Information processing device, information processing system, information processing method, program

Abstract

It is not possible to improve the accuracy of motion recognition of an object by measuring its temperature. [Solution] The information processing device of the present disclosure comprises a measuring unit that measures the operating speed of an object in a predetermined area, an acquisition unit that acquires a temperature distribution image of the predetermined area, a generating unit that generates a difference image of the temperature distribution image at time intervals based on the operating speed, and a recognition unit that recognizes the operation of the object based on the difference image.

Description

Technical Field

[0001] This disclosure relates to an information processing apparatus, an information processing system, an information processing method, and a program.

Background Art

[0002] As described in Patent Document 1, the actions of persons such as the elderly and care recipients are monitored to detect abnormalities. For example, in Patent Document 1, a temperature change within a detection area is detected using an infrared sensor to detect an abnormality of a person. By using a temperature sensor such as an infrared sensor, it is possible to detect an abnormality while protecting the privacy of the person.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, within the detection area as described above, there may be heat sources other than persons, such as heating devices and lighting fixtures, that have a high temperature. For this reason, there are cases where a person and a heat source other than a person are detected in a mixed state, and it is impossible to appropriately detect the actions of the person. As a result, there is a problem that it is impossible to improve the accuracy of recognizing the actions of an object by temperature measurement.

[0005] Therefore, one object of the present disclosure is to solve the above-described problem that it is impossible to improve the accuracy of recognizing the actions of an object by temperature measurement.

Means for Solving the Problems

[0006] An information processing apparatus according to one embodiment of the present disclosure is a measurement unit that measures the movement speed of an object in a predetermined area, An acquisition unit that acquires a temperature distribution image of the predetermined region, A generation unit that generates a difference image of the temperature distribution image at a time interval based on the operating speed, A recognition unit that recognizes the movement of the object based on the difference image, Equipped with, This is the structure it takes. Furthermore, an information processing system, which is one form of this disclosure, A radar that detects the movement of an object in a predetermined area, A temperature sensor for detecting the temperature distribution in the predetermined region, A measurement unit that measures the movement speed of the object based on the detection results from the radar, An acquisition unit that acquires a temperature distribution image of the predetermined region from the detection result by the temperature sensor, A generation unit that generates a difference image of the temperature distribution image at a time interval based on the operating speed, A recognition unit that recognizes the movement of the object based on the difference image, Equipped with, This is the structure it takes. Furthermore, the information processing method, which is one form of this disclosure, The movement speed of the object in a predetermined area is measured, A temperature distribution image of the predetermined region is acquired, A difference image of the temperature distribution image over time intervals based on the operating speed is generated. Based on the difference image, the movement of the object is recognized. This is the structure it takes. Furthermore, one form of this disclosure is a program, In an information processing device, The movement speed of the object in a predetermined area is measured, A temperature distribution image of the predetermined region is acquired, A difference image of the temperature distribution image over time intervals based on the operating speed is generated. Based on the difference image, the movement of the object is recognized. To execute the process This is the structure it takes. [Effects of the Invention]

[0007] By being configured as described above, the present disclosure can improve the accuracy of recognizing the operation of an object by temperature measurement.

Brief Description of the Drawings

[0008] [Figure 1] It is a diagram showing an example of a part of the configuration of an information processing system according to the present disclosure. [Figure 2] It is a block diagram showing an example of the configuration of an information processing system according to the present disclosure. [Figure 3] It is a flowchart showing an example of the processing operation of an information processing apparatus according to the present disclosure. [Figure 4] It is a diagram showing an example of the state of processing by an information processing apparatus according to the present disclosure. [Figure 5] It is a diagram showing an example of the state of processing by an information processing apparatus according to the present disclosure. [Figure 6] It is a block diagram showing an example of the hardware configuration of an information processing apparatus according to the present disclosure. [Figure 7] It is a block diagram showing an example of the configuration of an information processing apparatus according to the present disclosure.

Modes for Carrying Out the Invention

[0009] <First Embodiment> The first embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings may be relevant to any of the embodiments.

[0010] The information processing system of the present disclosure is used, for example, to recognize the actions of people such as the elderly and care recipients. In particular, in this embodiment, an example is given of the case where the actions of people in an indoor space are recognized using a radar and a temperature sensor. However, the information processing system of the present disclosure may be used not only for the elderly and the like, but also for recognizing the actions of any person such as infants, and furthermore, not only for people, but also for recognizing the actions of any object such as animals. Also, the space for recognizing the actions of the object is not limited to the indoor space, and may be any place.

[0011] An example of the configuration and operation of the information processing system in this embodiment will be described in detail. FIG. 1 shows an indoor space 1 which is an example of a predetermined area for recognizing the actions of a person 3. The indoor space 1 is, for example, a private toilet for care, in which a toilet 2 is installed, and it is assumed that an entrance / exit 7 through which the person 3 can enter with a wheelchair 4 is provided. Note that the structure of the indoor space 1 described above is an example, and any structure may be used.

[0012] And a temperature sensor 5 is installed in the indoor space 1. As an example, the temperature sensor 5 is a thermopile array sensor, and detects the temperature distribution of the indoor space 1 according to the number of elements of the thermopile array sensor installed. At this time, as will be described later, a thermoarray sensor with a low number of pixels is sufficient for use in this embodiment. And the temperature sensor 5 is installed on the ceiling of the indoor space 1, and detects the temperature distribution of the indoor space 1 from above to below. However, the temperature sensor 5 may be installed at any location in the indoor space 1. Note that the thermoarray sensor is an example of the temperature sensor 5, and the temperature sensor 5 with other configurations may also be used.

[0013] Furthermore, a radar 6 is installed in the indoor space 1. The radar 6 is, for example, a millimeter-wave radar, specifically a 24GHz Doppler radar. A 24GHz Doppler radar has a detection range of several meters to over ten meters depending on the gain setting, and can detect the movement of objects within the detection range, determining the speed of movement and whether it is approaching or moving away. With a high-precision device, it can detect not only human movement but also respiratory rate and pulse rate. The radar 6 is installed in the corner opposite the entrance / exit 7 of the indoor space 1, and detects the movement of objects in the indoor space 1 in the direction of the entrance / exit 7. However, the radar 6 may be installed anywhere in the indoor space 1. Note that the millimeter-wave radar is just one example of the radar 6; other configurations of the radar 6 are also possible.

[0014] As shown in Figure 2, the temperature sensor 5 and radar 6 are connected to the information processing device 10. The temperature sensor 5 and radar 6 each transmit their detection results to the information processing device 10 at predetermined time intervals.

[0015] Next, the configuration and operation of the information processing device 10 will be described. Figure 2 shows an example of the configuration of the information processing device 10, and Figure 3 shows an example of the operation of the information processing device 10. The information processing device 10 is composed of one or more information processing devices equipped with an arithmetic unit and a storage device. As shown in Figure 2, the information processing device 10 includes a speed measurement unit 11, an image acquisition unit 12, a difference generation unit 13, and an action recognition unit 14. The functions of the speed measurement unit 11, the image acquisition unit 12, the difference generation unit 13, and the action recognition unit 14 can be realized by the arithmetic unit executing a program for realizing each function stored in the storage device. The information processing device 10 also includes a data storage unit 15 realized in the storage device.

[0016] The following describes the function and operation of each component, using the situation when person 3 enters indoor space 1 as an example. Here, the diagrams (4-1X) (X: A, B, or C) in the upper part of Figure 4 show the state of indoor space 1, and the diagrams (4-2X) in the middle part of Figure 4 show the temperature distribution images obtained by the temperature sensor 5. The diagrams (4-3X) in the lower part of Figure 4 show the difference images of the temperature distribution images. Specifically, as will be described later, these show the difference images of the temperature distribution images at a time interval calculated from the movement speed of person 3 when they enter the room, compared to the temperature distribution image at the time person 3 enters the room. The diagrams (4-NA) (N: 1, 2, or 3) in the first column of Figure 4 show the time when person 3 enters indoor space 1, the diagram (4-NB) in the second column of Figure 4 shows the time when person 3 approaches the toilet 2, and the diagram (4-NC) in the third column of Figure 4 shows the time when person 3 sits on the toilet 2. In this case, the field of view (FOV) of the temperature sensor 5 is assumed to be an overhead view of the entire room space 1, including the entrance / exit 7 and the toilet 2. In addition, an entry / exit monitoring area 8 is set for the coordinates of the temperature sensor corresponding to the entrance / exit 7 in order to determine when a person 3 appears at the location of the entrance / exit 7.

[0017] First, the radar 6 detects the movement of an object within its detection range and transmits the detection result to the information processing device 10. Then, the speed measurement unit 11 (measurement unit) measures the movement speed of the object from the detection result by the radar 6 (step S1 in Figure 3). At this time, the speed measurement unit 11 can measure the movement speed of person 3 using the Doppler effect of the millimeter-wave radar, and can accurately determine the movement speed in real time. Specifically, as shown in Figure 4 (4-1A), when person 3 enters the indoor space 1, the speed measurement unit 11 detects the opening and closing operation of the door of the entrance 7 from the detection result of the radar 6, and measures the movement speed of person 3 from the result of the radar 6 detecting the movement of person 3 toward the indoor space 1. The speed measurement unit 11 may also store the measured movement speed in the data storage unit 15.

[0018] Furthermore, the temperature sensor 5 detects heat sources within its detection range and transmits the detection result to the information processing device 10. The image acquisition unit 12 (acquisition unit) then acquires a temperature distribution image (thermographic image) of the indoor space 1 from the detection result by the temperature sensor 5 (step S2 in Figure 3). Specifically, as shown in Figure 4 (4-1A), when person 3 enters or leaves the indoor space 1, the image acquisition unit 12 acquires a temperature distribution image as shown in Figure 4 (4-2A) and stores it in the data storage unit 15. At this time, the temperature distribution image shown in Figure 4 (4-2A) will include a heat source Aa emitted by person 3 who has entered the room, and a heat source An emitted by a heating appliance that was originally in the room. Note that heat source An is an external disturbance other than person 3 and may be mistakenly detected as person 3.

[0019] Subsequently, as shown in Figure 4(4-1B), when person 3 moves into the room from the entrance / exit 7, the speed measurement unit 11 measures the movement speed of person 3 from the detection results by the radar 6 (step S1 in Figure 3), as described above, and also measures the duration of the movement. Then, the image acquisition unit 12 acquires a temperature distribution image as shown in Figure 4(4-2B) (step S2 in Figure 3). At this time, the temperature distribution image shown in Figure 4(4-2B) will contain heat source Ab that does not fall within the entry / exit monitoring area 8 and heat source An that acts as a disturbance factor.

[0020] The difference generation unit 13 (generation unit) then determines the time interval of the temperature distribution image from which the difference is taken, based on the measured movement speed of person 3 (step S3 in Figure 3). At this time, the difference generation unit 13 determines a time interval in which the movement of person 3 can be captured. As an example, the difference generation unit 13 calculates the movement time of person 3 between elements of the thermopile array sensor, which is the temperature sensor 5, that is, between pixels of the temperature distribution image. Then, the difference generation unit 13 determines, from the movement time and the image distribution image, the time it takes for the position of heat source Aa (person 3) at the time of entering the indoor space 1 (first region) to move to the position of heat source Ab (person 3) (second region) which does not overlap with the entry / exit monitoring region 8, as the time interval in which the movement of person 3 can be captured. At this time, the approach time (Ab), which is the time elapsed from the time of person 3 entering (Aa) by the movement time, is identified.

[0021] Next, the difference generation unit 13 generates a difference image of each temperature distribution image before and after the time interval determined as described above (step S4 in Figure 3). In the above example, the difference image will be the image shown in Figure 4 (4-3B). As shown in this figure, in the difference image, in a standard room with a temperature of 25°C, the heat source Bb (Bn(n: a, b or c)) corresponding to the part of person 3 takes a positive value at the current position, and the heat source Ca (Cn(n: a or b)) appears as a negative value at past positions. The heat source An, which is a disturbance factor, changes generally slowly, so it takes a similar value at each point in time and is removed, and does not appear in the difference image. That is, in the difference image obtained by subtracting the temperature distribution image at the time of entry (4-2A) from the temperature distribution image at the time of person 3's approach (4-2B), as shown in Figure 4 (4-3B), the disturbance factor An, which does not change at a rate equivalent to the movement speed of person 3, is removed along with the other background. This allows for highly accurate determination of the heat source Bb portion, which is a positive difference value representing the three parts of the person at the time of approach, and the heat source Ca portion, which is a negative difference value with the opposite sign, corresponding to the three parts of the person at the time of entry.

[0022] Next, the difference generation unit 13 generates a difference image (4-3C) between the temperature distribution image (4-2B) and a temperature distribution image (4-2C) taken after a further time has passed. In this image as well, the disturbance factor An is removed along with the other background, and the heat source Bb portion, which is a positive difference value representing the current part of person 3, and the heat source Ca portion, which is a negative difference value with the opposite sign, corresponding to the past part of person 3, can be obtained with high accuracy. If we assume that the heat source Aa at the time of entering the room is a heat source due to a disturbance other than person 3, then since there is no movement into the room, the heat source Ab should not be observed, and therefore the heat sources Bb and Ca that appear in the difference image in Figure 4 (4-3C) are reliable data. Furthermore, since the heat source An does not move even when the radar 6 detects the opening and closing of the door or the movement of person 3, it can be seen that such heat source An is a disturbance factor. In this method, by detecting person movement, the value at a very close point in time, which is the minimum time difference, can be used, thereby minimizing the time change of temperature. Furthermore, external disturbances that change faster than the movement speed of Person 3 can be resolved by using average or cumulative values.

[0023] The motion recognition unit 14 (recognition unit) then recognizes the movements of person 3 based on the difference image described above. For example, the motion recognition unit 14 can recognize the position and movement of person 3 according to the position and changes of regions with mutually opposite signs in the difference image, that is, regions with positive values ​​and regions with negative values. As an example, by defining the presence of a negative temperature value in the entry / exit monitoring area 8 and a positive temperature value in the indoor space 1 excluding the entry / exit monitoring area 8 as the motion model for entering, it is possible to determine that person 3 has entered based on heat sources Bb and Ca, as shown in the difference image (4-3B) of Figure 4. Similarly, by defining the presence of a positive temperature value in the entry / exit monitoring area 8 and a negative temperature value in the indoor space 1 excluding the entry / exit monitoring area 8 as the motion model for exiting, it is possible to determine that person 3 has exited.

[0024] As described above, this disclosure makes it possible to improve the accuracy of object recognition. Specifically, by extracting the desired movement based on the movement speed of the object and accurately eliminating unnecessary heat sources that act as disturbances, recognition accuracy can be improved. Furthermore, by removing extraneous movements other than the desired movement, it is possible to focus only on the desired result. In addition, this allows the number of elements in the thermopile array sensor used for temperature detection to be kept to a minimum, thereby reducing costs. Data volume can also be reduced, processing speed can be improved, and processing load can be reduced. Moreover, by using a thermopile array sensor with a low number of elements, it becomes possible to monitor people while protecting their privacy, making it applicable to monitoring in private spaces such as toilets and bathrooms.

[0025] Furthermore, this disclosure makes it possible to reduce computational processing. Human detection using a thermopile array sensor usually requires processing to separate the human part from the background from the detection result. However, this disclosure does not require this, and only the difference result, which requires accuracy for use in judgment, is calculated, ensuring only the minimum accuracy, so computational processing can be greatly reduced. For example, the advantage of being able to minimize the processing unit of the edge system in an IoT system is significant, and it enables the miniaturization and weight reduction of the edge system, the construction of a battery-powered system that does not require external power supply, and energy harvesting using small solar or wind power generation. As an example, by applying this disclosure, the required processing power is about 1 / 15 of that of H.264 compression processing.

[0026] Furthermore, this disclosure offers the advantage of reducing data volume. Typically, the judgment data required for motion monitoring is video, necessitating the securing of a large amount of data and a communication interface. For example, motion monitoring using an 8x8 element thermopile array sensor requires 640 bytes of video data at 4fps and 2 seconds, even as the minimum required data volume. In contrast, the data provided by this disclosure consists only of the results of differential calculations, requiring only about 20 bytes, which is 1 / 30th in this example. This significantly contributes to solving the challenge of reducing data volume in edge systems, which has been a problem with low-capacity and inexpensive communication methods such as LPWA (Low Power Wide Area) wireless communication. Moreover, looking at the system as a whole, judgments such as occupancy or falls may be performed on the cloud side rather than on the edge device side, and in such cases, there is the advantage of being able to flexibly manage the judgment data. In this case, the edge device needs to transmit all the monitoring data, but the model data using differential acquisition as provided by this disclosure requires less data compared to normal video data, thus significantly contributing to the reduction of communication data volume.

[0027] Furthermore, this disclosure offers the advantage of cost reduction. Thermopile array sensors can produce more detailed images as they have more elements, but this also increases their cost. By applying this disclosure, even thermopile array sensors with a low number of elements can accurately extract and determine desired behavior. This is expected to reduce the cost of the entire system, not only the sensor device itself, but also by minimizing the processing unit and reducing the amount of data, thereby enabling the use of inexpensive communication methods.

[0028] Furthermore, according to this disclosure, there is a synergistic effect from combining dissimilar devices such as radar and temperature sensors. Temperature sensors lose accuracy when ambient temperature fluctuates, and it is difficult to detect people in high-temperature environments. However, radar has the characteristic that temperature fluctuations do not easily affect its monitoring characteristics, thus improving the overall environmental tolerance of the system. On the other hand, radar cannot distinguish between objects and people, and the information obtained is limited to information such as speed and size, making it difficult to understand the situation. However, temperature sensors can distinguish between objects and people based on the measured temperature, and visualization can be performed based on the temperature. Therefore, by utilizing the characteristics of each sensor, accurate monitoring can be easily achieved.

[0029] <Second Embodiment> Next, a second embodiment of this disclosure will be described with reference to the drawings. The drawings may be relevant to either embodiment.

[0030] In this embodiment, the operation for detecting falls based on changes in a person's posture will be explained. Figure 5 shows a temperature distribution image detected from behind by a temperature sensor such as a thermopile array sensor while a person is seated in a private toilet room, similar to the one described above. In this case, the temperature sensor is installed at a height of 100 cm above the floor on the side, and the room temperature is detected vertically from the side behind the person in question. In addition, the radar detects the direction of the entrance from the upper corner at the back of the room.

[0031] Figure 5(5-A) shows the temperature distribution image under normal conditions while a person is seated, and Figure 5(5-B) shows the temperature distribution image when a person falls over. These images were acquired by the image acquisition unit 12 from the detection results of the temperature sensor. In these figures, a person is detected in the field of view V (FOV) that extends vertically from the temperature sensor. The space between iv and v, which are the y-centers of the field of view V, corresponds to the floor height of 100 cm, which is the sensor installation height. The horizontal plane including this space is represented as the fall detection threshold height L within the field of view V. Furthermore, the dotted area R (first height area) located at the top of the room in the vertical direction is the fall monitoring area. The operation model for a fall is set to have negative temperature values ​​and no positive temperature values ​​in the fall monitoring area.

[0032] In the situation described above, the operation during monitoring of a person's fall will now be explained. When a person falls, the radar can capture the vertical movement component, and the speed measurement unit 11 detects the vertical movement speed. The difference generation unit 13 can then calculate the distance the person moves vertically within the field of view V of the temperature sensor from the detected movement speed and its duration. When the movement distance exceeds a certain threshold, a fall is considered possible. Therefore, starting from region R (first height region) immediately before the movement is detected, the elapsed time until the movement can be captured, that is, the time interval until the person moves to a region located below region R (second height region), is determined, and a difference image of the temperature distribution image during this time interval is obtained. At this time, the speed and duration detected by the radar may also be used as the trigger for the fall detection operation.

[0033] Then, as shown in Figure 5(5-C), a difference image of the temperature distribution image at the calculated time interval is obtained. In this figure, the region with code Ea represents a negative temperature value and corresponds to the part of the person under normal conditions. The region with code Fb represents a positive temperature value and corresponds to the part of the person when they fall. When the recognition unit 124 applies the motion model to the difference image in Figure 5(5-C), it can determine that a fall has occurred because the condition for code Ea is met. Specifically, in the above case, there is a region with negative values ​​and no region with positive values ​​in the upper region R, and there is a region with positive values ​​below the fall detection threshold L, i.e., below region R, so a fall is determined. Alternatively, to exclude temporary changes, the difference with Figure 5(5-A), which is the normal time point, can be calculated for a certain period of time to obtain several difference images, and a fall can be determined when all difference images satisfy the fall detection conditions.

[0034] <Third Embodiment> Next, a third embodiment of the present disclosure will be described with reference to the drawings. This embodiment shows an outline of the information processing device, etc., described in the embodiments described above. Note that the drawings may be relevant to any of the embodiments.

[0035] First, the hardware configuration of the information processing device 100 in this disclosure will be described. The information processing device 100 is composed of a general information processing device, and as an example, it is equipped with the following hardware configuration as shown in Figure 6. ·CPU(Central Processing Unit)101(Arithmetic unit) ROM (Read Only Memory) 102 (Storage Device) • RAM (Random Access Memory) 103 (Storage Device) • Program group 104 loaded into RAM 103 • Storage device 105 for storing the program group 104 • Drive device 106 for reading and writing to external storage medium 110 of the information processing device. • Communication interface 107 connecting to a communication network 111 outside the information processing device. • Input / output interface 108 for data input and output. • Bus 109 connecting each component

[0036] Figure 6 shows an example of the hardware configuration of the information processing device 100, and the hardware configuration of the information processing device is not limited to the case described above. For example, the information processing device may consist of only a part of the configuration described above, such as not having a drive device 106. In addition, the information processing device may use a GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating point number Processing Unit), PPU (Physics Processing Unit), TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination thereof instead of the CPU described above.

[0037] The information processing device 100 can be equipped with the measurement unit 121, acquisition unit 122, generation unit 123, and recognition unit 124 shown in Figure 7 by having the CPU 101 acquire the program group 104 and execute it. The program group 104 is, for example, stored in advance in a storage device 105 or ROM 102, and the CPU 101 loads it into RAM 103 and executes it as needed. The program group 104 may also be supplied to the CPU 101 via a communication network 111, or it may be stored in advance in a storage medium 110, and the drive device 106 reads the program and supplies it to the CPU 101. However, the measurement unit 121, acquisition unit 122, generation unit 123, and recognition unit 124 described above may be constructed with dedicated electronic circuits to realize such means.

[0038] The measurement unit 121 measures the operating speed of an object in a predetermined area. The acquisition unit 122 acquires a temperature distribution image of the predetermined area. The generation unit 123 generates a difference image of the temperature distribution image at time intervals based on the operating speed. The recognition unit 124 recognizes the operation of the object based on the difference image.

[0039] This disclosure, configured as described above, can improve the accuracy of object motion recognition through temperature measurement.

[0040] Furthermore, at least one of the functions of the measurement unit 121, acquisition unit 122, generation unit 123, and recognition unit 124 described above may be performed on an information processing device installed and connected to any location on the network, in other words, it may be performed using so-called cloud computing.

[0041] Furthermore, the aforementioned programs can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memory (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). Programs may also be supplied to a computer using various types of transient computer-readable media. Examples of transient computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can be supplied to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0042] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each of the embodiments described above can be combined with other embodiments as appropriate.

[0043] <Note> Some or all of the above embodiments may also be described as follows. The general configuration of the information processing apparatus, information processing method, and program in this disclosure is described below. However, this disclosure is not limited to the configurations described below. Furthermore, some or all of the configurations and functions described in Appendices 2 to 6, which are dependent on Appendice 1 below, may also be dependent on the other Appendices 7, 8, and 9 in the same way as Appendices 2 to 6. Moreover, not limited to Appendices 1, 7, 8, and 9, some or all of the configurations and functions described as appendices may also be dependent on similar hardware, software, various recording means for recording software, or systems, without departing from the embodiments described above. (Note 1) A measuring unit that measures the operating speed of an object in a predetermined area, An acquisition unit that acquires a temperature distribution image of the predetermined region, A generation unit that generates a difference image of the temperature distribution image at a time interval based on the operating speed, A recognition unit that recognizes the movement of the object based on the difference image, Equipped with an information processing device. (Note 2) The information processing device described in Appendix 1, The generation unit determines the time interval at which the movement of the object can be captured based on the operating speed, and generates the difference image of the temperature distribution image acquired at the determined time interval. Information processing device. (Note 3) The information processing device described in Appendix 1, The generation unit determines, based on the operating speed, the time interval during which the object moves from a first region set in the predetermined area to a second region different from the first region, and generates the difference image of the temperature distribution image acquired at the determined time interval. Information processing device. (Note 4) The information processing device described in Appendix 1, The recognition unit recognizes the movement of the object based on the regions in the difference image where the differences have different signs. Information processing device. (Note 5) The information processing device described in Appendix 1, The measuring unit measures the movement speed of the object in the vertical direction of the predetermined area. The acquisition unit acquires the temperature distribution image extending vertically over the predetermined region. The generation unit determines, based on the operating speed, the time interval during which the object moves from a first height region set in the predetermined region to a second height region that is different from the first height region and located below the first height region, and generates the difference image of the temperature distribution image acquired during the determined time interval. Information processing device. (Note 6) The information processing device described in Appendix 5, The recognition unit recognizes that the object's movement is a specific movement when, in the difference image, there is a region in the first height region where the difference value has a predetermined sign and no region where the difference value has the opposite sign, and there is a region in the second height region where the difference value has the opposite sign. Information processing device. (Note 7) A radar that detects the movement of an object in a predetermined area, A temperature sensor for detecting the temperature distribution in the predetermined region, A measurement unit that measures the movement speed of the object based on the detection results from the radar, An acquisition unit that acquires a temperature distribution image of the predetermined region from the detection result by the temperature sensor, A generation unit that generates a difference image of the temperature distribution image at a time interval based on the operating speed, A recognition unit that recognizes the movement of the object based on the difference image, An information processing system equipped with [the following features]. (Note 8) The movement speed of the object in a predetermined area is measured, A temperature distribution image of the predetermined region is acquired, A difference image of the temperature distribution image over time intervals based on the operating speed is generated. Based on the difference image, the movement of the object is recognized. Information processing methods. (Note 9) In an information processing device, The movement speed of the object in a predetermined area is measured, A temperature distribution image of the predetermined region is acquired, A difference image of the temperature distribution image over time intervals based on the operating speed is generated. Based on the difference image, the movement of the object is recognized. A program that executes a process. [Explanation of Symbols]

[0044] 1 Indoor space 2 toilet bowls 3 people 4 Wheelchairs 5. Temperature sensor 6 Radar 7 Entrance / exit 8. Entry / Exit Monitoring Area 10 Information Processing Devices 11 Speed ​​measurement unit 12 Image acquisition unit 13 Difference generation part 14 Motion recognition section 15 Data Storage Unit 100 Information Processing Devices 101 CPU 102 ROM 103 RAM 104 Program Groups 105 Storage device 106 Drive unit 107 Communication Interface 108 Input / Output Interfaces 109 Bus 110 Storage medium 111 Communication Network 121 Measurement Unit 122 Acquisition Department 123 Generation part 124 Recognition part

Claims

1. A measuring unit that measures the operating speed of an object in a predetermined area, An acquisition unit that acquires a temperature distribution image of the predetermined region, A generation unit that generates a difference image of the temperature distribution image at a time interval based on the operating speed, A recognition unit that recognizes the movement of the object based on the difference image, Equipped with an information processing device.

2. An information processing apparatus according to claim 1, The generation unit determines the time interval at which the movement of the object can be captured based on the operating speed, and generates the difference image of the temperature distribution image acquired at the determined time interval. Information processing device.

3. An information processing apparatus according to claim 1, The generation unit determines, based on the operating speed, the time interval during which the object moves from a first region set in the predetermined area to a second region different from the first region, and generates the difference image of the temperature distribution image acquired at the determined time interval. Information processing device.

4. An information processing apparatus according to claim 1, The recognition unit recognizes the movement of the object based on the regions in the difference image where the differences have different signs. Information processing device.

5. An information processing apparatus according to claim 1, The measuring unit measures the movement speed of the object in the vertical direction of the predetermined area. The acquisition unit acquires the temperature distribution image extending vertically over the predetermined region. The generation unit determines, based on the operating speed, the time interval during which the object moves from a first height region set in the predetermined region to a second height region that is different from the first height region and located below the first height region, and generates the difference image of the temperature distribution image acquired during the determined time interval. Information processing device.

6. An information processing device according to claim 5, The recognition unit recognizes that the object's movement is a specific movement when, in the difference image, there is a region in the first height region where the difference value has a predetermined sign and no region where the difference value has the opposite sign, and there is a region in the second height region where the difference value has the opposite sign. Information processing device.

7. A radar that detects the movement of an object in a predetermined area, A temperature sensor for detecting the temperature distribution in the predetermined region, A measurement unit that measures the movement speed of the object based on the detection results from the radar, An acquisition unit that acquires a temperature distribution image of the predetermined region from the detection result by the temperature sensor, A generation unit that generates a difference image of the temperature distribution image at a time interval based on the operating speed, A recognition unit that recognizes the movement of the object based on the difference image, An information processing system equipped with [the following features].

8. The movement speed of the object in a predetermined area is measured, A temperature distribution image of the predetermined region is acquired, A difference image of the temperature distribution image over time intervals based on the operating speed is generated. Based on the difference image, the movement of the object is recognized. Information processing methods.

9. In an information processing device, The movement speed of the object in a predetermined area is measured, A temperature distribution image of the predetermined region is acquired, A difference image of the temperature distribution image over time intervals based on the operating speed is generated. Based on the difference image, the movement of the object is recognized. A program that executes a process.

Images