optical drive, etc.) may be added. Also, the evaluation device 1 may be configured with multiple computers. In this case, the hardware configurations of the computers may or may not be the same.

[0048] [Processing flow] Next, a description will be given of the processing executed by the evaluation device 1 according to this embodiment. Fig. 5 is a flowchart of the processing executed by the evaluation device 1. The processing shown in the figure is started by an operation by an operator of the evaluation device 1.

[0049] First, in step S11, the data acquisition unit 111 acquires data (structure data) related to structures included in the space to be monitored. The structure data may be a file written in a predetermined format, or may be imported via the input / output unit 13. The operator of the device can generate structure data for the target space and import it into the evaluation device 1.

[0050] Next, in step S12, the data acquisition unit 111 acquires data (object data) related to objects moving within the monitored space. The object data may be a file or the like described in a predetermined format, and may be imported via the input / output unit 13. The operator of the device can generate object data corresponding to objects moving within the target space and import it into the evaluation device 1.

[0051] The object data may be generated automatically. For example, object data such as that shown in Fig. 3(B) can be generated based on data statistically describing the number of people visiting the monitored space per unit time, their gender, visiting conditions, exit conditions, behavioral patterns from visit to exit, etc. The object data may be generated using statistics and behavioral patterns of people who have previously visited the target space under certain conditions.

[0052] Steps S13 to S18 are steps for arranging a virtual surveillance camera in a virtual space corresponding to the space to be monitored, and simulating the field of view. These steps are executed by the simulation unit 112.

[0053] In step S13, a plurality of virtual surveillance cameras are provisionally arranged in a virtual space. The number of surveillance cameras may be any number up to a predetermined value, for example. The positions of the surveillance cameras may be determined by a general method.

[0054] Next, in step S14, the imaging area of ​​the temporarily placed multiple surveillance cameras is calculated. In this step, for example, based on the parameters of the surveillance cameras (e.g., the angle of view and focal length), the area physically visible from each camera is identified and set as the imaging area. In this step, the imaging area is calculated based on the structure data acquired in step S11 and taking into account the structures placed in the target space. The imaging area may be specified by coordinates in a three-dimensional space.

[0055] Next, in step S15, a time range (time width) for performing the simulation is set. The time range for performing the simulation may be specified by an operator of the device via the input / output unit 13. In this step, for example, a range such as "Monday 10:00 a.m. to 7:00 p.m." is specified as the time range.

[0056] In step S16, the movement of the object is simulated and the field of view from the surveillance camera is evaluated. In this step, the movement of the object is simulated using the object data for each time step included in the set time range, and the degree of occlusion caused by the object is determined for each of the multiple surveillance cameras. As mentioned above, when an object moves within a space, an area may appear that is not visible to the surveillance camera. In such a case, the area (hereinafter, "unmonitored area") is excluded from the original image capture area. The remaining area is the monitorable area. The monitorable area means an area that can be monitored without being affected by external factors such as objects. In step S16, such a determination is made for each time step, and statistics are collected on the ratio of the monitorable area to the original field of view (image capture area).

[0057] FIG. 6 is a flowchart showing in more detail the process executed in step S16.

[0058] The processes of steps S161 and S162 are executed for each predetermined time step included in the time range in which the simulation is performed. The time step is set at a predetermined interval, such as every minute. For example, if the simulation target is one hour and the predetermined interval is every minute, 60 time steps are set.

[0059] First, in step S161, the position (and pose) of an object is simulated. As shown in Fig. 4, the object data defines data on the position of an object (e.g., a person) for each time, and using this data, the position and pose of a person at a certain time can be determined.

[0060] Next, in step S162, for each of the multiple surveillance cameras, an unmonitored area caused by the presence of an object is calculated. The area blocked by the object can be obtained based on the position information in the three-dimensional space. If there is no unmonitored area, the captured area and the monitorable area are equal.

[0061] In the following description, the ratio of the non-monitoring area to the imaging area is referred to as the occlusion rate. For example, if 30% of the imaging area is occluded due to an object, the occlusion rate is 30%. The occlusion rate can be calculated for each time step as shown in FIG. 7. Cut.

[0062] When the processing for all time steps included in the time range for which the simulation is performed is completed, in step S163, the average occlusion ratio for each surveillance camera is calculated. The average occlusion ratio is the average value of the occlusion ratios obtained for each time step. A high average occlusion ratio means that more areas are occluded by objects and / or that the total time during which some areas are occluded by objects in the time range for which the simulation is performed is long.

[0063] Returning to FIG. 5, the explanation will be continued. In step S17, the result output unit 113 calculates an evaluation value for the arrangement pattern of the temporarily arranged surveillance cameras. In this embodiment, the evaluation value is higher as the average shading rate of the temporarily arranged surveillance cameras is lower. The evaluation value can be a numerical value ranging from 0 to 100, for example.

[0064] The space to be monitored may be weighted. For example, if there is an area to be monitored intensively within the space to be monitored, the area may be weighted more heavily before the evaluation value is calculated. For example, if the area is covered by an object for a long period of time, the evaluation value may be corrected to be lower. Furthermore, when there is an area that does not need to be monitored, that area may be excluded from the calculation of the coverage rate.

[0065] In step S18, the result output unit 113 determines whether the calculated evaluation value is equal to or greater than a predetermined threshold value. If the calculated evaluation value is below the predetermined threshold value, the process returns to step S13, and the temporary placement of the surveillance cameras is executed again.

[0066] When performing the provisional placement of the surveillance cameras multiple times, the placement positions of the surveillance cameras may be shifted by a predetermined value to cover all possible placement patterns. Alternatively, multiple placement patterns of the surveillance cameras may be set in advance, and the surveillance cameras may be provisionally placed according to the multiple placement patterns. Various methods employed in optimization calculations may be used to determine the placement positions.

[0067] In step S18, if the calculated evaluation value is equal to or greater than a predetermined threshold, the process proceeds to step S19, and the result output unit 113 outputs the processing result. The processing result may include the positions of the multiple surveillance cameras, information on the imaging area, information on the non-monitoring area, information on the monitoring area, the occlusion rate, the average occlusion rate, the calculated evaluation value, and the like. Furthermore, the processing result may include information on the movement of the object. For example, when an occluded area occurs in most of the multiple time steps, the time period in which the event occurs and information on the area may be output as part of the processing result. For example, information such as "during busy hours, a line forms in front of the register, so the shelves at the back are almost invisible" may be output.

[0068] In the example of Fig. 5, the process is terminated when the calculated evaluation value is equal to or greater than a predetermined threshold, but the process may be continued even if an evaluation value equal to or greater than the predetermined threshold is obtained to obtain a more suitable placement pattern for the surveillance cameras. In this case, the results may be sorted by evaluation value and finally output.

[0069] As described above, the evaluation device according to the present embodiment evaluates the visibility of a surveillance camera based on information about structures arranged in a given space and information about virtual objects moving in the space. In addition, based on the evaluation results, the device determines optimal placement positions of multiple surveillance cameras. Determine the location. In particular, by performing a simulation using information regarding the movement of objects, it becomes possible to accurately detect events in which monitoring is hindered due to the presence of objects.

[0070] Second Embodiment In the first embodiment, the field of view of the surveillance camera is evaluated in consideration of the movement of the virtual object, and an optimal placement position of the surveillance camera is determined. However, there are factors other than the dynamic object that hinder surveillance. For example, consider a case where ambient light (such as sunlight) enters the space to be monitored from outside the building. If the sunlight reflects off the internal structure, glare may appear in the image captured by the camera, resulting in areas that cannot be monitored adequately. In other words, areas that cannot be monitored may occur due to factors other than objects.

[0071] To deal with this, the second embodiment simulates the reflection of ambient light in the space to be monitored, and calculates unmonitored areas caused by the ambient light (for example, areas that cannot be seen due to glare caused by reflected sunlight, etc.) Furthermore, the simulation results of the object and the simulation results of the ambient light are used together to calculate an evaluation value.

[0072] In the second embodiment, the storage unit 12 stores data on the surface material of the structure (hereinafter, material data) and data on ambient light (hereinafter, ambient light data) in addition to the structure data. The data acquisition unit 111 is configured to be able to acquire the material data and the ambient light data. In the second embodiment, the simulation unit 112 further executes a simulation of the ambient light based on the data acquired by the data acquisition unit 111 .

[0073] FIG. 8 shows an example of material data used in the second embodiment. The material data is data related to the surface material of the structure defined by the structure data. The material data includes, for example, fields for a structure ID, a material ID, and characteristic information. The structure ID field stores an identifier assigned to each structure. The material ID field stores an identifier assigned to each surface material. The characteristic information field stores data related to the light reflection characteristics of the surface material. Examples of such data include the light reflection direction and reflectance. The reflection direction indicates the direction in which light is reflected when it hits the surface material. The reflectance indicates the percentage of incident light that is reflected (the percentage of light that is not absorbed by the material). In this example, the structure data and the material data are separate, but they may be one type of data. They can also be integrated by using a BIM model, etc.

[0074] FIG. 9 is an example of the ambient light data used in the second embodiment. Ambient light data is data related to the ambient light that illuminates the space to be monitored. More specifically, ambient light data is data that defines the direction in which ambient light is incident and the intensity of the light. Ambient light data is configured to include, for example, fields for type, lighting conditions, azimuth, and angle. The type field stores the type of ambient light (e.g., sunlight, artificial lighting, etc.). When ambient light changes depending on the season or time of day, the lighting conditions field stores related data. For example, the position of the sun constantly changes during the day. Also, the altitude of the sun changes throughout the year. In such cases, the lighting conditions field stores conditions (e.g., data indicating the date and time of day). The azimuth field stores data indicating the azimuth angle at which ambient light is incident. The angle field stores the angle at which ambient light is incident ( For example, data indicating the elevation angle of the sun) is stored. Note that the ambient light data may also include data relating to the characteristics of the ambient light (for example, intensity, wavelength, etc.). In the example of FIG. 9, the azimuth angle and angle are defined for each illumination condition. However, when defining a light source that moves continuously, such as the sun, these may be expressed by mathematical expressions.

[0075] 10 is a flowchart of the process executed by the control unit 11 in the second embodiment. Processes similar to those in the first embodiment are indicated by dashed lines, and the description thereof will be omitted.

[0076] After the object data is acquired in step S12, the data acquisition unit 111 acquires material data in step S121. Furthermore, the data acquisition unit 111 acquires ambient light data in step S122. Each piece of data may be a file written in a predetermined format, or may be imported via the input / output unit 13. The acquired material data and ambient light data are stored in the storage unit 12.

[0077] In the second embodiment, in step S16A, the simulation unit 112 simultaneously performs simulation of the object and simulation of the ambient light. Fig. 11 is a flowchart of the process executed in step S16A. The processes of steps S161-S162A are executed for each time step, similar to the first embodiment.

[0078] First, in step S161, the simulation unit 112 simulates the position of the object, as in the first embodiment.

[0079] Next, in step S1611, the simulation unit 112 executes a simulation of the ambient light in the virtual space based on the structure data, material data, and ambient light data. The simulation of ambient light may be performed, for example, by ray tracing. For example, the refraction and reflection of light that occurs on the surface of an object are simulated based on the amount and direction of light emitted from a light source. In this case, if light is reflected on the surface of a structure, the angle and amount of reflection of the light can be calculated using material data.

[0080] In step S162A, simulation unit 112 calculates, for each of the multiple surveillance cameras, both an unmonitored area caused by the presence of an object and an unmonitored area caused by reflection of ambient light.

[0081] In this step, it is determined whether or not light is incident on each of the multiple surveillance cameras with an intensity equal to or greater than a predetermined threshold. In this step, for example, it is determined whether or not the luminous flux (or the luminous flux per unit area) incident on the surface of the lens of the surveillance camera is equal to or greater than a predetermined threshold. Here, if there is a surveillance camera on which light is incident with an intensity equal to or greater than a predetermined threshold, it can be estimated that halation or glare occurs on the image captured by the surveillance camera. It can also be estimated that the occurrence of halation or glare causes a range in the image where the object is not fully visible. In this step, for example, a range on the lens surface on which the luminous flux is incident with an intensity equal to or greater than a predetermined value is identified, and an unmonitored area can be identified based on the range. The unobservable areas due to ambient light are merged with the unobservable areas due to objects.

[0082] In step S163, the average occlusion ratio for each monitoring camera is calculated as in the first embodiment. In the second embodiment, the average occlusion ratio is calculated by adding the unmonitored area caused by the object and the unmonitored area caused by the ambient light. The process from step S17 onwards is the same as in the first embodiment. The more areas that are occluded by objects and the more areas that are difficult to see due to environmental light, the lower the evaluation value is calculated. Also, the longer an area is occluded by an object and the longer an area is difficult to see due to environmental light, the lower the evaluation value is calculated.

[0083] As described above, in the second embodiment, an area that is difficult to see due to the reflection of the ambient light entering the monitored space is regarded as equivalent to an area blocked by an object, and an evaluation value is calculated for each monitoring camera. This makes it possible to determine an appropriate placement position for the monitoring camera, taking into account the influence of the ambient light.

[0084] (Modification) The above-described embodiment is merely an example, and the present disclosure can be modified and implemented as appropriate without departing from the spirit and scope of the present disclosure. For example, the processes and means described in this disclosure can be freely combined and implemented as long as no technical contradiction occurs.

[0085] In addition, in the description of the embodiment, the time period for which the simulation is performed is specified, but multiple simulations may be performed for multiple dates and time periods. In this case, the optimal placement positions of the surveillance cameras may be output for each date and time period based on the evaluation values ​​obtained for each date and time period.

[0086] In the description of the embodiment, the evaluation value is calculated using the average occlusion ratio for each time step. However, the evaluation value may be calculated by other methods as long as the evaluation value is smaller as the area occluded by the object in a certain time step is smaller and the time for which the area is occluded by the object is shorter.

[0087] Furthermore, the object data exemplified in the embodiment is data defining a virtual object, but the object data may be data generated based on actual measurements in real space.

[0088] In addition, in the description of the embodiment, the term "location of the surveillance camera" is used to mean the coordinates where the surveillance camera is located, but the location of the surveillance camera may be a concept including the coordinates and angle (the direction in which the lens is facing) of the surveillance camera. In this case, in the loop of steps S13 to S18, the evaluation value may be calculated while further changing the direction in which each surveillance camera is facing. Furthermore, when the number and arrangement (coordinates) of the surveillance cameras are fixed, the evaluation value may be calculated while changing only the orientation in the loop of steps S13 to S18. In other words, the arrangement position may be a concept that includes only the orientation.

[0089] In addition, in the description of the embodiment, the surveillance cameras are fixed cameras, but the surveillance cameras may be cameras whose placement positions can be dynamically changed (for example, a mobility device equipped with a camera). In this case, the evaluation device 1 may transmit instruction information for instructing a suitable position of the surveillance camera to a control device that controls the placement positions of the surveillance cameras. Furthermore, the multiple surveillance cameras may be cameras whose angles (directions) can be dynamically changed. In this case, the evaluation device 1 may transmit instruction information instructing the angles (directions) to a control device that controls the angles of the surveillance cameras. In addition, if the suitable placement positions of the surveillance cameras differ for each time period (time slot), the evaluation device 1 may be configured to transmit the above-mentioned instruction information to the surveillance camera control device in order to change the placement positions of each surveillance camera for each time period.

[0090] In addition, in the description of the embodiment, the simulation unit 112 automatically generates the placement positions of the surveillance cameras, but the placement positions of the surveillance cameras may be specified by an operator of the evaluation device 1. In this case, conditions related to the placement positions of the surveillance cameras, such as coordinates and orientation, may be acquired via the input / output unit 13, and an evaluation value (or a simulation result) under the conditions may be output. In other words, the evaluation device 1 may function as a device that evaluates the size of a monitorable area under specified conditions.

[0091] Furthermore, a process described as being performed by one device may be shared and executed by multiple devices. Alternatively, a process described as being performed by different devices may be executed by one device. In a computer system, the hardware configuration (server configuration) by which each function is realized can be flexibly changed.

[0092] The present disclosure can also be realized by supplying a computer program implementing the functions described in the above embodiments to a computer, and having one or more processors of the computer read and execute the program. Such a computer program may be provided to the computer by a non-transitory computer-readable storage medium connectable to the system bus of the computer, or may be provided to the computer via a network. Non-transitory computer-readable storage media include, for example, any type of disk, such as a magnetic disk (floppy disk, hard disk drive (HDD), etc.), an optical disk (CD-ROM, DVD disk, Blu-ray disk, etc.), a read-only memory (ROM), a random access memory (RAM), an EPROM, an EEPROM, a magnetic card, a flash memory, an optical card, and any type of medium suitable for storing electronic instructions. [Explanation of symbols]

[0093] 1. Evaluation device 11. Control section 12...Storage section 13...Input / output section

Claims

1. Structure data relating to structures present in a predetermined space; Object data relating to an object moving within the predetermined space; Based on the above, an evaluation result is generated that evaluates the degree of obstruction of the view caused by the object for the surveillance camera arranged in the predetermined space. An information processing device having a control unit.

2. the control unit calculates, as the evaluation result, an evaluation value that is higher as a proportion of an area occluded by the object within a field of view of the surveillance camera is smaller; The information processing device according to claim 1 .

3. the control unit calculates, as the evaluation result, an evaluation value that is higher as the ratio of a time during which at least a part of the field of view of the surveillance camera is blocked by the object to a predetermined time width is smaller. The information processing device according to claim 2 .

4. the control unit integrates the evaluation values ​​corresponding to the plurality of surveillance cameras, respectively, and evaluates an arrangement pattern of the plurality of surveillance cameras.

4. The information processing device according to claim 2 or 3.

5. The control unit determines an arrangement of the plurality of surveillance cameras in an arrangement pattern such that a sum of the plurality of evaluation values ​​exceeds a predetermined value. The information processing device according to claim 4.

6. The object data is data that defines the movements of the plurality of objects over time. The information processing device according to claim 1 .

7. the control unit simulates a movement of the object in the predetermined space based on the object data, and generates the evaluation result based on a result of the simulation. The information processing device according to claim 6.

8. the control unit calculates, as the evaluation result, an evaluation value that is higher as a proportion of an area occluded by the object within a field of view of the surveillance camera is smaller; The information processing device according to claim 7.

9. the control unit calculates, as the evaluation result, an evaluation value that is higher as the ratio of a time during which at least a part of the field of view of the surveillance camera is blocked by the object to a predetermined time width is smaller. The information processing device according to claim 8.

10. the control unit integrates the evaluation values ​​corresponding to the plurality of surveillance cameras, respectively, and evaluates an arrangement pattern of the plurality of surveillance cameras.

10. The information processing device according to claim 8.

11. The control unit determines an arrangement of the plurality of surveillance cameras in an arrangement pattern such that a sum of the plurality of evaluation values ​​exceeds a predetermined value. The information processing device according to claim 10.

12. The object data further includes data regarding a time period during which the object is present in the predetermined space.

10. The information processing device according to claim 8.

13. The control unit calculates the evaluation value for each time period. The information processing device according to claim 12.

14. An information processing device, acquiring structure data relating to structures present in a predetermined space; obtaining object data relating to an object moving within the predetermined space; generating an evaluation result of evaluating a degree of obstruction of a view caused by the object for a surveillance camera arranged in the predetermined space based on the structure data and the object data; An information processing method.

15. calculating, as the evaluation result, an evaluation value that is higher as the ratio of an area occluded by the object within the field of view of the surveillance camera is smaller; The information processing method according to claim 14.

16. calculating, as the evaluation result, an evaluation value that increases as the ratio of a time during which at least a part of the field of view of the surveillance camera is blocked by the object to a predetermined time width decreases; The information processing method according to claim 15.

17. a step of aggregating the evaluation values ​​corresponding to the plurality of surveillance cameras, respectively, and evaluating a layout pattern of the plurality of surveillance cameras; The information processing method according to claim 15.

18. determining an arrangement of the plurality of surveillance cameras in an arrangement pattern such that the sum of the plurality of evaluation values ​​exceeds a predetermined value; 18. The information processing method according to claim 17.

19. the object data is data defining movements of a plurality of the objects over time; simulating a movement of the object within the predetermined space based on the object data, and generating the evaluation result based on a result of the simulation; The information processing method according to claim 14.

20. A program for causing a computer to execute the information processing method according to any one of claims 14 to 19.

Images