Information processing device, surveillance camera system, information processing method, and program

Abstract

The present invention provides an information processing device that can reduce the number of markers compared to the case where markers are placed at all vertices of an individual detection area. [Solution] The information processing device 200 according to the present disclosure is an information processing device 200 which sets up a plurality of individual detection areas 12 corresponding to each of a plurality of imaging devices 100 that image the overall detection area 10, in an overall detection area 10 which is wider than the imaging area 16 which is the area imaged by a single imaging device 100, with markers 14 placed at the vertices, such that a composite individual detection area 13 includes the overall detection area 10, and is characterized by comprising: an information processing device receiving unit 215 that receives marker placement information from a plurality of imaging devices 100; a division point setting unit 213 that sets division points 24 that constitute the vertices of the plurality of individual detection areas 12 in the overall detection area 10; and an individual detection area setting unit 214 that sets up a plurality of individual detection areas 12 based on the division point placement information and marker placement information.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, a surveillance camera system, an information processing method, and a program.

Background Art

[0002] When detecting an object using an imaging device such as a surveillance camera, the object is not detected over the entire imaging area that the imaging device can image, but is detected in a detection area set within the imaging area.

[0003] In the invention described in Patent Document 1, a marker is placed within the imaging area, the coordinates of the detection area within the imaging area are set based on the coordinates of the marker, and the object is detected within the set detection area. In the invention described in Patent Document 1, the coordinates of the marker are the coordinates of the vertices of the detection area.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the invention described in Patent Document 1, the case of setting a detection area wider than the imaging area of a single imaging device is not considered. In this case, it is necessary to image the detection area using a plurality of imaging devices. And, when the said detection area is the overall detection area, and the detection areas of each of the plurality of imaging devices are individual detection areas, it is necessary to set the individual detection areas so that the overall detection area is included within the area obtained by combining the individual detection areas of each of the plurality of imaging devices. Applying the invention described in Patent Document 1 in this case has the problem that the number of markers increases because it is necessary to place markers at all vertices of the individual detection areas.

[0006] This disclosure is made to solve the problems described above and aims to provide an information processing device, a surveillance camera system, an information processing method, and a program that can reduce the number of markers compared to the case where markers are placed at all vertices of an individual detection area. [Means for solving the problem]

[0007] The information processing device according to this disclosure is an information processing device in which markers are placed at the vertices, and in an overall detection area that is wider than the imaging area which is the area imaged by a single imaging device, a plurality of individual detection areas are set corresponding to each of the plurality of imaging devices that image the overall detection area, and each of the plurality of imaging devices is set to detect an object, such that a composite individual detection area formed by combining the plurality of individual detection areas includes the overall detection area, and is characterized by comprising: an information processing device receiving unit that receives marker placement information regarding the placement of markers from the plurality of imaging devices; a division point setting unit that sets division points that constitute the vertices of the plurality of individual detection areas in the overall detection area based on the marker placement information; and an individual detection area setting unit that sets a plurality of individual detection areas based on division point placement information and marker placement information regarding the placement of division points.

[0008] Furthermore, the surveillance camera system relating to this disclosure is characterized by comprising the above-mentioned information processing device and a plurality of imaging devices that capture images of the entire detection area.

[0009] Furthermore, the information processing method relating to this disclosure is an information processing method in which markers are placed at the vertices, and in an overall detection area that is wider than the imaging area which is the area imaged by a single imaging device, a plurality of individual detection areas are set corresponding to each of the plurality of imaging devices that image the overall detection area, and each of the plurality of imaging devices is set to detect an object, such that a composite individual detection area formed by combining the plurality of individual detection areas includes the overall detection area, and is characterized by comprising the steps of: an information processing device receiving unit receiving marker placement information relating to the placement of markers from the plurality of imaging devices; a division point setting unit setting division points that constitute the vertices of the plurality of individual detection areas in the overall detection area based on the marker placement information; and an individual detection area setting unit setting a plurality of individual detection areas based on division point placement information relating to the placement of division points and marker placement information.

[0010] Furthermore, the program relating to this disclosure is a program for setting up multiple individual detection areas, which are areas where each of the multiple imaging devices detects an object, in an overall detection area that is wider than the imaging area which is the area imaged by a single imaging device, with markers placed at the vertices, such that a composite individual detection area formed by combining the multiple individual detection areas includes the overall detection area, and is characterized by causing a computer to execute the following steps: an information processing device receiving unit receives marker placement information relating to the placement of markers from the multiple imaging devices; a division point setting unit sets division points that constitute the vertices of the multiple individual detection areas in the overall detection area based on the marker placement information; and an individual detection area setting unit sets up multiple individual detection areas based on division point placement information relating to the placement of division points and marker placement information. [Effects of the Invention]

[0011] According to this disclosure, the information processing device, surveillance camera system, information processing method, and program can reduce the number of markers compared to the case where markers are placed at all vertices of individual detection areas. [Brief explanation of the drawing]

[0012] [Figure 1] This is a diagram showing the configuration of the surveillance camera system according to Embodiment 1. [Figure 2] This is a block diagram showing the configuration of the surveillance camera system according to Embodiment 1. [Figure 3] This is a schematic diagram showing an example of the overall detection area in Embodiment 1. [Figure 4] This is a schematic diagram showing an example of an individual detection area in Embodiment 1. [Figure 5] This is a schematic diagram showing an example of the imaging area of ​​the imaging device according to Embodiment 1. [Figure 6] This is a schematic diagram showing an example of a composite imaging area in Embodiment 1. [Figure 7] This is a schematic diagram showing an example of a shared imaging area in Embodiment 1. [Figure 8] This is a schematic diagram showing an example of a non-shared imaging area in Embodiment 1. [Figure 9] This is a schematic diagram showing an example of a composite individual detection area in Embodiment 1. [Figure 10] This is a schematic diagram showing an example of a method for setting division points in Embodiment 1. [Figure 11] This is a schematic diagram showing an example of an area where the non-shared imaging area and the overall detection area overlap in Embodiment 1. [Figure 12] Block diagram showing hardware configuration examples for each configuration of Embodiment 1. [Figure 13] This is a flowchart showing the processing flow of the surveillance camera system according to Embodiment 1. [Figure 14] This is a schematic diagram showing another example of the division point setting method of Embodiment 1. [Figure 15] This is a schematic diagram showing another example of the individual detection area in Embodiment 1. [Figure 16] This is a block diagram showing the configuration of the surveillance camera system according to Embodiment 2. [Figure 17] This is a schematic diagram showing the method for updating the division points based on likelihood in Embodiment 2. [Figure 18] It is a flowchart showing the processing flow of the monitoring camera system according to Embodiment 2.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, the monitoring camera system according to the embodiment will be described with reference to the drawings. The following embodiments are merely examples, and it is possible to appropriately combine the embodiments and appropriately change each embodiment. In the figures, the same components are denoted by the same reference numerals.

[0014] Embodiment 1. The monitoring camera system 1000 in Embodiment 1 will be described with reference to FIGS. 1 and 2. FIG. 1 is a configuration diagram of the monitoring camera system 1000 according to Embodiment 1. Further, FIG. 2 is a block diagram showing the configuration of the monitoring camera system 1000 according to Embodiment 1.

[0015] As shown in FIG. 1, the monitoring camera system 1000 includes a plurality of imaging devices 100 and an information processing device 200. Each of the plurality of imaging devices 100 is connected to the information processing device 200 via a local network 300. Hereinafter, when not distinguishing the first imaging device 100a, the second imaging device 100b, etc. which are the plurality of imaging devices 100, they are simply referred to as the imaging device 100. Also, the number of the plurality of imaging devices 100 is not particularly limited and any number can be used.

[0016] As shown in FIG. 2, the imaging device 100 includes an imaging unit 101, a marker detection unit 102, an object detection unit 103, an area determination unit 104, an imaging device side transmission unit 105, and an imaging device side reception unit 106. Further, the information processing device 200 includes a coordinate storage unit 211, a coordinate conversion unit 212, a division point setting unit 213, an individual detection area setting unit 214, an information processing device side reception unit 215, and an information processing device side transmission unit 216.

[0017] Figure 3 is a schematic diagram showing an example of the overall detection area 10 of Embodiment 1. The surveillance camera system 1000 of Embodiment 1, as shown in Figure 3, targets the detection of objects in an overall detection area 10 that is larger than the imaging area 16, which is the area captured by a single imaging device 100. In Figure 3, the hatched area is the overall detection area 10. Markers 14 are placed at the vertices of the overall detection area 10. In Figure 3, there are a total of four markers 14: the first marker 14a, the second marker 14b, the third marker 14c, and the fourth marker 14d, and the shape of the overall detection area 10 with the markers 14 as vertices is a rectangle. Furthermore, in Figure 3, the imaging device 100 consists of a total of six units: the first imaging device 100a, the second imaging device 100b, the third imaging device 100c, the fourth imaging device 100d, the fifth imaging device 100e, and the sixth imaging device 100f.

[0018] Figure 4 is a schematic diagram showing an example of an individual detection area 12 in Embodiment 1. Multiple individual detection areas 12 are set for each of the multiple imaging devices 100, and each of the multiple imaging devices 100 performs object detection in its corresponding individual detection area 12. In Figure 4, the hatched area is the first individual detection area 12a corresponding to the first imaging device 100a. Similarly, Figure 4 shows the second individual detection area 12b corresponding to the second imaging device 100b, the third individual detection area 12c corresponding to the third imaging device 100c, the fourth individual detection area 12d corresponding to the fourth imaging device 100d, the fifth individual detection area 12e corresponding to the fifth imaging device 100e, and the sixth individual detection area 12f corresponding to the sixth imaging device 100f. Hereafter, when multiple individual detection areas 12 are not distinguished, they will simply be referred to as individual detection areas 12. The method for setting the individual detection areas 12 will be described later.

[0019] The imaging unit 101 consists of a camera lens and the like, and captures the imaging area 16 of the imaging device 100, outputting the captured image to the marker detection unit 102 and the object detection unit 103. The imaging area 16 of the imaging device 100 is the entire area that a single imaging device 100 can capture, and includes the individual detection areas 12 of each of the multiple imaging devices 100. The range of the imaging area 16 is determined by the lens characteristics of the imaging unit 101, and is input in advance to the information processing device 200 by the user of the surveillance camera system 1000.

[0020] Figure 5 is a schematic diagram showing an example of the imaging area 16 of the imaging device 100 of Embodiment 1. In Figure 5, the hatched area is the first imaging area 16a corresponding to the first imaging device 100a. Similarly, Figure 5 shows the second imaging area 16b of the second imaging device 100b, the third imaging area 16c of the third imaging device 100c, the fourth imaging area 16d of the fourth imaging device 100d, the fifth imaging area 16e of the fifth imaging device 100e, and the sixth imaging area 16f of the sixth imaging device 100f.

[0021] Here, the area formed by combining the imaging areas 16 of each of the multiple imaging devices 100 is referred to as the composite imaging area 17. Figure 6 is a schematic diagram showing an example of the composite imaging area 17 in Embodiment 1. In Figure 6, the hatched area is the composite imaging area 17. As shown in Figure 6, the imaging devices 100 are arranged such that the composite imaging area 17 includes the overall detection area 10. Therefore, the marker 14 is arranged so that it is included in the imaging area 16 of at least one of the imaging devices 100.

[0022] The marker detection unit 102 determines whether or not the video input from the imaging unit 101 contains a marker 14. The marker 14 may be a geometric pattern such as an AR marker, and a known marker 14 whose coordinates can be determined from the video may be used. Alternatively, the marker detection unit 102 may store a trained model that has been learned by associating a unique, unknown marker 14 with data that can identify the marker 14, and use this trained model to determine whether or not the video input from the imaging unit 101 contains a marker 14.

[0023] Furthermore, if the video contains marker 14, the marker detection unit 102 determines the coordinates of marker 14 in a local coordinate system with the imaging device 100 as the origin. The method used by the marker detection unit 102 to determine the coordinates of marker 14 can be a known method. For example, the marker detection unit 102 can determine the coordinates of marker 14 in the local coordinate system by determining the distance from the imaging device 100 to marker 14 and the angle it makes with an axis in the local coordinate system, based on the size and shape of marker 14 in the video. The marker detection unit 102 outputs marker placement information regarding the presence or absence of marker 14 in the captured video and the coordinates of marker 14 in the local coordinate system to the imaging device side transmission unit 105. The imaging device side transmission unit 105 then outputs the input marker placement information to the information processing device side receiving unit 215. In other words, the information processing device side receiving unit 215 receives marker placement information regarding the placement of marker 14 from multiple imaging devices 100.

[0024] The object detection unit 103 can detect objects within the imaging area 16 by performing image analysis on the captured video. Target objects include, for example, people, vehicles, animals, and manufactured goods on a factory production line. Known techniques can be used for object detection; for example, the imaging device 100 may use a trained model, which is learned by associating images of objects with ground truth data representing those objects, to detect objects in the imaging area 16. The object detection unit 103 outputs object information about the detected object to the area determination unit 104. The object information includes information indicating that a target object has been detected, and information such as the object's coordinates in the local coordinate system. The object detection unit 103 does not need to output object information to the area determination unit 104 if it has not detected an object. Alternatively, if the object detection unit 103 has not detected an object, it may output information to the area determination unit 104 indicating that no objects exist within the imaging area 16 as object information.

[0025] The area determination unit 104 determines, based on the input object information, whether or not the detected object is located within the individual detection area 12. If the target object is detected within the individual detection area 12, the surveillance camera system 1000 may, for example, issue an alarm using a notification unit (not shown). This allows the surveillance camera system 1000 to, for example, notify a person that the area is a restricted area if it detects a person entering an area where entry is prohibited, such as a museum exhibition hall.

[0026] If a target object is detected within the individual detection area 12, the surveillance camera system 1000 may, for example, count the number of such objects. This allows the surveillance camera system 1000 to count the number of visitors in places where many people gather, such as event venues. It also allows the surveillance camera system 1000 to count the number of workers in large work areas such as factories. Furthermore, it allows the surveillance camera system 1000 to count the number of objects on a factory production line, such as manufactured goods or delivered items like cardboard boxes.

[0027] The information processing device receiving unit 215 outputs the input marker placement information to the coordinate storage unit 211. The coordinate storage unit 211 stores the coordinates of the markers 14 on a local coordinate system with each of the multiple imaging devices 100 as the origin, as marker placement information, and outputs it to the coordinate transformation unit 212.

[0028] The coordinate transformation unit 212 transforms the local coordinate system, with each of the multiple imaging devices 100 as its origin, into a global coordinate system that uses marker placement information to represent the coordinates of all the multiple imaging devices 100 and all the markers 14 that constitute the vertices of the overall detection area 10, viewed from a common origin. The coordinate transformation unit 212 is pre-inputted by the user with information regarding the coordinates of the multiple imaging devices 100 on the global coordinate system, and the field of view of each imaging unit 101 of the multiple imaging devices 100. The coordinate transformation unit 212 then uses the information input by the user and the marker placement information regarding the placement of the markers 14 on the local coordinate system, with each of the multiple imaging devices 100 as its origin, to represent the coordinates of the markers 14 on the global coordinate system. The coordinate transformation unit 212 then connects adjacent markers 14 to set up the overall detection area 10 with all the markers 14 as its vertices. Furthermore, the coordinate transformation unit 212 outputs to the division point setting unit 213 overall detection area information relating to the coordinates of the overall detection area 10 on the global coordinate system, and marker placement information relating to the placement of markers 14 on the global coordinate system.

[0029] The division point setting unit 213 sets division points 24 that constitute the vertices of multiple individual detection areas 12 in the overall detection area 10, based on marker placement information and overall detection area information. Below, an example of how the division point setting unit 213 sets division points will be described. Note that the division points 24 are not actually placed, but are virtual points set by the division point setting unit 213 on the global coordinate system.

[0030] Figure 7 is a schematic diagram showing an example of a shared imaging area 20 in Embodiment 1. As shown in Figure 7, the imaging device 100 is arranged such that it has an area shared by its own imaging area 16 and the imaging area 16 of an adjacent imaging device 100. That is, the imaging areas 16 of multiple imaging devices 100 each have an area shared with each other, and this area is called the shared imaging area 20. In Figure 7, the hatched area is the shared imaging area 20.

[0031] Furthermore, among the imaging areas 16 of each of the multiple imaging devices 100, the areas other than the shared imaging area 20 are called non-shared imaging areas 22. Figure 8 is a schematic diagram showing an example of a non-shared imaging area 22 in Embodiment 1. In Figure 8, the hatched area is the non-shared imaging area 22.

[0032] As described above, the range of each imaging area 16 of the multiple imaging devices 100 is pre-input into the information processing device 200 by the user. Therefore, the division point setting unit 213 can determine the range of each imaging area 16 of the multiple imaging devices 100 in the global coordinate system using the coordinates of the multiple imaging devices 100 in the global coordinate system and the field of view information of each imaging unit 101 of the multiple imaging devices 100, which are input by the user. Then, the division point setting unit 213 uses the range of each imaging area 16 of the multiple imaging devices 100 to determine the range of the shared imaging area 20 in the global coordinate system as shown in Figure 7.

[0033] Here, the area formed by combining multiple individual detection areas 12 is referred to as the composite individual detection area 13. Figure 9 is a schematic diagram showing an example of the composite individual detection area 13 in Embodiment 1. In Figure 9, the hatched area is the composite individual detection area 13. In Figure 9, the composite individual detection area 13 overlaps with the overall detection area 10. That is, as shown in Figure 9, the surveillance camera system 1000 sets the multiple individual detection areas 12 so that the composite individual detection area 13 includes the overall detection area 10. In other words, the division point setting unit 213 sets the division point 24 so that the composite individual detection area 13, which is a combination of multiple individual detection areas 12 set by the individual detection area setting unit 214, includes the overall detection area 10. As a result, the surveillance camera system 1000 can suppress the occurrence of areas in the overall detection area 10 where objects cannot be detected because they are not included in any of the individual detection areas 12.

[0034] Figure 10 is a schematic diagram showing an example of the division point setting method of Embodiment 1. As shown in Figure 10, the division point setting unit 213 sets division points 24 in the hatched shared imaging area 20 of the overall detection area 10, and uses the coordinates of the set division points 24 in the global coordinate system as division point placement information regarding the placement of division points 24. The division point setting unit 213 then outputs the division point placement information and marker placement information to the individual detection area setting unit 214. Based on the division point placement information and marker placement information, the individual detection area setting unit 214 sets a plurality of individual detection areas 12 as shown in Figure 4.

[0035] Furthermore, the division point setting unit 213 sets division points 24 so that the multiple individual detection areas 12 set by the individual detection area setting unit 214 do not overlap with each other. That is, as shown in Figure 4, the division point setting unit 213 sets division points 24 so that the first individual detection area 12a, the second individual detection area 12b, the third individual detection area 12c, the fourth individual detection area 12d, the fifth individual detection area 12e, and the sixth individual detection area 12f do not overlap with each other.

[0036] Furthermore, the division point setting unit 213 sets division points 24 such that the multiple individual detection areas 12 set by the individual detection area setting unit 214 include the area 26 where the non-shared imaging area 22 and the overall detection area 10 overlap. Figure 11 is a schematic diagram showing an example of the area 26 where the non-shared imaging area 22 and the overall detection area 10 overlap in Embodiment 1. In Figure 11, the hatched area is the area 26 where the non-shared imaging area 22 and the overall detection area 10 overlap. That is, the division point setting unit 213 sets division points 24 such that the multiple individual detection areas 12 set by the individual detection area setting unit 214 include the area 26 where the non-shared imaging area 22 and the overall detection area 10 overlap, which is hatched in Figure 11.

[0037] For example, as shown in Figure 10, the division point setting unit 213 sets the first division point 24a, the second division point 24b, the third division point 24c, the fourth division point 24d, the fifth division point 24e, and the sixth division point 24f on line segments connecting adjacent vertices of the overall detection area 10 in the shared imaging area 20.

[0038] Specifically, as shown in Figure 10, the division point setting unit 213 sets the first division point 24a on the line segment connecting the first marker 14a and the fourth marker 14d in the shared imaging area 20 shared by the first imaging area 16a and the sixth imaging area 16f. The division point setting unit 213 also sets the second division point 24b on the line segment connecting the first marker 14a and the second marker 14b in the shared imaging area 20 shared by the first imaging area 16a and the second imaging area 16b. The division point setting unit 213 also sets the third division point 24c on the line segment connecting the first marker 14a and the second marker 14b in the shared imaging area 20 shared by the second imaging area 16b and the third imaging area 16c. Furthermore, the division point setting unit 213 sets the fourth division point 24d on the line segment connecting the second marker 14b and the third marker 14c in the shared imaging area 20 shared by the third imaging area 16c and the fourth imaging area 16d. Furthermore, the division point setting unit 213 sets the fifth division point 24e on the line segment connecting the third marker 14c and the fourth marker 14d in the shared imaging area 20 shared by the fourth imaging area 16d and the fifth imaging area 16e. Furthermore, the division point setting unit 213 sets the sixth division point 24f on the line segment connecting the third marker 14c and the fourth marker 14d in the shared imaging area 20 shared by the fifth imaging area 16e and the sixth imaging area 16f.

[0039] Furthermore, in Figure 10, the division point 24 is set as the midpoint of a line segment cut out by the shared imaging area 20 from among line segments connecting adjacent vertices in the overall detection area 10, but is not limited to this. In other words, the division point 24 can be set on the line segment cut out by the shared imaging area 20.

[0040] Furthermore, as shown in Figure 10, the division point setting unit 213 sets a seventh division point 24g and an eighth division point 24h in the shared imaging area 20 in an area shared by the imaging areas 16 of at least three of the multiple imaging devices 100.

[0041] Specifically, the division point setting unit 213 sets the seventh division point 24g in the shared imaging area 20 shared by the first imaging area 16a, the second imaging area 16b, the fifth imaging area 16e, and the sixth imaging area 16f. The division point setting unit 213 also sets the eighth division point 24h in the shared imaging area 20 shared by the second imaging area 16b, the third imaging area 16c, the fourth imaging area 16d, and the fifth imaging area 16e.

[0042] Furthermore, in Figure 10, the division point 24 is set in the center of an area shared by the imaging areas 16 of at least three of the multiple imaging devices 100, but is not limited to this. In other words, the division point 24 only needs to be set within the area shared by the imaging areas 16 of at least three of the multiple imaging devices 100.

[0043] As described above, the individual detection area setting unit 214 sets up multiple individual detection areas 12 based on the division point placement information and marker placement information. For example, as shown in Figure 4, the individual detection area setting unit 214 sets up the first individual detection area 12a, the third individual detection area 12c, the fourth individual detection area 12d, and the sixth individual detection area 12f by connecting the marker 14 and the division point 24 as vertices. Also, for example, as shown in Figure 4, the individual detection area setting unit 214 sets up the second individual detection area 12b and the fifth individual detection area 12e by connecting only the division point 24 among the marker 14 and the division point 24 as vertices.

[0044] The individual detection area setting unit 214 then converts the multiple individual detection areas 12 set on the global coordinate system to a local coordinate system with the imaging device 100 corresponding to each of the multiple individual detection areas 12 as the origin, and outputs it as individual detection area information to the information processing device side transmission unit 216. The information processing device side transmission unit 216 outputs the individual detection area information to the imaging device side reception unit 106. At this time, the information processing device side transmission unit 216 outputs the individual detection area information corresponding to the imaging device 100 that outputs the individual detection area information from the input individual detection area information to the imaging device side reception unit 106 of the said imaging device 100. The imaging device side reception unit 106 outputs the input individual detection area information to the area determination unit 104.

[0045] As described above, the area determination unit 104 determines whether or not the detected object is located within the individual detection area 12 based on the object information and individual detection area information.

[0046] Next, we will describe hardware configuration examples for each component in Embodiment 1, namely the marker detection unit 102, object detection unit 103, area determination unit 104, imaging device side transmission unit 105, imaging device side reception unit 106, coordinate storage unit 211, division point setting unit 213, individual detection area setting unit 214, information processing device side reception unit 215, and information processing device side transmission unit 216. Figure 12 is a block diagram showing hardware configuration examples for each component in Embodiment 1. Each component in Embodiment 1 may be a dedicated hardware processing circuit 90 as shown in Figure 12A, or a processor 92 that executes a program stored in memory 94 as shown in Figure 12B.

[0047] As shown in Figure 12A, when each configuration in Embodiment 1 is dedicated hardware, the processing circuit 90 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-programmable Gate Array), or a combination thereof. Each function of each configuration in Embodiment 1 may be realized by the processing circuit 90, or the functions of each part may be realized by a single processing circuit 90.

[0048] As shown in Figure 12B, when each configuration in Embodiment 1 is a processor 92, the functions of each part are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in memory 94. The processor 92 realizes each function of each configuration in Embodiment 1 by reading and executing the program stored in memory 94. In other words, each configuration in Embodiment 1 is equipped with memory 94 for storing a program that, when executed by the processor 92, will result in the execution of the steps shown in Figures 13 and 18, which will be described later. These programs can also be said to cause the computer to execute the procedures or methods of each configuration in Embodiment 1.

[0049] Here, processor 92 refers to, for example, a CPU (Central Processing Unit), processing unit, arithmetic unit, processor, microprocessor, microcomputer, or DSP (Digital Signal Processor). Memory 94 may be, for example, a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable ROM), or EEPROM (Electrically EPROM), or a magnetic disk such as a hard disk or flexible disk, or an optical disk such as a MiniDisc, CD (Compact Disc), or DVD (Digital Versatile Disc).

[0050] Furthermore, for each function of each configuration in Embodiment 1, some may be implemented with dedicated hardware, and some may be implemented with software or firmware. In this way, the processing circuit 90 in Embodiment 1 can implement the above-mentioned functions by hardware, software, firmware, or a combination thereof.

[0051] Next, the processing flow of the surveillance camera system 1000 in Embodiment 1 will be described. Figure 13 is a flowchart of the processing flow of the surveillance camera system 1000 in Embodiment 1. In the preceding steps of the processing flow of the surveillance camera system 1000, the user inputs information. The information input by the user includes the internal parameters of the imaging device 100, the coordinates of the imaging device 100 in the global coordinate system, the field of view of the imaging unit 101 of the imaging device 100, and connection information such as the IP address of the imaging device 100. The internal parameters are specific to the lens of the imaging unit 101 of the imaging device 100 and consist of the focal length, optical center, shear coefficient, and distortion coefficient of the lens. The internal parameters can be determined by known methods such as camera calibration. Therefore, since the range of the imaging area 16 of the imaging device 100 can be determined by inputting the internal parameters, the information input by the user includes the range of the imaging area 16 determined by the lens characteristics of the imaging unit 101.

[0052] In step S101, the information processing device receiving unit 215 requests the imaging device 100 to output marker placement information via the local network 300.

[0053] In step S102, the marker detection units 102 of all imaging devices 100 that received a request in step S101 determine whether or not the video input from the imaging unit 101 contains the marker 14.

[0054] In step S103, if the video input from the imaging unit 101 contains the marker 14 (step S102: YES), the marker detection unit 102 determines the coordinates of the marker 14 in a local coordinate system with the imaging device 100 as the origin, and outputs marker placement information regarding the coordinates of the marker 14 in the local coordinate system to the imaging device side transmission unit 105. If the video input from the imaging unit 101 does not contain the marker 14 (step S102: NO), the marker detection unit 102 outputs marker placement information indicating this to the imaging device side transmission unit 105, and proceeds to step S104.

[0055] In step S104, the imaging device side transmitting unit 105 outputs marker placement information to the information processing device side receiving unit 215. That is, the information processing device side receiving unit 215 receives marker placement information regarding the placement of markers 14 from multiple imaging devices 100. The information processing device side receiving unit 215 then outputs the marker placement information to the coordinate storage unit 211. The coordinate storage unit 211 stores the coordinates of the markers 14 on a local coordinate system with each of the multiple imaging devices 100 as the origin as marker placement information and outputs it to the coordinate transformation unit 212.

[0056] In step S105, the coordinate transformation unit 212 transforms the local coordinate system, which has each of the multiple imaging devices 100 as its origin, into a global coordinate system that uses marker placement information to represent the multiple imaging devices 100 and all markers 14 that constitute the vertices of the overall detection area 10 in coordinates viewed from a common origin. The coordinate transformation unit 212 then represents the coordinates of the markers 14 on the global coordinate system and connects adjacent markers 14 to set up the overall detection area 10 with all markers 14 as its vertices. The coordinate transformation unit 212 also outputs the overall detection area information and marker placement information regarding the arrangement of the markers 14 on the global coordinate system to the division point setting unit 213.

[0057] In step S106, the division point setting unit 213 uses the range of the imaging area 16 of each of the multiple imaging devices 100 to determine the range of the shared imaging area 20 on the global coordinate system as shown in Figure 5.

[0058] In step S107, the division point setting unit 213 sets division points 24 that constitute the vertices of multiple individual detection areas 12 in the overall detection area 10, based on the marker placement information. The division point setting unit 213 then outputs the coordinates of the set division points 24 in the global coordinate system, along with division point placement information and marker placement information regarding the placement of the division points 24, to the individual detection area setting unit 214.

[0059] In step S108, the individual detection area setting unit 214 sets up multiple individual detection areas 12 based on the division point placement information and marker placement information. The individual detection area setting unit 214 then converts the multiple individual detection areas 12 set up on the global coordinate system to a local coordinate system with the imaging device 100 corresponding to each of the multiple individual detection areas 12 as the origin, and outputs the individual detection area information to the information processing device side transmission unit 216. The information processing device side transmission unit 216 outputs the individual detection area information to the imaging device side reception unit 106. The imaging device side reception unit 106 outputs the input individual detection area information to the area determination unit 104.

[0060] In step S109, the object detection unit 103 detects objects within the imaging area 16 by performing image analysis on the video captured by the imaging unit 101. The object detection unit 103 then outputs object information about the detected objects to the area determination unit 104. Note that step S109 is not limited to this order and may be performed before step S101, or between any of steps S102 and S108.

[0061] In step S110, the area determination unit 104 determines whether or not the detected object is located within the individual detection area 12, based on the object information and the individual detection area information.

[0062] In step S111, if it is determined that the detected object is located within the individual detection area 12 (step S110: YES), the area determination unit 104 may output a message to that effect to, for example, a notification unit (not shown), and the notification unit may issue an alarm. Alternatively, the area determination unit 104 may count the number of such objects. If it is determined that the detected object is not located within the individual detection area 12 (step S110: NO), step S111 is not performed. This concludes the explanation of the processing flow of the surveillance camera system 1000 in Embodiment 1.

[0063] Thus, the information processing device 200 in Embodiment 1 is an information processing device 200 in which markers 14 are placed at the vertices, and in an overall detection area 10 which is wider than the imaging area 16 which is the area imaged by a single imaging device 100, a plurality of individual detection areas 12 are set corresponding to each of the plurality of imaging devices 100 which image the overall detection area 10, and each of the plurality of imaging devices 100 which detects an object, and a composite individual detection area 13 formed by combining the plurality of individual detection areas 12 includes the overall detection area 10. The information processing device 200 includes an information processing device side receiving unit 215 which receives marker placement information regarding the placement of markers 14 from the plurality of imaging devices 100, a division point setting unit 213 which sets division points 24 which constitute the vertices of the plurality of individual detection areas 12 in the overall detection area 10 based on the marker placement information, and an individual detection area setting unit 214 which sets the plurality of individual detection areas 12 based on division point placement information regarding the placement of division points 24 and marker placement information.

[0064] With the above configuration, the information processing device 200 of Embodiment 1 can set individual detection areas 12 by using division points 24 instead of markers 14 for some of the vertices, thus reducing the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12. In addition, since the composite individual detection area 13 is set to include the overall detection area 10, the information processing device 200 of Embodiment 1 can suppress the occurrence of areas in the overall detection area 10 where objects cannot be detected because they are not included in any of the individual detection areas 12.

[0065] Furthermore, the division point setting unit 213 of Embodiment 1 sets division points 24 in the shared imaging area 20, which is an area shared by the respective imaging areas 16 of the multiple imaging devices 100. The multiple individual detection areas 12 do not overlap with each other and include an area 26 where the non-shared imaging area 22, which is an area other than the shared imaging area 20 among the respective imaging areas 16 of the multiple imaging devices 100, and the overall detection area 10 overlap.

[0066] With the above configuration, the information processing device 200 of Embodiment 1 can set individual detection areas 12 by using division points 24 instead of markers 14 for some of the vertices, thereby reducing the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12. In addition, since the multiple individual detection areas 12 of Embodiment 1 do not overlap with each other, the information processing device 200 of Embodiment 1 can suppress the detection of the same object in two or more different individual detection areas 12. As a result, for example, when the information processing device 200 of Embodiment 1 counts the number of detected objects, it can suppress duplicate counting.

[0067] Furthermore, the division point setting unit 213 of Embodiment 1 sets division points 24 in the shared imaging area 20, which is an area shared by the imaging areas 16 of the multiple imaging devices 100, on line segments connecting adjacent vertices of the overall detection area 10, and in areas shared by the imaging areas 16 of at least three of the multiple imaging devices 100. With the above configuration, the information processing device 200 of Embodiment 1 can set individual detection areas 12 by using division points 24 instead of markers 14 for some of the vertices, thereby reducing the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12.

[0068] Furthermore, the individual detection area setting unit 214 of Embodiment 1 sets the individual detection area 12 using only the division points 24 as vertices out of the markers 14 and division points 24. With the above configuration, the information processing device 200 of Embodiment 1 can reduce the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12.

[0069] Furthermore, the individual detection area setting unit 214 of Embodiment 1 sets individual detection areas 12 with the markers 14 and division points 24 as vertices. With the above configuration, the information processing device 200 of Embodiment 1 can reduce the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12.

[0070] Furthermore, the surveillance camera system 1000 of Embodiment 1 includes an information processing device 200 and a plurality of imaging devices 100. With the above configuration, the surveillance camera system 1000 of Embodiment 1 can reduce the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12.

[0071] Furthermore, the information processing method of Embodiment 1 is an information processing method in which a marker 14 is placed at the vertices, and in an overall detection area 10 which is wider than the imaging area 16 which is the area imaged by a single imaging device 100, a plurality of individual detection areas 12 are set corresponding to each of the plurality of imaging devices 100 which image the overall detection area 10, and each of the plurality of imaging devices 100 which detects an object, and a composite individual detection area 13 formed by combining the plurality of individual detection areas 12 includes the overall detection area 10, and comprises the steps of: an information processing device receiving unit 215 receiving marker placement information regarding the placement of markers 14 from the plurality of imaging devices 100; a division point setting unit 213 setting division points 24 that constitute the vertices of the plurality of individual detection areas 12 in the overall detection area 10 based on the marker placement information; and an individual detection area setting unit 214 setting a plurality of individual detection areas 12 based on division point placement information and marker placement information regarding the placement of division points 24. By adopting the above configuration, the information processing method of Embodiment 1 can reduce the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12.

[0072] Furthermore, the program of Embodiment 1 is a program for setting up multiple individual detection areas 12, which correspond to each of the multiple imaging devices 100 that image the overall detection area 10, and which are areas where each of the multiple imaging devices 100 detects an object, in an overall detection area 10 that is wider than the imaging area 16 which is the area imaged by a single imaging device 100, with markers 14 placed at the vertices, so that a composite individual detection area 13 formed by combining the multiple individual detection areas 12 includes the overall detection area 10. The program causes the computer to execute the following steps: an information processing device receiving unit 215 receives marker placement information regarding the placement of markers 14 from the multiple imaging devices 100; a division point setting unit 213 sets division points 24 that constitute the vertices of the multiple individual detection areas 12 in the overall detection area 10 based on the marker placement information; and an individual detection area setting unit 214 sets up the multiple individual detection areas 12 based on division point placement information and marker placement information regarding the placement of division points 24. By adopting the above configuration, the program of Embodiment 1 can reduce the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12.

[0073] Furthermore, the overall detection area 10 and the individual detection areas 12 are not limited to quadrilaterals; any polygon with vertices will produce the same effect. In other words, the number of markers 14 and division points 24 is not particularly limited, and any number can be used.

[0074] Figure 14 is a schematic diagram showing another example of the division point setting method of Embodiment 1. In Figure 14, there are a total of five markers 14: a first marker 14a, a second marker 14b, a third marker 14c, a fourth marker 14d, and a fifth marker 14e. The shape of the overall detection area 10, with the markers 14 as vertices, is a pentagon. In this case as well, the division point setting unit 213 sets the division points 24 such that the multiple individual detection areas 12 set by the individual detection area setting unit 214 do not overlap with each other, and that the multiple individual detection areas 12 set by the individual detection area setting unit 214 include an area 26 where the non-shared imaging area 22 and the overall detection area 10 overlap.

[0075] For example, as shown in Figure 14, the division point setting unit 213 sets the first division point 24a, the second division point 24b, the third division point 24c, and the fourth division point 24d on line segments connecting adjacent vertices of the overall detection area 10 in the hatched shared imaging area 20.

[0076] Specifically, in Figure 14, the division point setting unit 213 sets the first division point 24a on the line segment connecting the first marker 14a and the second marker 14b in the shared imaging area 20 shared by the first imaging area 16a and the second imaging area 16b. The division point setting unit 213 also sets the second division point 24b on the line segment connecting the first marker 14a and the second marker 14b in the shared imaging area 20 shared by the second imaging area 16b and the third imaging area 16c. The division point setting unit 213 also sets the third division point 24c on the line segment connecting the fourth marker 14d and the fifth marker 14e in the shared imaging area 20 shared by the third imaging area 16c and the fourth imaging area 16d. Furthermore, the division point setting unit 213 sets the fourth division point 24d on the line segment connecting the fourth marker 14d and the fifth marker 14e in the shared imaging area 20 shared by the fourth imaging area 16d and the first imaging area 16a.

[0077] Furthermore, as shown in Figure 14, the division point setting unit 213 sets a fifth division point 24e and a sixth division point 24f in the hatched shared imaging area 20 in an area shared by the imaging areas 16 of at least three of the multiple imaging devices 100.

[0078] Specifically, the division point setting unit 213 sets a fifth division point 24e in the shared imaging area 20 shared by the first imaging area 16a, the second imaging area 16b, and the fourth imaging area 16d. The division point setting unit 213 also sets a sixth division point 24f in the shared imaging area 20 shared by the second imaging area 16b, the third imaging area 16c, and the fourth imaging area 16d.

[0079] In this case as well, the individual detection area setting unit 214 sets up a plurality of individual detection areas 12 based on the division point placement information and the marker placement information. Figure 15 is a schematic diagram showing another example of the individual detection areas 12 in Embodiment 1. For example, as shown in Figure 15, the individual detection area setting unit 214 sets up the first individual detection area 12a and the third individual detection area 12c by connecting the marker 14 and the division point 24 as vertices. Alternatively, as shown in Figure 15, the individual detection area setting unit 214 sets up the second individual detection area 12b and the fourth individual detection area 12d by connecting only the division point 24 of the marker 14 and division point 24 as vertices. In this case, as shown in Figure 15, the shape of the first individual detection area 12a is a pentagon, the shape of the second individual detection area 12b is a square, the shape of the third individual detection area 12c is a hexagon, and the shape of the fourth individual detection area 12d is a square.

[0080] Furthermore, while it is assumed that the multiple individual detection areas 12 do not overlap with each other, this is not a limitation. That is, the multiple individual detection areas 12 may have areas that overlap with each other. For example, if the surveillance camera system 1000 detects human intrusion in an area where human entry is prohibited, such as a museum exhibition hall, and notifies the person that the area is a restricted area, notification is possible even if the multiple individual detection areas 12 have areas that overlap with each other.

[0081] Furthermore, while the coordinates of the imaging device 100 on the global coordinate system and the field of view of the imaging unit 101 of the imaging device 100 are input by the user, the system is not limited to these. For example, the surveillance camera system 1000 may use GPS (Global Positioning System) or the like to determine the coordinates of the imaging device 100 on the global coordinate system. Alternatively, for example, the surveillance camera system 1000 may use a gyro sensor or the like to determine the field of view of the imaging unit 101 of the imaging device 100.

[0082] Furthermore, although it has been assumed that the information processing device 200 is located outside the imaging device 100, this is not the only limitation. For example, an information processing device 200 may be located inside each of the multiple imaging devices 100, and each function of the information processing device 200 may be executed inside the imaging device 100.

[0083] Embodiment 2. The surveillance camera system 1001 in Embodiment 2 will now be described. The surveillance camera system 1001 in Embodiment 2 differs from the surveillance camera system 1000 in Embodiment 1 in that it updates the arrangement of division points 24 based on the likelihood representing the object-likeness of an object, and sets up a plurality of individual detection areas 12 based on the updated division point arrangement information and marker arrangement information. Components similar to those in Embodiment 1 are denoted by the same reference numerals. Furthermore, a detailed explanation of components similar to those in Embodiment 1 will be omitted, and the differences from Embodiment 1 will be described mainly.

[0084] Figure 16 is a block diagram showing the configuration of the surveillance camera system 1001 of Embodiment 2. The information processing device 201 of Embodiment 2 includes a coordinate comparison unit 217 in addition to the configuration of the information processing device 200 of Embodiment 1.

[0085] The object detection unit 103 detects objects by performing image analysis on the captured video. At this time, the object detection unit 103 calculates the likelihood of an object being an object and includes it in the object information. Here, the likelihood is a value that represents the plausibility of an object, and it refers to the image of the detected object and the ground truth image data representing the object, indicating the probability that the detected object matches an object that has been learned as ground truth data.

[0086] The object detection unit 103 outputs the object information to the imaging device side transmission unit 105 in addition to the area determination unit 104. The imaging device side transmission unit 105 outputs the marker placement information and object information to the information processing device side receiving unit 215. The information processing device side receiving unit 215 outputs the input marker placement information and object information to the coordinate storage unit 211. The coordinate storage unit 211 stores the marker placement information and object information and outputs it to the coordinate transformation unit 212.

[0087] The coordinate transformation unit 212, similar to Embodiment 1, transforms the local coordinate system, with each of the multiple imaging devices 100 as the origin, into a global coordinate system using marker placement information, in which all markers 14 constituting the vertices of the multiple imaging devices 100 and the overall detection area 10 are represented in coordinates viewed from a common origin. It then connects adjacent markers 14 to set up the overall detection area 10 with all markers 14 as its vertices. At this time, the coordinate transformation unit 212 uses object information to represent the coordinates of the detected object on the global coordinate system. The coordinate transformation unit 212 then includes the overall detection area information and the object's coordinates on the global coordinate system in the object information and outputs it to the coordinate comparison unit 217 and the division point setting unit 213.

[0088] When the coordinate comparison unit 217 receives multiple object information inputs from the coordinate transformation unit 212 that include the coordinates of objects detected by multiple imaging devices 100, it determines whether the coordinates included in the multiple object information are the same. If the coordinates are the same, the coordinate comparison unit 217 determines that the objects detected by the multiple imaging devices 100 are the same object located in the shared imaging area 20, and outputs information to that effect to the division point setting unit 213. If the coordinates are not the same, the coordinate comparison unit 217 determines that the objects detected by the multiple imaging devices 100 are not the same object. Here, considering the case where the objects move, the coordinate comparison unit 217 may also determine that the objects detected by the multiple imaging devices 100 are the same object located in the shared imaging area 20 if the coordinates differ within a range that can be approximated as matching. The coordinate comparison unit 217 includes information in the object information indicating whether the objects detected by the multiple imaging devices 100 are the same object located in the shared imaging area 20, and outputs it to the division point setting unit 213.

[0089] The accuracy of object detection by the object detection unit 103 is affected by the presence or absence of obstacles and the coordinates of the target object, and the range of the individual detection area 12 may not be appropriate. Therefore, the division point setting unit 213 receives information from the coordinate comparison unit 217 indicating that the objects detected by multiple imaging devices 100 are the same object located in the shared imaging area 20, and if the object is located within the overall detection area 10, it compares the likelihood of the object calculated by each of the multiple imaging devices 100 that detected the object, which is included in the input object information.

[0090] Then, the division point setting unit 213 updates the arrangement of the division points 24 and the division point arrangement information so that the object is included in the individual detection area 12 corresponding to the imaging device 100 that has calculated a higher likelihood among the multiple imaging devices 100, based on the likelihood that the object is indeed an object. A specific example of the division point update method is shown below.

[0091] Figure 17 is a schematic diagram showing the likelihood-based method for updating the division points 24 in Embodiment 2. Figure 17 illustrates an object 28 within a shared imaging area that is detected by the first imaging device 100a and the second imaging device 100b and determined to be the same object in the shared imaging area 20 shared by the first imaging area 16a and the second imaging area 16b. In the state before the division points 24 are changed, the object 28 within the shared imaging area is located outside the first individual detection area 12a, whose vertices are the first division point 24a, the second division point 24b, the seventh division point 24g, and the first marker 14a, and is located within the second individual detection area 12b, whose vertices are the second division point 24b, the third division point 24c, the seventh division point 24g, and the eighth division point 24h.

[0092] Here, the likelihood of the object 28 in the shared imaging area calculated by the object detection unit 103 of the first imaging device 100a is assumed to be higher than the likelihood of the object 28 in the shared imaging area calculated by the object detection unit 103 of the second imaging device 100b. In this case, the division point setting unit 213 determines that the first imaging device 100a can detect the object 28 in the shared imaging area with higher accuracy than the second imaging device 100b. The division point setting unit 213 then updates the arrangement of the second division point 24b and the seventh division point 24g to the arrangement of the second modified division point 24b1 and the seventh modified division point 24g1, respectively, so that the object 28 in the shared imaging area is located within the first individual detection area 12a corresponding to the first imaging device 100a. Accordingly, the division point setting unit 213 updates the division point arrangement information to show the arrangement of the modified division points 24 and outputs it to the individual detection area setting unit 214.

[0093] The individual detection area setting unit 214 sets up multiple individual detection areas 12 based on the updated division point placement information and marker placement information. Specifically, in Figure 17, the individual detection area setting unit 214 sets up the first modified individual detection area 12a1 with the first division point 24a, the second modified division point 24b1, the seventh modified division point 24g1, and the first marker 14a as its vertices, and sets up the second modified individual detection area 12b1 with the second modified division point 24b1, the third division point 24c, the seventh modified division point 24g1, and the eighth division point 24h as its vertices. As a result, the object 28 in the shared imaging area will be located within the individual detection area 12 of the first imaging device 100a, which is calculated to have a higher likelihood than the second imaging device 100b.

[0094] Furthermore, in the second embodiment as well, the division point setting unit 213 sets the division point 24 such that the composite individual detection area 13, which is a combination of multiple individual detection areas 12 set by the individual detection area setting unit 214 after the division point 24 is updated, includes the overall detection area 10. As a result, the surveillance camera system 1001 can suppress the occurrence of areas in the overall detection area 10 where objects cannot be detected because they are not included in any of the individual detection areas 12.

[0095] Next, the processing flow of the surveillance camera system 1001 in Embodiment 2 will be described. Figure 18 is a flowchart showing the processing flow of the surveillance camera system 1001 in Embodiment 2. Note that, prior to the processing flow of Embodiment 2 shown in Figure 18, the processing flow of Embodiment 1 shown in Figure 9, namely the setting of the division points 24 by the division point setting unit 213 and the setting of the individual detection areas 12 by the individual detection area setting unit 214, is performed in advance.

[0096] In step S201, the object detection unit 103 detects an object by performing image analysis on the video captured by the imaging unit 101 within the imaging area 16, and calculates the likelihood of the object being an object. The object detection unit 103 then outputs the coordinates of the object in a local coordinate system with the imaging device 100 as the origin, and the likelihood of the object, as object information to the imaging device side transmission unit 105.

[0097] In step S202, the imaging device side transmitting unit 105 outputs marker placement information and object information to the information processing device side receiving unit 215. That is, the information processing device side receiving unit 215 receives marker placement information and object information from the imaging device side transmitting unit 105. The information processing device side receiving unit 215 outputs the input marker placement information and object information to the coordinate storage unit 211. The coordinate storage unit 211 stores the marker placement information and object information and outputs it to the coordinate transformation unit 212.

[0098] In step S203, the coordinate transformation unit 212 transforms the local coordinate system, which has each of the multiple imaging devices 100 as its origin, into a global coordinate system that uses marker placement information to represent the coordinates of all markers 14 constituting the vertices of the multiple imaging devices 100 and the overall detection area 10 from a common origin, and uses object information to represent the coordinates of the detected object on the global coordinate system. The coordinate transformation unit 212 then includes the object's coordinates on the global coordinate system in the object information and outputs it to the coordinate comparison unit 217 and the division point setting unit 213.

[0099] In step S204, the coordinate comparison unit 217 determines whether the coordinates match if the object information contains multiple coordinates of an object detected by multiple imaging devices 100. The coordinate comparison unit 217 then adds information to the object information indicating whether the object detected by the multiple imaging devices 100 is the same object located in the shared imaging area 20, and outputs it to the division point setting unit 213.

[0100] In step S205, if it is determined that the object detected by multiple imaging devices 100 is the same object located in the shared imaging area 20 (step S204: YES), and the object is located within the overall detection area 10, the division point setting unit 213 compares the likelihood of the object calculated by each of the multiple imaging devices 100 that detected the object, which is included in the input object information. If it is determined that the object detected by multiple imaging devices 100 is not the same object located in the shared imaging area 20 (step S204: NO), the process returns to step S204.

[0101] In step S206, the division point setting unit 213 updates the arrangement of division points 24 and the division point arrangement information so that the object is included in the individual detection area 12 corresponding to the imaging device 100 that has calculated a higher likelihood among the multiple imaging devices 100, based on the likelihood that the object is likely to be an object. The division point setting unit 213 then updates the division point arrangement information to show the changed arrangement of division points 24 and outputs it to the individual detection area setting unit 214.

[0102] In step S207, the individual detection area setting unit 214 updates and sets multiple individual detection areas 12 based on the updated division point placement information and marker placement information. The individual detection area setting unit 214 then converts the multiple individual detection areas 12 set on the global coordinate system to a local coordinate system with the imaging device 100 corresponding to each of the multiple individual detection areas 12 as the origin, and outputs the individual detection area information to the information processing device side transmission unit 216. The information processing device side transmission unit 216 outputs the individual detection area information to the imaging device side reception unit 106. The imaging device side reception unit 106 outputs the input individual detection area information to the area determination unit 104.

[0103] In step S208, the object detection unit 103 detects an object by performing image analysis on the video captured by the imaging unit 101. The object detection unit 103 then outputs object information about the detected object to the area determination unit 104. Note that step S208 is not limited to this order and may be performed before step S201, or between any of the steps from step S201 to step S207.

[0104] In step S209, the area determination unit 104 determines whether or not the detected object is located within the individual detection area 12, based on the object information and the individual detection area information.

[0105] In step S210, if it is determined that the detected object is located within the individual detection area 12 (step S209: YES), the area determination unit 104 may output a message to that effect to, for example, a notification unit (not shown), and the notification unit may issue an alarm. Alternatively, the area determination unit 104 may count the number of such objects. If it is determined that the detected object is not located within the individual detection area 12 (step S209: NO), step S210 is not performed. This concludes the explanation of the processing flow of the surveillance camera system 1001 in Embodiment 2.

[0106] The information processing device 201 in Embodiment 2 is similar to Embodiment 1 in that markers 14 are placed at the vertices, and in an overall detection area 10 which is wider than the imaging area 16 which is the area imaged by a single imaging device 100, the information processing device 201 sets up a plurality of individual detection areas 12 which correspond to each of the plurality of imaging devices 100 that image the overall detection area 10, and the composite individual detection area 13 formed by combining the plurality of individual detection areas 12 includes the overall detection area 10, and comprises an information processing device receiving unit 215 that receives marker placement information regarding the placement of markers 14 from the plurality of imaging devices 100, a division point setting unit 213 that sets division points 24 which constitute the vertices of the plurality of individual detection areas 12 in the overall detection area 10 based on the marker placement information, and an individual detection area setting unit 214 that sets up a plurality of individual detection areas 12 based on division point placement information regarding the placement of division points 24 and marker placement information.

[0107] With the above configuration, the information processing device 201 of Embodiment 2 can set individual detection areas 12 by using division points 24 instead of markers 14 for some of the vertices, thus reducing the number of markers 14 compared to the case where markers 14 are placed at all vertices of the individual detection area 12. In addition, since the composite individual detection area 13 is set to include the overall detection area 10, the information processing device 201 of Embodiment 2 can suppress the occurrence of areas in the overall detection area 10 where objects cannot be detected because they are not included in any of the individual detection areas 12.

[0108] Furthermore, the division point setting unit 213 of Embodiment 2 updates the arrangement of division points 24 and division point arrangement information so that the object is included in the individual detection area 12 corresponding to the imaging device 100 that has calculated a higher likelihood among the multiple imaging devices 100, based on the likelihood that the object is likely to be an object. The individual detection area setting unit 214 then sets multiple individual detection areas 12 based on the updated division point arrangement information and marker arrangement information.

[0109] With the above configuration, the information processing device 201 of Embodiment 2 can update the range of the individual detection area 12 so that the object is located within the individual detection area 12 of the imaging device 100, which can detect the object with higher accuracy, if the range of the individual detection area 12 is not appropriate due to the presence or absence of obstacles and the coordinates of the target object.

[0110] (Note 1) An information processing device is configured such that a composite individual detection area, formed by combining the multiple individual detection areas, includes the overall detection area, where a marker is placed at the vertex, and the overall detection area is wider than the imaging area which is the area imaged by a single imaging device, and each of the multiple imaging devices that images the overall detection area has multiple individual detection areas corresponding to the area where each of the multiple imaging devices detects an object, and the overall detection area includes the overall detection area, An information processing device receiving unit that receives marker placement information regarding the placement of the markers from the plurality of imaging devices, Based on the marker placement information, a division point setting unit sets division points that constitute the vertices of the plurality of individual detection areas within the overall detection area, Based on the division point arrangement information and marker arrangement information relating to the arrangement of the division points, an individual detection area setting unit sets the plurality of individual detection areas. An information processing device equipped with the following features. (Note 2) The division point setting unit sets the division point in a shared imaging area, which is an area shared by the imaging areas of each of the multiple imaging devices. The plurality of individual detection areas do not overlap with each other, and each of the plurality of imaging areas of the plurality of imaging devices includes an area that overlaps with the overall detection area, which is an area other than the shared imaging area. The information processing device described in Appendix 1. (Note 3) The division point setting unit sets the division points in the shared imaging area, which is the area shared by the imaging areas of each of the multiple imaging devices, on the line segments connecting adjacent vertices of the overall detection area, and in the area shared by the imaging areas of at least three of the multiple imaging devices. The information processing device described in Appendix 1 or Appendix 2. (Note 4) The division point setting unit updates the arrangement of the division points and the division point arrangement information so that the object is included in the individual detection area corresponding to the imaging device that calculated the highest likelihood among the plurality of imaging devices, based on the likelihood representing the object-likeness of the object. The individual detection area setting unit sets the plurality of individual detection areas based on the updated division point placement information and the marker placement information. An information processing device as described in any one of the items from Appendix 1 to Appendix 3. (Note 5) The individual detection area setting unit sets an individual detection area using only the division points as vertices among the markers and the division points. An information processing device as described in any one of the items from Appendix 1 to Appendix 4. (Note 6) The individual detection area setting unit sets individual detection areas using the marker and the division point as vertices. An information processing device as described in any one of the items from Appendix 1 to Appendix 5. (Note 7) An information processing device described in any one of the items from Appendix 1 to Appendix 6, The plurality of imaging devices, A surveillance camera system equipped with [the following features]. (Note 8) An information processing method in which markers are placed at the vertices, and in an overall detection area that is wider than the imaging area which is the area imaged by a single imaging device, a plurality of individual detection areas, each corresponding to a plurality of imaging devices that image the overall detection area, are set such that a composite individual detection area formed by combining the plurality of individual detection areas includes the overall detection area, wherein the individual detection areas are set such that a composite individual detection area is formed by combining the plurality of individual detection areas, The information processing device receiving unit receives marker placement information regarding the placement of the markers from the plurality of imaging devices, The division point setting unit sets division points that constitute the vertices of the plurality of individual detection areas in the overall detection area based on the marker placement information, The individual detection area setting unit sets the plurality of individual detection areas based on the division point arrangement information and the marker arrangement information relating to the arrangement of the division points, An information processing method having (Note 9) A program for setting up a composite individual detection area, which is formed by combining the multiple individual detection areas, to include the overall detection area, in which a marker is placed at the vertices, and in an overall detection area that is wider than the imaging area which is the area captured by a single imaging device, the individual detection areas, which correspond to each of the multiple imaging devices that capture the overall detection area, and each of the multiple imaging devices detects an object, wherein the composite individual detection area is formed by combining the multiple individual detection areas, and the composite individual detection area includes the overall detection area, The information processing device receiving unit receives marker placement information regarding the placement of the markers from the plurality of imaging devices, The division point setting unit sets division points that constitute the vertices of the plurality of individual detection areas in the overall detection area based on the marker placement information, The individual detection area setting unit sets the plurality of individual detection areas based on the division point arrangement information and the marker arrangement information relating to the arrangement of the division points, A program that causes a computer to execute something. [Explanation of Symbols]

[0111] 1000, 1001 Surveillance camera system, 100 Imaging device, 100a First imaging device, 100b Second imaging device, 100c Third imaging device, 100d Fourth imaging device, 100e Fifth imaging device, 100f Sixth imaging device, 101 Imaging unit, 102 Marker detection unit, 103 Object detection unit, 104 Area determination unit, 105 Imaging device side transmission unit, 106 Imaging device side reception unit, 200, 201 Information processing device, 211 Coordinate storage unit, 212 Coordinate transformation unit, 213 Division point setting unit, 214 Individual detection area setting unit, 215 Information processing device side reception unit, 216 Information processing device side transmission unit, 217 Coordinate comparison unit, 300 Local network, 10 Overall detection area, 12 Individual detection area, 12a First individual detection area, 12a1 12b First modified individual detection area, 12b1 Second modified individual detection area, 12c Third individual detection area, 12d Fourth individual detection area, 12e Fifth individual detection area, 12f Sixth individual detection area, 13 Combined individual detection area, 14 Marker, 14a First marker, 14b Second marker, 14c Third marker, 14d Fourth marker, 14e Fifth marker, 16a Imaging area, 16b Second imaging area, 16c Third imaging area, 16d Fourth imaging area, 16e Fifth imaging area, 16f Sixth imaging area, 17 Combined imaging area, 20 Shared imaging area, 22 Non-shared imaging area, 24 Segmentation point, 24a First segmentation point, 24b Second segmentation point, 24b1 24c Second modified division point, 24d Third division point, 24e Fourth division point, 24f Sixth division point, 24g Seventh division point, 24g1 Seventh modified division point, 24h Eighth division point, 26 Area where the non-shared imaging area and the overall detection area overlap, 28 Objects within the shared imaging area, 90 Processing circuit, 92 Processor, 94 Memory

Claims

1. An information processing device is configured such that a composite individual detection area, formed by combining the multiple individual detection areas, includes the overall detection area, where a marker is placed at the vertex, and the overall detection area is wider than the imaging area which is the area imaged by a single imaging device, and each of the multiple imaging devices that images the overall detection area has multiple individual detection areas corresponding to the area where each of the multiple imaging devices detects an object, and the overall detection area includes the overall detection area, An information processing device receiving unit that receives marker placement information regarding the placement of the markers from the plurality of imaging devices, Based on the marker placement information, a division point setting unit sets division points that constitute the vertices of the plurality of individual detection areas within the overall detection area, Based on the division point arrangement information and marker arrangement information relating to the arrangement of the division points, an individual detection area setting unit sets the plurality of individual detection areas. An information processing device equipped with the following features.

2. The division point setting unit sets the division point in a shared imaging area, which is an area shared by the imaging areas of each of the multiple imaging devices. The plurality of individual detection areas do not overlap with each other, and each of the plurality of imaging areas of the plurality of imaging devices includes an area that overlaps with the overall detection area, which is an area other than the shared imaging area. The information processing apparatus according to claim 1.

3. The division point setting unit sets the division points in the shared imaging area, which is the area shared by the imaging areas of each of the multiple imaging devices, on the line segments connecting adjacent vertices of the overall detection area, and in the area shared by the imaging areas of at least three of the multiple imaging devices. The information processing apparatus according to claim 1.

4. The division point setting unit updates the arrangement of the division points and the division point arrangement information so that the object is included in the individual detection area corresponding to the imaging device that calculated the highest likelihood among the plurality of imaging devices, based on the likelihood representing the object-likeness of the object. The individual detection area setting unit sets the plurality of individual detection areas based on the updated division point placement information and the marker placement information. The information processing apparatus according to claim 1.

5. The individual detection area setting unit sets an individual detection area using only the division points as vertices among the markers and the division points. The information processing apparatus according to claim 1.

6. The individual detection area setting unit sets individual detection areas using the marker and the division point as vertices. The information processing apparatus according to claim 1.

7. An information processing device according to any one of claims 1 to 6, The plurality of imaging devices, A surveillance camera system equipped with [the following features].

8. An information processing method in which markers are placed at the vertices, and in an overall detection area that is wider than the imaging area which is the area imaged by a single imaging device, a plurality of individual detection areas, each corresponding to a plurality of imaging devices that image the overall detection area, are set such that a composite individual detection area formed by combining the plurality of individual detection areas includes the overall detection area, wherein the individual detection areas are set such that a composite individual detection area is formed by combining the plurality of individual detection areas, The information processing device receiving unit receives marker placement information regarding the placement of the markers from the plurality of imaging devices, The division point setting unit sets division points that constitute the vertices of the plurality of individual detection areas in the overall detection area based on the marker placement information, The individual detection area setting unit sets the plurality of individual detection areas based on the division point arrangement information and the marker arrangement information relating to the arrangement of the division points, An information processing method having

9. A program for setting up a composite individual detection area, which is formed by combining the multiple individual detection areas, to include the overall detection area, in which a marker is placed at the vertices, and in an overall detection area that is wider than the imaging area which is the area captured by a single imaging device, the individual detection areas, which correspond to each of the multiple imaging devices that capture the overall detection area, and each of the multiple imaging devices detects an object, wherein the composite individual detection area is formed by combining the multiple individual detection areas, and the composite individual detection area includes the overall detection area, The information processing device receiving unit receives marker placement information regarding the placement of the markers from the plurality of imaging devices, The division point setting unit sets division points that constitute the vertices of the plurality of individual detection areas in the overall detection area based on the marker placement information, The individual detection area setting unit sets the plurality of individual detection areas based on the division point arrangement information and the marker arrangement information relating to the arrangement of the division points, A program that causes a computer to execute something.

Images