JP7228767B2 - SENSOR SYSTEM, AIR CONDITIONING SYSTEM, OBJECT DETECTION METHOD AND PROGRAM - Google Patents

Description

TECHNICAL FIELD The present disclosure generally relates to a sensor system, an air conditioning system, an object detection method, and a program, and more specifically, a sensor system, an air conditioning system, an object detection method, and a program for detecting an object from the output of a temperature sensor. Regarding.

Patent Literature 1 describes an air conditioner provided with a human sensor that detects the presence and position of a person in the room. This air conditioner refers to the presence of a person in the room and the position of the person in the room specified by the detection result (detection signal) of the human sensor, and controls the fan unit and the like.

For example, the air conditioner can determine the direction of the left/right airflow direction plate based on the detection result of the human sensor, and can direct the airflow to the people in the room with high accuracy. Further, according to the function of the human sensor, the airflow can follow the movement of the person in the room, and even if the person in the room moves, the airflow can reach the person in the room accurately. As a result, the occupants of the room can reliably feel coolness based on the cooling effect of the airflow.

As such a human sensor, it is possible to use an object detection system that detects an object (a person in the room) in the detection area based on the output of a temperature sensor that detects the temperature of the detection area.

JP 2014-126295 A

However, in the object detection system described above, the area in which an object can be detected is limited to within the viewing angle of the temperature sensor. room occupants) may not be detected.

This indication is made in view of the above-mentioned reason, and aims at providing a sensor system, an air conditioning system, an object detection method, and a program which can expand the area which can detect a subject.

A sensor system according to one aspect of the present disclosure includes an object detection system and a temperature sensor. The temperature sensor is rotatable. The object detection system includes a switching section, a determination section, and a background correction section. The switching unit rotates the temperature sensor to switch detection areas among a plurality of areas including at least a specific area. The determination unit determines the presence or absence of an object in the detection area based on a result of comparison between output data of the temperature sensor that detects the temperature of the detection area and background data corresponding to each of the plurality of areas. do. The background correction unit corrects the background data corresponding to the specific area based on a temperature change amount during a period in which the detection area is an area other than the specific area.

An air conditioning system according to one aspect of the present disclosure includes the sensor system and an air conditioner that operates based on the output of the determination unit.

An object detection method according to an aspect of the present disclosure includes switching processing, determination processing, and background correction processing. The switching process is a process of rotating the temperature sensor to switch the detection area between a plurality of areas including at least a specific area. The determination process determines the presence or absence of an object within the detection area based on a result of comparison between output data of the temperature sensor that detects the temperature of the detection area and background data corresponding to each of the plurality of areas. It is a process to The background correction processing is processing for correcting the background data corresponding to the specific area based on the amount of temperature change during a period in which the detection area is an area other than the specific area.

A program according to an aspect of the present disclosure is a program for causing a computer system to execute the object detection method.

FIG. 1 is a block diagram showing configurations of an object detection system, a sensor system, and an air conditioning system according to Embodiment 1. FIG. 2A and 2B are explanatory diagrams of the operation when there is an object in the same object detection system. 3A and 3B are explanatory diagrams of the operation of the same object detection system when there is no object. 4A and 4B are explanatory diagrams of determination processing in the same object detection system. FIG. 5 is a flowchart showing an operation example of the object detection system same as above. FIG. 6 is a flowchart showing an operation example of the object detection system; FIG. 7 is a flow chart showing an operation example related to determination processing of the object detection system. FIG. 8 is an explanatory diagram of the operation of the same object detection system. FIG. 9 is a flow chart showing an operation example of the object detection system according to the comparative example. 10A and 10B are explanatory diagrams of the operation of the same object detection system. 11A to 11C are explanatory diagrams of the operation of the object detection system according to the modification of the first embodiment. FIG. 12 is an explanatory diagram of the operation of the object detection system according to the first configuration example of the second embodiment. 13A is an explanatory diagram of the operation of the object detection system according to the second configuration example of the second embodiment; FIG. 13B is an explanatory diagram of the operation of the object detection system according to the third configuration example of the second embodiment; FIG.

(Embodiment 1)
(1) Overview The object detection system 1 according to the present embodiment constitutes a sensor system 20 together with the temperature sensor 2, as shown in FIG. In other words, the sensor system 20 according to this embodiment includes the object detection system 1 and the temperature sensor 2 . Further, the sensor system 20 constitutes an air conditioning system 30 together with the air conditioner 3 . In other words, the air conditioning system 30 according to this embodiment includes the sensor system 20 and the air conditioner 3 .

This object detection system 1 is a system that detects an object 5 (see FIG. 2A) within a detection area 4 (see FIG. 2A) based on the output of a temperature sensor 2 . In this object detection system 1, the presence or absence of the object 5 in the detection area 4 is determined based on the result of comparison between the output data D1 (see FIG. 4B) of the temperature sensor 2 and the background data D2 (see FIG. 4B). That is, the object detection system 1 regards the object 5 as a heat source, and detects the existence of the object 5 based on the temperature change in the detection area 4 due to the presence of the object 5 in the detection area 4 .

In the air conditioning system 30 , for example, the air conditioner 3 operates based on the detection result of the sensor system 20 . As an example, the sensor system 20 used in the air conditioning system 30 detects whether or not a person (object 5) is present in the room where the air conditioner 3 is installed. to judge. Then, when the sensor system 20 determines that there is no person (object 5) in the room, the air conditioner 3 performs control such as switching the operation mode to the power saving mode or stopping the operation, for example. do.

The object detection system 1 according to this embodiment includes a switching unit 12, a determination unit 11, and a background correction unit 13, as shown in FIG. The switching unit 12 switches the detection area 4 among a plurality of areas A1 to A3 (see FIG. 2A) including at least the specific area. The determination unit 11 determines the presence or absence of the object 5 within the detection area 4 based on the result of comparison between the output data D1 of the temperature sensor 2 and the background data D2. Temperature sensor 2 detects the temperature of detection area 4 . Background data D2 corresponds to each of a plurality of areas A1 to A3. The background correction unit 13 corrects the background data D2 corresponding to the specific area based on the amount of temperature change during the period when the detection area 4 is an area other than the specific area.

According to this configuration, the detection area 4 in which the temperature is detected by the temperature sensor 2 is switched between the plurality of areas A1 to A3 by the switching unit 12. Therefore, compared to the case where the detection area 4 is fixed, The area in which the object 5 can be detected can be expanded. That is, in the object detection system 1 configured as described above, the area in which the object 5 can be detected is not limited to within the viewing angle of the temperature sensor 2, and the object 5 existing outside the viewing angle of the temperature sensor 2 can also be detected. becomes.

Moreover, in the object detection system 1 according to the present embodiment, the background correction unit 13 corrects the background data D2 corresponding to the specific area based on the amount of temperature change during the period when the detection area 4 is an area other than the specific area. do. As a result, even though the detection area 4 is switched among the plurality of areas A1 to A3, the reliability (detection accuracy) of detection of the object 5 in the object detection system 1 is less likely to decrease. This point will be described in detail in the section "(2.3) Operation".

(2) Details Hereinafter, the object detection system 1, the sensor system 20, and the air conditioning system 30 according to this embodiment will be described in more detail.

(2.1) Overall Configuration The air conditioning system 30 according to this embodiment includes the sensor system 20 and the air conditioner 3 as described above. In this embodiment, as an example, the air conditioning system 30 includes only one air conditioner 3. However, the air conditioning system 30 is not limited to this example, and the air conditioning system 30 may include a plurality of air conditioners 3. good.

Further, the sensor system 20 according to this embodiment includes the object detection system 1 and the temperature sensor 2 as described above. In this embodiment, the sensor system 20 further includes a drive section 21 . Further, in this embodiment, all components of the sensor system 20 are integrated with the air conditioner 3 . In other words, all the components of the air conditioning system 30 are provided in the housing 31 (see FIG. 2A) of one air conditioner 3 .

In this embodiment, as an example, a case where the air conditioning system 30 is installed in a residential facility such as a detached house or collective housing will be described. Specifically, the housing 31 of the air conditioner 3 is attached to the wall or ceiling of one living room 40 (see FIG. 2A) in a residential facility. In this case, the air conditioner 3 adjusts the temperature, humidity, air cleanliness, airflow, etc. in the living room 40 .

The sensor system 20 used in the air conditioning system 30 detects whether or not a person (object 5) exists in the room 40 in which the air conditioner 3 is installed. to judge whether That is, the area targeted for detection of the object 5 by the sensor system 20 and the area targeted for air conditioning by the air conditioner 3 are set in the same space (inside the living room 40). Therefore, when the sensor system 20 determines that there is no person (object 5) in the living room 40, the air conditioner 3 controls, for example, switching the operation mode to the power saving mode or stopping the operation. to run.

Furthermore, the sensor system 20 according to the present embodiment recognizes not only the presence or absence of a person (object 5), but also the positions of people present in the living room 40 and the number of people present in the living room 40 (number of persons). It is possible. Therefore, the air conditioner 3 performs control such as changing the air flow direction (wind direction) or the air volume according to at least one of the positions and the number of people in the living room 40 .

Further, in this embodiment, the temperature sensor 2 is an infrared array sensor in which a plurality of sensor elements that detect infrared rays are arranged two-dimensionally. The “infrared rays” referred to in the present disclosure are light rays (heat rays) radiated at least from the human body, and are light having a wavelength of around 10 [μm], for example. This type of temperature sensor 2 outputs a thermal image representing the temperature distribution of a detection area set within a predetermined viewing angle. A “thermal image” as used in the present disclosure is an image configured by two-dimensionally arranging a plurality of pixels, with the temperature detected by each of a plurality of sensor elements as the pixel value. Here, as an example, the temperature sensor 2 is an infrared array sensor in which 64 sensor elements are two-dimensionally arranged such that 8 elements are aligned in the X-axis direction and 8 elements are aligned in the Y-axis direction. Therefore, the temperature sensor 2 outputs a thermal image having eight pixels in each of the X-axis direction and the Y-axis direction as the output data D1. In other words, the output data D1 is image data including a plurality of pixels each having a temperature value as a pixel value.

Further, the drive unit 21 generates power for moving the temperature sensor 2 . In this embodiment, the drive unit 21 drives the temperature sensor 2 so that the temperature sensor 2 rotates around the rotation axis. The rotation axis of the temperature sensor 2 is, for example, an axis along the vertical direction or an axis inclined at a predetermined angle with respect to the vertical direction. Here, the drive unit 21 rotates the temperature sensor 2 to change the orientation of the temperature sensor 2, thereby realizing switching of the detection area 4 among the plurality of areas A1 to A3 (see FIG. 2A). That is, the temperature sensor 2 is configured to be rotatable in the horizontal direction (pan direction) by the drive unit 21, and the detection area 4 is switched depending on the orientation of the temperature sensor 2 in the horizontal direction.

Details will be described in the section "(2.2) Configuration of object detection system", but in this embodiment, the detection area 4 is composed of three areas, a first area A1, a second area A2, and a third area A3. Assuming you switch. Therefore, as shown in FIG. 2A, the drive unit 21 reciprocates the temperature sensor 2 within the range of a predetermined rotation angle, and causes the temperature sensor 2 to swing. Switch between the first area A1, the second area A2 and the third area A3. Specifically, the drive unit 21 includes an electric motor, and swings the temperature sensor 2 according to a drive signal from the switching unit 12, which will be described later.

(2.2) Configuration of Object Detection System Next, the configuration of the object detection system 1 will be described.

As shown in FIG. 1, the object detection system 1 according to the present embodiment further includes a background updating unit 14, an acquiring unit 15, and a background storing unit 16 in addition to the determining unit 11, the switching unit 12, and the background correcting unit 13. ing.

Here, the determination unit 11, the switching unit 12, the background correction unit 13, and the background update unit 14 are implemented by, for example, the processing unit 10 mainly composed of a computer system such as a microcomputer. The processing unit 10 is mainly composed of a computer system including a processor and a memory, and by executing a program recorded in the memory by the processor, the determination unit 11, the switching unit 12, the background correction unit 13, and the background updating unit 14 Realize the function. The program may be prerecorded in a memory, may be provided through an electric communication line such as the Internet, or may be provided by being recorded in a non-temporary recording medium such as a memory card.

An acquisition unit 15 and a background storage unit 16 are connected to the processing unit 10 . Furthermore, the drive unit 21 and the air conditioner 3 are connected to the processing unit 10 . Here, the processing unit 10 and the driving unit 21 or the air conditioner 3 need only be connected in a state in which information can be transmitted. may be connected using

As described above, the determination unit 11 determines the presence or absence of the object 5 within the detection area 4 based on the result of comparison between the output data D1 of the temperature sensor 2 and the background data D2. The “background data” referred to in the present disclosure is data that serves as a reference for the output data D1 when the determination unit 11 determines whether or not the object 5 exists, and is the temperature of the detection area 4 when the object 5 does not exist (this In the embodiment, it is data representing a thermal image). In this embodiment, basically, the output data D1 of the temperature sensor 2 when the object 5 does not exist is used as the background data D2.

Here, in this embodiment, as described above, the output data D1 is image data including a plurality of pixels each having a temperature value as a pixel value. Therefore, the background data D2 serving as a reference for the output data D1 is also image data including a plurality of pixels each having a temperature value as the pixel value, similarly to the output data D1. Specifically, the background data D2 is a thermal image having eight pixels in each of the X-axis direction and the Y-axis direction.

In addition, “based on the comparison result” in the present disclosure is not only based on the result (difference) of directly comparing the output data D1 and the background data D2, but also the case where the output data D1 and the background data D2 are substantially Also includes cases based on the results of comparison with In other words, the judgment of the presence or absence of the object 5 in the judging section 11 is realized by one of the following methods 1 to 3, as an example. The first method is a method of determining the presence or absence of the object 5 based on the result (difference) of directly comparing the output data D1 and the background data D2. This is a method of determining the presence or absence of the object 5 without directly comparing the data D1 and the background data D2.

That is, in the first method, the determination unit 11 calculates the difference data by taking the difference between the output data D1 and the background data D2, and compares the calculated difference data with a threshold to determine the The presence or absence of the target object 5 is determined. In this case, the determination unit 11 determines that the object 5 is "presence" when the difference data exceeds the threshold. In this embodiment, it is assumed that the determination unit 11 adopts the first method. The details of the processing related to the determination of the presence or absence of the object 5 in the determination unit 11 will be described in the section "(2.3) Operation".

In the second method, the determination unit 11 compares the output data D1 and the synthesized data obtained by adding a threshold value to the background data D2 without obtaining difference data, thereby determining whether the object 5 in the detection area 4 is detected. determine whether or not In this case, the judgment unit 11 judges that the object 5 is "presence" when the output data D1 exceeds the synthesized data. In the third method, the determination unit 11 compares the synthesized data obtained by subtracting the threshold value from the output data D1 with the background data D2 without obtaining the difference data, thereby determining whether the object 5 in the detection area 4 is detected. determine whether or not In this case, the judgment unit 11 judges that the object 5 is "presence" when the synthesized data exceeds the background data D2.

Further, in the present embodiment, the detection area 4 is switched between the plurality of areas A1 to A3 by the switching unit 12, so the background data D2 is set in association with each of the plurality of areas A1 to A3. That is, background data D2 is set for each area (first area A1, second area A2, or third area A3) as a candidate for detection area 4. FIG. Then, the determination unit 11 determines the object in the detection area 4 based on the result of comparison between the background data D2 corresponding to the area as the detection area 4 and the output data D1 of the temperature sensor 2 among the plurality of areas A1 to A3. The presence or absence of the object 5 is determined. That is, when the detection area 4 is the area A1 among the plurality of areas A1 to A3, the determination unit 11 compares the background data D2 corresponding to the area A1 and the output data D1 of the temperature sensor 2. to determine the presence or absence of the object 5 within the detection area 4 .

In the object detection system 1 according to this embodiment, the target object 5 is a moving object. More strictly, the object 5 is a “person” present in the living room 40 . Therefore, when the target object 5 (person) does not exist in the detection area 4, the determination unit 11 determines that there is no target object 5, and from this state, the target object 5 (person), which is a moving object, is detected. When entering the area 4, it is determined that the object 5 is present. The target object 5 may be any moving body, and is not limited to a person, and may be, for example, a small animal.

Here, the judgment unit 11 judges the presence/absence of the object 5 a plurality of times while the detection area 4 is in the same area. That is, in this embodiment, the detection area 4 is switched among the plurality of areas A1 to A3 by the switching unit 12. FIG. While the detection area 4 is stopped at any one of the plurality of areas A1 to A3, the judgment section 11 executes the judgment of the presence or absence of the target object 5 multiple times. In other words, during the period from when the detection area 4 is switched to when the next detection area 4 is switched, the determination unit 11 determines whether or not the object 5 exists a plurality of times.

The switching unit 12 switches the detection area 4 among a plurality of areas A1 to A3 including at least the specific area, as described above. That is, the detection area 4 to be detected by the temperature sensor 2 is not fixed, but switched by the switching unit 12 . The multiple areas that are candidates for the detection area 4 include three or more areas. In this embodiment, it is assumed that the detection area 4 is switched between three areas, ie, the first area A1, the second area A2, and the third area A3. That is, the multiple areas that are candidates for the detection area 4 include three areas: the first area A1, the second area A2, and the third area A3.

Specifically, as shown in FIG. 2A, of the three areas obtained by dividing the space in the living room 40 into three in plan view, the central area as viewed from the temperature sensor 2 is the first area A1. The area on the right side is the second area A2, and the area on the left side is the third area A3. Here, as an example, the viewing angle of the temperature sensor 2 in plan view is approximately 60 degrees, and the range of approximately 180 degrees centered on the front of the air conditioner 3 is divided into three equal parts, the first area A1 and the second area A1. Three areas are formed, a second area A2 and a third area A3.

In the present embodiment, as described above, the drive unit 21 swings the temperature sensor 2 to realize switching of the detection area 4 among the plurality of areas A1 to A3. Therefore, the switching unit 12 outputs a driving signal to the driving unit 21 and controls the driving unit 21 with the driving signal, thereby switching the detection area 4 among the plurality of (here, three) areas A1 to A3.

In addition, the “specific area” referred to in the present disclosure is an arbitrary one area included in a plurality of areas A1 to A3 and of interest. In this embodiment, it is assumed that any of the first area A1, the second area A2 and the third area A3 can be the "specific area". That is, the specific area is not fixed, but changes depending on which one of the first area A1, the second area A2 and the third area A3 is focused. For example, when the first area A1 is the "specific area", the second area A2 and the third area A3 are "areas other than the specific area". Similarly, when the second area A2 is the "specific area", the first area A1 and the third area A3 are "areas other than the specific area", and when the third area A3 is the "specific area", the first The area A1 and the second area A2 are "areas other than the specific area".

Further, in the present embodiment, the switching unit 12 switches the detection area 4 at intervals of a predetermined time (for example, several tens of seconds to several minutes). In other words, the switching of the detection area 4 by the switching unit 12 is performed intermittently rather than continuously. Specifically, for example, when the switching unit 12 operates the driving unit 21 to switch the detection area 4 from the first area A1 to the second area A2, the switching unit 12 temporarily stops the driving unit 21 and shifts the detection area 4 to the second area A2. Temporarily fixed to area A2. When the second area A2 becomes the detection area 4 and a predetermined time elapses, the switching unit 12 operates the driving unit 21 to switch the detection area 4 from the second area A2 to the first area A1. Again, the switching unit 12 temporarily stops the driving unit 21 to temporarily fix the detection area 4 to the first area A1. As a result, the drive unit 21 does not always operate, but intermittently operates only when switching the detection area 4 . Therefore, compared to a configuration in which the driving section 21 operates continuously, it is possible to suppress the power consumption of the driving section 21 and reduce deterioration of the driving section 21 . Furthermore, when the temperature sensor 2 and the object detection system 1 are connected by a cable, it is possible to reduce the load on the cable.

The background correction unit 13 corrects the background data D2 corresponding to the specific area based on the amount of temperature change during the period when the detection area 4 is an area other than the specific area. Here, a period during which the detection area 4 is an area other than the specific area is called a "first period", and a period during which the detection area 4 is the specific area is called a "second period". That is, the detection area 4 is set in an area other than the specific area in the first period, and the detection area 4 is set in the specific area in the second period. That is, when the first period in which the detection area 4 is an area other than the specific area and the second period in which the detection area 4 is the specific area are switched in this order, the background correction unit 13 determines that the temperature generated in the first period is The background data D2 used in the second period is corrected based on the amount of change. In this case, during the first period in which the detection area 4 is an area other than the specific area, the background data D2 corresponding to the specific area is not updated. Background data D2 used in . In order to reduce such a deviation, the background correction unit 13 converts the amount of temperature change during the first period, in which the detection area 4 is an area other than the specific area, into the background data in the second period, in which the detection area 4 is the specific area. Correct D2.

In addition, the “temperature change amount” in the present disclosure means the change amount when the temperature changes in a certain period. For example, the temperature change amount during the first period is the temperature at the start point of the first period. It is the difference from the temperature at the end point of the first period.

Here, as described above, the specific area is not fixed, but changes depending on which one of the first area A1, the second area A2 and the third area A3 is focused. Therefore, for example, when the first area A1 is the "specific area", both the period in which the detection area 4 is the second area A2 and the period in which the detection area 4 is the third area A3 are the first period, and the detection The period during which the area 4 is the first area A1 is the second period. Similarly, when the second area A2 is the "specific area", both the period in which the detection area 4 is the first area A1 and the period in which the detection area 4 is the third area A3 are the first period, and the detection area 4 is the second area A2 is the second period. When the third area A3 is the "specific area", both the period during which the detection area 4 is the first area A1 and the period during which the detection area 4 is the second area A2 are the first period, and the detection area 4 is the second area. The period of 3 areas A3 is the second period.

Here, the temperature change amount used in the background correction unit 13 is a representative value of the change amount of the temperature values of the pixels of the background data D2 during the period when the detection area 4 is an area other than the specific area. The "representative value" referred to in the present disclosure includes an average value, a mode value, a median value, etc. In this embodiment, as an example, it is assumed that the representative value is the average value. That is, as described above, each of the output data D1 and the background data D2 is image data including a plurality of pixels each having a temperature value as a pixel value. Therefore, in the present embodiment, the background correction unit 13 calculates the average value of the amount of change in the temperature value of all the pixels forming the background data D2 during the period (first period) in which the detection area 4 is an area other than the specific area. , is used as the amount of temperature change that occurred during this period (first period).

The background update unit 14 updates the background data D2. The background update unit 14 updates the background data D2 corresponding to the detection area 4 as needed while the detection area 4 is in the same area. That is, while the detection area 4 remains in any one of the plurality of areas A1 to A3, the background updating unit 14 updates the background data D2 corresponding to this area as needed. The details of the process related to the update of the background data D2 in the background update unit 14 will be described in the section "(2.3) Operation".

In this embodiment, the determination unit 11 determines the presence or absence of the object 5 multiple times while the detection area 4 is in the same area. The background data D2 is updated each time. In other words, the number of times the determination unit 11 determines the presence or absence of the object 5 and the number of times the background update unit 14 updates the background data D2 are the same during the period when the detection area 4 is in the same area.

The acquisition unit 15 is connected to the temperature sensor 2 and acquires the output data D1 from the temperature sensor 2 . In the present embodiment, the temperature sensor 2 outputs a thermal image as the output data D1, so the acquisition unit 15 acquires the output data D1 consisting of a thermal image. Here, the frequency with which the acquisition unit 15 acquires the output data D1 is defined by the frame rate of the temperature sensor 2, for example. That is, if the frame rate of the temperature sensor 2 is, for example, 10 [fps], the acquiring unit 15 acquires the output data D1 at intervals of 0.1 [s].

The background storage unit 16 is composed of, for example, a non-volatile memory, and stores background data D2. The background storage unit 16 stores the background data D2 in association with each of the first area A1, the second area A2 and the third area A3. That is, in the present embodiment, the background data D2 is stored in the background storage unit 16 for each area (first area A1, second area A2, or third area A3) as a candidate for the detection area 4. FIG.

When the background data D2 is corrected by the background correction unit 13, the background data D2 stored in the background storage unit 16 is rewritten with the corrected background data D2. For example, when the background data D2 corresponding to the first area A1 is corrected by the background correction unit 13, the background data D2 corresponding to the first area A1 stored in the background storage unit 16 is the corrected background data D2. can be rewritten to

Similarly, when the background data D2 is updated by the background updating unit 14, the background data D2 stored in the background storage unit 16 is rewritten with the updated background data D2. For example, when the background data D2 corresponding to the first area A1 is updated by the background update unit 14, the background data D2 corresponding to the first area A1 stored in the background storage unit 16 is changed to the updated background data D2. can be rewritten to

Therefore, the background storage unit 16 always stores the latest background data D2, that is, the corrected or updated background data D2.

By the way, from the output data D1 of the temperature sensor 2, that is, the thermal image acquired by the acquisition unit 15, not only determination of the presence or absence of the object 5 but also temperature of the space, floor, wall, ceiling, etc. of the detection area 4 can be performed. can be estimated. Therefore, in addition to the presence or absence of the target object 5, or instead of the presence or absence of the target object 5, the object detection system 1 transmits information about the temperature of the space, floor, wall, ceiling, etc. of the detection area 4 to the air conditioner 3. may be output. In this case, the air conditioner 3 can operate based on the temperature of the space in the detection area 4, the floor, the walls, the ceiling, and the like.

(2.3) Operation Next, operation of the object detection system 1 will be described with reference to FIGS. 2A to 4B. Here, in the sensor system 20 (including the object detection system 1) used in the air conditioning system 30, as shown in FIG. A case where the object 5 is detected will be described.

In the object detection system 1, the judgment unit 11 judges the presence or absence of the object 5 in the detection area 4 based on the result of comparison between the output data D1 of the temperature sensor 2 and the background data D2 acquired by the acquisition unit 15. do. Here, the object detection system 1 switches the detection area 4 between a plurality of areas (first area A1, second area A2, and third area A3) in the switching unit 12, and switches between the plurality of areas A1 to A3. , the presence or absence of the object 5 is determined by the determination unit 11 . That is, FIG. 2A is a schematic plan view showing how the detection area 4 is switched among the first area A1, the second area A2, and the third area A3, and in particular, the state in which the detection area 4 is in the first area A1. is shown. Here, as an example, the object detection system 1 switches the detection area 4 in order of the first area A1, the second area A2, the first area A1, the third area A3, the second area A2, the first area A1, and so on. , the presence or absence of the object 5 is determined.

In the object detection system 1, the temperature sensor 2 acquires a thermal image as the output data D1 in the acquisition unit 15 while the detection area 4 is fixed to one of the plurality of areas A1 to A3, and this output data D1 is compared with the background image D2. FIG. 2B shows a thermal image acquired as output data D1 by the acquisition unit 15 when the detection area 4 is in each of the first area A1, the second area A2, and the third area A3 in the example of FIG. 2A. showing. In FIG. 2B, the output data D1 acquired in the first area A1 is denoted as "center", the output data D1 acquired in the second area A2 is denoted as "right", and the output data D1 acquired in the third area A3. "Left" is written in the output data D1. That is, as shown in FIG. 2B, in the output data D1 when the detection area 4 is in the first area A1, the temperature value (pixel value ) becomes larger. In FIG. 2B, pixels whose temperature values exceed a predetermined value are indicated by shaded areas. Similarly, as shown in FIG. 2B, in the output data D1 when the detection area 4 is in the second area A2, the temperature value (pixel value) increases.

In order to extract the pixel P1 corresponding to the object 5 (person) as described above, the object detection system 1 compares the output data D1 and the background data D2. The object detection system 1 basically uses the output data D1 of the temperature sensor 2 when the object 5 does not exist as the background data D2 as described above. Therefore, as shown in FIGS. 3A and 3B, the object detection system 1 uses the acquisition unit 15 to acquire the output data D1 of the temperature sensor 2 when the object 5 is not present as the background data D2. FIG. 3A is a schematic plan view showing how the detection area 4 is switched among the first area A1, the second area A2 and the third area A3, and particularly shows the state where the detection area 4 is in the first area A1. ing. FIG. 3B shows a thermal image acquired as background data D2 by the acquisition unit 15 when the detection area 4 is in each of the first area A1, the second area A2, and the third area A3 in the example of FIG. 3A. showing.

Then, the object detection system 1 obtains the difference between the output data D1 and the background data D2 to calculate difference data, and compares the calculated difference data with a threshold value to detect the object 5 in the detection area 4. determine whether or not In the present embodiment, both the output data D1 and the background data D2 are thermal images, so the determination unit 11 generates difference data by calculating the difference for each pixel. In other words, the difference data consists of image data whose pixel values are the difference values between the same pixels in the output data D1 and the background data D2. The judgment unit 11 judges that the object 5 is "presence" when the difference data exceeds the threshold.

As an example, FIG. 4B schematically represents a Y1 line cross section in the output data D1 shown in FIG. 4A. That is, it is assumed that a temperature distribution as shown in FIG. 4B is obtained by extracting one row of pixels P1 along the horizontal axis (X-axis) of the output data D1 shown in FIG. 4A. In this case, as shown in FIG. 4B, the object detection system 1 calculates the difference data by taking the difference between the output data D1 and the background data D2, and compares the calculated difference data with the threshold value Vth1. , to determine the presence or absence of the object 5 within the detection area 4 . Here, the judgment unit 11 judges that the object 5 is "presence" when the difference data exceeds the threshold value Vth1. That is, in the example of FIG. 4B, the difference data exceeds the threshold Vth1 in the hatched area exceeding the data (indicated by the dashed line) obtained by adding the threshold Vth1 to the background data D2 in the output data D1. The judgment unit 11 judges that the target object 5 exists, that is, that a "person" exists in this hatched area.

Here, in order to distinguish between the object 5 and heat sources other than the object 5, the determination unit 11 determines the size, shape, and pixel value (temperature value) of pixels (shaded regions) whose difference data exceeds the threshold value Vth1. ) may be used to determine whether or not the object 5 (person).

5 to 7 are flowcharts showing an operation example of the object detection system 1 according to this embodiment. In particular, in FIGS. 5 and 6, processing is distinguished according to which of the plurality of areas A1 to A3 the detection area 4 is located. 5 and 6, the processing when the detection area 4 is the first area A1 is described in the "center" column, and the processing when the detection area 4 is the second area A2 is described in the "right" column. The processing when area 4 is the third area A3 is described in the "left" column.

As shown in FIG. 5, after being activated, the object detection system 1 first acquires background data D2 corresponding to the third area A3 (S1). Next, the object detection system 1 executes switching processing for switching the detection area 4 from the third area A3 to the first area A1 (S2), and acquires the background data D2 corresponding to the first area A1 (S3). . Next, the object detection system 1 executes switching processing for switching the detection area 4 from the first area A1 to the second area A2 (S4), and acquires the background data D2 corresponding to the second area A2 (S5). . Thereby, in the object detection system 1, acquisition of the background data D2 corresponding to the first area A1, the second area A2, and the third area A3 is completed. The acquired background data D2 is stored in the background storage unit 16 in association with each of the first area A1, the second area A2 and the third area A3.

After that, the object detection system 1 executes switching processing to switch the detection area 4 from the second area A2 to the first area A1 (S6), and reads the background data D2 corresponding to the first area A1 from the background storage unit 16 ( S7). Then, the object detection system 1 executes the later-described determination process (S8) for the first area A1. Next, in the object detection system 1, the background correction unit 13 calculates the amount of temperature change that occurred while the detection area 4 was the first area A1 (S9). At this time, the background correction unit 13 sets the average value (representative value) of the amount of change in the temperature values of the plurality of pixels of the background data D2 during the period when the detection area 4 is the first area A1 as the "temperature change amount." calculate.

After that, the object detection system 1 executes switching processing for switching the detection area 4 from the first area A1 to the second area A2 (S10), and reads the background data D2 corresponding to the second area A2 from the background storage unit 16 ( S11). Then, the object detection system 1 causes the background correction unit 13 to perform background correction processing (S12) for correcting the background data D2. At this time, since the specific area is the second area A2, based on the amount of temperature change that occurred during the period when the detection area 4 was an area other than the specific area (first area A1), that is, the amount of temperature change obtained in step S9, to correct the background data D2 corresponding to the second area A2. Then, the object detection system 1 executes the determination process (S13) using the corrected background data D2 for the second area A2. Next, in the object detection system 1, the background correction unit 13 calculates the amount of temperature change that occurred while the detection area 4 was the second area A2 (S14). At this time, the background correction unit 13 sets the average value (representative value) of the amount of change in the temperature values of the plurality of pixels of the background data D2 during the period when the detection area 4 is the second area A2 as the "temperature change amount." calculate.

After that, the object detection system 1 executes switching processing for switching the detection area 4 from the second area A2 to the first area A1 (S15), and as shown in FIG. It is read out from the background storage unit 16 (S16). Then, the object detection system 1 causes the background correction unit 13 to perform background correction processing (S17) for correcting the background data D2. At this time, since the specific area is the first area A1, based on the amount of temperature change that occurred during the period when the detection area 4 was an area other than the specific area (second area A2), that is, the amount of temperature change obtained in step S14, to correct the background data D2 corresponding to the first area A1. Then, the object detection system 1 executes the determination process (S18) using the corrected background data D2 for the first area A1. Next, in the object detection system 1, the background correction unit 13 calculates the amount of temperature change that occurred while the detection area 4 was the first area A1 (S19). At this time, the background correction unit 13 sets the average value (representative value) of the amount of change in the temperature values of the plurality of pixels of the background data D2 during the period when the detection area 4 is the first area A1 as the "temperature change amount." calculate.

After that, the object detection system 1 executes switching processing for switching the detection area 4 from the first area A1 to the third area A3 (S20), and reads the background data D2 corresponding to the third area A3 from the background storage unit 16 ( S21). Then, the object detection system 1 causes the background correction unit 13 to perform background correction processing (S22) for correcting the background data D2. At this time, since the specific area is the third area A3, based on the amount of temperature change that occurred during the period when the detection area 4 was an area (first area A1) other than the specific area, that is, the amount of temperature change obtained in step S19, to correct the background data D2 corresponding to the third area A3. Then, the object detection system 1 executes the determination process (S23) using the post-correction background data D2 for the third area A3.

After that, by repeating the same processing, the object detection system 1 determines whether or not the object 5 exists in each of the plurality of areas A1 to A3 while switching the detection area 4 between the plurality of areas A1 to A3.

FIG. 7 shows an overview of each determination process (S8, S13, S18, S23). That is, in the determination process, the object detection system 1 first acquires the latest thermal image as the output data D1 from the temperature sensor 2 (S101). Next, the object detection system 1 calculates difference data by taking the difference between the output data D1 and the background data D2 (S102). Next, the object detection system 1 determines the presence or absence of the object 5 (person) within the detection area 4 by comparing the calculated difference data with a threshold value (S103).

After that, the object detection system 1 updates the background data D2 in the background updating unit 14 (S104). At this time, the background update unit 14 updates the background data D2 so as to be closer to the output data D1. Specifically, the background update unit 14 generates difference data by taking a difference between the output data D1 and the background data D2 for each pixel, and updates the difference data by multiplying the difference data by a predetermined ratio (for example, several percent). The background data D2 is updated by adding the data for the background data D2. However, if it is determined in step S103 that the object 5 exists, the output data D1 is used to update the background data D2 except for the area where the object 5 exists. In other words, only the pixels in the area where the object 5 does not exist in the output data D1 are used for updating the background data D2. As a result, when the temperature of the living room 40 gradually changes, the background data D2 is updated so as to follow this temperature change.

Next, the object detection system 1 determines whether or not a predetermined time has passed since the start of the determination process (S105). At this time, if the predetermined time has not elapsed (S105: No), the process returns to step S101, and if the predetermined time has elapsed (S105: Yes), the determination process is terminated. As a result, the above-described processes S101 to S104 are repeated until a predetermined period of time elapses.

According to the operation of the object detection system 1 described above, the background correction unit 13 corrects the background data D2 corresponding to the specific area based on the amount of temperature change during the period when the detection area 4 is an area other than the specific area. . Therefore, even if the temperature of the living room 40 rises due to the air conditioner 3 during the period when the detection area 4 is an area other than the specific area, the reliability of detection of the object 5 in the object detection system 1 (detection accuracy) is unlikely to decrease.

That is, as shown in FIG. 8, by correcting the background data D2 based on the temperature change amount ΔT1, erroneous detection of the object 5 or failure to detect the object 5 is less likely to occur. Similar to FIG. 4B, FIG. 8 schematically represents a Y1 line cross section in the output data D1 shown in FIG. 4A. In short, for example, when the specific area is the first area A1, the temperature change amount ΔT1 generated during the period when the detection area 4 is an area other than the specific area (first area A1) is corrected. In the example of FIG. 8, the background data D2' before correction is indicated by an imaginary line (chain two-dot line), and the background data D2 after correction is indicated by a solid line. Since the determination process is performed based on the corrected background data D2, erroneous detection of the object 5 or failure to detect the object 5 is less likely to occur.

FIG. 9 is a flow chart showing the operation of the object detection system according to the comparative example. It is assumed here that the object detection system according to the comparative example has a configuration in which the background correction unit 13 is omitted from the object detection system 1 according to the present embodiment. That is, the object detection system according to the comparative example has the same configuration as the object detection system 1 according to this embodiment except that the background correction unit 13 is not provided.

As shown in FIG. 9, in the comparative example, there is no temperature variation calculation processing (S9, S14, S19 in FIGS. 5 and 6) and background correction processing (S12, S17, S22 in FIGS. 5 and 6). Except for this point, the same operation as that of the object detection system 1 according to this embodiment is realized. That is, the process "Sc(α)" (α is 1 to 23) in FIG. 9 corresponds to the process "S(α)" (α is 1 to 23) in FIGS.

According to the object detection system according to the comparative example, the detection area 4 can be switched among the plurality of areas A1 to A3. Background data D2 is not updated. Therefore, for example, when the specific area is the first area A1, during the period when an area other than the specific area (the second area A2) is set as the detection area 4, the update of the background data D2 corresponding to the specific area is Not done. Therefore, for example, as shown in FIG. 10A , the output The difference data between the data D1 and the background data D2 may exceed the threshold. As a result, even if the object 5 does not exist, it is determined that the object 5 is present, and an erroneous detection occurs.

Further, in the object detection system according to the comparative example, it is also possible to newly acquire the background data D2 instead of the process of reading the background data D2 (Sc11, Sc16, Sc21). In this case, the background data D2 is newly acquired each time the detection area 4 is switched between the plurality of areas A1 to A3. Failure to detect the intruding object 5 (person) may occur. That is, for example, as shown in FIG. 10B, an object 5 (person) who has entered the specific area (first area A1) during a period when an area (second area A2) other than the specific area is set as the detection area 4 may not be detected.

On the other hand, in the object detection system 1 according to the present embodiment, the background correction unit 13 corrects the background data D2 corresponding to the specific area based on the amount of temperature change during the period when the detection area 4 is an area other than the specific area. erroneous detection and detection omission are less likely to occur. Therefore, in the present embodiment, even though the detection area 4 is switched between a plurality of areas A1 to A3, there is an advantage that the reliability (detection accuracy) of detection of the object 5 in the object detection system 1 is less likely to decrease. There is

(3) Modifications Embodiment 1 is merely one of various embodiments of the present disclosure. Embodiment 1 can be modified in various ways according to design and the like, as long as the object of the present disclosure can be achieved. Also, functions similar to those of the object detection system 1 according to the first embodiment may be embodied by an object detection method, a program, or a non-temporary recording medium recording the program. An object detection method according to one aspect includes a switching process (see S2, S4, S6, S10, S15, and S20 in FIGS. 5 and 6) and a determination process (see S8, S13, S18, and S23 in FIGS. 5 and 6). ) and background correction processing (see S12, S17, and S22 in FIGS. 5 and 6). The switching process is a process of switching the detection area 4 among a plurality of areas A1 to A3 including at least a specific area. The judgment processing is processing for judging the presence or absence of the object 5 in the detection area 4 based on the difference data between the output data D1 of the temperature sensor 2 and the background data D2. Temperature sensor 2 detects the temperature of detection area 4 . Background data D2 corresponds to each of a plurality of areas A1 to A3. The background correction process is a process of correcting the background data D2 corresponding to the specific area based on the amount of temperature change during the period when the detection area 4 is an area other than the specific area. A program according to one aspect is a program for causing a computer system to execute the object detection method.

Modifications of the first embodiment are listed below. Modifications described below can be applied in combination as appropriate.

In the object detection system 1, as shown in FIGS. 11A to 11C, the areas A1 to A3 that can be the detection area 4 may be adjustable. Specifically, in FIG. 11A, of the three areas obtained by dividing the space in the living room 40 into three in plan view, the central area is the first area A1 and the right area is the first area A1 when viewed from the temperature sensor 2. is the second area A2, and the left area is the third area A3. On the other hand, as shown in FIG. 11B , when the air conditioner 3 is installed in the left corner of the living room 40 in plan view, the central first area A1 faces the front of the air conditioner 3. tilt to the right. As shown in FIG. 11C, when the air conditioner 3 is installed in the right corner of the living room 40 in plan view, the central first area A1 is tilted leftward with respect to the front of the air conditioner 3. adjusted to As a result, in the object detection system 1, the first area A1 can be directed toward the center of the living room 40 regardless of the position of the air conditioner 3, and most of the living room 40 can be used as the detection area 4. be.

11A to 11C, the time during which the detection area 4 is fixed to each of the plurality of areas A1 to A3 differs depending on the areas A1 to A3. In short, the switching unit 12 switches the detection areas 4 at intervals of a predetermined time, so the detection areas 4 are fixed to the respective areas A1 to A3 for a predetermined period of time. Here, the predetermined time is set individually for the first area A1, the second area A2, and the third area A3, so that the time for which the detection area 4 is fixed to each of the plurality of areas A1 to A3 is the area A1 ~A3 will vary. In particular, for the first area A1 corresponding to the center of the living room 40, it is preferable to set the predetermined time longer than the second area A2 and the third area A3. As a result, the object detection system 1 can detect the presence or absence of the object 5 intensively in the first area A1 where the object 5 (person) is likely to exist.

The object detection system 1 according to the present disclosure includes a computer system in, for example, the processing unit 10 and the like. A computer system is mainly composed of a processor and a memory as hardware. The functions of the object detection system 1 in the present disclosure are realized by the processor executing a program recorded in the memory of the computer system. The program may be recorded in advance in the memory of the computer system, may be provided through an electric communication line, or may be recorded in a non-temporary recording medium such as a computer system-readable memory card, optical disk, or hard disk drive. may be provided. A processor in a computer system consists of one or more electronic circuits, including semiconductor integrated circuits (ICs) or large scale integrated circuits (LSIs). The integrated circuit such as IC or LSI referred to here is called differently depending on the degree of integration, and includes integrated circuits called system LSI, VLSI (Very Large Scale Integration), or ULSI (Ultra Large Scale Integration). In addition, a field-programmable gate array (FPGA) that is programmed after the LSI is manufactured, or a logic device capable of reconfiguring the bonding relationship inside the LSI or reconfiguring the circuit partitions inside the LSI may also be adopted as the processor. can be done. A plurality of electronic circuits may be integrated into one chip, or may be distributed over a plurality of chips. A plurality of chips may be integrated in one device, or may be distributed in a plurality of devices.

In addition, it is not an essential configuration of the object detection system 1 that a plurality of functions in the object detection system 1 are integrated in one housing, and the constituent elements of the object detection system 1 are distributed over a plurality of housings. may be provided. Furthermore, at least part of the functions of the object detection system 1, for example, part of the functions of the processing unit 10, may be realized by the cloud (cloud computing) or the like.

Moreover, the object detection system 1, the sensor system 20, and the air conditioning system 30 may be introduced not only in residential facilities but also in non-residential facilities such as offices, shops, hospitals, schools, and nursing homes.

Further, the object detection system 1 and the sensor system 20 may be used not only in the air conditioning system 30, but also in a lighting control system, an entry/exit management system, or the like.

Further, the drive unit 21 is not an essential component of the sensor system 20 and may be omitted as appropriate. When the driving unit 21 is omitted, the switching unit 12, for example, selectively selects and uses the outputs of the plurality of temperature sensors 2 installed in association with the plurality of areas A1 to A3. The detection area 4 may be switched between the areas A1 to A3.

Further, the multiple areas that are candidates for the detection area 4 are not limited to the three areas A1 to A3, and may include four or more areas. Alternatively, the multiple areas that are candidates for the detection area 4 may be two areas. When the detection area 4 switches only between the two areas of the first area A1 and the second area A2, for example, when the first area A1 is the "specific area", the second area A2 is the "other than the specific area area”. Similarly, when the second area A2 is the "specific area", the first area A1 is the "area other than the specific area". In this case, when the first area A1 is the "specific area", the period during which the detection area 4 is the first area A1 is the first period and the third period, and the period during which the detection area 4 is the second area A2. It will be the second period. Similarly, when the second area A2 is the "specific area", the period during which the detection area 4 is the second area A2 is the first period and the third period, and the period during which the detection area 4 is the first area A1 is the first period. It will be 2 periods.

Further, it is not an essential configuration of the object detection system 1 that the background updating unit 14 updates the background data D2 each time the determining unit 11 determines the presence or absence of the object. In other words, even if the number of times the determination unit 11 determines the presence or absence of the object 5 and the number of times the background update unit 14 updates the background data D2 during the period when the detection area 4 is in the same area, good.

(Embodiment 2)
The object detection system 1 according to the present embodiment differs from the object detection system 1 according to the first embodiment in the method of calculating the amount of temperature change used by the background correction unit 13 . In the following, configurations similar to those of the first embodiment are denoted by common reference numerals, and descriptions thereof are omitted as appropriate.

In the first configuration example of the present embodiment, as shown in FIG. 12, it is assumed that the first area A1 and the second area A2 or the third area A3 overlap in the overlapping area A10. That is, the first area A1 and the second area A2 partially overlap each other in the overlap region A10. Similarly, the first area A1 and the third area A3 partially overlap each other in the overlap region A10.

In this case, the temperature change amount used in the background correction unit 13 is the temperature value of the pixel corresponding to the overlap region A10 among the plurality of pixels of the background data D2 during the period when the detection area 4 is an area other than the specific area. is a representative value (for example, average value) of the amount of change in . That is, the amount of temperature change is the amount of pixels in the overlap region A10 among the plurality of pixels of the background data D2 during the period in which the detection area 4 is an area other than the specific area and overlaps the specific area in the overlap region A10. is a representative value of the amount of change in the temperature value for For example, if the specific area is the second area A2, the representative value of the amount of change in the temperature value of the pixels in the overlapping area A10 among the plurality of pixels of the background data D2 during the period when the detection area 4 is the first area A1. is used as the temperature variation. Further, if the specific area is the third area A3, the representative value of the amount of change in the temperature value of the pixels in the overlapping area A10 among the plurality of pixels of the background data D2 during the period when the detection area 4 is the first area A1. is used as the temperature variation.

According to the first configuration example, the temperature change that occurs in the overlap region A10, which is a part of the specific area, is reflected in the correction of the background data D2 corresponding to the specific area. improves.

Further, in the second configuration example according to the present embodiment, the temperature change amount used by the background correction unit 13 reflects the distribution of the temperature values in the background data D2 during the period when the detection area 4 is an area other than the specific area. is the value That is, when the background data D2 changes with a specific distribution during the period when the detection area 4 is an area other than the specific area, this distribution is reflected in the temperature change amount.

As an example, it is assumed that the temperature inside the living room 40 rises while the detection area 4 is the first area A1, and the temperature rises more in the second area A2 than in the third area A3. In this case, assuming that the specific area is the second area A2 or the third area A3, the background data D2 is shown in FIG. change as shown. In FIG. 13A, the background data D2 before change during the period in which the detection area 4 is the first area A1 is indicated by an imaginary line (two-dot chain line), and the background data D2 after change is indicated by a solid line. From the distribution of the temperature values in the background data D2 during the period in which the detection area 4 is an area other than the specific area, the temperature rise in the area on the right side of the first area A1 (second area A2) It can be seen that it is larger than the area (third area A3). Therefore, the background correction unit 13 uses the temperature change amount ΔT1 to correct the background data D2 corresponding to the second area A2, and uses the temperature change amount ΔT2 ( <ΔT1) is used.

According to the second configuration example, since the temperature distribution of the areas other than the specific area is reflected in the correction of the background data D2 corresponding to the specific area, the accuracy of correction of the background data D2 is improved.

Further, in the third configuration example according to the present embodiment, the temperature change amount used in the background correction unit 13 is the specified number of pixels of the background data D2 during the period when the detection area 4 is an area other than the specified area. This is a representative value of the amount of change in temperature value for pixels other than the pixels. That is, during the period in which the detection area 4 is an area other than the specific area, the change in the temperature value of all the pixels of the background data D2 is not reflected in the temperature change amount, but only some pixels (specific pixels) are A change in the temperature value is reflected in the temperature change amount.

As an example, during the period when the detection area 4 is the first area A1, for example, the television receiver 401 (see FIG. 2A) is activated, and the television receiver 401 becomes a fixed heat source, so that locally in the living room 40 Assume that a temperature rise occurs. In this case, assuming that the specific area is the second area A2 or the third area A3, the background data D2 is shown in FIG. change as shown. In FIG. 13B, the background data D2 before change during the period in which the detection area 4 is the first area A1 is indicated by an imaginary line (two-dot chain line), and the background data D2 after change is indicated by a solid line. In the background data D2 during the period when the detection area 4 is an area other than the specific area, it can be seen that a local temperature rise occurs due to the influence of the fixed heat source. Therefore, the background correction unit 13 uses the representative value of the amount of change in the temperature value of the pixels excluding the specific pixels (pixels in the range indicated by Z1 in FIG. 13B) to correct the background data D2 corresponding to the second area A2. A temperature change amount ΔT1, which is (for example, an average value), is used. Here, as an example, when a temperature value difference equal to or greater than a specified value occurs between some of the plurality of pixels that make up the background data D2 and other pixels, local In other words, it is determined that some pixels are specific pixels.

According to the third configuration example, since the influence of the fixed heat source in the specific area is not reflected in the correction of the background data D2 corresponding to the specific area, the accuracy of correction of the background data D2 is improved.

The configuration described in the second embodiment can be employed in appropriate combination with the various configurations (including modifications) described in the first embodiment.

(summary)
As described above, the object detection system (1) according to the first aspect includes a switching section (12), a determination section (11), and a background correction section (13). A switching unit (12) switches a detection area (4) between a plurality of areas (A1 to A3) including at least a specific area. A determination unit (11) compares output data (D1) of a temperature sensor (2) that detects the temperature of a detection area (4) with background data (D2) corresponding to each of a plurality of areas (A1 to A3). Based on the result, the presence or absence of the object (5) within the detection area (4) is determined. A background correction unit (13) corrects the background data (D2) corresponding to the specific area based on the temperature change amount (ΔT1) during the period when the detection area (4) is an area other than the specific area.

According to this aspect, since the detection area (4) where the temperature is detected by the temperature sensor (2) is switched between the plurality of areas (A1 to A3) by the switching unit (12), the detection area (4) is fixed, the area in which the object (5) can be detected can be expanded. That is, in the object detection system (1), the area in which the object (5) can be detected is not limited within the viewing angle of the temperature sensor (2). (5) can also be detected. Moreover, in the object detection system (1), the background correction unit (13) converts the background data (D2) corresponding to the specific area to the temperature change amount ( ΔT1). As a result, even though the detection area (4) is switched between a plurality of areas (A1 to A3), the reliability of detection of the object (5) in the object detection system (1) is less likely to decrease.

In the object detection system (1) according to the second aspect, in the first aspect, each of the output data (D1) and the background data (D2) includes a plurality of pixels (P1) each having a temperature value as a pixel value. image data containing

According to this aspect, the presence or absence of the object (5) is determined from the image data, so the reliability of detection of the object (5) is improved.

In the object detection system (1) according to the third aspect, in the second aspect, the amount of temperature change (ΔT1) is a plurality of background data (D2) during the period when the detection area (4) is an area other than the specific area. is a representative value of the amount of change in the temperature value for the pixel (P1) of .

According to this aspect, it is possible to improve the accuracy of correction of the background data (D2) corresponding to the specific area.

In the object detection system (1) according to the fourth aspect, in the second aspect, the amount of temperature change (ΔT1) is determined by the number of pixels (P1 ) in the overlapping area (A10). The period is an area other than the specific area and overlaps with the specific area in the overlap region (A10) that is part of the specific area.

According to this aspect, it is possible to improve the accuracy of correction of the background data (D2) corresponding to the specific area.

In the object detection system (1) according to the fifth aspect, in the second aspect, the temperature change amount (ΔT1) is This value reflects the distribution of temperature values.

According to this aspect, it is possible to improve the accuracy of correction of the background data (D2) corresponding to the specific area.

In the object detection system (1) according to the sixth aspect, in the second aspect, the temperature change amount (ΔT1) is a plurality of background data (D2) during the period when the detection area (4) is an area other than the specific area. is a representative value of the amount of change in the temperature value of the pixels (P1) excluding the specific pixel.

According to this aspect, it is possible to improve the accuracy of correction of the background data (D2) corresponding to the specific area.

In the object detection system (1) according to the seventh aspect, in any one of the first to sixth aspects, the determination unit (11) detects the object (5) during a period in which the detection area (4) is in the same area. The presence or absence of is judged multiple times.

According to this aspect, it is possible to improve the detection accuracy of the object (5).

An object detection system (1) according to an eighth aspect is, in the seventh aspect, a background updating unit ( 14).

According to this aspect, it is possible to improve the detection accuracy of the object (5).

In the object detection system (1) according to the ninth aspect, in any one of the first to eighth aspects, the object (5) is a moving object.

According to this aspect, the movement of the object (5), which is a moving body, can be detected.

In the object detection system (1) according to the tenth aspect, in any one of the first to ninth aspects, the time at which the detection area (4) is fixed to each of the plurality of areas (A1 to A3) differs depending on the area .

According to this aspect, detection of the object (5) can be focused on any one of the plurality of areas (A1 to A3).

In the object detection system (1) according to the eleventh aspect, in any one of the first to tenth aspects, the plurality of areas (A1 to A3) includes three or more areas.

According to this aspect, the area in which the object (5) can be detected can be expanded.

A sensor system (20) according to a twelfth aspect comprises the object detection system (1) according to any one of the first to eleventh aspects and a temperature sensor (2).

According to this aspect, since the detection area (4) where the temperature is detected by the temperature sensor (2) is switched between the plurality of areas (A1 to A3) by the switching unit (12), the detection area (4) is fixed, the area in which the object (5) can be detected can be expanded. That is, in the sensor system (20), the area in which the object (5) can be detected is not limited within the viewing angle of the temperature sensor (2). 5) can also be detected.

An air conditioning system (30) according to a thirteenth aspect includes the sensor system (20) according to the twelfth aspect, and an air conditioner (3) that operates based on the output of the determination section (11).

According to this aspect, since the detection area (4) where the temperature is detected by the temperature sensor (2) is switched between the plurality of areas (A1 to A3) by the switching unit (12), the detection area (4) is fixed, the area in which the object (5) can be detected can be expanded. That is, in the air conditioning system (30), the area in which the object (5) can be detected is not limited to within the viewing angle of the temperature sensor (2), and objects existing outside the viewing angle of the temperature sensor (2) (5) can also be detected.

An object detection method according to a fourteenth aspect includes switching processing, determination processing, and background correction processing. The switching process is a process of switching the detection area (4) between a plurality of areas (A1 to A3) including at least a specific area. The determination process is based on the result of comparison between the output data (D1) of the temperature sensor (2) that detects the temperature of the detection area (4) and the background data (D2) corresponding to each of the plurality of areas (A1 to A3). This is the process of determining the presence or absence of the object (5) within the detection area (4). The background correction process is a process of correcting the background data (D2) corresponding to the specific area based on the temperature change amount (ΔT1) during the period when the detection area (4) is an area other than the specific area.

According to this aspect, since the detection area (4) where the temperature is detected by the temperature sensor (2) is switched among the plurality of areas (A1 to A3) by the switching process, the detection area (4) is fixed. The area in which the object (5) can be detected can be expanded compared to the case where the object (5) can be detected. That is, in the above object detection method, the area in which the object (5) can be detected is not limited within the viewing angle of the temperature sensor (2), and the object (5) existing outside the viewing angle of the temperature sensor (2) is detected. ) can also be detected.

A program according to a fifteenth aspect is a program for causing a computer system to execute the object detection method according to the fourteenth aspect.

According to this aspect, since the detection area (4) where the temperature is detected by the temperature sensor (2) is switched among the plurality of areas (A1 to A3) by the switching process, the detection area (4) is fixed. The area in which the object (5) can be detected can be expanded compared to the case where the object (5) can be detected. That is, in the above program, the area in which the object (5) can be detected is not limited within the viewing angle of the temperature sensor (2), and the object (5) existing outside the viewing angle of the temperature sensor (2) can also be detected.

Various configurations (including modifications) of the object detection system (1) according to Embodiments 1 and 2 can be embodied by the object detection method and program, without being limited to the above aspects.

The configurations according to the second to eleventh aspects are not essential to the object detection system (1), and can be omitted as appropriate.

1 object detection system 2 temperature sensor 3 air conditioner 4 detection area 5 target object 11 determination unit 12 switching unit 13 background correction unit 14 background update unit 20 sensor system 30 air conditioning system A1 to A3 area D1 output data D2 background data ΔT1 temperature amount of change

Claims (14)

A sensor system comprising an object detection system and a temperature sensor,
The temperature sensor is configured to be rotatable,
The object detection system includes:
a switching unit that rotates the temperature sensor to switch a detection area between a plurality of areas including at least a specific area;
a determination unit that determines the presence or absence of an object in the detection area based on a comparison result between output data of the temperature sensor that detects the temperature of the detection area and background data corresponding to each of the plurality of areas;
a background correction unit that corrects the background data corresponding to the specific area based on a temperature change amount during a period in which the detection area is an area other than the specific area;
sensor system. each of the output data and the background data is image data including a plurality of pixels each having a temperature value as a pixel value;
A sensor system according to claim 1 . The temperature change amount is a representative value of the change amount of the temperature values for the plurality of pixels of the background data during a period in which the detection area is an area other than the specific area.
3. The sensor system of claim 2. The amount of change in temperature is an area other than the specific area and overlaps with the specific area in an overlap region that is a part of the specific area. is a representative value of the amount of change in the temperature value for the pixels in the overlap region among the pixels in
3. The sensor system of claim 2. The temperature change amount is a value that reflects the distribution of the temperature values in the background data during a period in which the detection area is an area other than the specific area.
3. The sensor system of claim 2. The temperature change amount is a representative value of the change amount of the temperature value of pixels excluding a specific pixel among the plurality of pixels of the background data during a period in which the detection area is an area other than the specific area. ,
3. The sensor system of claim 2. The determination unit determines the presence or absence of the object a plurality of times during a period in which the detection area is in the same area.
The sensor system according to any one of claims 1-6. Further comprising a background update unit that updates the background data each time the determination unit determines the presence or absence of the object,
A sensor system according to claim 7 . the object is a moving object,
The sensor system according to any one of claims 1-8. The time that the detection area is fixed to each of the plurality of areas varies depending on the area,
The sensor system according to any one of claims 1-9. The plurality of areas includes three or more areas,
The sensor system according to any one of claims 1-10. A sensor system according to any one of claims 1 to 11;
An air conditioner that operates based on the output of the determination unit,
air conditioning system. A switching process of rotating the temperature sensor to switch the detection area between a plurality of areas including at least a specific area;
a determination process of determining the presence or absence of an object within the detection area based on a comparison result between output data of the temperature sensor that detects the temperature of the detection area and background data corresponding to each of the plurality of areas;
background correction processing for correcting the background data corresponding to the specific area based on a temperature change amount during a period in which the detection area is an area other than the specific area;
Object detection method. A program for causing a computer system to execute the object detection method according to claim 13.

Images