JP2001118155A - Human body detection device, human body detection method and computer readable recording medium recording program making computer execute the method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a human body detection device where erroneous detection and misdetection can be reduced, and to provide a human body detection method and a computer readable recording medium recording a program making a computer execute the method. SOLUTION: A human body detection device 1 detecting that a human body exists in a prescribed area has a heat source detection part 2 detecting a temperature change in the area, a picture input part 4 which has a picture sensor such as an artificial retina sensor 3, image-picks up a picture in the area and generates picture information and a human body estimation part 5 estimating that the human body exists based on the detection result of the heat source detection part 2 and picture information that the picture input part 4 generates.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a human body detecting device for detecting presence of a person in a predetermined area, a human body detecting method, and a computer-readable recording medium storing a program for causing a computer to execute the method.
In particular, the present invention relates to a human body detection device, a human body detection method, and a computer-readable recording medium that records a program for causing a computer to execute the method, which reduces erroneous detection or non-detection even when a person is present. .

[0002]

2. Description of the Related Art For security of buildings, etc., a human body detecting device for detecting the presence of a person in a predetermined area is used. As a conventional general human body detection device, a device using a passive infrared sensor (Passive Infrared Sensor) is known. The passive infrared sensor detects a temperature change in the detection area as a change in the amount of received far infrared light. Thus, the intrusion of a person is detected by detecting a temperature change due to a difference between the temperature of the human body and the temperature of the background wall or floor.
In such a conventional human body detection device, in order to cover an area to be efficiently guarded, a plurality of optical systems (mirrors, lenses, etc.) are combined to guide a wide range of far-infrared energy to a passive infrared sensor, and one The area that can be detected by the human body detection device has been expanded.

[0003]

However, according to the above-mentioned prior art, since only passive infrared sensors are used, the temperature of the background wall or floor is reduced to near body temperature on a hot summer day. When it rises, there is a problem that it may not be detected even though there is a person (miss detection). On the other hand, if the sensitivity of the passive infrared sensor is increased to prevent loss detection, the passive infrared sensor reacts to the presence of a mouse or the like, and there is a problem that erroneous detection is frequently performed.

The present invention has been made in view of the above, and has been made in consideration of the above circumstances. A human body detecting apparatus, a human body detecting method, and a computer recording a program for causing a computer to execute the method can reduce both erroneous detection and false detection. It is an object to obtain a readable recording medium.

[0005]

Means for Solving the Problems To solve the above-mentioned problems,
In order to achieve the object, in the human body detection device according to the present invention, in a human body detection device that detects the presence of a human body in a predetermined area, a detection unit that detects a temperature change in the area, An imaging unit that captures an image in the area to generate image information, and an estimation unit that estimates that a human body is present based on a detection result of the detection unit and image information generated by the imaging unit. It is characterized by doing.

According to the present invention, the detecting means detects a temperature change in a predetermined area, the image capturing means captures an image in the area to generate image information, and the estimating means detects the temperature change in the predetermined area. The presence of a human body is estimated based on the detection result and the image information generated by the imaging unit. This makes it possible to estimate the presence of a human body based on two types of information: temperature change information and image information.

In the human body detection device according to the next invention, the imaging means performs imaging when a detection result of the detection means satisfies a predetermined condition.

According to this invention, the imaging means stops operating until the detection result of the detection means satisfies a predetermined condition,
When the detection result of the detection means satisfies a predetermined condition, imaging is performed.

In the human body detecting apparatus according to the next invention, when the estimating means cannot estimate the presence of the human body from the image information generated by the imaging means, the estimating means estimates the presence of the human body from the detection result of the detecting means. It is characterized by doing.

According to this invention, even when the estimating means cannot estimate the presence of the human body from the image information generated by the imaging means, the estimating means estimates the presence of the human body only from the detection result of the detecting means.

[0011] In the human body detecting apparatus according to the next invention, the detecting means estimates which part of the area has changed in temperature.

According to the present invention, the location where the temperature has changed can be estimated by the detecting means.

[0013] In the human body detecting device according to the next invention, the detecting means has heat-sensitive elements arranged in an array, and based on the outputs of these heat-sensitive elements, the temperature change in any part of the area is determined. It is characterized by whether there was any

According to the present invention, the detecting means estimates at which part of the area a temperature change has occurred based on the outputs of the heat-sensitive elements arranged in an array.

[0015] In the human body detecting apparatus according to the next invention, the detecting means has a thermosensitive element, and scans the area by driving the thermosensitive element, and which part of the area has a temperature change. Is estimated.

According to this invention, the detecting means scans the area by driving the thermal element, and estimates which part of the area has changed in temperature.

In the human body detecting apparatus according to the next invention, the detecting means has an infrared camera and estimates which part of the area has changed in temperature.

According to the present invention, the detecting means estimates, by the infrared camera, in which part of the area the temperature has changed.

In the human body detecting apparatus according to the next invention, the imaging means performs image processing on an image of only a portion estimated by the detecting means as having a temperature change.

According to the present invention, the imaging means processes the image of only the portion estimated by the detection means as having a temperature change, generates image information of only this part, and
The presence of a human body is estimated from this image information.

In the human body detecting apparatus according to the next invention, the estimating means estimates the distance from the imaged object to the own device, and estimates the size of the object.

According to this invention, the estimating means estimates the size of the object based on the distance from the imaged object to the own device, and estimates whether the object is a human body.

In the human body detection device according to the next invention, the imaging means generates a plurality of pieces of image information from different positions, and the estimating means generates a plurality of pieces of image information based on the plurality of pieces of image information generated by the imaging means. And estimating the distance from the imaged object to the own device and estimating the size of the object.

According to the present invention, the imaging means generates a plurality of pieces of image information from different positions, and the estimating means estimates the distance from the imaged object to the own apparatus based on the plurality of pieces of image information. Then, the size of the object is estimated, and whether or not the object is a human body is estimated.

In the human body detecting apparatus according to the next invention, the image pickup means performs image pickup periodically.

According to the present invention, the image capturing means periodically performs image capturing and periodically generates image information.

In the human body detecting apparatus according to the next invention, the estimating means stores the image information generated by the imaging means, compares the past image information with new image information, and It is characterized in that a change is determined.

According to the present invention, the estimating means stores the image information generated by the imaging means, compares the past image information with the new image information, and determines a change in the image information. Thereby, it can be estimated that the own device has been moved or that an object in the area has been moved.

In the human body detecting device according to the next invention, the estimating means estimates that the own device has been moved.

According to the present invention, the estimating means estimates that the own apparatus has been moved, for example, by comparing the image information of the background image when no person is present with the image information generated by the imaging means. .

In the human body detecting apparatus according to the next invention, the estimating means estimates that an object located in the area has been moved or placed.

According to the present invention, the estimating means compares the image information of the background image when no person is present with the image information generated by the imaging means, so that the object located in the area moves. Estimate what was done or placed.

In the human body detecting apparatus according to the next invention, the imaging means generates color image information, and the estimating means generates color image information based on the color information of the color image information generated by the imaging means. The method is characterized in that a plurality of imaged objects are separated.

According to the present invention, the imaging means generates color image information, and the estimating means separates a plurality of imaged objects based on the color information of the color image information generated by the imaging means. Estimate the presence of the human body.

In the human body detecting device according to the next invention, the imaging means has an artificial retinal sensor.

According to the present invention, the image pickup means performs image pickup using the inexpensive and compact artificial retinal sensor and generates image information.

In the human body detecting method according to the next invention, in the human body detecting method for detecting the presence of a human body in a predetermined area, an imaging step of capturing an image in the area to generate image information And an estimation step of estimating whether or not a human body exists based on the image information generated in the imaging step and temperature change information indicating a temperature change in the area.

According to the present invention, in the imaging step, an image in the area is imaged to generate image information, and in the estimation step, the image information generated in the imaging step and the temperature change information indicating the temperature change in the area. Is used to estimate whether or not a human body exists. Thereby, the temperature change information and the image information 2
The presence of a human body can be estimated from the type information.

The human body detecting method according to the next invention is characterized in that in the imaging step, imaging is performed when the temperature change information satisfies a predetermined condition.

According to the present invention, in the imaging step, the imaging is stopped until the temperature change information satisfies the predetermined condition, and when the temperature change information satisfies the predetermined condition, the imaging is performed.

In the human body detecting method according to the next invention, when the presence of the human body cannot be estimated from the image information generated in the imaging step in the estimation step, the presence of the human body is estimated from the temperature change information. It is characterized by the following.

According to the present invention, in the estimation step, even when the presence of a human body cannot be estimated from the image information generated in the imaging step, the presence of the human body is estimated only from the temperature change information.

The human body detecting method according to the next invention is characterized in that the method further includes a partial estimating step of estimating in which part of the area the temperature has changed.

According to the present invention, in the partial estimation step, which part of the area has undergone the temperature change is estimated.

The human body detecting method according to the next invention is characterized in that, in the imaging step, image processing is performed on an image of only a portion estimated to have undergone a temperature change in the partial estimation step.

According to the present invention, in the imaging step, image processing is performed on the image of only the portion estimated to have undergone a temperature change in the partial estimation step, and only the portion estimated to have undergone a temperature change, which is a necessary portion, is processed. Is generated.

In the human body detecting method according to the next invention, in the estimating step, a distance from the imaged object to the own apparatus is estimated based on the image information generated in the image capturing step, and the object is estimated. Is characterized by estimating the size of.

According to the present invention, in the estimating step, the distance from the imaged object to the own apparatus is estimated based on the image information generated in the imaging step, the size of the object is estimated, Estimate whether there is.

The human body detecting method according to the next invention is characterized in that in the image capturing step, image information is generated by periodically performing image capturing.

According to the present invention, even when there is no predetermined change in the temperature change information, image information is generated by periodically performing imaging in the imaging step.

In the human body detecting method according to the next invention, in the estimating step, the image information generated in the imaging step is stored, and the past image information is compared with the new image information to obtain the image information. Is determined.

According to the present invention, in the estimation step, the image information generated in the image pickup step is stored, and the change of the image information can be determined by comparing the past image information with the new image information.

The human body detection method according to the next invention further includes an imaging movement estimating step of estimating that the imaging position or the imaging direction has been moved based on the image information generated in the imaging step. It is characterized by the following.

According to the present invention, in the imaging movement estimating step,
Based on the image information generated in the imaging process, it is estimated that the imaging position or the imaging direction has been moved.

[0055] In the human body detecting method according to the next invention, it is further provided that the object located in the area is moved or placed based on the image information generated in the imaging step. The method includes a step of estimating an object movement to be estimated.

According to the present invention, in the object movement estimating step, it is estimated that an object located in the area has been moved or placed, based on the image information generated in the imaging step.

In the human body detecting method according to the next invention, in the estimating step, a plurality of imaged objects are separated based on image information generated in the image capturing step.

According to the present invention, in the estimation step, a plurality of imaged objects are separated based on the image information generated in the imaging step, and the existence of a human body is estimated.

A computer-readable recording medium according to the next invention is characterized by recording a program for causing a computer to execute the method according to the invention.

According to the present invention, it is possible to make a computer execute the method according to the present invention.

[0061]

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of a human body detecting device, a human body detecting method, and a computer-readable recording medium storing a program for causing a computer to execute the method will be described in detail with reference to the drawings. explain. The present invention is not limited by the embodiment.

FIG. 1 is a block diagram showing a schematic configuration of a human body detection device according to one embodiment of the present invention. The human body detection device 1 according to the present embodiment detects a temperature change in a predetermined area and outputs a value (temperature change information) according to the amount of temperature change, an artificial retinal sensor 3, and the like. An image input unit 4 that captures an image in a predetermined area and outputs image information, and detects a feature amount from temperature change information from the heat source detection unit 2 and image information from the image input unit 4. A human body estimating unit 5 for estimating whether or not the extracted and imaged object is a human body. Note that the heat source detection unit 2 corresponds to the detection unit of the present invention, and the image input unit 4
The human body estimation unit 5 corresponds to the imaging unit of the present invention, and corresponds to the estimation unit of the present invention.

FIG. 2 is a perspective view showing a schematic configuration of the human body detecting device 1 according to the present embodiment. Human body detection device 1
Is configured to be incorporated in one housing having openings for the heat source detection unit 2 and the image input unit 4. For example, as shown in FIG. 3, the human body detection device 1 is attached to a ceiling 19 so that the desk 9 enters a detection area (detection area) in a room where an object such as the desk 9 is placed.
When there is no human body in the room and there is no abnormality, the image input unit 4 captures a background image including the floor 6, the wall 7, the door 8, the desk 9, and the like as shown in FIG. .

The image input unit 4 captures the background image in advance, and the human body estimating unit 5 stores the image information of the background image in advance. In addition, the human body estimation unit 5 controls the image input unit 4 so that the temperature change information from the heat source detection unit 2 is set to a predetermined threshold 1
The operation of the image input unit 4 is stopped until the above temperature change is indicated. When the temperature change information indicates a temperature change equal to or greater than the threshold value 1, the operation of the image input unit 4 is started to capture an image as shown in FIG. Then, a difference for each pixel between the image information from the image input unit 4 and the stored image information of the background image is obtained, and a changed region in the image is extracted to confirm that the human body 10 exists. presume.

However, when there is a large difference in the luminance value between the background image and the captured image (captured image), a change is observed in all pixels, and the changed area cannot be specified from the captured image. There are times. As described above, when the presence of the human body 10 cannot be estimated from the image, the human body estimating unit 5
Estimates the presence of the human body 10 only from the temperature change information.
Specifically, when the temperature change is equal to or larger than the threshold value 2 that is larger than the threshold value 1, the heat source detection unit 2 determines that a reliable reaction has been performed, and estimates that the human body 10 is present.

Here, the heat source detecting section 2 may estimate which area in the detection area has changed in temperature, and may generate change area information for specifying the area. FIG. 6 is an explanatory diagram illustrating an example of a configuration of the heat source detection unit 2 according to the present embodiment illustrated in FIG. Heat source detector 2
Is a thermal element array 12 in which a plurality of thermal elements 11 such as passive infrared sensors for detecting a temperature change are arranged, a lens 13 for collecting infrared rays in the thermal element array 12, and temperature change information according to the output of the thermal element array 12. And a temperature change region determining unit 15 that estimates a region where a temperature change has occurred from the output of the thermosensitive element array 12 and generates change region information.

The lens 13 collects infrared rays from the detection area to the thermal element array 12, and each thermal element 11 of the thermal element array 12 detects a temperature change in a different area in the detection area. The temperature change output unit 14 is connected to the thermal element array 12.
Is output to the human body estimating unit 5 in accordance with the output of. The temperature change area determination unit 15 analyzes the output of each thermosensitive element 11 of the thermosensitive element array 12 to estimate the area where the temperature has changed, and outputs the change area information to the human body estimation unit 5.

In this case, when the temperature change information from the temperature change information output unit 14 indicates a temperature change equal to or greater than the threshold value 1, the human body estimation unit 5 inputs the change region information from the temperature change region determination unit 15, The region of the heat source is specified from the input change region information. Then, the image input unit 4 captures an image of only the specified area 20 (FIG. 5), generates and inputs image information of the captured image, performs image processing, or is captured by the image input unit 4. Region 20 specified for image
Only the image processing is performed, and the moving object in the image is
Is estimated. As described above, since only the image information of the area where the temperature has changed, that is, the image information necessary for the human body detection is generated, the information can be made more efficient.

FIG. 7 is an explanatory diagram showing another configuration of the heat source detecting section 2 according to the present embodiment shown in FIG. In addition,
The same parts as those in FIG. 6 are denoted by the same reference numerals, and description thereof is omitted. The heat source detecting unit 2 includes a thermosensitive element 11, a lens 13 for collecting infrared rays to the thermosensitive element 11, and a temperature change output unit 14 for outputting temperature change information according to the output of the thermosensitive element 11.
A driving unit 16 for mechanically driving the thermosensitive element 11, a sensor position detecting unit 17 for detecting the position of the thermosensitive element 11 moved by the driving unit 16, and a temperature change based on the detection result of the sensor position detecting unit 17. And a temperature change area determining unit 15 for estimating the changed area and generating change area information.

The drive section 16 mechanically drives the thermosensitive element 11 in one-dimensional or two-dimensional directions, whereby the thermosensitive element 11 scans the detection area and detects a temperature change. The sensor position detector 17 detects the position of the thermosensitive element 11. The temperature change area determination unit 15 estimates the area where the temperature has changed based on the detection result (position information) of the sensor position detection unit 17 and outputs the change area information to the human body estimation unit 5. Also in this case, when the temperature change information from the temperature change information output unit 14 indicates a temperature change equal to or greater than the threshold value 1, the human body estimation unit 5 inputs and inputs the change region information from the temperature change region determination unit 15. The region of the heat source is specified from the change region information. Then, the area 20 specified by the image input unit 4 is specified.
An image of only (FIG. 5) is captured, image information of the captured image is generated and input, and it is estimated whether or not the moving object in the image is the human body 10.

FIG. 8 is an explanatory diagram showing another configuration of the heat source detecting section 2 according to the present embodiment shown in FIG. In addition,
The same parts as those in FIG. 6 are denoted by the same reference numerals, and description thereof will be omitted. The heat source detection unit 2 includes an infrared camera 18 that captures an image in the detection area and outputs a thermal image signal, a temperature change output unit 14 that outputs temperature change information according to the thermal image signal from the infrared camera 18, A temperature change region determining unit 15 that estimates a region where a temperature change has occurred from a difference between frames of a thermal image signal from the infrared camera 18 and generates change region information.
And

The infrared camera 18 captures an image in the detection area. The temperature change area determination unit 15 estimates the area where the temperature has changed from the difference between the frames of the thermal image signal from the infrared camera 18 and generates change area information. Also in this case, when the temperature change information indicates a temperature change equal to or greater than the threshold value 1, the human body estimation unit 5 inputs the change region information from the temperature change region determination unit 15 and determines the region of the heat source from the input change region information. Identify. Then, the image input unit 4 captures an image of only the area 20 (FIG. 5), generates and inputs image information of the captured image, and estimates whether or not the moving object in the image is the human body 10. I do. Alternatively, image processing is performed only on the region 20 specified for the image captured by the image input unit 4, and it is estimated whether the moving object in the image is the human body 10.

Further, the human body estimating unit 5 performs imaging by the image input unit 4, and estimates the distance from the imaged object to the human body detecting device 1 according to the position of the object in the obtained image. You may. For example, the distance from the target to the human body detecting device 1 is estimated from the position of the center of gravity of the target in the captured image, and the actual size of the target is estimated from the size of the target in the image. , It is determined whether or not the human body 10.

Further, the image input section 4 may include a plurality of retinal prosthesis sensors 3 and output image information of images picked up from a plurality of positions. FIG. 9 is an explanatory diagram for describing imaging by the image input unit 4 according to the present embodiment. The image input unit 4 has two artificial retinal sensors 3, captures an image of a detection area using these two artificial retinal sensors 3, and outputs respective image information to the human body estimation unit 5. The human body estimation unit 5 performs photogrammetry from these two stereo images (two pieces of image information), and measures the distance from the captured object to the human body detection device 1. The size of the actual object is estimated from the distance from the imaged object to the human body detection device 1 and the size of the object in the imaged image, and whether the object is the human body 10 is estimated.

The human body estimating unit 5 periodically captures the background image by the image input unit 4, stores the captured image information, and stores the image information of the past background image and the image information of the new background image. May be compared to estimate that the direction of the human body detection device 1 has been changed. For example, the human body estimation unit 5 captures an image (FIG. 10), obtains new image information, and binarizes the image information using a predetermined threshold value 3. The same applies to the image information of the past image (FIG. 4).
Perform value conversion. Then, by correlating these image information,
When the correlation value is equal to or smaller than the predetermined threshold value 4, it is estimated that the detection area has been changed, that is, the direction of the human body detection device 1 has been changed. As a result, it is possible to estimate that the human body detection device 1 has been tampered with and issue an alarm.

Further, the human body estimating unit 5 compares the image information of the past background image with the image information of the new background image to estimate that the position of the component in the detection area has been moved. It may be. For example, the human body estimation unit 5
Captures an image (FIG. 11), obtains new image information,
The binarization of the image information is performed using the threshold value 3. The binarization is similarly performed on the image information of the past image (FIG. 4). Then, the image information is correlated, and if the correlation value is equal to or less than a predetermined threshold value 5, someone moves the position of an object such as the desk 9 in the background image (FIG. 4), or It is presumed that a new object has been placed. As a result, it is possible to presume that there has been some kind of fraudulent operation, and to issue an alarm.

Further, the image input unit 4 generates image information including color information using the artificial retinal sensor 3 capable of obtaining a color image, and the human body estimating unit 5 captures images based on the color information of the image information. The object may be separated. For example, the human body estimation unit 5 obtains an image (FIG. 12) by using the image input unit 2 when the output of the heat source detection unit 2 exceeds the threshold 1 due to the human body 10 having entered the detection area. From the image information, the objects 21, 22, 23, 24, and 25 imaged for each of the objects having similar color information are separated. The size of each of the objects 21 to 25 in the image is the human body 10.
When it is determined that the human body 10 is close to the human body 10, the human body 10 is estimated.

In the above configuration, the operation of the human body detecting device according to the present embodiment will be described with reference to the flowchart of FIG. FIG. 13 is a flowchart showing a flow of the operation of the human body estimation unit 5 according to the present embodiment. First, the human body estimation unit 5 determines whether or not it is an imaging time for periodic imaging (S1). If it is the imaging time, the process proceeds to step S4. If it is not the imaging time, the temperature change information from the heat source detection unit 2 is input (S2).

Next, it is determined whether or not the temperature change information is equal to or greater than a predetermined threshold value 1 (S3). If the temperature change information is less than the threshold 1, the process returns to step S1, and if the temperature change information is more than the threshold 1, the change area information from the heat source detector 2 is input (S4). Then, an area where the temperature has changed is specified from the input change area information, and the image input unit 4 is controlled to capture an image of only the specified area (S
5). Then, the image information of the captured image is input and stored, and various characteristic amounts are calculated (S6).

Next, it is determined whether or not the presence of the human body 10 can be estimated from the calculated characteristic amounts (S7). If it is not possible to estimate the presence of the human body 10 from the characteristic amounts, the human body 10 is determined only from the temperature change information. Is estimated (S8), and step S12 is performed.
Proceed to. On the other hand, when the presence of the human body 10 can be estimated from the feature amount, each object is separated based on the color information of the image information or the like (S9). Then, the distance between each object and the human body estimating device 1 is estimated by photogrammetry or the like (S10), and the object is determined based on the distance to the object and the size of the object in the image.
Is determined (S11).

The comparison between the image information of the captured image and the image information of the background image captured in the past indicates that the human body estimating apparatus 1 has been moved or that an object located in the area has been moved. Is estimated (S12). Thereafter, whether there is an abnormality, that is, whether it is estimated that the human body 10 exists, that the human body estimation device 1 has been moved, or that it has been estimated that an object located in the area has been moved Is determined (S13). If there is no abnormality, the process returns to step S1, and if there is an abnormality, an alarm is generated (S14), and the process ends.

As described above, according to the present embodiment,
Since temperature change information and image information are acquired and the presence of the human body 10 is estimated from these information, false reports and unreported reports can be reduced. In addition, since the area where the temperature has changed can be specified, only the area where the temperature has changed can be imaged to estimate the presence of the human body 10, and false reports and false reports can be reduced. In addition, since it can be estimated that the own device has been moved or that an object in the detection area has been moved, it is possible to estimate that there has been an unauthorized operation even if the heat source detection unit 2 does not react.

[0083]

As described above, according to the present invention, the detecting means detects a temperature change in a predetermined area,
The imaging unit captures an image in the area to generate image information, and the estimation unit estimates that a human body is present based on the detection result of the detection unit and the image information generated by the imaging unit. This makes it possible to estimate the presence of a human body based on two types of information, temperature change information and image information, and thus has the effect of reducing both erroneous detection and loss detection.

According to the next invention, the imaging means stops operating until the detection result of the detection means satisfies the predetermined condition, and when the detection result of the detection means satisfies the predetermined condition,
Since imaging is performed, power consumption can be reduced.

According to the next invention, even when the estimation means cannot estimate the presence of a human body from the image information generated by the imaging means, the estimation means estimates the presence of the human body only from the detection result of the detection means. Even when the determination becomes impossible, there is an effect that the presence of the human body can be detected.

According to the next invention, it is possible to estimate the place where the temperature has changed by the detecting means.
This has the effect of increasing the efficiency of image information.

According to the next invention, since the detecting means estimates which part of the area has undergone a temperature change based on the outputs of the thermal elements arranged in an array, the efficiency of image information can be improved. It has the effect of being able to.

According to the next invention, the detecting means scans the area by driving the thermosensitive element and estimates which part of the area has changed in temperature, so that the efficiency of image information can be improved. The effect is as follows.

According to the next invention, since the detecting means estimates which part of the area has changed in temperature by the infrared camera, it is possible to improve the efficiency of image information.

According to the next invention, the image pickup means picks up an image of only the portion estimated by the detecting means as having a temperature change, generates image information of only this portion, and the estimating means outputs the image information from this image information. Since the image processing is performed and the presence of the human body is estimated, it is possible to improve the efficiency of the image information.

According to the next invention, the estimating means estimates the distance from the imaged object to the own device, estimates the size of the object, and estimates whether the object is a human body. This makes it possible to estimate the presence of a human body from the image.

According to the next invention, the imaging means generates a plurality of pieces of image information from different positions, and the estimating means determines the distance from the imaged object to the own apparatus based on the plurality of pieces of image information. Since the estimation is performed, the size of the object is estimated, and whether or not the object is a human body, it is possible to estimate that a human body is present from a captured image.

[0093] According to the next invention, since the imaging means periodically performs imaging and periodically generates image information, the presence or absence of a human body can be determined even if the response of the detection means is not sufficient.
It is possible to estimate an illegal operation or the like.

According to the next invention, the estimating means stores the image information generated by the imaging means, compares the past image information with the new image information, and determines a change in the image information. Accordingly, it is possible to estimate that the own device has been moved, or that an object in the area has been moved, and the like, so that it is possible to estimate unauthorized manipulation.

According to the next invention, the estimating means estimates that the own device has been moved, for example, by comparing the image information of the background image when no person is present with the image information generated by the imaging means. Therefore, it is possible to estimate a fraudulent operation on the own device.

According to the next invention, the object located in the area is determined by comparing the image information of the background image when no person is present with the image information generated by the imaging means. Since it is estimated that the object has been moved or placed, it is possible to estimate that there has been any unauthorized manipulation.

According to the next invention, the imaging means generates color image information, and the estimating means separates a plurality of imaged objects based on the color information of the color image information generated by the imaging means. Since the presence of the human body is estimated, the presence of the human body can be estimated from the captured image.

According to the next invention, since the imaging means performs imaging with an inexpensive and compact artificial retinal sensor and generates image information, the cost can be reduced and the apparatus itself can be miniaturized. It works.

According to the next invention, in the imaging step, an image in the area is captured to generate image information, and in the estimation step, the image information generated in the imaging step and the temperature change indicating the temperature change in the area. It is estimated whether or not a human body exists based on the information. This makes it possible to estimate the presence of a human body based on two types of information, namely, temperature change information and image information, so that both erroneous detection and loss detection can be reduced.

According to the next invention, in the imaging step, imaging is stopped until the temperature change information satisfies a predetermined condition, and when the temperature change information satisfies a predetermined condition, imaging is performed. This has the effect that it can be reduced.

According to the next invention, even when the presence of a human body cannot be estimated from the image information generated in the imaging step in the estimation step, the presence of the human body is estimated only from the temperature change information. This makes it possible to detect the presence of a human body even when the operation becomes impossible.

According to the next invention, in the partial estimating step, in which part of the area the temperature has changed is estimated.
This has the effect of increasing the efficiency of image information.

According to the next invention, in the imaging step, image processing is performed on the image of only the portion estimated to have undergone a temperature change in the partial estimation step, and the necessary portion is estimated to have a temperature change. Since only image information is generated, information can be made more efficient.

According to the next invention, in the estimation step, the distance from the imaged object to the own apparatus is estimated based on the image information generated in the imaging step, and the size of the object is estimated.
Estimating whether or not it is a human body has the effect of being able to estimate the presence of a human body from a captured image.

According to the next invention, in the imaging step, image information is periodically generated to generate image information. Therefore, even if there is no predetermined change in the temperature change information, the presence or absence of a human body or unauthorized manipulation is checked. This has the effect that it can be estimated.

According to the next invention, in the estimation step, the image information generated in the imaging step is stored, and the past image information and the new image information are compared to determine a change in the image information.
Accordingly, it is possible to estimate that the own device has been moved, or that an object in the area has been moved, and the like, so that it is possible to estimate unauthorized manipulation.

According to the next invention, in the imaging movement estimating step, it is estimated that the imaging position or the imaging direction has been moved based on the image information generated in the imaging step. It has the effect of being able to.

According to the next invention, in the object movement estimation step,
Based on the image information generated in the imaging step, it is estimated that an object located in the area has been moved or placed, so that an illegal operation can be estimated.

According to the next invention, in the estimating step, based on the image information generated in the imaging step, a plurality of captured objects are separated to estimate the presence of a human body. The effect that it can be estimated that there exists.

According to the next invention, since a program for causing a computer to execute the method according to the present invention is recorded, it is possible to cause the computer to execute the method according to the present invention.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a schematic configuration of a human body detection device according to an embodiment of the present invention.

FIG. 2 is a perspective view illustrating a schematic configuration of a human body detection device according to the present embodiment.

FIG. 3 is an explanatory diagram showing an example of the arrangement of the human body detection device according to the embodiment;

FIG. 4 is an explanatory diagram illustrating a background image captured by an image input unit according to the embodiment;

FIG. 5 is an explanatory diagram illustrating an image captured by an image input unit according to the embodiment;

FIG. 6 is an explanatory diagram illustrating an example of a configuration of a heat source detection unit according to the present embodiment illustrated in FIG. 1;

FIG. 7 is an explanatory diagram illustrating another configuration of the heat source detection unit according to the embodiment illustrated in FIG. 1;

FIG. 8 is an explanatory diagram illustrating another configuration of the heat source detection unit according to the embodiment illustrated in FIG. 1;

FIG. 9 is an explanatory diagram for describing imaging by the image input unit according to the embodiment;

FIG. 10 is an explanatory diagram illustrating an image captured by the image input unit according to the embodiment;

FIG. 11 is an explanatory diagram illustrating an image captured by the image input unit according to the embodiment;

FIG. 12 is an explanatory diagram illustrating an image captured by the image input unit according to the present embodiment;

FIG. 13 is a flowchart showing the flow of the operation of the human body estimation unit according to the present embodiment.

[Explanation of symbols]

1 Human body detection device, 2 heat source detection unit, 3 artificial retina sensor, 4 image input unit, 5 human body estimation unit, 6 beds, 7
Wall, 8 doors, 9 desks, 10 human body, 11 thermal element,
12 thermosensitive element array, 13 lens, 14 temperature change output section, 15 temperature change area determination section, 16 drive section, 1
7 Sensor position detector, 18 infrared camera, 19 ceiling, 20 areas, 21 to 25 objects.

──────────────────────────────────────────────────の Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) H04N 7/18 G01V 9/04 S (72) Inventor Yasushi Miyake 2-3-2 Marunouchi, Chiyoda-ku, Tokyo No. Mitsubishi Electric Co., Ltd. (72) Inventor Toshiyuki Tamura 2-3-2 Marunouchi, Chiyoda-ku, Tokyo Mitsui Electric Co., Ltd. (72) Kenichi Tanaka 2-3-2 Marunouchi, Chiyoda-ku, Tokyo 3 Rishi Electric Co., Ltd. (72) Inventor Kazuo Kuma 2-3-2 Marunouchi, Chiyoda-ku, Tokyo Mitsui Electric Co., Ltd. (72) Inventor Kazuo Kimizuka 1-6-6 Moto-Akasaka, Minato-ku, Tokyo Sogo Inside Security Service Co., Ltd. (72) Katsuyuki Miyoshi, Inventor 1-6-6 Moto Akasaka, Minato-ku, Tokyo Inside Sogo Security Service Co., Ltd. (72) Inventor Eiji Shimada Motoreda, Minato-ku, Tokyo 1-6-6 F General Term Security Security Co., Ltd. F term (reference) 5C054 CA05 CA10 CC00 CC02 CD03 CG01 CG06 CG07 CH03 EA01 FC00 FC12 FC15 HA18 5C084 AA02 AA07 AA08 AA13 BB04 BB31 CC19 DD12 DD13 DD43 DD44 GG84 GG04 GG56 GG04 GG78

Claims (28)

[Claims] 1. A human body detecting device for detecting the presence of a human body in a predetermined area, a detecting unit for detecting a temperature change in the area, and generating image information by capturing an image in the area. A human body detection device comprising: an imaging unit; and an estimation unit configured to estimate the presence of a human body based on a detection result of the detection unit and image information generated by the imaging unit. 2. The human body detection device according to claim 1, wherein the imaging unit performs imaging when a detection result of the detection unit satisfies a predetermined condition. 3. The method according to claim 1, wherein the estimating unit estimates the presence of a human body from the detection result of the detecting unit when the presence of the human body cannot be estimated from the image information generated by the imaging unit. 3. The human body detection device according to 1. 4. The human body detection device according to claim 1, wherein the detection unit estimates which part of the area has changed in temperature. 5. The apparatus according to claim 1, wherein said detecting means has a plurality of heat-sensitive elements arranged in an array, and estimates which part of said area has a temperature change based on the outputs of these heat-sensitive elements. Item 4. The human body detection device according to item 1, 2, or 3. 6. The sensor according to claim 1, wherein the detecting unit includes a thermosensitive element, scans the area by driving the thermosensitive element, and estimates which part of the area has changed in temperature. 4. The human body detection device according to 1, 2, or 3. 7. The detecting means has an infrared camera,
4. The human body detecting device according to claim 1, wherein a portion of the area where the temperature has changed is estimated. 5. 8. The human body detection device according to claim 4, wherein the imaging unit processes an image of only a portion estimated by the detection unit as having a temperature change. . 9. The apparatus according to claim 1, wherein the estimating unit estimates a distance from the imaged object to the own apparatus, and estimates a size of the object. Human body detection device. 10. The image pickup means generates a plurality of pieces of image information from different positions, and the estimating means generates a plurality of pieces of image information from an imaged object to its own device based on the plurality of pieces of image information generated by the image pickup means. The human body detection device according to any one of claims 1 to 8, wherein a distance is estimated and a size of the object is estimated. 11. The human body detection device according to claim 1, wherein the imaging unit performs imaging periodically. 12. The method according to claim 1, wherein the estimating means stores image information generated by the imaging means, compares past image information with new image information, and determines a change in the image information. The human body detection device according to any one of claims 1 to 11, wherein 13. The human body detecting device according to claim 1, wherein the estimating unit estimates that the own device has been moved. 14. The apparatus according to claim 1, wherein the estimating unit estimates that an object located in the area has been moved or placed. Human body detection device. 15. The image capturing means generates color image information, and the estimating means separates a plurality of captured objects based on color information of the color image information generated by the image capturing means. The human body detection device according to any one of claims 1 to 14, wherein 16. The human body detection device according to claim 1, wherein the imaging unit has an artificial retinal sensor. 17. A human body detection method for detecting the presence of a human body in a predetermined area, comprising: an imaging step of capturing an image in the area to generate image information; and an image information generated in the imaging step. And an estimation step of estimating whether or not a human body is present based on temperature change information indicating a temperature change in the area. 18. The human body detection method according to claim 17, wherein in the imaging step, imaging is performed when the temperature change information satisfies a predetermined condition. 19. In the estimating step, when the presence of a human body cannot be estimated from the image information generated in the imaging step,
19. The human body detecting method according to claim 17, wherein the presence of a human body is estimated from the temperature change information. 20. The human body detecting method according to claim 17, further comprising a partial estimating step of estimating in which part of the area the temperature has changed. 21. The human body detecting method according to claim 20, wherein, in the imaging step, an image of only a portion estimated to have undergone a temperature change in the partial estimation step is image-processed. 22. The estimating step, wherein a distance from an imaged object to the own apparatus is estimated based on the image information generated in the imaging step, and a size of the object is estimated. The human body detection method according to any one of claims 17 to 21. 23. The human body detecting method according to claim 17, wherein in the imaging step, imaging is performed periodically. 24. The estimating step, wherein the image information generated in the image capturing step is stored, and past image information is compared with new image information to determine a change in the image information. Item 24. The human body detection method according to any one of Items 17 to 23. 25. The imaging method according to claim 17, further comprising an imaging movement estimation step of estimating that an imaging position or an imaging direction has been moved based on the image information generated in the imaging step. The human body detection method according to any one of the above. 26. An object movement estimating step of estimating that an object located in the area has been moved or placed based on the image information generated in the imaging step. The human body detection method according to any one of claims 17 to 25. 27. The method according to claim 17, wherein in the estimating step, a plurality of imaged objects are separated based on image information generated in the image capturing step. Human body detection method. 28. A computer-readable recording medium on which a program for causing a computer to execute the method according to claim 17 is recorded.