Information processing apparatus, information processing method, and storage medium

Abstract

The invention relates to an information processing apparatus, an information processing method, and a storage medium. The present invention evaluates an area that can be monitored by a monitoring camera. On the basis of structure data relating to a structure present in a predetermined space and object data relating to an object moving in the predetermined space, an evaluation result is generated for a monitoring camera disposed in the predetermined space, said evaluation result being obtained by evaluating the degree of occlusion of a field of view due to the object.

Description

Technical Field

[0001] The present invention relates to surveillance cameras. Background Art

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

[0003] Patent Document 1: Japanese Patent Application Publication No. 2017-225108 Patent Document 2: Japanese Patent Application Publication No. 2021-010069 Summary of the invention Problems to be solved by the invention

[0004] The present disclosure aims to evaluate an area that can be monitored by a monitoring camera. Means for solving problems

[0005] One embodiment of the present disclosure is an information processing device, It has a control unit that generates an evaluation result of the degree of obstruction of the field of view caused by the object for a surveillance camera arranged in the specified space based on structure data related to the structure existing in the specified space and object data related to the object moving in the specified space.

[0006] One embodiment of the present disclosure is an information processing method, wherein: The information processing device executes: the step of acquiring structure data related to a structure existing in a specified space; the step of acquiring object data related to an object moving in the specified space; and the step of generating, for a surveillance camera arranged in the specified space, an evaluation result of the degree of obstruction of the field of view caused by the object based on the structure data and the object data.

[0007] Furthermore, as another aspect, there may be a program for causing a computer to execute the above-described method, or a computer-readable storage medium storing the program in a non-temporary manner. Effects of the Invention

[0008] According to the present invention, it is possible to evaluate an area that can be monitored by a monitoring camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a schematic diagram for explaining a space to be monitored. Figure 2 It is a diagram for explaining the block configuration of the evaluation device 1 . Figure 3 This is a diagram for explaining data stored in the storage unit 12 . Figure 4 A diagram for explaining motion information included in object data. Figure 5 This is a flowchart of the processing performed in the first embodiment. Figure 6 This is a flowchart of the processing performed in the first embodiment. Figure 7 It is a graph showing the average occlusion rate of each camera. Figure 8 This is an example of material data used in the second embodiment. Fig. 9 This is an example of ambient light data used in the second embodiment. Fig.10 This is a flowchart of the processing performed in the second embodiment. Fig.11 This is a flowchart of the processing performed in the second embodiment. DETAILED DESCRIPTION

[0010] In order to monitor a predetermined space such as the interior of a store of a commercial facility, a plurality of monitoring cameras are generally used. When monitoring the interior of a facility by a plurality of monitoring cameras, it is preferable to determine the arrangement positions of the monitoring cameras so as to minimize the range of blind spots.

[0011] As a related technology, there is a system that uses information about the positions of structures arranged in a space to calculate the areas that can be captured by each of a plurality of surveillance cameras and determines the positions of the surveillance cameras to reduce blind spots. This can minimize the occurrence of areas that cannot be monitored, such as the shadow of a pillar, for example.

[0012] However, in such a system, since information other than the structure cannot be used, there is a possibility that the range that can be monitored cannot be appropriately estimated. For example, consider the situation where a dynamic object such as a person or a car exists in the space of the monitoring object. Here, the following situation may occur: if the dynamic object comes in front of the monitoring camera, the field of view of the monitoring camera is blocked, resulting in an area that cannot be fully monitored.

[0013] For example, consider the case where multiple surveillance cameras are installed in a store for the purpose of automatic checkout of goods. In order to determine when a store user takes a product from a shelf, it is necessary to capture the user's hand through an image, but if the number of users increases, there may be a situation where the target person's hand cannot be observed due to the shadow of the person.

[0014] To address this problem, it is preferred to evaluate the field of view of the surveillance camera taking into account the presence of moving objects. The information processing device according to the present disclosure solves the above-mentioned problems.

[0015] An information processing device involved in one embodiment has a control unit, which generates an evaluation result of the degree of obstruction of the field of view caused by the object for a surveillance camera arranged in the specified space based on structure data related to the structure existing in the specified space and object data related to the object moving in the specified space.

[0016] The predetermined space refers to a space to be monitored, and is typically an indoor space. Structure data is data related to fixed structures located in the space. Structure data may be, for example, data related to the shape, size, and configuration position of one or more structures. In addition, structure data may also include information related to openings (such as windows) provided in the structures. Structure data may also be data representing the configuration of multiple structures in a three-dimensional space.

[0017] Object data is data related to an object moving in a predetermined space. Object data may include, for example, data related to the type and size of the object, the time period when the object appears in the predetermined space, the movement in the predetermined space, and the like.

[0018] The control unit can determine the physical blind spot from a specific position by using the structure data, and can determine the field of view observed from a certain monitoring camera. In addition, the control unit can simulate the movement of objects such as people located in the space by using the object data. Thus, it can be determined that a part of the field of view of the monitoring camera is blocked by the object (that is, the area that can be monitored is narrower than expected). In addition, it can be determined to what extent the field of view of the monitoring camera is blocked by the object.

[0019] In addition, the control unit may calculate an evaluation value such that the lower the ratio of the area blocked by the object in the field of view of the monitoring camera, the higher the value. In other words, the control unit may generate an evaluation value such that the smaller the blocked area, the larger the value, and the larger the blocked area, the smaller the value.

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

[0021] Furthermore, the control unit may evaluate the arrangement pattern of the plurality of monitoring cameras by integrating the plurality of evaluation values ​​corresponding to the plurality of monitoring cameras, respectively. Alternatively, the arrangement pattern of the plurality of monitoring cameras may be determined such that the sum of the plurality of evaluation values ​​does not exceed a predetermined value.

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

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

[0024] (First Embodiment) The following describes an overview of an evaluation device according to a first embodiment. The evaluation device according to this embodiment is a device that determines optimal arrangement positions of a plurality of monitoring cameras in a predetermined space.

[0025] First, the optimal arrangement positions of monitoring cameras will be described. Figure 1 1 is a top view illustrating a space to be monitored by a plurality of monitoring cameras. The space to be monitored may be, for example, the interior of a commercial facility such as a store.

[0026] exist Figure 1 In the example, there are structures such as walls and pillars in the store that obstruct the unobstructed view. In the store, for example, there are pillars represented by reference numerals 102A and 102B. In addition, there are shelves and checkout counters for displaying goods in the store. The shelves and counters can also be part of the structures.

[0027] Here, consider an example in which the interior of such a store is monitored by multiple surveillance cameras. Reference numeral 101 is a surveillance camera placed in a corner of the store. The surveillance camera has a predetermined field of view. Here, surveillance camera 101 is a surveillance camera capable of capturing images of the range represented by reference numeral 103. In the following description, a three-dimensional area that can be captured by each camera without a physical barrier is referred to as a capturing area. In order to monitor the entire interior of such a store, it is preferable to arrange the monitoring cameras so that the imaging area formed by the plurality of monitoring cameras can cover the entire area inside the store.

[0028] However, even with this alone, there may still be areas that cannot be monitored by any surveillance camera. For example, in Figure 1 In the example shown in FIG. 1 , a person stands at the position indicated by reference numeral 104. In such a case, a part of the shelf is hidden in the shadow of the person and cannot be captured by the monitoring camera 101. In the example shown in the figure, the area indicated by reference numeral 105 becomes temporarily unobservable. If this state continues for a long time, another monitoring camera must be configured to monitor the area 105. The occurrence of this phenomenon cannot be inferred based only on the position information of the structure.

[0029] The evaluation device 1 in this embodiment evaluates the field of view formed by multiple monitoring cameras by simulating human actions in addition to the position information of the structure. In addition, the configuration positions of the monitoring cameras are evaluated based on multiple patterns, and the appropriate configuration positions of the monitoring cameras are determined based on the evaluation results.

[0030] [Device configuration] Figure 2 It is a diagram showing an example of the configuration of the evaluation device 1 . The evaluation device 1 is a computer such as a server device, a personal computer, a smart phone, a mobile phone, a tablet computer, or a personal information terminal. 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 meet the prescribed purpose described later can be realized. However, some or all of the functions can also be realized as hardware modules by hardware circuits such as ASIC (Application Specific Integrated Circuit) and FPGA (Field Programmable Gate Array).

[0032] The control unit 11 is a computing unit that implements various functions of the evaluation device 1 by executing a predetermined program. The control unit 11 can be implemented 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 flash memory, and the like.

[0033] The control unit 11 includes three software modules: a data acquisition unit 111, a simulation unit 112, and a result output unit 113. Each software module can be realized by the control unit 11 (CPU) executing 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 position of the monitoring camera for a predetermined space. In the present embodiment, the data acquisition unit 111 acquires data related to structures existing in the target space (hereinafter referred to as structure data) and data related to virtual dynamic objects moving in the space (hereinafter referred to as object data).

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

[0036] The result output unit 113 generates and outputs information on appropriate arrangement of the plurality of monitoring cameras based on the simulation result performed by the simulation unit 112 .

[0037] The storage unit 12 is a means for storing information, and is composed of a storage medium such as a RAM, a magnetic disk, a flash memory, etc. The storage unit 12 stores a program executed by the control unit 11, data used when the program is executed, and the like.

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

[0039] Here, an example of structure data will be described. Figure 3 (A) is an example of structure data. The structure data is data related to the shape and size of the structure existing in the space. The structure data is composed of fields such as structure ID, type, and position information. The structure ID field stores the identifier assigned to each structure. The type field stores the type of structure (for example, pillars, walls, windows, etc.). The position information field stores data related to the position of the structure in the space. As such data, for example, a three-dimensional model of the structure, information related to the size of the structure, information related to the configuration position of the structure, etc. can be exemplified. By referring to the position information, the control unit 11 can determine the position of the structure in the space of the monitored object. Furthermore, the structure data may be a BIM (Building Information Modeling) model or a model obtained by 3D-CAD. Furthermore, the structure data may include data related to the structure of the building itself.

[0040] Next, an example of object data will be described. Figure 3 (B) is an example of object data. The object data is data defining a plurality of virtual objects moving in a monitored space. Examples of virtual objects include people, cars, bicycles, and personal transportation tools. In the present embodiment, the virtual objects are people. Each record of object data is defined for each object. Figure 3 In the example (B), three persons are defined as objects. The object data is composed of fields including object ID, type, shape information, time information, and action information.

[0041] The object ID field stores the identifier of the virtual object. The type field stores the type of the object, such as a person or a car. The shape information field stores data related to the shape and size of the object (shape information). When the object is a person, the shape information may be information related to height, gender, etc. In addition, when the object is a car, the shape information may be information related to the grade, shape, size, etc. of the car. In addition, the shape information may also be three-dimensional model data.

[0042] The time information field stores information related to the time period and time when the corresponding object visits the store of the monitored object, etc. For example, for a virtual character, there may be information such as "visited the store between 12:00 and 13:00 from Monday to Friday and stayed for 15 minutes."

[0043] The action information field stores information related to the action of the corresponding object. For example, when the monitored object is a store, the action information may be data defining the actions of a visitor from entering the store to leaving the store (position changes over time). The action information may also be data automatically generated based on the typical behavior patterns of the visitor.

[0044] The motion information may also be a combination of information indicating the position of an object in space (position information) and information indicating the posture of the object (person) (posture information). Figure 4 As shown, the position information and posture information are defined as data for each time. Here, time t1 is the time when the object enters the monitored space, and time t2 is the time when the object exits the monitored space.

[0045] The object in this embodiment is typically a virtual object that moves, such as a person, a car, a bicycle, a personal transportation tool, etc. The object may be a living thing or an inorganic thing. The object data may be prepared by the user of the evaluation device 1 or may be generated based on the behavior of an object observed in the past. Alternatively, the object data may be generated using a machine learning model or the like.

[0046] return Figure 2 Continue with the explanation. The input / output unit 13 is a unit that receives input operations performed by an operator and presents 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 device may also be integrally formed by, for example, a touch panel display.

[0047] In addition, the specific hardware configuration of the evaluation device 1 can appropriately omit, replace, and add components in accordance with the implementation. For example, the control unit 11 may also include multiple hardware processors. The hardware processor may also be composed of a microprocessor, an FPGA, a GPU, etc. In addition, input and output devices other than the illustrated devices (such as optical drives, etc.) may also be added. In addition, the evaluation device 1 may also be composed of multiple computers. In this case, the hardware configurations of the computers may be consistent or inconsistent.

[0048] [Processing flow] Next, the processing executed by the evaluation device 1 according to the present embodiment will be described. Figure 5 1 is a flowchart of a process executed by the evaluation device 1. The illustrated process is started by an operation of an operator of the evaluation device 1.

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

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

[0051] Furthermore, object data can also be automatically generated. For example, a monitoring system may be generated based on data that statistically records the number of people who visit the monitored space per unit time, gender, access conditions, exit conditions, and behavior patterns from access to exit. Figure 3In the generation of object data, statistics and behavior patterns of people who have visited the target space in the past under certain conditions may be used.

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

[0053] In step S13, a plurality of virtual monitoring cameras are virtually arranged in the virtual space. The number of monitoring cameras can be set to any number with a predetermined value as an upper limit, for example. The arrangement positions of the monitoring cameras can be determined by a common method.

[0054] Next, in step S14, the imaging area formed by the virtually arranged plurality of monitoring cameras is calculated. In this step, for example, the area physically observable from each camera is determined as the imaging area based on the parameters of the monitoring camera (e.g., viewing angle, focal length, etc.). In this step, the imaging area is calculated based on the structure data acquired in step S11, taking into account the structure arranged in the target space. The imaging area can also be determined by coordinates in a three-dimensional space.

[0055] Next, in step S15, the time range (time width) for simulation is set. The time range for simulation can be specified by the operator of the device via the input / output unit 13. In this step, for example, "Monday 10 am to 7 pm" is specified as the time range.

[0056] In step S16, the movement of the object is simulated to evaluate the field of view observed by the monitoring camera. 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 obstruction caused by the object is determined for each of the multiple monitoring cameras. As mentioned above, when an object moves in space, there may be a situation where an area becomes unobservable from the surveillance camera. In this case, the corresponding area (hereinafter referred to as the unobservable area) is removed from the original camera area. The remaining area is the monitorable area. The monitorable area refers to an area that can be monitored without being affected by external factors such as objects. In step S16, the above determination is performed for each time step, and the ratio of the monitorable area to the original field of view (imaging area) is counted.

[0057] Figure 6 : is a flowchart showing the processing executed in step S16 in more detail.

[0058] The processing of steps S161 and S162 is performed for each time step included in the time range for simulation. The time step is set at a predetermined interval, such as 1 minute each. For example, when the object of simulation is 1 hour and the predetermined interval is 1 minute, 60 time steps are set.

[0059] First, in step S161, the position (and posture) of the object is simulated. Figure 4 As shown, in the object data, data related to the position of the object (eg, a person) is defined at each time, and therefore, the position and posture of the person at a certain time can be determined using these data.

[0060] Next, in step S162, the unmonitored area due to the existence of the object is calculated for each of the multiple monitoring cameras. The area blocked by the object can be obtained based on the position information in the three-dimensional space. In the absence of the unmonitored area, the camera area is equal to the monitorable area.

[0061] In the following description, the ratio of the unmonitorable area to the camera area is referred to as the obstruction rate. For example, if 30% of the camera area is obstructed by an object, the obstruction rate is 30%. Figure 7 The result is shown for each time step.

[0062] After the processing is completed for all time steps included in the time range for simulation, in step S163, the average occlusion rate of each monitoring camera is calculated. The average occlusion rate refers to the average value of the occlusion rates obtained for each time step. The higher the average occlusion rate, the more areas are obscured by objects and / or the total time that a part of the area is obscured by objects in the time range for simulation is longer.

[0063] return Figure 5 Continue with the explanation. In step S17, the result output unit 113 calculates an evaluation value for the arrangement pattern of the virtually arranged monitoring cameras. In this embodiment, the evaluation value is higher as the average shielding rate of the virtually arranged monitoring cameras is lower. The evaluation value can be set to a numerical value in the range of 0-100, for example.

[0064] In addition, the space of the monitored object may also be weighted. For example, if there is an area that should be monitored intensively within the space of the monitored object, the evaluation value may be calculated by assigning a greater weight to the area. For example, if the area is blocked by an object for a long time, correction may be performed to make the evaluation value lower. Furthermore, when there is an area that does not need to be monitored, the area may be excluded from the calculation of the shielding 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 lower than the predetermined threshold value, the process returns to step S13 and the virtual arrangement of the monitoring camera is performed again.

[0066] Furthermore, when performing multiple virtual configurations of monitoring cameras, all configuration patterns that are considered can be included while shifting the configuration positions of each monitoring camera by a predetermined value. In addition, multiple configuration patterns of monitoring cameras can be pre-set, and monitoring cameras can be virtually configured according to the multiple configuration patterns. Various methods used in optimization calculations can be used to determine the configuration positions.

[0067] In step S18, when the calculated evaluation value is above the prescribed threshold, the process jumps to step S19, and the result output unit 113 outputs the processing result. The processing result may include the configuration positions of multiple monitoring cameras, information related to the camera area, information related to the unmonitored area, information related to the monitorable area, the occlusion rate, the average occlusion rate, and the calculated evaluation value. In addition, the processing result may also include information related to the movement of the object. For example, in the case where an obscured area occurs in most of the multiple time steps, the time period in which the phenomenon occurs and the information related to the corresponding area may also be output as part of the processing result. For example, information such as "a queue is formed in front of the checkout counter during the busy period, so the shelves located at the back are basically not observable" may be output.

[0068] In addition, Figure 5 In the example, the processing is terminated when the calculated evaluation value is above the predetermined threshold value, but the processing can be continued even if the evaluation value is above the predetermined threshold value to obtain a more appropriate configuration mode of the monitoring camera. In this case, the results can also be sorted according to the evaluation value and outputted last.

[0069] As described above, the evaluation device according to this embodiment evaluates the field of view of a monitoring camera based on information about a structure arranged in a predetermined space and information about a virtual object moving in the space, and determines appropriate arrangement positions of a plurality of monitoring cameras based on the evaluation results. In particular, by performing simulation using information related to the movement of the object, it is possible to detect with high accuracy a phenomenon in which monitoring is hindered due to the presence of the object.

[0070] (Second Embodiment) In the first embodiment, the field of view of the monitoring camera is evaluated in consideration of the movement of the virtual object, and the appropriate arrangement position of the monitoring camera is determined. On the other hand, there are factors that hinder monitoring in addition to dynamic objects. For example, consider the case where ambient light (sunlight, etc.) enters the space of the monitored object from the outside of the building. Here, if the sunlight is reflected by the internal structure, there may be glare in the image captured by the camera, resulting in an area that cannot be fully monitored. In other words, there may be a case where the unmonitorable area is caused by factors other than objects.

[0071] In order to cope with the above situation, the second embodiment simulates the reflection of ambient light in the space of the monitored object, and calculates the unmonitored area due to the ambient light (for example, the unobservable area due to the glare caused by the reflection of sunlight, etc.). In addition, the evaluation value is calculated using the simulation results of the object and the simulation results of the ambient light.

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

[0073] Figure 8 This is an example of material data used in the second embodiment. Material data is data related to the surface raw material of the structure defined according to the structure data. Material data is composed of fields including structure ID, material ID, and characteristic information, for example. The structure ID field stores identifiers assigned to each structure. The material ID field stores identifiers assigned to each surface raw material. The characteristic information field stores data related to the reflection characteristics of the surface raw material. As such data, for example, the reflection direction and reflectivity of light can be exemplified. The reflection direction indicates the direction in which light is reflected when light irradiates the surface raw material. The reflectivity indicates how much proportion is reflected relative to the incident light (the proportion of light not absorbed by the raw material). In this example, the structure data and the material data are different data, but the two may be the same type of data, and the two may be integrated by using a BIM model or the like.

[0074] Fig. 9 This is an example of ambient light data used in the second embodiment. Ambient light data is data related to the ambient light that illuminates the space of the monitored object. Specifically, ambient light data is data that defines the direction and light intensity of the ambient light. Ambient light data is, for example, composed of fields including type, lighting conditions, azimuth, and angle. The type of ambient light (e.g., sunlight, artificial lighting, etc.) is stored in the type field. In the case where the ambient light changes according to the season or time period, the related data is stored in the lighting condition field. For example, the position of the sun changes continuously throughout the day. In addition, the height of the sun changes over the year. In such a case, the conditions (e.g., data indicating the date or time period) are stored in the lighting condition field. The azimuth field stores data indicating the azimuth of the ambient light incident. The angle field stores data indicating the angle of the ambient light incident (e.g., the elevation angle of the sun). In addition, in addition to the above data, the ambient light data may also include data related to the characteristics of the ambient light (e.g., intensity, wavelength, etc.). In addition, Fig. 9 In the example, the azimuth and angle are defined for each lighting condition. However, when defining a continuously moving light source such as the sun, the azimuth and angle can also be expressed by a formula.

[0075] Fig.10 This is a flowchart of the processing executed by the control unit 11 in the second embodiment. The same processing as that in the first embodiment is indicated by a dotted line, and the description thereof is omitted.

[0076] After the object data is acquired in step S12, the data acquisition unit 111 acquires the material data in step S121. In addition, in step S122, the data acquisition unit 111 acquires the ambient light data. Each data may be a file described in a prescribed format, or may be received 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 performs the simulation of the object and the simulation of the ambient light simultaneously. Fig.11 2 is a flowchart of the process executed in step S16A. The processes of steps S161 to S162A are executed for each time step similarly to the first embodiment.

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

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

[0080] In step S162A, the simulation unit 112 calculates both the non-monitoring area due to the presence of an object and the non-monitoring area due to reflection of ambient light for each of the plurality of monitoring cameras.

[0081] In this step, it is determined for each of the plurality of monitoring cameras whether light is incident with an intensity above a prescribed threshold. In this step, for example, it is determined whether the light beam (or the light beam per unit area) incident on the surface of the lens of the monitoring camera is above a prescribed threshold. Here, in the case where there is a monitoring camera where light is incident with an intensity above a prescribed threshold, it can be inferred that halos and glare are generated in the image captured by the monitoring camera. In addition, it is possible to infer that a range in which the object cannot be fully observed is generated in the image through the generation of halos and glare. In this step, for example, it is also possible to determine a range on the lens surface where the light beam is incident with an intensity above a prescribed intensity, and determine the unmonitored area based on the corresponding range. The unmonitored area due to ambient light and the unmonitored area due to objects are integrated.

[0082] In step S163, the average obstruction rate of each monitoring camera is calculated similarly to the first embodiment. In the second embodiment, the average obstruction rate is calculated based on the unmonitorable area due to the object plus the unmonitorable area due to the ambient light. The processing after step S17 is the same as that of the first embodiment. That is, the more areas are shielded by the object, the more areas become difficult to observe due to the ambient light, the lower the evaluation value is calculated. In addition, the longer the shielding by the object occurs, the longer the area becomes difficult to observe due to the ambient light, the lower the evaluation value is calculated.

[0083] As described above, in the second embodiment, the area that becomes difficult to observe due to the reflection of the ambient light incident on the space of the monitored object is captured in the same manner as the area blocked by the object, and the evaluation value of each monitoring camera is calculated. In this way, the appropriate configuration position of the monitoring camera can be determined taking into account the influence of the ambient light.

[0084] (Variation Example) The above-described embodiment is merely an example, and the present disclosure can be implemented with appropriate modifications without departing from the gist of the disclosure. For example, the processes and units described in the present disclosure can be freely combined and implemented as long as no technical contradiction occurs.

[0085] In the description of the embodiment, the time period for the simulation is specified, but the simulation may be performed multiple times for multiple dates and time periods. In this case, the appropriate monitoring camera configuration position may be output for each date and time period based on the evaluation value obtained for each date and time period.

[0086] In the description of the implementation method, the evaluation value is calculated using the average occlusion rate of each time step, but other methods may be used as long as the evaluation value is smaller as the area occluded by the object in a certain time step and the occlusion time is shorter.

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

[0088] In the description of the embodiment, the phrase "the location of the monitoring camera" is used to mean the coordinates at which the monitoring camera is located, but the location of the monitoring camera may also be a concept including the coordinates and angle (direction of the lens) of the monitoring camera. In this case, the evaluation value may be calculated while changing the direction of each monitoring camera in the loop of steps S13 to S18. Furthermore, when the number and arrangement (coordinates) of monitoring cameras are determined, the evaluation value may be calculated while only the orientation is changed in the loop of steps S13 to S18. That is, the arrangement position may be a concept including only the orientation.

[0089] In the description of the embodiment, the monitoring camera is set as a fixed camera, but the plurality of monitoring cameras may also be cameras whose configuration positions can be changed dynamically (for example, mobile devices equipped with cameras). In this case, the evaluation device 1 may also send instruction information indicating the position of an appropriate monitoring camera to the control device that controls the configuration position of the monitoring camera. In addition, the plurality of monitoring cameras may be cameras whose angles (orientations) can be changed dynamically. In this case, the evaluation device 1 may transmit instruction information indicating the angles (orientations) to a control device that controls the angles of the monitoring cameras. Furthermore, when the appropriate placement position of the monitoring camera is different in each time slot, the placement position of each monitoring camera should be changed in each time slot, and the evaluation device 1 may send the above-mentioned instruction information to the control device of the monitoring camera.

[0090] In the description of the embodiment, the simulation unit 112 automatically generates the configuration position of the monitoring camera, but the configuration position of the monitoring camera may be specified by the operator of the evaluation device 1. In this case, the coordinates, orientation and other conditions related to the configuration position of the monitoring camera may be acquired via the input / output unit 13, and the evaluation value (or simulation result) under the corresponding conditions may be output. That is, the evaluation device 1 may also function as a device for evaluating the range of the monitorable area under the specified conditions.

[0091] In addition, 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, it is possible to flexibly change which hardware components (server components) implement each function.

[0092] The present disclosure can also be implemented in the following manner: that is, a computer program with the functions described in the above-mentioned embodiment installed is provided to a computer, and the program is read and executed by one or more processors of the computer. Such a computer program can be provided to a computer via a non-temporary computer-readable storage medium that can be connected to the system bus of the computer, or it can be provided to the computer via a network. Non-temporary computer-readable storage media include any type of disk such as a magnetic disk (floppy disk (registered trademark), hard disk drive (HDD)), optical disk (CD-ROM, DVD disk, Blu-ray disk, etc.), read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic card, flash memory, or optical card, etc. Any type of medium suitable for storing electronic instructions. Description of the label

[0093] 1…Evaluation device 11…Control Unit 12… Storage 13…Input and output section

Claims

1. An information processing device comprising a control unit, The control unit generates an evaluation result for evaluating the degree of obstruction of the field of view caused by the object for a monitoring camera arranged in the prescribed space, based on structure data related to the structure existing in the prescribed space and object data related to the object moving in the prescribed space.

2. The information processing device according to claim 1, in, The control unit calculates, as the evaluation result, an evaluation value whose value becomes higher as the ratio of the area blocked by the object in the field of view of the monitoring camera decreases.

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

4. The information processing device according to claim 2 or 3, in, The control unit evaluates the arrangement pattern of the plurality of monitoring cameras by integrating the plurality of evaluation values ​​respectively corresponding to the plurality of monitoring cameras.

5. The information processing device according to claim 4, in, The control unit determines the arrangement of the plurality of monitoring cameras in an arrangement pattern in which a total of the plurality of evaluation values ​​does not exceed a predetermined value.

6. The information processing device according to claim 1, in, The object data is data defining the motion of the plurality of objects over time.

7. The information processing device according to claim 6, in, The control unit simulates the 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.

8. The information processing device according to claim 7, in, The control unit calculates, as the evaluation result, an evaluation value whose value becomes higher as the ratio of the area blocked by the object in the field of view of the monitoring camera decreases.

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

10. The information processing device according to claim 8 or 9, in, The control unit evaluates the arrangement pattern of the plurality of monitoring cameras by integrating the plurality of evaluation values ​​respectively corresponding to the plurality of monitoring cameras.

11. The information processing device according to claim 10, in, The control unit determines the arrangement of the plurality of monitoring cameras in an arrangement pattern in which a total of the plurality of evaluation values ​​does not exceed a predetermined value.

12. The information processing device according to claim 8 or 9, in, The object data further includes data related to a time period during which the object exists in the predetermined space.

13. The information processing device according to claim 12, in, The control unit calculates the evaluation value for each of the different time periods.

14. An information processing method, in, The information processing device performs: A step of acquiring structure data related to a structure existing in a predetermined space; A step of acquiring object data related to an object moving within the specified space; as well as A step of generating, based on the structure data and the object data, an evaluation result of evaluating the degree of shielding of the field of view by the object for a monitoring camera arranged in the predetermined space.

15. The information processing method according to claim 14, in, An evaluation value is calculated as the evaluation result, in which the value becomes higher as the ratio of the area blocked by the object in the field of view of the monitoring camera decreases.

16. The information processing method according to claim 15, in, An evaluation value is calculated as the evaluation result, the lower the ratio of the time during which at least a part of the field of view of the monitoring camera is blocked by the object relative to a predetermined time width, and the higher the value is.

17. The information processing method according to claim 15, in, The method further includes the step of evaluating an arrangement pattern of the plurality of monitoring cameras by integrating the plurality of evaluation values ​​respectively corresponding to the plurality of monitoring cameras.

18. The information processing method according to claim 17, in, The arrangement of the plurality of monitoring cameras is determined to be an arrangement pattern in which a total of the plurality of evaluation values ​​does not exceed a predetermined value.

19. The information processing method according to claim 14, in, The object data is data defining the actions of the plurality of objects over time, The movement of the object in the predetermined space is simulated based on the object data, and the evaluation result is generated based on a result of the simulation.

20. A non-transitory storage medium storing a program, The program is for causing a computer to execute the information processing method according to any one of claims 14 to 19.

Images