Floor stain estimation method and floor stain estimation program

Abstract

This invention provides a method for estimating floor contamination that can quantitatively estimate the level of contamination on the floor of a location to be evaluated. [Solution] The floor soiling estimation method includes a pedestrian flow measurement step S1, which measures pedestrian flow data indicating the movement of people at the location to be evaluated 100, and a floor soiling estimation step S3, which estimates the soiling of the floor 101 at the location to be evaluated 100 based on the pedestrian flow data.

Description

Technical Field

[0001] The present disclosure relates to a method for estimating floor dirt and a floor dirt estimation program.

Background Art

[0002] In recent years, due to the influence of the spread of the coronavirus infection, people's interest in the hygienic environment has been increasing.

Summary of the Invention

Problems to be Solved by the Invention

[0003] For example, in restaurants and the like, it is required to maintain the interior clean and externally show that the interior is maintained clean. However, at present, since the dirt situation of the interior (especially the floor) cannot be easily grasped, the entire interior is cleaned haphazardly.

[0004] An object of the present disclosure is to provide a method for estimating floor dirt and a floor dirt estimation program that can quantitatively estimate the floor dirt of an evaluation location.​​​​​​​​​​​​​​​​​​​​​​​​ According to this disclosure, the level of dirt on the floor of the location being evaluated can be quantitatively estimated based on the measured pedestrian flow. [Brief explanation of the drawing]

[0008] [Figure 1] A schematic block diagram illustrating a floor soiling estimation system according to one embodiment of the present disclosure. [Figure 2] A diagram showing the evaluation location in general terms. [Figure 3] A schematic diagram illustrating the process of estimating the level of dirt on the floor. [Figure 4] A graph showing the number of pixels for each pixel value of dirt transferred from footwear to the floor. [Figure 5] A graph showing the relationship between the number of steps taken and the amount of dirt transferred from footwear to the floor. [Figure 6] A flowchart illustrating the process for estimating the level of dirt on the floor. [Figure 7] A diagram showing an example of pedestrian flow data. [Figure 8] A diagram showing an example of the total number of stains at position (Xn, Yn). [Figure 9] A diagram showing an example of altered pedestrian flow data. [Figure 10] A diagram showing an example of the total number of soiling points at location (Xn, Yn) based on modified pedestrian flow data. [Figure 11] A diagram illustrating the general extent of floor stains. [Figure 12] A diagram illustrating the general extent of floor soiling when a mat is installed. [Figure 13] A flowchart illustrating the process for estimating the level of floor soiling in a modified example. [Figure 14] A flowchart illustrating the process for estimating floor contamination in further modified cases. [Modes for carrying out the invention]

[0009] Referring to the accompanying drawings below, a floor dirt estimation system 1 according to an embodiment of the present disclosure will be described. Note that the following description is merely illustrative in nature and is not intended to limit the present invention, its applications, or its uses.

[0010] FIG. 1 schematically shows a floor dirt estimation system 1 for estimating floor dirt according to an embodiment of the present disclosure. The floor dirt estimation system 1 quantitatively estimates the dirt on the floor 101 of the evaluation location 100 shown in FIG. 2. The floor dirt estimation system 1 includes a camera 10, an input device 11, a computer 20, and a display device 30. In the present embodiment, the evaluation location 100 is described as a convenience store, but it may be any arbitrary location such as another store where it is desired to quantitatively estimate the floor dirt. [[ID=⑤]] [[ID=⑥]]

[0011] [[ID=⑦]] [[ID=⑧]]The camera 10 is used to measure the flow of people at the evaluation location 100. For example, in the present embodiment, an RGB-D camera is adopted as the camera 10. Specifically, the camera 10 captures the flow of people at the evaluation location 100 as a video together with depth information. As shown in FIG. 2, in the present embodiment, two cameras 10 are attached to different positions on the ceiling of the evaluation location 100, but the number of cameras 10 is not limited, and it may be one or three or more as long as it can measure the flow of people at the evaluation location 100. [[ID=⑨]] [[ID=⑩]]

[0012] [[ID=⑪]] [[ID=⑫]]The input device 11 can input various information to the computer 20 and may be used, for example, to input the arrangement information of mats. As the input device 11, any well-known input device such as a keyboard or a tablet can be adopted. [[ID=⑬]] [[ID=⑭]]

[0013] [[ID=⑮]] [[ID=⑯]]The computer 20 drives the camera 10 to acquire a video and calculates the flow of people data based on the acquired video. The computer 20 estimates the dirt on the floor 101 of the evaluation location 100 based on the flow of people data. [[ID=⑰]] [[ID=⑱]]

[0014] [[ID=⑲]] The pedestrian flow data includes step count data indicating which step each of a plurality of people moving through the evaluated location is at during a predetermined evaluation period, and the stepping-in position at the evaluated location 100 for each step count data. In other words, it can be said that the pedestrian flow data indicates the movement trajectories of a plurality of people at the evaluated location 100 respectively.

[0015] The display device 30 displays the dirt on the floor 101 estimated by the computer 20. For example, the display device 30 maps and displays the dirt at each estimated position according to the layout at the evaluated location 100.

[0016] FIG. 3 shows a schematic process of the floor dirt estimation method. In the dirt estimation system 1 according to the present embodiment, in advance, the first correlation formula F1 is calculated in the first step P1, and then, after the pedestrian flow data is calculated in the second step P2 using the computer 20, the floor dirt is estimated in the third step P3 based on the first correlation formula F1 and the pedestrian flow data.

[0017] The first correlation formula F1 indicates the amount of dirt adhesion with respect to the number of steps, and shows the relationship with the amount of dirt adhesion to the floor 101 for each step when stepping in while moving through the evaluated location 100. The first correlation formula F1 is calculated for each of the evaluated locations 100. Also, the first correlation formula F1 may be calculated in advance according to the properties and / or characteristics of the floor, such as tile, concrete, wood, etc.

[0018] In this embodiment, the first correlation equation F1 was calculated based on experimental data. Specifically, first, the degree of dirt accumulation for each step was captured when moving on a black felt laid on the floor 101 with dirty shoes. Next, the captured images were converted to grayscale, and Figure 4 shows a histogram representing the relationship between each pixel value constituting the grayscale image and the number of pixels having that pixel value. As shown in Figure 4, the number of pixels is high in two locations (below 150 and around 150), and the higher pixel values ​​in the bimodal pattern indicate whiter areas, so it is estimated that these areas indicate dirt. By setting an appropriate threshold in this way, it becomes possible to automatically detect image areas where dirt is present. It is estimated that the high number of pixels in the edge region around 255 pixel values ​​is due to noise.

[0019] In this embodiment, the degree of dirt adhesion was measured by moving footwear over black felt with a powder conforming to type 2 of test powder 1 specified in JIS Z8901 pre-attached as dirt, but this is not limited to this. The measurement may also be performed by moving footwear over the floor 101 of the actual evaluation location 100, and in this case, any dirt may be pre-attached to the footwear, for example, dirt (e.g., oil, mud, etc.) that is expected depending on the location / attributes of the evaluation location 100 may be attached before the measurement is performed.

[0020] Next, the ratio of pixels at peaks with a pixel value around 150 to the total number of pixels, i.e., the dirt accumulation rate, was calculated. This calculation was performed for all footprints, and a graph showing the number of steps and the dirt accumulation rate was obtained, as shown in Figure 5. As shown in Figure 5, it can be seen that the dirt accumulation rate decreases as the number of steps increases. Based on each plot in Figure 5, the first correlation equation F1 was calculated by finding an approximate formula showing the relationship between the number of steps and the dirt accumulation rate, for example, by the least squares method. In this embodiment, the first correlation equation F1 was calculated experimentally, but it is not limited to this and may be set by any method or concept. For example, the first correlation equation F1 may be set so that the dirt accumulation rate decreases as the number of steps increases. In this embodiment, the dirt accumulation rate calculated by the first correlation equation F1 was used as the number of dirt points for each step, as described later.

[0021] The configuration of the computer 20 for executing the second process P2 and the third process P3 will be described below with reference to Figure 1.

[0022] Computer 20 is a well-known computer having memory, a storage unit 21, and an arithmetic processing unit 22. The storage unit 21 stores the first correlation formula F1, which was calculated in advance in the first step P1.

[0023] The arithmetic processing unit 22 has a functional unit that performs specific functions by executing various programs stored in the storage unit 21, and this functional unit includes a pedestrian flow data measurement unit 23, a pedestrian flow data estimation unit 24, a pedestrian flow data modification unit 25, a second correlation formula calculation unit 26, a dirt score calculation unit 27, and a display output unit 28.

[0024] The pedestrian flow data measurement unit 23 calculates first pedestrian flow data, which shows the movement of people at the evaluation location 100 during a predetermined first period, based on the input from the camera 10. In this embodiment, an Azure Kinect RGB-D camera manufactured by Microsoft is used as the camera 10, but other camera systems capable of acquiring skeletal data may be used. The pedestrian flow data measurement unit 23 acquires skeletal data for each person being measured as they move around the evaluation location 100 from the video captured by the camera 10, using the functions of the Azure Kinect.

[0025] Next, the human flow data measurement unit 23 acquires the position (coordinates) and date and time when the subject's feet contact the floor 101, based on the acquired skeletal data. If the accuracy of the toe data is insufficient and the accuracy of the knee data is sufficient, for example, the human flow data measurement unit 23 will acquire the data when the knee acceleration in the acquired skeletal data is zero, or can be considered substantially zero (for example, when the absolute value of the acceleration is 0.05 m / s²). 2 The foot may be determined to have made contact with the floor 101 when the following conditions are met. The pedestrian flow data measurement unit 23 acquires step count data and coordinates for each person being measured by assigning step count data (which step it is) in order of earliest time.

[0026] The pedestrian flow data estimation unit 24 estimates second pedestrian flow data, which shows the movement of people at the evaluation location 100 during a second period that is longer than the first period, based on the first pedestrian flow data. For example, the first pedestrian flow data may be expressed as a function of period (number of days, hours), and the second pedestrian flow data may be estimated by extrapolating the pedestrian flow data for the second period using this function.

[0027] The pedestrian flow data modification unit 25 modifies the second pedestrian flow data based on the mat placement information. Specifically, for each of the second pedestrian flow data, the unit adds information about whether or not people stepped on the mats and the number of times people stepped on the mats, taking into account the mat placement information, to create modified pedestrian flow data. The pedestrian flow data modification unit 25 may also modify the first pedestrian flow data based on the mat placement information, in which case the pedestrian flow data estimation unit 24 may estimate the modified second pedestrian flow data from the modified first pedestrian flow data.

[0028] The second correlation formula calculation unit 26 calculates the second correlation formula F2. The second correlation formula F2 indicates the amount of dirt adhering from the footwear to the floor 101 for each step (which step) after stepping on the mat. In this embodiment, the second correlation formula calculation unit 26 calculates the second correlation formula F2 by multiplying the first correlation formula F1 by a predetermined coefficient (for example, 0.7) according to the number of times the mat was stepped on before each step. For example, if the mat was stepped on twice before the step in question, the second correlation formula calculation unit 26 calculates the second correlation formula F2 by multiplying the first correlation formula F1 by the predetermined coefficient twice. The predetermined coefficient is set to less than 1 so that the dirt adhesion rate decreases as the mat is stepped on.

[0029] The dirt score calculation unit 27 calculates the dirt score for each of the second pedestrian flow data and the modified pedestrian flow data based on the first correlation formula F1 or the second correlation formula F2. The dirt score calculation unit 27 calculates the total dirt score for each location on the floor 101 of the evaluation location 100 by organizing and summing the dirt scores calculated for each of the pedestrian flow data of multiple people for each location. In other words, a higher total dirt score indicates that the floor is dirtier.

[0030] The display output unit 28 outputs the total number of soiled areas at each location, calculated based on the second pedestrian flow data and the modified pedestrian flow data, to the display device 30. The display output unit 28 may also map the soiling at each location to the display device 30 by changing the color according to the magnitude of the total number of soiled areas.

[0031] Figure 6 is a flowchart showing the flow of the second step P2 and the third step P3. Referring to Figure 6, the process for estimating floor soiling will be explained. As mentioned above, the first correlation equation F1 is calculated in advance and stored in the storage unit 21 of the computer 20.

[0032] First, in step S1, the pedestrian flow data measurement unit 23 measures first pedestrian flow data for each of the multiple people being evaluated who move around the evaluation location 100 during a predetermined first period, based on input from the camera 10. As shown in Figure 7, the pedestrian flow data 1 in one example is the pedestrian flow data for one of the multiple people being evaluated, and includes the date and time, step count data (which step it is), and the position (plane coordinates Xn, Yn) of each step. In the pedestrian flow data 1, step count data from the first step to the nth step is measured along with each position.

[0033] Next, in step S2, the pedestrian flow data estimation unit 24 estimates the second pedestrian flow data from the first pedestrian flow data. As described above, the second period related to the second pedestrian flow data is longer than the first period related to the first pedestrian flow data.

[0034] Next, in step S3, the dirt score calculation unit 27 calculates the total dirt score Z100 for each position on the floor 101 of the evaluation location 100 based on the second pedestrian flow data and the first correlation formula F1.

[0035] As shown in Figure 8, as an example, the dirt score calculation unit 27 calculates dirt scores Z1... from the first correlation formula F1 for the step count data of each of the multiple people being evaluated who have stepped into location (Xn, Yn). Next, the dirt score calculation unit 27 calculates the total dirt score Z100 for the second pedestrian flow data at location (Xn, Yn) by summing the multiple dirt scores Z1... calculated for each of the multiple step count data at location (Xn, Yn). The total dirt score Z100 is used to estimate the level of dirt on the floor 101 during the first period at location (Xn, Yn).

[0036] Next, in step S4, the arrangement information of the mats 70 is input to the computer 20 via the input device 11. As shown in Figure 12, in one example of the arrangement of the mats 70, mats 71 and 72 are placed on both the outside and inside sides of the entrance 110 of the evaluation location 100, mats 73 and 74 are placed on both the inside and outside sides of the cash register corner 120, mat 75 is placed in the handwashing corner 130, and mat 76 is placed in the self-service coffee server corner 140.

[0037] Next, in step S5, the pedestrian flow data modification unit 25 modifies the second pedestrian flow data, taking into account the placement information of the mats 70. Specifically, for each step data, the pedestrian flow data modification unit 25 considers the walking trajectory S shown in Figure 12 and the placement information of the mats 70, and adds to each step data whether or not the mat 70 was stepped on before the step, and if the mat 70 was stepped on, the number of steps. As shown in Figure 9, the modified pedestrian flow data 1 in one example shows that the mat 70 was stepped on in the first step and the second mat 70 was stepped on in the fourth step.

[0038] Next, in step S6, the dirt score calculation unit 27 calculates the total dirt score Z200 for each position on the floor 101 of the evaluation location 100 based on the modified pedestrian flow data, the first correlation formula F1, and the second correlation formula F2.

[0039] As shown in Figure 10, as an example, the dirt score calculation unit 27 calculates a dirt score Z11... for each of the step count data for multiple people being evaluated who stepped on the mat 70, by applying the first correlation formula F1 or the second correlation formula F2 according to the number of times the mat 70 was stepped on to the step count data for each of the step count data.

[0040] Here, if the number of times the mat 70 is stepped on is zero, the first correlation formula F1 is used, and if the number of times the mat 70 is stepped on is one or more, the second correlation formula F2 is used. As described above, the second correlation formula F2 is calculated by multiplying the first correlation formula F1 by a predetermined coefficient according to the number of times the mat 70 is stepped on. In the example in Figure 10, the mat 70 is stepped on for the second time on the fourth step, so on the fifth step, the second correlation formula F2 is calculated by multiplying the first correlation formula F1 by a predetermined coefficient twice. In other words, step S6 includes a step for calculating the second correlation formula.

[0041] Next, the dirt score calculation unit 27 calculates a total dirt score Z200 for the modified pedestrian flow data at location (Xn, Yn) by summing up the multiple dirt score Z11... calculated for each of the multiple step count data at location (Xn, Yn). The total dirt score Z200 is used to estimate the level of dirt on the floor 101 during the second period with the mat in place at location (Xn, Yn).

[0042] Next, in step S7, the display output unit 28 outputs the total number of stains Z100 and Z200 at each position on the floor 101 of the evaluation location 100 to the display device 30. The display output unit 28 outputs the total number of stains Z100 and Z200 for each position to the display device 30 as data for mapping and displaying in colors set according to the size of the stains.

[0043] Finally, the display device 30 maps the estimated dirt to each location on the floor 101 of the evaluation location 100. By referring to the mapping displayed on the display device 30, the dirt on the floor 101 of the evaluation location 100 can be visually understood, and the location and degree of dirt can be quantitatively grasped.

[0044] Furthermore, by comparing the mapping display for the total number of stains Z100 without the mat 70 in place (Figure 11) with the mapping display for the total number of stains Z200 with the mat 70 in place (Figure 12), it is possible to examine the effect of reducing stain adhesion to the floor 101 by placing the mat 70. In addition, by comparing the mapping displays for the total number of stains in the first and second states, which have different display states for the mat 70, it is possible to easily consider a more appropriate placement of the mat 70.

[0045] The floor soiling estimation system described in this disclosure provides the following benefits:

[0046] (1) The method for estimating floor contamination includes a pedestrian flow measurement step S1, which measures pedestrian flow data indicating human movement at the location to be evaluated 100, Floor dirt estimation steps S3 and S6 estimate the level of dirt on the floor of the 100 locations to be evaluated based on pedestrian flow data. Includes. According to this configuration, the level of dirt on the floor 101 at the location 100 to be evaluated can be quantitatively evaluated by estimating the level of dirt on the floor 101 based on measured pedestrian flow data.

[0047] (2) A second pedestrian flow estimation step S2 is performed, in which, based on the first pedestrian flow data, second pedestrian flow data is estimated that shows the movement of people in the evaluation location 100 over a second period longer than the first period. It further includes, In floor soiling estimation step S3, the amount of soiling on the floor at the evaluation location 100 during the second period is predicted based on the second pedestrian flow data. This configuration allows for a quantitative evaluation of floor contamination over a longer period by estimating second-tier pedestrian flow data.

[0048] (3) The pedestrian flow data includes step count data for each step taken at each of the 100 locations under evaluation. With this configuration, the level of dirt on the floor at each of the locations to be evaluated 100 can be accurately estimated based on the step count data at each location to be evaluated 100.

[0049] (4) The step count data shows the position of each step, with the first step being the step taken after passing through the designated entrance 110. With this configuration, the level of dirt on the floor can be estimated more accurately at each location of the evaluation site 100 based on the position of each step.

[0050] (5) The process further includes a correlation formula calculation step in which a first correlation formula F1 is calculated in advance to determine the level of dirt on floor 101 in relation to the step count data, The floor soiling estimation step S3 includes calculating a total soiling score Z100 by accumulating the soiling score Z for each step data based on the step data and the first correlation equation F1. According to this configuration, the first correlation equation F1 calculates the amount of dirt on the floor 101 as a dirt score Z for each step data indicating which step the foot took. For example, the first correlation equation F1 can represent a pattern where the amount of dirt transferred from the footwear to the floor is relatively large for the first step, and gradually decreases as the number of steps increases. Therefore, by using the first correlation equation F1, the amount of dirt transferred from the footwear to the floor 101 can be predicted with high accuracy for each step data, and the amount of dirt on the floor 101 can be estimated with even greater accuracy at each location of the evaluation site 100.

[0051] (6) When one or more mats 70 are installed at the evaluation location 100, The process further includes a second correlation calculation step, which calculates a second correlation formula F2 that indicates the level of dirt on the floor 101 in relation to the step count data when stepping on mat 70. The step count data for each location includes stepping information indicating whether or not the mat 70 was stepped on before the step corresponding to that step data. In the floor soiling estimation step S6, for each step data, the first correlation formula F1 is used if the mat 70 was not stepped on, and the second correlation formula F2 is used if the mat 70 was stepped on, based on the stepping information. With this configuration, by using the second correlation formula F2, the degree of soiling on the floor 101 can be accurately estimated by considering whether or not the mat 70 has been stepped on.

[0052] (7) The step count data for each position includes information on the number of times the mat 70 was stepped on before the step corresponding to that step count data. The second correlation formula calculation step calculates the second correlation formula F2 according to the number of times the mat 70 is stepped on. With this configuration, the second correlation equation F2 can be optimized according to the number of times the mat 70 is stepped on.

[0053] (8) The second correlation equation F2 is obtained by multiplying the first correlation equation F1 by a predetermined coefficient. With this configuration, the second correlation equation F2 can be easily calculated from the first correlation equation F1.

[0054] (9) Further includes comparing the total number of soiled items in the first and second states, which have different installation conditions for the mat 70. With this configuration, the effect of reducing dirt by installing the mat 70 can be examined by comparing the total number of dirt points in the first and second states. It is also possible to consider the optimal installation location for the mat 70. For example, if the installation location of the mat 70 is changed in several patterns, the amount of dirt on the floor 101 can be estimated by determining how many times the mat 70 has been stepped on for each step at each position in each pattern.

[0055] (10) The floor soiling estimation program causes the computer 20 to function as a floor soiling estimation means, which estimates the soiling of the floor 101 of the evaluation location 100 based on first human flow data that shows the movement of people in the evaluation location 100, which has been measured in advance.

[0056] The floor soiling estimation system 1 according to this disclosure is not limited to the configuration of the embodiment described above, and various modifications are possible.

[0057] In the above embodiment, the case in which second pedestrian flow data is obtained from first pedestrian flow data that has been measured was explained as an example, but the embodiment is not limited to this. That is, the number of soiled items in the first period may be calculated from the first pedestrian flow data, or the number of soiled items in the first period with the mat arrangement may be calculated by modifying the first pedestrian flow data considering the mat arrangement information.

[0058] In other words, as shown in Figure 13, without performing step S2 to estimate the second pedestrian flow data, In the pedestrian flow measurement step S1, first pedestrian flow data showing the movement of people in the evaluation location 100 during the first period is measured. In floor contamination estimation steps S3 and S6, the amount of contamination on the floor at the location to be evaluated 100 during the first period is estimated based on the first pedestrian flow data. According to this configuration, the degree of soiling of the floor 101 at the location 100 to be evaluated during the first period can be quantitatively evaluated based on the first pedestrian flow data measured during the first period.

[0059] Furthermore, as shown in Figure 14, a step S11 may be added to determine whether the mat 70 needs to be replaced based on the number of times the mat has been stepped on, and the mat replacement information may be displayed on the display device 30 along with the mapping display. In this case, as shown by the dashed line in Figure 1, the calculation processing unit 22 is further configured with a mat replacement determination unit 29. The mat replacement determination unit 29 determines whether the mat 70 needs to be replaced by comparing the number of times the mat 70 has been stepped on with a predetermined threshold. According to the mat replacement determination unit 29, information on replacing the mat 70 can be provided based on the number of times the mat has been stepped on, making it easier to maintain the dirt removal performance of the mat 70.

[0060] In the above embodiment, the second correlation formula F2 was described as being calculated by multiplying the first correlation formula F1 by a predetermined coefficient, but it is not limited to this. For example, the second correlation formula F2 may be calculated experimentally in the same way as the first correlation formula F1, depending on the number of times the mat 70 is stepped on.

[0061] The floor soiling estimation system described herein provides the following aspects.

[0062] [Aspect 1] A pedestrian flow measurement step, which measures pedestrian flow data showing the movement of people at the location to be evaluated, A floor soiling estimation step, which estimates the soiling of the floor at the location to be evaluated based on the pedestrian flow data, and A method for estimating floor dirt, including [specific details omitted].

[0063] [Aspect 2] In the aforementioned pedestrian flow measurement step, first pedestrian flow data showing the movement of people at the location under evaluation during a first period is measured. In the floor soiling estimation step, the amount of soiling on the floor at the location to be evaluated during the first period is estimated based on the first pedestrian flow data. The method for estimating floor contamination as described in Embodiment 1.

[0064] [Aspect 3] The method further includes a second pedestrian flow estimation step, which estimates second pedestrian flow data showing the movement of people in a second period longer than the first period at the location under evaluation, based on the first pedestrian flow data. In the floor soiling estimation step, the amount of soiling on the floor at the location to be evaluated during the second period is predicted based on the second pedestrian flow data. The method for estimating floor contamination as described in Embodiment 2.

[0065] [Aspect 4] The aforementioned pedestrian flow data includes step count data for each step taken at each location of the place being evaluated. A method for estimating floor soiling according to any one of embodiments 1 to 3.

[0066] [Aspect 5] The aforementioned step count data indicates the position of each step, with the first step being the step taken after passing through a predetermined entrance. The method for estimating floor contamination as described in Embodiment 4.

[0067] [Aspect 6] The process further includes a correlation formula calculation step, which pre-calculates a first correlation formula that calculates the dirtiness of the floor as a dirtiness score in relation to the step count data. The floor soiling estimation step includes calculating a total soiling score by accumulating the soiling score for each of the step data based on the step count data and the first correlation formula. A method for estimating floor soiling according to embodiment 4 or 5.

[0068] [Aspect 7] When one or more mats are installed at the location to be evaluated, The process further includes a second correlation formula calculation step, which calculates a second correlation formula indicating the degree of dirtiness on the floor in relation to the step count data when the mat is stepped on. The step count data at each of the aforementioned positions includes stepping information indicating whether or not the mat was stepped on before the stepping corresponding to the step count data. The floor soiling prediction step uses, for each step data, the first correlation formula if the mat was not stepped on, and the second correlation formula if the mat was stepped on, based on the stepping information. The method for estimating floor contamination as described in Embodiment 6.

[0069] [Aspect 8] The step count data at each of the aforementioned positions includes information on the number of times the mat was stepped on before the step corresponding to the step count data. The second correlation formula calculation step calculates the second correlation formula according to the number of times the mat is stepped on. The method for estimating floor contamination as described in Embodiment 7.

[0070] [Aspect 9] The second correlation equation is obtained by multiplying the first correlation equation by a predetermined coefficient. The method for estimating floor soiling according to embodiment 7 or 8.

[0071] [Aspect 10] This further includes comparing the total number of soiled items in a first state and a second state, where the mats are installed in different ways. A method for estimating floor soiling according to any one of embodiments 7 to 9.

[0072] [Aspect 11] A floor dirt estimation program that causes a computer to function as a floor dirt estimation means, which estimates the dirtiness of the floor at a location to be evaluated based on first pedestrian flow data that shows the movement of people at the location to be evaluated, which has been measured in advance. [Explanation of symbols]

[0073] 1. Floor soiling estimation system 10 Cameras 11 Input devices 20 Computers 21 Memory section 22 Arithmetic Processing Unit 23 People flow data measurement section 24 People flow data estimation section 25 Human flow data modification department 26. Second Correlation Formula Calculation Unit 27. Dirt Score Calculation Unit 28 Display Output Section 29 Mat replacement determination unit 30 Display device 70 mat 110 Entrance

Claims

1. A pedestrian flow measurement step, which measures pedestrian flow data showing the movement of people at the location to be evaluated, A floor soiling estimation step, which estimates the soiling of the floor at the location to be evaluated based on the pedestrian flow data, and A method for estimating floor dirt, including [specific details omitted].

2. In the pedestrian flow measurement step, first pedestrian flow data showing the movement of people in the evaluation location during a first period is measured. In the floor soiling estimation step, the amount of soiling on the floor at the location to be evaluated during the first period is estimated based on the first pedestrian flow data. The method for estimating floor soiling according to claim 1.

3. The process further includes a second pedestrian flow estimation step, which estimates second pedestrian flow data showing the movement of people in the location under evaluation over a second period longer than the first period, based on the first pedestrian flow data. In the floor soiling estimation step, the amount of soiling on the floor at the location to be evaluated during the second period is predicted based on the second pedestrian flow data. The method for estimating floor soiling according to claim 2.

4. The aforementioned pedestrian flow data includes step count data for each step taken at each location of the place being evaluated. The method for estimating floor soiling according to claim 1.

5. The aforementioned step count data indicates the position of each step, with the first step being the step taken after passing through a predetermined entrance. The method for estimating floor soiling according to claim 4.

6. The process further includes a correlation formula calculation step, which involves pre-calculating a first correlation formula that calculates the dirtiness of the floor as a dirtiness score in relation to the step count data. The floor soiling estimation step includes calculating a total soiling score by accumulating the soiling score for each of the step data based on the step count data and the first correlation formula. The method for estimating floor soiling according to claim 4 or 5.

7. When one or more mats are installed at the location to be evaluated, The process further includes a second correlation formula calculation step, which calculates a second correlation formula indicating the degree of dirtiness on the floor in relation to the step count data when the mat is stepped on. The step count data at each of the aforementioned positions includes stepping information indicating whether or not the mat was stepped on before the stepping related to the step count data. The floor soiling prediction step uses, for each step data, the first correlation formula if the mat was not stepped on, and the second correlation formula if the mat was stepped on, based on the stepping information. The method for estimating floor soiling according to claim 6.

8. The step count data at each of the aforementioned positions includes information on the number of times the mat was stepped on before the step corresponding to the step count data. The second correlation formula calculation step calculates the second correlation formula according to the number of times the mat is stepped on. The method for estimating floor soiling according to claim 7.

9. The second correlation equation is obtained by multiplying the first correlation equation by a predetermined coefficient. The method for estimating floor soiling according to claim 7.

10. This further includes comparing the total number of soiled items in a first state and a second state, where the mats are installed in different ways. The method for estimating floor soiling according to claim 7.

11. A floor dirt estimation program that causes a computer to function as a floor dirt estimation means, which estimates the dirtiness of the floor at a location to be evaluated based on first pedestrian flow data that shows the movement of people at the location to be evaluated, which has been measured in advance.

Images