Number of people estimation system, number of people estimation method, and program

Abstract

A headcount estimation system (1001) according to the present disclosure comprises an image capture unit (11), an image processing unit (21), a congestion level evaluation unit (22), and a correction unit (23). The image capture unit (11) captures an image of a prescribed area. On the basis of the image captured by the image capture unit (11), the image processing unit (21) calculates the number of people in the prescribed area and the number of people in each of a plurality of sections obtained by dividing the prescribed area. The congestion level evaluation unit (22) evaluates the level of congestion in the prescribed area. The correction unit (23) identifies the section to be referred to on the basis of the level of congestion, and corrects the number of people in the prescribed area on the basis of the identified section.

Description

[Technical Field]

[0001] The present invention relates to a number of people estimation system, a number of people estimation device, a number of people estimation method, and a non-transitory computer-readable medium. [Background technology]

[0002] Patent Document 1 describes an information processing device that estimates the number of people. The information processing device described in Patent Document 1 detects people from an image captured of a predetermined area and estimates the number of people. Furthermore, the information processing device described in Patent Document 1 divides a predetermined area into a first area with no seats and a second area with seats, and if the number of people detected in the first area is equal to or greater than a first threshold, the number of people in the second area is set to a predetermined number. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-071923 Summary of the Invention [Problem to be solved by the invention]

[0004] The information processing device described in Patent Document 1 merely determines whether to set the number of people in the first area to a predetermined number based on the number of people in the second area. Therefore, it cannot be said that the information processing device described in Patent Document 1 fully considers the influence of the congestion level of the predetermined area in estimating the number of people. In other words, the information processing device described in Patent Document 1 has a problem in that it cannot estimate the number of people with sufficient accuracy.

[0005] The present disclosure has been made to solve such problems, and aims to provide a number of people estimation system, a number of people estimation device, a number of people estimation method, and a non-transitory computer-readable medium that can improve the accuracy of number of people estimation. [Means for solving the problem]

[0006] The number of people estimation system according to the present disclosure includes: an imaging unit that images a predetermined area; an image processing unit that calculates the number of people in the predetermined area and the number of people in each of a plurality of sections obtained by dividing the predetermined area based on the image captured by the imaging unit; a congestion degree evaluation unit for evaluating the congestion degree of the predetermined area; a correction unit that identifies a section to be referenced based on the congestion degree, and corrects the number of people in the predetermined area based on the identified section; It is a population estimation system.

[0007] The number of people estimation device according to the present disclosure includes: an image processing unit that calculates the number of people in a predetermined area and the number of people in a plurality of sections obtained by dividing the predetermined area based on an image of the predetermined area; a congestion degree evaluation unit for evaluating the congestion degree of the predetermined area; a correction unit that identifies a section to be referenced based on the congestion degree, and corrects the number of people in the predetermined area based on the identified section; It is a people estimation device.

[0008] The number of people estimation method according to the present disclosure includes: Calculating the number of people in a predetermined area and the number of people in a plurality of sections obtained by dividing the predetermined area based on an image of the predetermined area; Evaluating the degree of congestion in the predetermined area; Identifying a section to be referenced based on the congestion degree; Correcting the number of people in the predetermined area based on the identified section. This is a method for estimating the number of people.

[0009] The present disclosure provides a non-transitory computer-readable medium, comprising: Calculating the number of people in a predetermined area and the number of people in a plurality of sections obtained by dividing the predetermined area based on an image of the predetermined area; Evaluating the degree of congestion in the predetermined area; Identifying a section to be referenced based on the congestion degree; a program that causes a computer to execute an operation of correcting the number of people in the predetermined area based on the identified section; It is a non-transitory computer-readable medium. [Effects of the Invention]

[0010] The present disclosure makes it possible to provide a number of people estimation system, a number of people estimation device, a number of people estimation method, and a non-transitory computer-readable medium that can improve the accuracy of number of people estimation. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a block diagram showing a configuration of a number of people estimation system according to a first embodiment. [Figure 2] FIG. 10 is a block diagram showing the configuration of a number of people estimation system according to a second embodiment. [Figure 3] FIG. 10 is a schematic overhead view showing a specific example of the number of people estimation system according to the second embodiment. [Figure 4] FIG. 10 is a schematic overhead view showing a specific example of the number of people estimation system according to the second embodiment. [Figure 5] FIG. 10 is a schematic overhead view showing a specific example of the number of people estimation system according to the second embodiment. [Figure 6] 10 is a flowchart showing the operation of the number of people estimation system according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] (First embodiment) The number of people estimation system according to the first embodiment will be described in detail below with reference to the drawings. Fig. 1 is a block diagram showing the configuration of the number of people estimation system according to the first embodiment.

[0013] The number of people estimation system 1001 according to the first embodiment includes an imaging unit 11, an image processing unit 21, a congestion degree evaluation unit 22, and a correction unit . The photographing unit 11 photographs a predetermined area. The image processing unit 21 calculates the number of people in a predetermined area and the number of people in each of the multiple sections into which the predetermined area is divided, based on the image captured by the imaging unit. The congestion degree evaluation unit 22 evaluates the congestion degree of a predetermined area. The correction unit 23 identifies a section to be referenced based on the congestion degree, and corrects the number of people in a predetermined area based on the identified section.

[0014] In this way, the number of people estimation system according to this embodiment identifies a section to be referenced based on the congestion level of a predetermined area, and corrects the number of people in the predetermined area based on the identified section. With this configuration, the number of people estimation system according to this embodiment can improve the accuracy of number of people estimation.

[0015] (Second embodiment) <Configuration of the number of people estimation system> The number of people estimation system according to the second embodiment will be described in detail below with reference to the drawings. First, the configuration of the number of people estimation system according to the second embodiment will be described. Fig. 2 is a block diagram showing the configuration of the number of people estimation system according to the second embodiment.

[0016] The number of people estimation system 1002 is a system for estimating the number of people in a predetermined area. More specifically, the number of people estimation system 1002 captures an image of the predetermined area and estimates the number of people based on the captured image. The predetermined area may be, for example, outdoors, indoors, or the inside of a moving object such as a train, bus, or ship. In other words, the predetermined area may be any area where a group of people is formed. The number of people estimation system 1002 includes a photographing device 10 and a number of people estimation device 20.

[0017] The image capturing device 10 is a device for capturing an image of a predetermined area, and may be, for example, a surveillance camera. Furthermore, if the predetermined area is the inside of a train, the image capturing device 10 may be a small camera embedded in the lighting equipment inside the train. Furthermore, the image capturing device 10 does not need to be fixed to a predetermined location, and may be, for example, a small camera that can be carried or worn by a person, such as a wearable camera, or a camera mounted on a small aircraft such as a drone, that can be freely positioned and moved. In other words, the image capturing device 10 may have any configuration as long as it is capable of capturing an image of a predetermined area. The photographing device 10 photographs a predetermined area and outputs the image to the number of people estimation device 20. The photographing device 10 corresponds to the photographing section 11 according to the first embodiment.

[0018] The number of people estimation device 20 acquires an image of a predetermined area from the photographing device 10 and estimates the number of people in the predetermined area based on the image. The number of people estimation device 20 includes an image processing unit 21, a congestion degree evaluation unit 22, and a correction unit 23.

[0019] The number of people estimation device 20 may be configured as, for example, a computer device that receives, as data, an image of a predetermined area captured by the photographing device 10. In this case, the number of people estimation device 20 may include, for example, a calculation unit such as a central processing unit (CPU) (not shown), and a storage unit such as a random access memory (RAM) or a read only memory (ROM) that stores programs and data for controlling the calculation unit. The image processing unit 21, the congestion degree evaluation unit 22, and the correction unit 23 may be realized as functions of the calculation unit.

[0020] The program includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0021] The image processing unit 21 calculates the number of people in a predetermined area based on the image captured by the image capturing device 10. The image processing unit 21 outputs the calculated number of people in the predetermined area to the congestion degree evaluation unit 22.

[0022] For example, the image processing unit 21 may detect the heads of people from the image captured by the image capturing device 10 and count the number of detected heads of people to calculate the number of people in a predetermined area. In addition, the image processing unit 21 may, for example, have an artificial intelligence (AI) that has learned images containing multiple people read the images captured by the image capturing device 10 and calculate the number of people within a specified area.

[0023] Furthermore, the image processing unit 21 calculates the number of people in each of the sections obtained by dividing a predetermined area into a plurality of sections. For example, the image processing unit 21 may divide the image captured by the image capturing device 10 into parts corresponding to each section, detect the heads of people appearing in each section, and count the number of detected heads of people to calculate the number of people in each section.

[0024] The congestion degree evaluation unit 22 acquires the calculated number of people in the predetermined area from the image processing unit 21. Then, the congestion degree evaluation unit 22 evaluates the congestion degree of the predetermined area based on the number of people in the predetermined area calculated by the image processing unit 21, and outputs the evaluated congestion degree to the correction unit 23.

[0025] The congestion degree evaluation unit 22 may evaluate the congestion degree by dividing it into stages, for example. That is, the congestion degree may be evaluated by dividing the congestion degree into a plurality of stages, with an upper limit and a lower limit for each stage, and the stage corresponding to the number of people in a predetermined area calculated by the image processing unit 21 may be evaluated as the congestion degree.

[0026] For example, suppose that there is a correspondence between each level and the number of people as shown in Table 1 below, and the number of people in a predetermined area calculated by the image processing unit 21 is 25. In this case, the congestion level evaluation unit 22 evaluates that "the congestion level of the predetermined area is at the second level."

[0027] [Table 1] ...Table 1

[0028] Alternatively, the congestion degree evaluation unit 22 may evaluate the congestion degree as a ratio of the calculated number of people in a predetermined area to a predetermined number of people. For example, if the calculated number of people in a predetermined area is 80 people and the predetermined number of people is 100 people, the congestion degree evaluation unit 22 may evaluate the congestion degree to be 80 percent.

[0029] The congestion degree evaluation unit 22 may also evaluate the congestion degree based on the population density within a predetermined area. That is, the congestion degree evaluation unit 22 may calculate the population density by dividing the calculated number of people within the predetermined area by the area of ​​the predetermined area, and evaluate the calculated population density value as the congestion degree.

[0030] The correction unit 23 acquires the calculated number of people in the predetermined area and the number of people in the section from the image processing unit 21, and acquires the congestion level of the predetermined area from the congestion level evaluation unit 22. The correction unit 23 identifies a section to refer to based on the congestion level, and corrects the number of people in the predetermined area based on the identified section. The correction unit 23 may correct the number of people in the predetermined area, for example, by correcting the calculated number of people in the identified section. Alternatively, the correction unit 23 may refer to a correction standard for the number of people in the predetermined area that is predetermined for each identified section, and correct the number of people in the predetermined area based on the correction standard. If the congestion level is less than a predetermined threshold, the number of people in the predetermined area may be corrected without taking the sections into consideration. In other words, the number of identified sections may be zero.

[0031] The correction unit 23 according to the present embodiment determines the sections for which the number of people calculated is to be corrected based on the congestion level. More specifically, the correction unit 23 increases the number of sections for which the number of people calculated by the image processing unit 21 is to be corrected as the congestion level increases.

[0032] Here, the section determined to be corrected by the correction unit 23 is preferably a section where an error between the calculated number of people and the actual number of people is likely to occur. Examples of sections where an error in the number of people is likely to occur include a section that includes an area that is a blind spot of the image capture device 10, a section that includes the edge of the image, and a section that includes an area where the image capture may be blocked by a person.

[0033] In such sections, as the congestion level increases, the error between the actual number of people and the calculated number of people increases, but the correlation varies depending on the section. Therefore, by assigning an appropriate congestion level to each section and correcting the number of people when the corresponding congestion level is exceeded, the accuracy of the number of people estimation can be improved. In other words, by increasing the number of sections for which the number of people is corrected as the congestion level increases, the accuracy of the number of people estimation can be improved.

[0034] For example, correction unit 23 may correct the number of people in a section that can accommodate a larger number of people, and as the degree of congestion increases, correct the number of people in a section that can accommodate a smaller number of people. As the number of people that can be accommodated in a section increases, the number of people in the section increases accordingly, causing people to overlap on the image, and there is a possibility that some people cannot be detected by image processing unit 21. Therefore, by giving priority to correcting the number of people in a section that can accommodate a larger number of people, the accuracy of the number of people estimation can be improved.

[0035] Furthermore, the correction unit 23 may perform correction starting with the number of people in sections that are more difficult to photograph, and as the degree of congestion increases, correct the number of people in sections that are easier to photograph. In sections that are difficult to photograph, there is a possibility that people may exist that cannot be detected by the image processing unit 21. Therefore, by prioritizing correction of the number of people in sections that are more difficult to photograph, the accuracy of the number of people estimation can be improved.

[0036] Furthermore, the correction unit 23 may perform correction starting with the number of people in sections corresponding to the image edges, and as the degree of congestion increases, correct the number of people in sections corresponding to the center of the image. There is a possibility that people who are not shown in the image and cannot be detected by the image processing unit 21 may exist in sections corresponding to the image edges. Therefore, by giving priority to correcting the number of people in sections corresponding to the image edges, the accuracy of estimating the number of people can be improved.

[0037] For example, when the congestion level evaluation unit 22 evaluates the congestion level by dividing the level into stages, the correction unit 23 may increase the number of sections for which the number of people is corrected by one when the level of the congestion level increases.Furthermore, when the level increases, the correction unit 23 may increase the number of sections for which the number of people is corrected by two or more. The correction unit 23 may increase the number of sections for correcting the number of people in two or more stages.

[0038] The correction unit 23 corrects the calculated number of people in the section where it has been determined that the calculated number of people should be corrected. More specifically, the correction unit 23 corrects the number of people calculated by the image processing unit 21 in the section using a correction standard that is predetermined for each section. The correction unit 23 may change the correction standard to be used based on the congestion level even in the same section.

[0039] The correction standard may include, for example, adding a predetermined number of people to the number of people calculated by the image processing unit 21. Furthermore, the correction standard may include, for example, multiplying the number of people calculated by the image processing unit 21 by a predetermined coefficient. A specific example in which such a correction standard is used is when the predetermined area is the inside of a train and the section in question is a section including the area around the train entrance and exit.

[0040] Furthermore, the correction standard may include, for example, changing the number of people calculated by the image processing unit 21 to a predetermined constant. A specific example in which such a correction standard is used is when the predetermined area is the inside of a train and the section in question is a section including the area around the train entrance and exit.

[0041] These specific examples will now be described in more detail with reference to the drawings. Fig. 3 is a schematic overhead view showing a specific example of a predetermined area. More specifically, Fig. 3 is a schematic overhead view of a predetermined area when the predetermined area is the inside of a train. 3, the predetermined area R0 in this example includes train entrances D1 and D2, seats C1, C2, C3, and C4, and aisle A. The predetermined area R0 is photographed by an image capturing device 10 attached near the entrance D2.

[0042] First, a specific example will be described in which the correction unit 23 executes correction by adding a predetermined number of people to the number of people calculated by the image processing unit 21 or by multiplying a predetermined coefficient. 4 is a schematic overhead view for clearly indicating the section R1 for which the calculated number of people is corrected. The section R1, which corresponds to the area around the entrance / exit D2, includes an area that is a blind spot for the image capturing device 10. In such a section R1, the correction unit 23 may assume that there are a predetermined number of people within the blind spot area included in section R1 and perform a correction to add the predetermined number of people to the number of people in section R1 calculated by the image processing unit 21. In addition, the correction unit 23 may perform a correction by multiplying the number of people in section R1 calculated by the image processing unit 21 by a predetermined coefficient of 1 or more, assuming that the number of people in the blind spot area included in section R1 is proportional to the number of people in section R1.

[0043] Next, a specific example will be described in which the correction unit 23 executes a correction to change the number of people calculated by the image processing unit 21 to a predetermined number of people. 5 is a schematic overhead view showing the area R2 where the calculated number of people is corrected. The area R2, which corresponds to the area around the chair C2, includes an area that is blocked from being photographed by the photographing device 10 when the degree of congestion increases to the point where people are lining up in the aisle A. In such a section R2, if the degree of congestion increases to the point where people are lining up in the aisle A, the correction unit 23 may assume that there are a number of people in section R2 corresponding to the capacity of the chairs, i.e., a predetermined number of people, and perform a correction to change the number of people in section R2 calculated by the image processing unit 21 to the predetermined number of people.

[0044] The method for correcting the number of people in these sections R1 and R2 is not limited to the above. For example, in section R1, a correction may be made to change the calculated number of people to a predetermined number. In addition, in section R2, a correction may be made to add a predetermined number of people or to multiply by a predetermined coefficient.

[0045] For example, the correction unit 23 may correct the number of people in sections including the areas around train entrances and exits, and as the degree of congestion increases, correct the number of people in sections including the areas around train seats. On trains, congestion tends to begin in sections including the areas around entrances and exits, followed by sections including the areas around seating. In other words, the error between the actual number of people and the calculated number of people tends to increase in sections including the areas around entrances and exits, even at a stage where the degree of congestion is lower, compared to sections including the areas around seating. Therefore, the accuracy of the number of people estimated can be improved by prioritizing correction of the number of people in sections including the areas around train entrances and exits.

[0046] Returning to the explanation of Figure 2. The correction unit 23 corrects the number of people calculated by the image processing unit 21 in the section determined to be corrected, and then corrects the number of people in the predetermined area calculated by the image processing unit 21. For example, the correction unit 23 may calculate the difference between the number of people before and after correction for a section in which the number of people has been corrected, and correct the number of people within a specified area calculated by adding this difference. In addition, after correcting the number of people in a section, the correction unit 23 may add up the number of people in all sections that make up a specified area and perform a correction to change the calculated number of people in the specified area to that total value.

[0047] <Operation of the number of people estimation system> Next, the operation of the number of people estimation system according to the second embodiment, i.e., the number of people estimation method, will be described in detail with reference to the drawings. Fig. 6 is a flowchart showing the operation of the number of people estimation system according to the second embodiment. In the following description, Fig. 2 will be referred to as appropriate.

[0048] First, the photographing device 10 photographs a predetermined area (step ST1). Next, the image processing unit 21 calculates the number of people present in the predetermined area based on the photographed image of the predetermined area (step ST2). Next, based on the photographed image of the predetermined area, the image processing unit 21 calculates the number of people present in each of the multiple sections into which the predetermined area is divided (step ST3). However, the order in which steps ST2 and ST3 are performed is not limited to this, and they may be performed in the reverse order or in parallel.

[0049] Next, the congestion degree evaluation unit 22 evaluates the congestion degree of the predetermined area based on the calculated number of people in the predetermined area (step ST4). Next, the correction unit 23 determines a section for correcting the calculated number of people based on the congestion degree (step ST5).

[0050] Next, the correction unit 23 corrects the number of people present in the determined section (step ST6). Finally, the correction unit 23 corrects the calculated number of people present in the predetermined area (step ST7), and the series of operations ends.

[0051] As described above, the number of people estimation system according to this embodiment determines the zones in which the calculated number of people will be corrected based on the degree of congestion in a specified area, and as the degree of congestion increases, the number of zones in which the image processing unit will correct the calculated number of people is increased. With this configuration, the number of people estimation system according to this embodiment can estimate the number of people with sufficient accuracy even in areas where the estimated number of people needs to be corrected for multiple sections and the sections for which the estimated number of people needs to be corrected each have different correlations with the congestion level. In other words, the number of people estimation system according to this embodiment can improve the accuracy of number of people estimation.

[0052] (Other embodiments) A number of people estimation system according to an embodiment of the present disclosure may estimate the number of people in a specified area by performing a number of people estimation for only a portion of the specified area and assuming that the number of people in the remaining portion is distributed at a similar population density. For example, when a passenger number estimation system according to an embodiment of the present disclosure is used to estimate the number of passengers on a train consisting of multiple cars, the passenger number estimation system according to an embodiment of the present disclosure may estimate the number of passengers for only one car, and then estimate the total number of passengers on the train consisting of multiple cars by assuming that a similar number of people are on board in the remaining cars.

[0053] The number of people estimation system according to the second embodiment includes one image capturing device 10, but the number of people estimation system according to the embodiment of the present disclosure may include multiple image capturing devices 10. In this case, the multiple camera devices 10 may include a camera device 10 that captures the entire predetermined area and a camera device 10 that captures only a portion of the area. The number of people in the predetermined area may be estimated based on images captured by the camera device 10 that captures the entire predetermined area, and the number of people in the corresponding portion may be calculated based on images captured by the camera device 10 that captures only a portion of the area.

[0054] Furthermore, when the number of people estimation system according to the embodiment of the present disclosure includes a plurality of image capturing devices 10, the plurality of image capturing devices may share the task of capturing images of a predetermined area. In such a case, the correction unit 23 may correct the number of people in the section by subtracting a predetermined number of people from the number of people calculated by the image processing unit 21. In other words, the correction unit 23 may correct the number of people in the section by taking into consideration the possibility that one person may be photographed by multiple cameras at the same time and be counted multiple times.

[0055] In the number of people estimation systems according to the first and second embodiments, the number of people in a specified area and in each section was calculated based on an image of the specified area, but the method of calculating the number of people in a specified area and in each section is not limited to this. For example, the number of people in a predetermined area and each section may be calculated by detecting people in the predetermined area and each section using a sensor or the like and counting the number of people detected. Also, if the specified area is a vehicle such as a bus or train, the number of people in the specified area and each section may be calculated based on the vehicle weight, or the number of people in the specified area and each section may be calculated based on how the vehicle sinks. In other words, any method may be used to calculate the number of people in a predetermined area and each section, as long as it can estimate the number of people in a predetermined area and each section with sufficient accuracy.

[0056] The present disclosure has been described above in accordance with the above-described embodiments, but the present disclosure is not limited to the configurations of the above-described embodiments, and naturally includes various modifications, alterations, and combinations that a person skilled in the art could make within the scope of the claims of the present application.

[0057] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) an imaging unit that images a predetermined area; an image processing unit that calculates the number of people in the predetermined area and the number of people in each of a plurality of sections obtained by dividing the predetermined area based on the image captured by the imaging unit; a congestion degree evaluation unit for evaluating the congestion degree of the predetermined area; a correction unit that identifies a section to be referenced based on the congestion degree, and corrects the number of people in the predetermined area based on the identified section; People count estimation system. (Appendix 2) the congestion degree evaluation unit evaluates the congestion degree of the predetermined area based on the number of people in the predetermined area calculated by the image processing unit. 1. The people count estimation system of claim 1. (Appendix 3) the correction unit increases the number of sections for which the number of people calculated by the image processing unit is corrected as the congestion degree increases. 3. The number of people estimation system according to claim 1 or 2. (Appendix 4) the correction unit corrects the number of people in each section calculated by the image processing unit based on a correction standard predetermined for each section; 4. The number of people estimation system according to any one of appendices 1 to 3. (Appendix 5) the correction unit corrects the number of people in the section by adding a predetermined number of people to the number of people calculated by the image processing unit. 5. The people count estimation system according to claim 4. (Appendix 6) the correction unit corrects the number of people in the section by multiplying the number of people calculated by the image processing unit by a predetermined coefficient; 6. The number of people estimation system according to claim 4 or 5. (Appendix 7) the correction unit corrects the number of people in the section by changing the number of people calculated by the image processing unit to a predetermined number of people; 7. The number of people estimation system according to any one of appendixes 4 to 6. (Appendix 8) the predetermined area is the interior of a train, When the correction unit determines to correct a section including the area around a train entrance / exit, the correction unit adds a predetermined number of people to the number of people in the section calculated by the image processing unit. 8. The number of people estimation system according to any one of appendices 1 to 7. (Appendix 9) the predetermined area is the interior of a train, When the correction unit determines to correct a section including the area around the train entrance / exit, the correction unit multiplies the number of people in the section calculated by the image processing unit by a predetermined coefficient of 1 or more. 9. The number of people estimation system according to any one of appendices 1 to 8. (Appendix 10) the predetermined area is the interior of a train, When the correction unit determines to correct a section including a seat on a train, the correction unit changes the number of people in the section calculated by the image processing unit to a number of people equivalent to the capacity of the seat. 10. The number of people estimation system according to any one of appendices 1 to 9. (Appendix 11) an image processing unit that calculates the number of people in a predetermined area and the number of people in a plurality of sections obtained by dividing the predetermined area based on an image of the predetermined area; a congestion degree evaluation unit for evaluating the congestion degree of the predetermined area; a correction unit that identifies a section to be referenced based on the congestion degree, and corrects the number of people in the predetermined area based on the identified section; Number of people estimation device. (Appendix 12) the congestion degree evaluation unit evaluates the congestion degree of the predetermined area based on the number of people in the predetermined area calculated by the image processing unit. 12. The number of people estimation device according to claim 11. (Appendix 13) the correction unit increases the number of sections for which the number of people calculated by the image processing unit is corrected as the congestion degree increases. 13. The number of people estimation device according to claim 11 or 12. (Appendix 14) the correction unit corrects the number of people in each section calculated by the image processing unit based on a correction standard predetermined for each section; 14. The number of people estimation device according to any one of appendices 11 to 13. (Appendix 15) the correction unit corrects the number of people in the section by adding a predetermined number of people to the number of people calculated by the image processing unit. 15. The number of people estimation device according to claim 14. (Appendix 16) the correction unit corrects the number of people in the section by multiplying the number of people calculated by the image processing unit by a predetermined coefficient; 16. The number of people estimation device according to claim 14 or 15. (Appendix 17) the correction unit corrects the number of people in the section by changing the number of people calculated by the image processing unit to a predetermined number of people; 17. The number of people estimation device according to any one of appendices 14 to 16. (Appendix 18) the predetermined area is the interior of a train, When the correction unit determines to correct a section including the area around a train entrance / exit, the correction unit adds a predetermined number of people to the number of people in the section calculated by the image processing unit. 18. The number of people estimation device according to any one of appendices 11 to 17. (Appendix 19) the predetermined area is the interior of a train, When the correction unit determines to correct a section including the area around the train entrance / exit, the correction unit multiplies the number of people in the section calculated by the image processing unit by a predetermined coefficient of 1 or more. 19. The number of people estimation device according to any one of appendices 11 to 18. (Appendix 20) the predetermined area is the interior of a train, When the correction unit determines to correct a section including a seat on a train, the correction unit changes the number of people in the section calculated by the image processing unit to a number of people equivalent to the capacity of the seat. 20. The number of people estimation device according to any one of appendices 11 to 19. (Appendix 21) Calculating the number of people in a predetermined area and the number of people in a plurality of sections obtained by dividing the predetermined area based on an image of the predetermined area; Evaluating the degree of congestion in the predetermined area; Identifying a section to be referenced based on the congestion degree; Correcting the number of people in the predetermined area based on the identified section. How to estimate the number of people. (Appendix 22) Calculating the number of people in a predetermined area and the number of people in a plurality of sections obtained by dividing the predetermined area based on an image of the predetermined area; Evaluating the degree of congestion in the predetermined area; Identifying a section to be referenced based on the congestion degree; a program that causes a computer to execute an operation of correcting the number of people in the predetermined area based on the identified section; Non-transitory computer-readable medium. [Explanation of symbols]

[0058] 10 Imaging equipment 11 Filming Department 20 People estimation device 21 Image processing section 22 Congestion evaluation section 23 Correction unit 1001, 1002 People count estimation system

Claims

1. an imaging unit that images a predetermined area; an image processing unit that calculates the number of people in the predetermined area and the number of people in each of a plurality of sections obtained by dividing the predetermined area based on the image captured by the imaging unit; a congestion degree evaluation unit for evaluating the congestion degree of the predetermined area; a correction unit that increases the number of sections for which the number of people calculated by the image processing unit is corrected as the degree of congestion increases, and corrects the number of people in sections that can accommodate more people by priority, and corrects the number of people in sections that can accommodate fewer people as the degree of congestion increases; People count estimation system.

2. The congestion degree evaluation unit, based on the number of people in the predetermined area calculated by the image processing unit, Evaluating the degree of congestion in the predetermined area; The number of people estimation system according to claim 1 .

3. The correction unit adds a predetermined number of people to the number of people calculated by the image processing unit. The number of people in the area is corrected accordingly. The number of people estimation system according to claim 2 .

4. The correction unit multiplies the number of people calculated by the image processing unit by a predetermined coefficient. The number of people in the area is corrected accordingly. The number of people estimation system according to claim 2 .

5. The correction unit changes the number of people calculated by the image processing unit to a predetermined number of people, Correct the number of people in the area, The number of people estimation system according to claim 2 .

6. the predetermined area is the interior of a train, When the correction unit determines to correct the section including the area around the train entrance / exit, adding a predetermined number of people to the number of people in the section calculated by the processing unit; The number of people estimation system according to any one of claims 1 to 5.

7. Based on an image of a predetermined area, the number of people in the predetermined area and the area The number of people in each divided section is calculated. Evaluating the degree of congestion in the predetermined area; As the degree of congestion increases, the number of sections for which the number of people calculated by the image processing unit is corrected is increased, and the number of people in sections that can accommodate more people is corrected with priority, and as the degree of congestion increases, the number of people in sections that can accommodate fewer people is corrected. How to estimate the number of people.

8. Based on an image of a predetermined area, the number of people in the predetermined area and the area The number of people in each divided section is calculated. Evaluating the degree of congestion in the predetermined area; As the degree of congestion increases, the number of sections for which the image processing unit corrects the number of people calculated is increased, and the number of people in sections that can accommodate more people is corrected with priority, and as the degree of congestion increases, the number of people in sections that can accommodate fewer people is corrected. to execute, program.

Images