JP2003254712A - Moving pattern recognizer - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a moving pattern recognizer that can recognize a moving pattern. <P>SOLUTION: This moving pattern recognizer is provided with a sensor head 21 for detecting a moving signal for indicating a position of a moving body changed with the lapse of time, using a sensor for detecting the presence of the moving body, in a detection area detected by the sensor where the moving body moves, a memory of a signal processing circuit 22 stored with a data as to the various kinds of moving patterns when the moving body moves within the detection area prepared preliminarily, and a CPU of the signal processing circuit 22 for selecting the data as to the moving pattern corresponding to the moving signal detected by the sensor head 21, from the memory. The moving pattern of the moving body can be recognized by the moving pattern recognizer. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a movement pattern recognizing device for detecting the moving direction of a human body at an entrance or the like or the number of people passing by using an infrared array sensor.

[0002]

2. Description of the Related Art In recent years, in security, air-conditioning control, and lighting control, there is an increasing demand for measuring the condition of people in the room and the temperature distribution in order to detect the presence or absence of people in the room and the amount of activity. Further, it is required for companies and the like to grasp and manage the number of visitors and exiters of a room or building by managing the occupants.

[0003] Conventional occupant management includes a method of having a person register at a reception desk in a building or a room, a method of counting with a manual counter at the entrance of a room, a method of mechanically entering and leaving each person and counting. is there.

Further, JP-A-3-196286, 5-3
A method for detecting the number of people and the moving direction by installing a pressure sensor on a mat such as a doorway or stairs like 24955, and Japanese Patent Laid-Open Nos. 3-186998, 4-95794, 5-8150.
There is a method of counting the moving direction and the number of people by using a plurality of infrared sensors as shown in FIG. That is, the human body can be detected by detecting the weight of the human body, and the moving direction and the number of people passing through can be detected, and the human body can be detected by detecting the infrared rays emitted from the human body, and the signal thereof is air-conditioned. Equipment for detecting infrared sources using infrared sensors has come to be used for the purpose of controlling environmental control equipment such as aircraft and lighting equipment, crime prevention systems, etc., and for measuring the number of people entering and leaving. It was

Further, in order to solve the above-mentioned problems, one infrared sensor provided with a plurality of detecting portions is used to detect the moving direction of the passing human body and the number of people passing, and to detect the number of people in the room. The present applicant has applied for a sensor for detecting the number of passing people and a system for the same which can manage the above.

[0006]

However, when the number of people is counted by using a person as described above, there are drawbacks that the cost is high, and it is very troublesome and time-consuming.

Further, the mechanical detection method requires large-scale equipment and is very expensive.
There was also a problem that there was no space for its installation.

Further, in the method of detecting a human body by using a plurality of infrared sensors, since a plurality of sensors are used, the cost is high, and since it is not known whether all the entrances and exits are detected, many false detections occur. There was a problem that it was easy to measure the number of people accurately. In particular,
In the detection of the sensor when a person continuously moves or crosses with a slight distance, there are many false detections and misjudgments, and there is a problem that accurate human body detection cannot be performed. Furthermore, each of these methods should require a signal processing method or algorithm suitable for the method, but it has not been disclosed at all.

Therefore, the present invention has been tried in view of the above-mentioned problems, and, for example, recognition of a movement pattern capable of detecting the direction of a moving body and calculating the number of movements for each direction. It is an object of the present invention to provide a moving pattern recognition device that enables

[0010]

The present invention uses a condenser lens that condenses infrared rays at a predetermined angle and an infrared array sensor that detects the infrared rays condensed by the condenser lenses by a plurality of detectors. And a moving signal detecting means for detecting a moving signal indicating the position of the heating element that changes with time when the heating element moves in the detection area that collects the infrared rays, and the moving signal detecting means detects the movement signal. A moving signal normalizing means for generating normalized data of the generated moving signal, and preliminarily created in consideration of the normalized data by the moving signal normalizing means, when the heating element moves in the detection area. ,
From the movement pattern storage means that stores data relating to various movement patterns and the movement pattern storage means,
Movement pattern selection means for selecting data relating to the movement pattern corresponding to the normalized data generated by the movement signal normalization means, and movement of the heating element based on the data selected by the movement pattern selection means A moving pattern recognition device comprising a moving pattern recognition means for recognizing a pattern.

The movement signal detecting means of the present invention has a plurality of sets of the condenser lens and the infrared array sensor, and each of the plurality of sets covers a predetermined area in which the heating element moves. It may be.

The present invention further comprises dust data storage means for storing a plurality of dust data which is data that cannot be generated by the movement signal normalization means, and the movement signal normalization means is provided for the movement signal normalization means. When the normalized data of the movement signal detected by the detection means is generated and the normalized data includes the dust data stored in the dust data storage means, the dust data is removed from the normalized data. May be done.

The present invention further comprises a reference temperature storage means for storing reference data relating to a predetermined reference temperature, and the movement signal normalizing means uses the reference data stored in the reference temperature storage means. Then, the ratio or difference of each of the signals obtained from the plurality of detection units of the infrared array sensor is obtained, and the magnitude of the ratio or difference is compared between the detection unit and the adjacent detection unit to obtain a binary value. Normalized data of the movement signal may be generated by performing a digitization process. The predetermined reference temperature is a temperature detected by the movement signal detecting means when the heating element is not present in the detection area, and the reference data is obtained by sampling for a predetermined time. The average value and the standard deviation of the reference temperature calculated using the reference temperature may be used.

Further, according to the present invention, the movement pattern data stored in the movement pattern storage means has sub-information relating to the movement direction of the movement pattern and / or the number of passages in that direction, The recognition means may recognize the movement direction and / or the number of passages in that direction regarding the movement pattern of the heating element based on the data regarding the movement pattern selected by the movement pattern selection means.

In the present invention, the movement signal detecting means uses a sensor for detecting the presence of the moving body, and in the detection area where the moving body can be detected by the sensor, the movement signal of the moving body changes with time. A movement signal indicating the position is detected.
The movement pattern storage means stores data relating to various movement patterns when the moving body moves within the detection area. Then, data regarding the various movement patterns is created in advance. The movement pattern selection means selects, from the movement pattern storage means, data regarding the movement pattern corresponding to the movement signal detected by the movement signal detection means.

In the present invention, the movement signal detecting means uses a condensing lens that condenses infrared rays at a predetermined angle and an infrared array sensor that detects the infrared rays condensed by the condensing lenses by a plurality of detecting sections. Then, when the heating element moves within the detection area that collects the infrared rays, a movement signal indicating the position of the heating element that changes with time is detected. The moving signal normalizing means generates normalized data of the moving signal detected by the moving signal detecting means. The movement pattern storage means stores data relating to various movement patterns, which are created in advance in consideration of the normalized data by the movement signal normalization means, when the heating element moves in the detection area. . The movement pattern selection means selects, from the movement pattern storage means, data relating to the movement pattern corresponding to the normalized data generated by the movement signal normalization means. The movement pattern recognition means recognizes the movement pattern of the heating element based on the data selected by the movement pattern selection means.

The movement signal detecting means of the present invention has a plurality of sets of the condenser lens and the infrared array sensor, and each of the plurality of sets covers a predetermined area in which the heating element moves. It may be.

Further, in the present invention, the dust data storage means stores a plurality of pieces of dust data which are data that cannot be generated by the movement signal normalization means, and the movement signal normalization means is used for the movement signal normalization means. When the normalized data of the movement signal detected by the detection means is generated and the normalized data includes the dust data stored in the dust data storage means, the dust data is removed from the normalized data. May be done.

Further, in the present invention, the reference temperature storage means is
Reference data relating to a predetermined reference temperature is stored, and the movement signal normalization means uses the reference data stored in the reference temperature storage means to obtain signals obtained from a plurality of detection units of the infrared array sensor. To obtain the normalized data of the movement signal by comparing the magnitudes of the ratios or differences and performing binarization processing between the detection unit and a detection unit adjacent to the detection unit. It may be generated. The predetermined reference temperature is a temperature detected by the movement signal detecting means when the heating element is not present in the detection area, and the reference data is obtained by sampling for a predetermined time. The average value and the standard deviation of the reference temperature calculated using the reference temperature may be used.

Further, in the present invention, the data relating to the movement pattern stored in the movement pattern storage means is
The moving pattern recognizing means has sub-information relating to the moving direction of the moving pattern and / or the number of times of passage in the direction, and the moving pattern recognizing means, based on the data concerning the moving pattern selected by the moving pattern selecting means, the heating element. The movement direction and / or the number of passages in that direction regarding the movement pattern may be recognized.

[0021]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a perspective view showing an embodiment of the movement signal detecting means used in the movement pattern recognition device of the present invention.

Generally, an infrared sensor or the like is used as a sensor used in a device for detecting an infrared source.
Two types of infrared sensors are known: a quantum sensor that captures infrared rays as photons, and a thermal sensor that absorbs infrared rays as electromagnetic waves and utilizes changes in the physical properties of the element that occur as a result of thermal action that raises the element temperature. ing. Since the former requires cooling with liquid nitrogen or the like, the latter thermal sensor is generally used. Among the thermal sensors, the pyroelectric infrared sensor has higher sensitivity than other sensors, and is suitable for detecting the infrared source.

However, since the pyroelectric infrared sensor basically detects a change in infrared light, when an attempt is made to detect a stationary infrared light source, the infrared light is intermittently detected by some method. It is necessary to devise so that the light may enter the light receiving portion. Normally, infrared rays are intermittently incident (chopping) on the sensor light receiving portion by rotating or vibrating a chopper such as a disk with a slit or a flat plate.

Therefore, the infrared array sensor of the movement signal detecting means of this embodiment is composed of a plurality of line-shaped pyroelectric elements 11.
It is composed of An infrared light shielding plate 12 is attached so as to cover the front surface of the pyroelectric element 11. The infrared transmission lens 13, which is a silicon infrared transmission lens, is attached so as to focus the infrared rays 17 on the pyroelectric element 11. If a wide-angle lens is used as the infrared transmitting lens 13, it is possible to detect the heating elements that move in a lump without rotating the infrared array sensor. The chopper 14 is provided for intermittently blocking the infrared rays 17 entering the infrared transmitting lens 13. The chopper 14 is rotatable and the chopper shaft 1
It is mechanically connected to the brushless motor 16 via 5. If the chopping frequency is set to 10 Hz or higher, human body detection can be performed faster, more accurately, and with higher accuracy.

Further, since this infrared array sensor has a plurality of line-shaped pyroelectric elements 11, the time-dependent output of each pyroelectric element 11 is based on the plurality of pyroelectric elements 11. Considering the value, it is possible to detect in which direction the moving heating element has moved on the plurality of pyroelectric elements 11.

FIG. 2 is a block diagram of another embodiment according to the moving pattern recognition apparatus of the present invention. The sensor head 21, which is a movement signal detecting means, includes the sensor shown in FIG.
Since the sensor head 21 has the plurality of line-shaped pyroelectric elements 11 shown in FIG. 1, the output values of the pyroelectric elements 11 at each time are set with reference to the plurality of pyroelectric elements 11. In consideration of the above, it is possible to detect in which direction on the plurality of pyroelectric elements 11 the heating element has moved. The output of the sensor head 21 is input to the signal processing circuit 22 via a cable of several meters. The signal processing circuit 22 includes an amplifier circuit (Amp. In FIG. 2) and an A / D converter (A / D in FIG. 2) inside.
D). The output of the sensor head 21 input to the signal processing circuit 22 is amplified by the amplifier circuit, and then input to the A / D converter to output a digital signal (AD
Value). The digital signal is arithmetically processed by the CPU, memory, etc. of the signal processing circuit 22, and the movement pattern of the moving heating element based on the infrared line sensor of the sensor head 21 is recognized. The recognition result is output from the RS-232C and transmitted to the computer or the display device 23.

The program for this arithmetic processing (the flowchart of which will be described later) is stored in a semiconductor memory such as a ROM or a memory card, or a disk memory such as a hard disk, a magneto-optical disk or a flexible disk. In addition, pre-made data or the like referred to in the arithmetic processing may be a semiconductor memory such as a ROM or a memory card, or a hard disk,
It is stored in a disk memory such as a magneto-optical disk or a flexible disk. Signal processing circuit 22
The memory included in is a main memory for loading the program, and is the above-mentioned memory.

By the way, the CPU of the signal processing circuit 22 activating the program is the moving signal normalizing means, the moving pattern selecting means of the moving pattern recognition apparatus of the present invention,
It corresponds to the movement pattern recognition means. The memory of the signal processing circuit 22 corresponds to the movement pattern storage means, dust data storage means, and reference temperature storage means of the present invention.

FIG. 4 is a diagram showing a state in which the sensor head 21 of this embodiment is installed above the entrance of a room. The sensor head 21 is located above the center of the entrance / exit 44 of a commonly-used room having a width of 100 cm and a height of 220 cm.
Is installed so as to collect infrared rays from the lower center of the entrance / exit 44 at a predetermined angle. This sensor head 21
The infrared light collected by is input to the signal processing circuit 22, and the information such as entrance and exit obtained by being processed there is displayed on the computer or the display device 43. If the incident angle of the sensor at this time is 6 °, the detection area 4
6 is as shown in the figure, and it can be sufficiently detected even if the human body 45 passes the most end.

Next, the operation of this apparatus in this installed state will be described.

FIG. 5 is a flow chart regarding the processing of the CPU of FIG. 2 in which the program is activated. That is, the floor temperature, which is the background that is constantly detected, is sampled for a predetermined time, and the average value (X
var) and standard deviation (S) are calculated. These average value and standard deviation are stored in the memory of the signal processing circuit 22. As the memory operation, if the human body 45 does not exist in the detection area 46 during the predetermined sampling time,
The calculated new average value and standard deviation are updated.

These average values and standard deviations are used by (Equation 1) to obtain A obtained by inputting from each of the plurality of pyroelectric elements of the infrared array sensor for each chopping.
From the D value, the rate of change (HENKA) of each of the signals obtained from the plurality of pyroelectric elements is calculated.

[0034]

## EQU00001 ## HENKA (i, j) = (AD value-Xvar) / S When the change rate is 3 times or more the standard deviation, the change rates between the adjacent pyroelectric elements in the infrared array sensor are compared. Binarization processing is performed by setting the larger one to 1.

FIG. 6 shows, as a concrete example, three pyroelectric elements 1.
FIG. 3 is a diagram showing how normalized data of a moving signal detected by No. 1 is generated. The detection area of the infrared array sensor installed 2.5 m above consists of detection areas 1, 2, and 3. The state A shown in (a) is a moving state when a human body enters the detection area 3. State B1 shown in (b)
B2 is a moving state when the vehicle moves toward the detection area 2. States C1 and C2 shown in (c) are movement states when the detection area 1 is reached. The binarized data at this time is as shown in the graph on the right of each figure.
That is, in the change rate of 3 times or more of the standard deviation σ (S),
If the larger one compared to the adjacent pyroelectric element is 1,
A: (001), B1: (011), B2: (01
0), C1: (110), and C2: (100). FIG. 7: is a figure which shows an example of another operation | movement obtained similarly to FIG. For example, when a person passes by, as shown in (a), (000) (001) (011) (110)
It changes like (000). Also, when a person makes a U-turn in the middle, it is considered that the change will occur as shown in (b) or (c).

Based on the binarized data obtained in this way, data relating to various movement patterns when the human body moves in the detection area is created in advance and stored in the memory of the signal processing circuit 22. Has been done.

The actual movement pattern detected and processed by the infrared array sensor is compared with the various movement patterns stored in this memory and the data relating to the relevant movement pattern is selected.

The movement pattern of the human body is recognized based on the data relating to the selected movement pattern. That is, if the information regarding the direction of movement is included in the data regarding the movement pattern, the direction in which the human body has moved is recognized. In the case of the present embodiment, the movement pattern recognition device recognizes whether a person has entered from the entrance 44 or has exited.

By this method, the human body can be detected with high reliability and high accuracy, and the moving direction can be determined, and the moving direction detection rate, which has been about 90% in the past, is 99.
I was able to make it over%.

FIG. 8 is a flowchart showing the operation of another embodiment of the moving pattern recognition device of the present invention.
The configuration and operation of the moving pattern recognition device of this embodiment are
Similar to the embodiment described with reference to FIG. 1 to FIG. 7, the difference is the type of information of data relating to various movement patterns, and the processing of recognition of information after the movement pattern is selected and its acquisition. Is the result of FIG. 9 is a diagram showing specific binarized data regarding a movement pattern when a person goes in and out of an entrance. It shows a case where two human bodies intersect or a case where two human bodies pass continuously. In the present embodiment, such a movement pattern is taken into consideration, and information indicating in which direction the person has passed through the detection area is provided together with the data regarding the movement pattern, and the signal processing circuit 22 of FIG.
Stored in advance in the memory. As a result, the movement pattern recognition device of this embodiment can count how many people have entered or left the entrance. It is also possible to calculate the number of visitors by time zone.

With this method, it is possible to detect the human body with high reliability and with high accuracy, judge the moving direction, and measure the number of passing people. It could be over 95%.

FIG. 10 is a flowchart showing the operation of another embodiment of the moving pattern recognition device of the present invention. The configuration and operation of the moving pattern recognition device of this embodiment are
This embodiment is the same as the embodiment described with reference to FIGS. 1 to 9 and is different in the handling of dust patterns described below.
First, in the memory of the signal processing circuit 22 of FIG. 2, a plurality of pieces of dust data, which are data that cannot be obtained by generating the normalized data of the movement signal of FIG. 6, are stored in advance.

Therefore, how this dust pattern is used will be described. The floor surface temperature that is the background is sampled for a predetermined time, and the average value and standard deviation of the floor surface temperature are calculated. These average value and standard deviation are stored in the memory of the signal processing circuit 22. As a storage operation, if a human body does not exist in the detection area during a predetermined sampling time, the calculated new average value and standard deviation are updated.

Using these average values and standard deviations according to (Equation 1), A obtained by inputting from each of the plurality of pyroelectric elements of the infrared array sensor for each chopping is obtained.
From the D value, the rate of change (HENKA) of each of the signals obtained from the plurality of pyroelectric elements is calculated.

When the rate of change is three times the standard deviation or more, the rate of change between adjacent pyroelectric elements in the infrared array sensor is compared, and the larger one is set to 1 to perform the binarization process. To be done.

If the binarized data has data corresponding to the dust pattern, the data is deleted as dust. The dust pattern is, for example, (000) (010)
This is data in the case where only 1 suddenly appears as in (000), and in such a case, it is automatically canceled by dust deletion.

FIG. 11 is a block diagram showing another embodiment of the moving pattern recognition device of the present invention. Sensor heads (111a, 111) that are a plurality of movement signal detection means
b, ...) Each includes the sensor of FIG. Each output of the sensor head is input to each signal processing circuit (112a, 112b, ...). Each of the signal processing circuits is internally provided with an amplifier circuit (Am in FIG. 11).
p. ), An A / D converter (A / D in FIG. 11), and a motor driver. The output of the sensor head input to each of the signal processing circuits is amplified by the amplifier circuit and then input to the A / D converter and converted into a digital signal (AD value). The digital signal is CP
U based on the infrared line sensor of the sensor head which has been input to the control device 113 having a memory and the like, has undergone arithmetic processing by the CPU, a memory and the like, and has detected the signal,
The movement pattern of the moving heating element is recognized. The result is output from the RS-232C or PIO to the computer 114, or output from the PIO to the display device 11.
5 is sent.

The program for this arithmetic processing (the flowchart of which will be described later) is stored in a semiconductor memory such as a ROM or a memory card, or a disk memory such as a hard disk, a magneto-optical disk or a flexible disk. Further, the data referred to in the arithmetic processing is also stored in a semiconductor memory such as a ROM or a memory card, or a disk memory such as a hard disk, a magneto-optical disk or a flexible disk. The memory included in the control device 113 is a main memory for loading the program and is the above-mentioned memory.

By the way, the CPU of the control device 113 activating the program corresponds to the movement signal normalizing means, movement pattern selecting means and movement pattern recognizing means of the movement pattern recognizing device of the present invention. In addition, the control device 113
This memory corresponds to the movement pattern storage means, dust data storage means, and reference temperature storage means of the present invention.

FIG. 12 is a diagram showing a state in which the sensor head of this embodiment is installed above the entrance of a room. Width 2
Wide entrance 125 with a height of 00 cm and a height of 250 cm
On top of the four sensor heads (111a, 111b,
111c and 111d) are perpendicular to the passing direction of the human body 126 and are always looking at the floor surface at a certain interval, and the plurality of pyroelectric elements constituting each infrared array sensor of the sensor head are Install so that the arrangement direction is parallel to the passing direction of the human body. If the incident angle of the sensor head at this time is 6 °, the detection area 127a or 1
Since 27b is as shown in the figure, even if the human body 126 passes the most end, it can be sufficiently detected.

Next, the processing of this embodiment will be described.
First, the floor temperature, which is the background that is constantly detected, is sampled for a predetermined time, and the average value and standard deviation of the floor temperature are calculated. These average value and standard deviation are stored in the memory of the control device 113 in FIG. As the operation of the memory, if the human body 126 is not present in each detection area during a predetermined time of sampling,
Updated with the new mean and standard deviation.

These average values and standard deviations are used in (Equation 1) to obtain for each chopping by inputting from each of the plurality of pyroelectric elements forming the infrared array sensor of each sensor head. From the AD value, the rate of change of each of the signals obtained from the plurality of pyroelectric elements (HENKA)
Is calculated.

When the rate of change is three times the standard deviation or more, the rates of change between adjacent pyroelectric elements in the infrared array sensor are compared, and the larger one is set to 1, and the binarization processing is performed. To be done.

Based on the binarized data obtained as described with reference to FIGS. 6 and 7, data relating to various movement patterns when the human body moves within the detection area are created in advance. , Stored in the memory of the control device 113 of FIG.

The actual movement pattern detected and processed by the infrared array sensor is compared with the various movement patterns stored in this memory and the data relating to the relevant movement pattern is selected.

The movement pattern of the human body is recognized based on the data regarding the selected movement pattern. That is, if the information regarding the direction of movement and the number of passages in that direction is included in the data regarding the movement pattern, it is recognized in which direction, how many times, that is, how many persons have moved. In the case of the present embodiment, the movement pattern recognition device recognizes how many people have entered or exited from the entrance 125.

As described above, according to this embodiment, even a human body having a non-uniform temperature distribution entering a room or a building can be easily detected at low cost, and the number of passing people can be accurately and highly reliable. Can be measured and the number of people in the room can be displayed.

FIG. 13 is a flow chart showing the operation of another embodiment of the moving pattern recognition device of the present invention. The configuration of the moving pattern recognition device of this embodiment is shown in FIG.
The configuration is the same as that of the embodiment described by using, but is different in that processing is performed in consideration of a plurality of movement signals from a plurality of sensor heads installed.

Therefore, the processing in this embodiment will be described.

First, the floor temperature, which is the background that is constantly detected, is sampled for a predetermined time, and the average value (Xvar) and standard deviation (S) of the floor temperature are calculated. These average value and standard deviation are stored in the memory of the control device 113 in FIG. The operation of the storage is to update the calculated new average value and standard deviation if there is no person in each detection area during a predetermined sampling time.

These average values and standard deviations are used in (Equation 1), and are obtained for each chopping by being input from each of the plurality of pyroelectric elements forming the infrared array sensor of each sensor head. From the AD value, the rate of change of each of the signals obtained from the plurality of pyroelectric elements (HENKA)
Is calculated.

When the rate of change is three times the standard deviation or more, the rate of change between adjacent pyroelectric elements in the infrared array sensor is compared, and the larger one is set to 1, and the binarization processing is performed. To be done.

If the binarized data has data corresponding to the dust pattern, the data is deleted as dust. Here, in the memory of the control device 113, a plurality of pieces of dust data, which are data that cannot be obtained by the binarization process, are stored in advance.

Based on the data thus binarized, data relating to various movement patterns when the human body moves in the detection area is created in advance, and the control device 1
It is stored in 13 memories. Then, the actual movement pattern detected and processed by the infrared array sensor of each sensor head is compared with various movement patterns stored in this memory, and data relating to the corresponding movement pattern is selected. .

The number of passing human bodies is detected by comprehensively judging the data relating to the movement pattern selected by each sensor head. For example, referring to the example of FIG. 12, when outputs appear at the sensor heads 111a and 111b at the same time, or when outputs appear at the sensor head 111a or 111b, it is determined that only one person has passed. You can In addition, the sensor head 111a
If the outputs appear in 111 and 111d at the same time, it can be determined that two people have passed.

As described above, according to this embodiment, it is possible to easily detect a person entering a room or a building even at a wide entrance / exit, and to measure the number of people passing through with high accuracy and high reliability. The number of people in the room can be displayed.

FIG. 14 is a block diagram showing another embodiment of the movement pattern recognition device of the present invention. The configuration of the movement pattern recognition device of this embodiment is the same as that of the embodiment described with reference to FIG. As shown in FIG. 14, a wide entrance / exit 14 with a width of 160 cm and a height of 250 cm.
Two sensor heads (111a, 111b)
And 111c) are perpendicular to the passing direction of the human body and are always looking at the floor surface at a certain interval, and the sensor heads (111a and 111c) at both ends are arranged so that the array direction of the infrared array sensors is the same as the human body. The sensor head 111b at the center is installed so as to be parallel to the passing direction and vertically. By installing in this way, the detection areas (143a, 143b and 14) of each infrared array sensor are
3c) is as shown in the figure. Sensor heads on both ends (111
If the incident angle of a and 111c) is 6 °, the detection regions (143a and 143c) are as shown in the figure, and therefore, even if the human body passes through the end, it can be sufficiently detected.

Next, the processing of this embodiment will be described.

First, the floor temperature, which is the background that is constantly detected, is sampled for a predetermined time, and the average value and standard deviation of the floor temperature are calculated. These average value and standard deviation are stored in the memory of the control device 113 in FIG. As a storage operation, if there is no human body in each detection area during a predetermined sampling time, the calculated new average value and standard deviation are updated.

These average values and standard deviations are used in (Equation 1), and are obtained for each chopping by being input from each of the plurality of pyroelectric elements forming the infrared array sensor of each sensor head. From the AD value, the rate of change of each of the signals obtained from the plurality of pyroelectric elements (HENKA)
Is calculated.

When the rate of change is three times the standard deviation or more, the rate of change between adjacent pyroelectric elements in the infrared array sensor is compared, and the larger one is set to 1 to perform binarization processing. To be done.

Based on the binarized data obtained as described with reference to FIGS. 6 and 7, data relating to various movement patterns when the human body moves within the detection area are created in advance. , Stored in the memory of the control device 113.

Sensor heads (111a, 111b and 1)
The actual movement pattern detected and processed by each infrared array sensor of 11c) is compared with the various movement patterns stored in this memory and the data relating to the corresponding movement pattern is selected.

The number of passing human bodies is detected by comprehensively judging from the data on the movement pattern selected by each sensor head. That is, the detection areas (1) of the sensor heads (111a and 111c) at both ends are
Sensor head 11 including 43a and 143c)
The number of passing people is determined by the detection area 143b of 1b. The sensor heads (111a and 111) at both ends are
The moving direction and the number of people passing through are detected by c). For example, three sensor heads (111a, 111b and 11)
It is assumed that the number of pyroelectric elements forming each infrared array sensor in 1c) is eight. This sensor head 1
When 11b detects a human body with three or less pyroelectric elements, even if the sensor heads (111a and 111c) at both ends detect the human body at the same time, the number of people who have passed is counted as one. In addition, this sensor head 111b
When a human body is detected by 4 to 6 pyroelectric elements, it is counted as 2 people.

By this method, it is possible to detect the human body with high reliability and high accuracy and to judge the number of people passing by.
I was able to make it over%.

In the above embodiment, the sensor head is
Although the infrared array sensor including a plurality of pyroelectric elements is included, the sensor is not limited to this, and may be a sensor such as an ultrasonic wave or a radar. In short, the movement signal detecting means of the present invention is only required to be able to detect the directionality of the moving body moving within the predetermined area.

Although the sensor head of the above embodiment has the chopper 14, the chopper shaft 15 and the brushless motor 16, the movement signal detecting means of the present invention only needs to detect the moving human body. The chopper 14, the chopper shaft 15 and the brushless motor 16 are not necessarily required.

In the above embodiment, the signal processing circuit 22 shown in FIG. 2 is configured to include the motor driver. However, the configuration is not limited to this, and the signal processing circuit 22a and the signal processing circuit 22a are provided as shown in FIG. The relay box 22b having a motor driver may have another configuration, or the relay box 22b may be incorporated in the sensor head 21.

In the above embodiment, the floor surface temperature is used as the reference for calculating the rate of change, but the present invention is not limited to this, and the wall surface temperature may be used.

Further, in the above embodiment, the normalized data of the movement pattern is generated by using three pyroelectric elements in FIGS. 6, 7 and 9, but the present invention is not limited to this, and the infrared array sensor is not limited thereto. If n is composed of n pyroelectric elements, 2 to n of the pyroelectric elements may be used to generate the normalized data of the movement pattern.

[0081]

As is apparent from the above description, the movement pattern recognition device of the present invention can recognize the movement pattern of a moving body. Alternatively, there is an effect that the movement pattern of the moving heating element can be recognized.

Further, according to the present invention, by adding various information to the data relating to the movement pattern stored in the movement pattern storage means, it is possible to provide a device that meets various needs. For example, by adding the direction of movement and the number of passes in that direction, it is possible not only to detect people entering and exiting a room or building, but also to measure the number of people passing through to obtain accurate entrance. It has the advantage of being able to provide a device that can detect the number of people and the number of people in the room.

Further, according to the present invention, when the infrared array sensor of the movement signal detecting means is installed so as to collect infrared rays from the floor surface, the temperature fluctuation of the floor surface can be fed back at all times. Even if the surface temperature fluctuates, the average value can be made to follow the fluctuation.
The moving signal detecting means detects the moving heating element by using the average value and the standard deviation, and therefore has an effect of being able to detect even the heating element is a low temperature object having a low temperature.

Further, according to the present invention, there is an effect that the moving body or the moving heating element can be accurately detected even when the moving body continuously passes or crosses.

Further, in the present invention, by removing the dust pattern generated when the moving signal detecting means apparently does not detect the moving body or the moving heating element, low temperature and high temperature objects are mixed. Even if there is, there is an effect that accurate detection can be performed.

Further, according to the present invention, it is possible to obtain a moving pattern recognition device which is compact in system, low in cost, accurate and highly reliable, and can easily and immediately detect the number of people in the room. can do.

Further, in the present invention, erroneous detection as in the case of using other conventional sensors is not observed, and accurate and highly reliable human body detection and passing person detection can be performed.

In addition, in the present embodiment, by using an algorithm that is very simple in terms of programming, accurate human body detection with little false detection even during continuous passage or crossing passage can be easily realized at low cost. can do.

Further, according to the present invention, it is possible to easily and highly accurately detect the human body and measure the number of people in the room, and it is possible to greatly contribute to a comfortable intelligent building system.

[Brief description of drawings]

FIG. 1 is a perspective view showing an embodiment of a movement signal detecting means used in a movement pattern recognition device of the present invention.

FIG. 2 is a configuration diagram of another embodiment according to the movement pattern recognition device of the present invention.

FIG. 3 is a configuration diagram in which a part of the configuration of the embodiment of FIG. 2 is changed.

FIG. 4 is a diagram showing a state in which a sensor head 21 of the present embodiment is installed above an entrance of a room.

5 is a flowchart regarding processing of the CPU in FIG. 2 in which the program is activated.

FIG. 6 is a diagram showing how normalized data of movement signals detected by three pyroelectric elements 11 is generated.

FIG. 7 is a diagram showing an example of another operation obtained in the same manner as in FIG.

FIG. 8 is a flowchart showing the operation of another embodiment of the movement pattern recognition device of the present invention.

FIG. 9 is a diagram showing specific binarized data regarding a movement pattern when a person goes in and out of a doorway.

FIG. 10 is a flowchart showing the operation of another embodiment of the moving pattern recognition device of the present invention.

FIG. 11 is a configuration diagram of another example of the movement pattern recognition device of the present invention.

FIG. 12 is a diagram showing a state in which the sensor head of the present embodiment is installed above the entrance of a room.

FIG. 13 is a flowchart showing the operation of another embodiment of the moving pattern recognition device of the present invention.

FIG. 14 is a configuration diagram of another example of the movement pattern recognition device of the present invention.

[Explanation of symbols]

11 Pyroelectric element 12 Infrared light shield 13 Infrared transparent lens 14 Chopper 15 Chopper shaft 16 brushless motor 17 infrared 21 sensor head 22, 22a Signal processing circuit 22b Relay BOX 23 Computer or display 44 Doorway 45 human body 46 Detection area

   ─────────────────────────────────────────────────── ─── Continued front page    (72) Inventor Kiyoshi Matsueda             1006 Kadoma, Kadoma-shi, Osaka Matsushita Electric             Sangyo Co., Ltd. (72) Inventor Chihiro Kawaguchi             1006 Kadoma, Kadoma-shi, Osaka Matsushita Electric             Sangyo Co., Ltd. F term (reference) 2F065 AA02 AA03 AA07 AA09 BB05                       CC16 FF41 GG09 JJ02 JJ05                       JJ25 LL10 LL30 NN19 QQ03                       QQ07 QQ13 QQ23 QQ41 QQ42

Claims (6)

[Claims] 1. An infrared ray is condensed using a condenser lens for condensing infrared rays at a predetermined angle and an infrared array sensor for detecting the infrared rays condensed by the condenser lens by a plurality of detectors. Movement signal detecting means for detecting a movement signal indicating a time-varying position of the heating element when the heating element moves in the detection area, and normalized data of the movement signal detected by the movement signal detecting means. And a movement signal normalizing means for generating the movement signal, and data relating to various movement patterns when the heating element moves in the detection area, which is created in advance in consideration of the normalized data by the movement signal normalizing means. Movement pattern storage means stored, and data relating to the movement pattern corresponding to the normalized data generated by the movement signal normalization means from the movement pattern storage means. A movement pattern recognition device comprising: a movement pattern selection means for selecting the movement pattern; and a movement pattern recognition means for recognizing the movement pattern of the heating element based on the data selected by the movement pattern selection means. . 2. The movement signal detection means has a plurality of sets of the condenser lens and the infrared array sensor, and each of the plurality of sets covers a predetermined area in which the heating element moves. The movement pattern recognition device according to claim 1, wherein 3. A dust data storage unit that stores a plurality of dust data that is data that cannot be generated by the movement signal normalization unit, wherein the movement signal normalization unit detects the movement signal detection unit. If the dust data stored in the dust data storage means is included in the normalized data of the generated movement signal, the dust data may be removed from the normalized data. The moving pattern recognition device according to claim 2, wherein the moving pattern recognition device is a moving pattern recognition device. 4. A reference temperature storage means for storing reference data relating to a predetermined reference temperature, wherein the movement signal normalization means uses the reference data stored in the reference temperature storage means for the infrared rays. The ratio or difference of each of the signals obtained from the plurality of detection units of the array sensor is obtained, and the size of the ratio or difference is compared between the detection unit and the adjacent detection unit to perform binarization processing. The moving pattern recognition device according to any one of claims 1 to 3, wherein the normalized data of the moving signal is thereby generated. 5. The predetermined reference temperature is a temperature detected by the movement signal detecting means when the heating element is not present in the detection area, and the reference data is sampled for a predetermined time. The movement pattern recognition device according to claim 4, wherein the movement pattern recognition device is an average value and a standard deviation of the reference temperature calculated by using the obtained reference temperature. 6. The movement pattern data stored in the movement pattern storage means has sub-information relating to the movement direction of the movement pattern and / or the number of passages in the direction, and the movement pattern recognition means includes: The movement direction and / or the number of times of passage in the movement direction regarding the movement pattern of the heating element is recognized based on the data regarding the movement pattern selected by the movement pattern selection means. The movement pattern recognition device according to any one of claims.