Determination device and determination method

Abstract

A determination device (20) comprises an image acquisition unit (26) that acquires an image that is based on sub-terahertz waves radiated at a prescribed area (22), a subject information acquisition unit (28) that acquires subject information that includes position information that indicates the position of a subject (1) that is in the prescribed area (22) and orientation information that indicates the orientation of the subject, an intensity distribution information acquisition unit (32) that acquires intensity distribution information that indicates an intensity distribution within the prescribed area (22) for the sub-terahertz waves radiated at the prescribed area (22), a determination unit (34) that determines whether the subject (1) includes a prescribed object on the basis of the image, the subject information, and the intensity distribution information, and an output unit (36) that outputs the determination results determined by the determination unit (364).

Description

Determination device and determination method

[0001] The present disclosure relates to a determination device and a determination method for determining whether a subject includes a predetermined object.

[0002] Conventionally, there have been known determination devices and the like that capture an image including a subject and determine whether or not a predetermined object is included in the subject using the captured image. As an example of the determination device and the like, Patent Literature 1 discloses a first imaging system that captures a first image based on terahertz waves from an inspection object, a second imaging system that captures a second image of the inspection object based on electromagnetic waves having a wavelength different from the terahertz waves, and a processing system that detects an inspection area based on the second image and processes information on an area corresponding to the inspection area in the first image.

[0003] Japanese Patent Application Laid-Open No. 2020-153975

[0004] Here, there is a demand for more accurate determination of whether or not a predetermined object is included in the subject.

[0005] Therefore, an object of the present disclosure is to provide a determination device or the like that can more accurately determine whether or not a subject includes a predetermined object.

[0006] A determination device according to one aspect of the present disclosure includes an image acquisition unit that acquires an image based on sub-terahertz waves irradiated onto a predetermined area; a subject information acquisition unit that acquires subject information including position information indicating the position of a subject located in the predetermined area and orientation information indicating the orientation of the subject; an intensity distribution information acquisition unit that acquires intensity distribution information indicating the intensity distribution in the predetermined area of ​​the sub-terahertz waves irradiated onto the predetermined area; a determination unit that determines whether the subject includes a predetermined object based on the image, the subject information, and the intensity distribution information; and an output unit that outputs the determination result determined by the determination unit.

[0007] A determination method according to one aspect of the present disclosure includes an image acquisition step of acquiring an image based on sub-terahertz waves irradiated onto a predetermined area; a subject information acquisition step of acquiring subject information including position information indicating the position of a subject located in the predetermined area and orientation information indicating the orientation of the subject; an intensity distribution information acquisition step of acquiring intensity distribution information indicating the intensity distribution in the predetermined area of ​​the sub-terahertz waves irradiated onto the predetermined area; a determination step of determining whether or not the subject includes a predetermined object based on the image, the subject information, and the intensity distribution information; and an output step of outputting the determination result determined by the determination step.

[0008] According to the determination device and the like according to one aspect of the present disclosure, it is possible to more accurately determine whether a subject includes a predetermined object.

[0009] Fig. 1 is a schematic diagram showing a determination system etc. according to an embodiment. Fig. 2 is a schematic diagram showing an example of a sub-terahertz wave image captured by an imaging unit of the determination system of Fig. 1. Fig. 3 is a schematic diagram showing an example of a subject detection unit of the determination system of Fig. 1. Fig. 4 is a schematic diagram showing an example of intensity distribution information stored in a storage unit of the determination system of Fig. 1. Fig. 5 is a schematic diagram for explaining the intensity of sub-terahertz waves reflected by a reflector. Fig. 6 is a flowchart showing an example of the operation of a determination device of the determination system of Fig. 1.

[0010] (Summary of the Present Disclosure) An overview of one aspect of the present disclosure is as follows.

[0011] A determination device according to one aspect of the present disclosure includes an image acquisition unit that acquires an image based on sub-terahertz waves irradiated onto a predetermined area; a subject information acquisition unit that acquires subject information including position information indicating the position of a subject located in the predetermined area; an intensity distribution information acquisition unit that acquires intensity distribution information indicating the intensity distribution in the predetermined area of ​​the sub-terahertz waves irradiated onto the predetermined area; a determination unit that determines whether the subject includes a predetermined object based on the image, the subject information, and the intensity distribution information; and an output unit that outputs the determination result determined by the determination unit.

[0012] In this specification, the term "sub-terahertz waves" refers to electromagnetic waves having a frequency of 0.05 THz or more and 2 THz or less. The sub-terahertz waves in this specification may also refer to electromagnetic waves having a frequency of 0.08 THz or more and 1 THz or less.

[0013] According to this, the subject information indicates the position of the subject, and the intensity distribution information indicates the intensity of the sub-terahertz waves irradiated onto the subject. Therefore, even if there is unevenness in the intensity distribution of the sub-terahertz waves irradiated onto a predetermined area, it is possible to appropriately determine whether or not the subject includes a predetermined object based on the intensity of the sub-terahertz waves irradiated onto the subject, thereby making it possible to more accurately determine whether or not the subject includes a predetermined object.

[0014] Furthermore, for example, the determination unit may correct the image based on the subject information and the intensity distribution information, and determine whether the subject includes the specified object based on the corrected image.

[0015] According to this, although the intensity distribution of the sub-terahertz waves irradiated onto a specified area varies depending on the position of the subject, the image can be corrected based on the intensity distribution of the sub-terahertz waves according to the position of the subject, and it can be determined based on the corrected image whether or not the subject includes a specified object, thereby enabling even more accurate determination of whether or not the subject includes a specified object.

[0016] Furthermore, for example, the subject information may further include orientation information indicating the orientation of the subject.

[0017] According to this, the intensity distribution of the sub-terahertz waves irradiated onto a specified area changes depending on the orientation of the subject, but since the orientation of the subject can be determined from the subject information, it is possible to more accurately determine whether or not the subject includes a specified object.

[0018] Furthermore, for example, the judgment unit may determine a learning model for determining whether or not the subject includes the specified object based on the subject information and the intensity distribution information, and use the determined learning model to determine whether or not the subject includes the specified object.

[0019] This allows a determination as to whether or not a specified object is included in the subject to be made using a learning model that corresponds to the intensity of the sub-terahertz waves irradiated onto the subject, thereby enabling an even more accurate determination as to whether or not a specified object is included in the subject.

[0020] Furthermore, for example, the determination unit may determine a threshold value for determining whether or not the subject includes the specified object based on the subject information and the intensity distribution information, and determine whether or not the subject includes the specified object using the determined threshold value.

[0021] This allows a determination as to whether or not a specified object is included in the subject to be made using a threshold value corresponding to the intensity of the sub-terahertz waves irradiated onto the subject, thereby enabling an even more accurate determination as to whether or not a specified object is included in the subject.

[0022] Furthermore, for example, the predetermined area may be an area sandwiched between a pair of reflecting plates each of which diffusely reflects the sub-terahertz waves.

[0023] In this specification, "diffuse reflection" means that sub-terahertz waves incident on a reflector at a single angle of incidence from a macroscopic perspective are reflected at multiple reflection angles by the uneven surface structure having multiple microscopic irregularities.

[0024] This allows the sub-terahertz waves to be diffusely reflected, and by diffusely reflecting the sub-terahertz waves, the sub-terahertz waves can be more uniformly irradiated onto a specified area, making it possible to more accurately determine whether or not a specified object is included in the subject.

[0025] Furthermore, for example, the apparatus may further include a storage unit that stores the intensity distribution information, and the intensity distribution information acquisition unit may acquire the intensity distribution information from the storage unit.

[0026] This allows the intensity distribution information to be easily obtained.

[0027] Furthermore, for example, the intensity distribution may indicate the intensity of the sub-terahertz waves at each position in the predetermined region.

[0028] This allows the intensity of the sub-terahertz waves at each position in a specified area to be determined, and the intensity of the sub-terahertz waves being irradiated onto the subject to be determined more accurately, making it possible to more accurately determine whether or not the subject includes a specified object.

[0029] The method also includes, for example, an image acquisition step of acquiring an image based on sub-terahertz waves irradiated onto a predetermined area, a subject information acquisition step of acquiring subject information including position information indicating the position of a subject located in the predetermined area, an intensity distribution information acquisition step of acquiring intensity distribution information indicating the intensity distribution in the predetermined area of ​​the sub-terahertz waves irradiated onto the predetermined area, a determination step of determining whether or not the subject includes a predetermined object based on the image, the subject information, and the intensity distribution information, and an output step of outputting the determination result determined by the determination step.

[0030] This provides the same effects as the above-described determination device.

[0031] Furthermore, for example, the determination device may include an image acquisition unit that acquires an image based on sub-terahertz waves irradiated onto a predetermined area; a subject information acquisition unit that acquires subject information including position information indicating the position of a subject located in the predetermined area and orientation information indicating the orientation of the subject; an intensity distribution information acquisition unit that acquires intensity distribution information indicating the intensity distribution in the predetermined area of ​​the sub-terahertz waves irradiated onto the predetermined area; a determination unit that determines whether or not the subject includes a predetermined object based on the image, the subject information, and the intensity distribution information; and an output unit that outputs the determination result determined by the determination unit.

[0032] Furthermore, for example, the intensity distribution information may indicate multiple intensities of the sub-terahertz waves when the sub-terahertz waves irradiated onto the specified region are reflected by the same object facing a specified direction at each of multiple positions within the specified region.

[0033] Furthermore, for example, the determination unit may correct the intensity of the sub-terahertz waves for each of multiple points of the subject in the image based on the subject information and the intensity distribution information, and determine whether the subject includes the specified object based on the corrected image.

[0034] Furthermore, for example, the judgment unit may acquire the intensity of the sub-terahertz waves irradiated at each of multiple points on the subject based on the subject information and the intensity distribution information, determine a learning model for determining whether the subject includes the specified object, and use the determined learning model to determine whether the subject includes the specified object.

[0035] Furthermore, for example, the determination unit may have a plurality of learning models corresponding to the intensity of the sub-terahertz waves, and may determine the learning model according to the intensity of the acquired sub-terahertz waves.

[0036] Furthermore, for example, the judgment unit may acquire the intensity of the sub-terahertz waves irradiated at each of a plurality of points on the subject based on the subject information and the intensity distribution information, determine a threshold value for each of the plurality of points on the subject to determine whether or not the subject includes the specified object, and use the determined threshold value to determine whether or not the subject includes the specified object.

[0037] Furthermore, for example, if the threshold value when the sub-terahertz waves are irradiated onto the subject at a predetermined intensity is a first threshold value, the judgment unit may calculate a second threshold value as the threshold value based on the intensity of the acquired sub-terahertz waves, the predetermined intensity, and the first threshold value.

[0038] Furthermore, for example, the predetermined area may be an area sandwiched between a pair of reflecting plates, each of which diffusely reflects the sub-terahertz waves.

[0039] Also, for example, the apparatus may further include a storage unit that stores the intensity distribution information, and the intensity distribution information acquisition unit may acquire the intensity distribution information from the storage unit.

[0040] Furthermore, for example, the determination method may include an image acquisition step of acquiring an image based on sub-terahertz waves irradiated onto a specific region; a subject information acquisition step of acquiring subject information including position information indicating the position of a subject located in the specific region and orientation information indicating the orientation of the subject; an intensity distribution information acquisition step of acquiring intensity distribution information indicating the intensity distribution in the specific region of the sub-terahertz waves irradiated onto the specific region; a determination step of determining whether or not the subject includes a specific object based on the image, the subject information, and the intensity distribution information; and an output step of outputting the determination result determined by the determination step.

[0041] Hereinafter, the embodiments will be specifically described with reference to the drawings.

[0042] The embodiments described below are all comprehensive or specific examples, and the numerical values, shapes, materials, components, arrangement and connection of the components, steps, and order of steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure.

[0043] Furthermore, in this specification, terms indicating the relationship between elements, such as "parallel," terms indicating the shape of an element, such as "flat plate," terms indicating time, such as "immediately after," and numerical ranges are not expressions that only express a strict meaning, but are expressions that also include a substantially equivalent range, for example, a difference of about a few percent.

[0044] In addition, the drawings are not necessarily strict illustrations, and the same reference numerals are used to designate substantially the same components in the drawings, and redundant explanations are omitted or simplified.

[0045] (Embodiment) FIG. 1 is a schematic diagram showing a determination system 10 according to an embodiment.

[0046] The determination system 10 is a system that determines whether or not a subject 1 contains a predetermined object. For example, the subject 1 includes a person and an object held by the person. For example, the predetermined object includes a metal object, a flammable object, or the like. That is, the determination system 10 determines, for example, whether or not a person is holding a metal object, or whether or not a person is holding a flammable object. As shown in FIG. 1 , the determination system 10 includes an irradiation unit 12, a pair of reflectors 14, an imaging unit 16, a subject detection unit 18, and a determination device 20.

[0047] The irradiation unit 12 irradiates a predetermined region 22 with sub-terahertz waves. The predetermined region 22 is a three-dimensional region. In the present embodiment, the irradiation unit 12 has a plurality of light sources 24. Each of the plurality of light sources 24 irradiates the predetermined region 22 with sub-terahertz waves. Note that, for example, the irradiation unit 12 may have a single light source 24 instead of a plurality of light sources 24.

[0048] In the present embodiment, the predetermined region 22 is a region sandwiched between a pair of reflectors 14. Each of the pair of reflectors 14 diffusely reflects sub-terahertz waves. Specifically, each of the pair of reflectors 14 diffusely reflects sub-terahertz waves incident at least from the side of the predetermined region 22 (i.e., the inner side of the pair of reflectors 14). In the present embodiment, the sub-terahertz waves emitted from the irradiation unit 12 are diffusely reflected one or more times by at least one of the pair of reflectors 14 and are irradiated onto the subject 1 located within the predetermined region 22. In this way, by sandwiching the predetermined region 22 between the pair of reflectors 14 that diffusely reflect sub-terahertz waves, the sub-terahertz waves irradiated onto the predetermined region 22 are more likely to remain, and the sub-terahertz waves can be irradiated onto the subject 1 from various angles. Note that, for example, each of the pair of reflectors 14 may be flat or curved. Also, for example, the predetermined area 22 does not have to be sandwiched between a pair of reflectors 14, and the sub-terahertz waves emitted from the irradiation unit 12 consisting of multiple light sources 24 may be directly irradiated onto the subject 1.

[0049] The imaging unit 16 captures an image based on the sub-terahertz waves irradiated onto the predetermined region 22. Note that, hereinafter, an image based on the sub-terahertz waves irradiated onto the predetermined region 22 may be referred to as a sub-terahertz wave image. For example, the imaging unit 16 is a camera configured with an image sensor (not shown), an optical system (not shown), etc. For example, the image sensor is configured with a plurality of pixels, each including a detection element for detecting sub-terahertz waves, and peripheral circuits, etc.

[0050] The imaging unit 16 receives sub-terahertz waves irradiated from the irradiation unit 12 onto a predetermined region 22 and reflected by the subject 1. The imaging unit 16 performs exposure at the timing when the irradiation unit 12 emits the sub-terahertz waves, and detects the intensity of the received sub-terahertz waves. The imaging unit 16 converts an image of the sub-terahertz waves emitted from the subject 1 during exposure into an electrical signal corresponding to the intensity, and generates an image based on the converted electrical signal. The image generated by the imaging unit 16 is output to the image acquisition unit 26.

[0051] Sub-terahertz waves pass through clothing, bags, etc., and are specularly reflected by the human body, metal, etc. Therefore, image capture unit 16 receives sub-terahertz waves specularly reflected by the human body, metal, etc., from areas of the human body, metal, etc. included in subject 1 that are included within the angle range in which image capture unit 16 can receive waves. For example, if a person included in subject 1 is concealing an object such as a knife or a container containing flammable material under clothing, in a bag, etc., image capture unit 16 receives sub-terahertz waves specularly reflected by the concealed object from areas of the concealed object that are included within the angle range in which image capture unit 16 can receive waves.

[0052] FIG. 2 is a schematic diagram showing an example of a sub-terahertz wave image captured by the imaging unit 16 of the determination system 10 of FIG.

[0053] 2 , for example, when subject 1 includes a person 2 and a predetermined object 3, the intensity of the sub-terahertz waves reflected by person 2 differs from the intensity of the sub-terahertz waves reflected by predetermined object 3. Therefore, the person 2 and the predetermined object 3 appearing in the sub-terahertz wave image can be distinguished from each other based on the intensity of the sub-terahertz waves in the sub-terahertz wave image, and it can be determined whether subject 1 includes the predetermined object 3 or not.

[0054] Returning to FIG. 1 , the subject detection unit 18 detects the subject 1 located in the predetermined region 22. For example, the subject detection unit 18 detects the position and orientation of the subject 1 located in the predetermined region 22. For example, the position of the subject 1 is the position of a reflective surface that reflects sub-terahertz waves in a portion of the subject 1. Furthermore, for example, the orientation of the subject 1 is the orientation of the reflective surface that reflects sub-terahertz waves in a portion of the subject 1. Specifically, for example, the position of the subject 1 is the position of a point on the reflective surface that reflects sub-terahertz waves in the subject 1, and the orientation of the subject 1 is the orientation of a normal that passes through the point and is perpendicular to the tangent at the point. For example, the position and orientation of the subject 1 may be the collection of the positions of points on the reflective surface of a portion of the subject 1 and the orientations of normals that pass through the point and are perpendicular to the tangent at the point, over the entire subject 1. In other words, for example, the position of the subject 1 may be the positions of multiple points on the reflective surface of the subject 1, and the orientation of the subject 1 may be the orientation of a normal that passes through each of the multiple points and is perpendicular to the tangent at the point.

[0055] For example, the subject detection unit 18 is a distance sensor that detects the position of the subject 1 by measuring the distance to the subject 1. For example, the distance sensor is a ToF (Time of Flight) camera, a monocular camera, a compound eye camera, or the like. Furthermore, for example, the subject detection unit 18 is a visible light camera or an infrared camera that uses machine learning to detect the position and orientation of the subject 1 from an image captured by the visible light camera or the infrared camera. Furthermore, for example, the subject detection unit 18 is a millimeter wave sensor. Furthermore, for example, the subject detection unit 18 is a weight sensor that estimates the position and orientation of the subject 1 based on the position where weight is applied. Furthermore, for example, the subject detection unit 18 is a ceiling camera or a floor camera that estimates the position and orientation of the subject 1 from an image captured by the ceiling camera or the floor camera.

[0056] FIG. 3 is a schematic diagram showing an example of the subject detection unit 18 of the determination system 10 of FIG.

[0057] 3 , for example, the subject detection unit 18 is a visible camera, and detects the position and orientation of the subject 1 from an image captured by the visible camera. For example, for each of one or more points on the reflecting surface of the subject 1, the subject detection unit 18 detects an X coordinate value (see X in FIG. 3 ) indicating the position in the X-axis direction, a Y coordinate value (see Y in FIG. 3 ) indicating the position of the subject 1 in the Y-axis direction, and a Z coordinate value (see Z in FIG. 3 ) indicating the position of the subject 1 in the Z-axis direction. Furthermore, for each of the one or more points, the subject detection unit 18 detects an X vector (see Xn in FIG. 3 ) indicating the X-axis component of a normal vector that passes through the point and is perpendicular to a tangent at the point, a Y vector (see Yn in FIG. 3 ) indicating the Y-axis component, and a Z vector (see Zn in FIG. 3 ) indicating the Z-axis component.

[0058] Returning to FIG. 1, the determination device 20 includes an image acquisition unit 26, a subject information acquisition unit 28, a storage unit 30, an intensity distribution information acquisition unit 32, a determination unit 34, and an output unit 36.

[0059] The image acquisition unit 26 acquires an image based on the sub-terahertz waves irradiated onto the predetermined region 22. In this embodiment, the image acquisition unit 26 acquires a sub-terahertz wave image captured by the imaging unit 16.

[0060] The subject information acquisition unit 28 acquires subject information. For example, the subject information includes position information indicating the position of the subject 1 located in the predetermined area 22 and orientation information indicating the orientation of the subject 1 located in the predetermined area 22. In the present embodiment, the subject information includes position information indicating the position of the subject 1 detected by the subject detection unit 18 and orientation information indicating the orientation of the subject 1 detected by the subject detection unit 18. That is, in the present embodiment, the position information includes the X coordinate value, the Y coordinate value, and the Z coordinate value of each of one or more points on the reflecting surface of the subject 1, and the orientation information includes an X vector indicating the X-axis component of a normal vector that passes through the point and is perpendicular to a tangent at the point, a Y vector indicating the Y-axis component, and a Z vector indicating the Z-axis component.

[0061] The memory unit 30 stores intensity distribution information. The intensity distribution information indicates the intensity distribution in the predetermined region 22 of the sub-terahertz waves irradiated onto the predetermined region 22. The intensity distribution indicates the intensity of the sub-terahertz waves at each position in the predetermined region 22. The intensity distribution of the sub-terahertz waves irradiated onto the predetermined region 22 is measured in advance by simulation, experiment, or the like. For example, by irradiating the predetermined region 22 with sub-terahertz waves while a reflector 38 (see FIG. 5 ) that reflects the sub-terahertz waves is disposed at a certain position and in a certain orientation in the predetermined region 22, it is possible to measure the intensity distribution in the predetermined region 22 of the sub-terahertz waves irradiated onto the predetermined region 22 with the sub-terahertz waves while the reflector 38 is positioned at the certain position and in the certain orientation. For example, the reflector 38 is a flat plate, a person, or the like.

[0062] FIG. 4 is a schematic diagram showing an example of intensity distribution information stored in the storage unit 30 of the determination system 10 of FIG.

[0063] As shown in Figure 4, by irradiating the predetermined area 22 with sub-terahertz waves while a reflector 38 that reflects the sub-terahertz waves is positioned at a certain position in the predetermined area 22 and in a certain direction (for example, the direction in which the subject 1 moves through the predetermined area 22), it is possible to measure the intensity distribution of the sub-terahertz waves in the predetermined area 22 when the sub-terahertz waves are irradiated onto the predetermined area 22 with the reflector 38 positioned at the certain position and in the certain direction.

[0064] FIG. 5 is a schematic diagram for explaining the intensity of the sub-terahertz wave reflected by the reflector 38. As shown in FIG.

[0065] 5 , even if the position at which the sub-terahertz waves are reflected by reflector 38 is the same, the intensity of the sub-terahertz waves reflected by reflector 38 varies (see the arrows in FIG. 5 ) depending on the orientation of reflector 38 (see the dashed lines and dash-dotted lines in FIG. 5 ). Therefore, for example, by positioning reflector 38 at as many positions as possible in predetermined region 22 and measuring in advance the intensity distribution of the sub-terahertz waves when the predetermined region 22 is irradiated with the sub-terahertz waves in each of the positions, and by positioning reflector 38 in as many orientations as possible and measuring in advance the intensity distribution of the sub-terahertz waves when the predetermined region 22 is irradiated with the sub-terahertz waves in each of the orientations, it is possible to obtain a wider range of intensity distributions.

[0066] 1 , the intensity distribution information acquisition unit 32 acquires intensity distribution information that indicates the intensity distribution in the predetermined region 22 of the sub-terahertz waves irradiated onto the predetermined region 22. In this embodiment, the intensity distribution information acquisition unit 32 acquires the intensity distribution information stored in the storage unit 30. In this embodiment, the intensity distribution information acquisition unit 32 acquires the intensity distribution information from the storage unit 30.

[0067] The determination unit 34 determines whether or not the subject 1 includes a predetermined object based on the sub-terahertz wave image, the subject information, and the intensity distribution information.

[0068] Conventionally, for example, if the intensity of the sub-terahertz waves at the subject 1 captured in the sub-terahertz wave image is greater than an upper threshold and less than a lower threshold, it is determined that the subject 1 contains a specified object, and if the intensity of the sub-terahertz waves at the subject 1 captured in the sub-terahertz wave image is less than the upper threshold and greater than the lower threshold, it is determined that the subject 1 does not contain a specified object.

[0069] However, it is difficult to uniformly irradiate the predetermined region 22 with the sub-terahertz waves, and the predetermined region 22 may have areas where the intensity of the sub-terahertz waves is relatively high and areas where the intensity of the sub-terahertz waves is relatively low.

[0070] For example, if subject 1 is located in a location where the intensity of the sub-terahertz waves in the specified region 22 is relatively high, the intensity of the sub-terahertz waves in subject 1 captured in the sub-terahertz wave image will be high, and even though subject 1 does not contain a specified object, the intensity of the sub-terahertz waves in subject 1 captured in the sub-terahertz wave image may be higher than the upper limit threshold, and it may be determined that subject 1 contains a specified object even though it does not.

[0071] Furthermore, for example, if subject 1 is located in a location where the intensity of the sub-terahertz waves in specified region 22 is relatively low, the intensity of the sub-terahertz waves in subject 1 captured in the sub-terahertz wave image will be low, and even though subject 1 contains a specified object, the intensity of the sub-terahertz waves in subject 1 captured in the sub-terahertz wave image may be lower than the upper limit threshold, and it may be determined that subject 1 does not contain the specified object even though it actually does contain the specified object.

[0072] Therefore, the determination unit 34 determines whether or not the subject 1 includes a predetermined object by using not only the sub-terahertz wave image but also the subject information and the intensity distribution information.

[0073] For example, the determination unit 34 corrects the sub-terahertz wave image based on the subject information and intensity distribution information indicating the intensity distribution in the specified area 22 of the sub-terahertz waves irradiated to the specified area 22 when the subject 1 is not in the specified area 22, and determines whether the subject 1 includes a specified object based on the corrected sub-terahertz wave image.

[0074] For example, the determination unit 34 first acquires the position and orientation of the subject 1 from the subject information, and then acquires the intensity distribution of the sub-terahertz waves when the predetermined region 22 is irradiated with sub-terahertz waves while the reflector 38 is positioned at the position and in the orientation. As described above, the intensity distribution is measured in advance by simulation, experiment, or the like, and stored in the storage unit 30. Note that, for example, the determination unit 34 may acquire only the position of the subject 1 from the subject information, and then acquire the intensity distribution of the sub-terahertz waves when the predetermined region 22 is irradiated with sub-terahertz waves while the reflector 38 is positioned at the position. Alternatively, for example, the determination unit 34 may acquire the intensity distribution in the predetermined region 22 of the sub-terahertz waves irradiated onto the predetermined region 22 when the subject 1 is not present in the predetermined region 22.

[0075] For example, the determination unit 34 next does not correct the intensity of a first pixel that represents a portion of a predetermined first intensity in the acquired intensity distribution among the multiple pixels that make up the sub-terahertz wave image, but corrects the intensity of a second pixel that represents a portion of the intensity distribution that has a second intensity different from the first intensity by multiplying the pixel by (first intensity) / (second intensity). Specifically, the determination unit 34 reduces the intensity associated with the second pixel when the second intensity is greater than the first intensity, and increases the intensity associated with the second pixel when the second intensity is less than the first intensity. This allows the determination unit 34 to obtain a sub-terahertz wave image that resembles a case in which the predetermined region 22 is uniformly irradiated with sub-terahertz waves.

[0076] For example, if the subject 1 captured in the corrected sub-terahertz wave image has a portion where the intensity of the sub-terahertz waves is greater than an upper threshold, the determination unit 34 determines that the subject 1 includes a predetermined object. Furthermore, for example, if the subject 1 captured in the corrected sub-terahertz wave image has a portion where the intensity of the sub-terahertz waves is less than a lower threshold, the determination unit 34 determines that the subject 1 includes a predetermined object. Furthermore, for example, if the subject 1 captured in the corrected sub-terahertz wave image does not have a portion where the intensity of the sub-terahertz waves is greater than the upper threshold and less than the lower threshold, the determination unit 34 determines that the subject 1 does not include a predetermined object.

[0077] Furthermore, for example, the judgment unit 34 determines a learning model for determining whether or not the subject 1 contains a specified object based on the subject information and the intensity distribution information, and determines whether or not the subject 1 contains a specified object using the determined learning model.

[0078] For example, first, the determination unit 34 acquires the position and orientation of the subject 1 from the subject information, and acquires the intensity distribution of the sub-terahertz waves when the predetermined area 22 is irradiated with sub-terahertz waves while the reflector 38 is positioned at the position and in the orientation. As described above, the intensity distribution is measured in advance by simulation, experiment, or the like, and stored in the storage unit 30. Note that, for example, the determination unit 34 may acquire only the position of the subject 1 out of the position and orientation from the subject information, and acquire the intensity distribution of the sub-terahertz waves when the predetermined area 22 is irradiated with sub-terahertz waves while the reflector 38 is positioned at the position.

[0079] For example, next, the determination unit 34 obtains the intensity of the sub-terahertz waves irradiating the subject 1 from the obtained intensity distribution, and determines a learning model based on the obtained intensity. For example, multiple learning models are generated according to the intensities of the sub-terahertz waves, and the determination unit 34 determines a learning model according to the obtained intensity. For example, each of the multiple learning models is a model that has been trained to output a result indicating whether or not a predetermined object is included in the subject 1 when a sub-terahertz wave image is input.

[0080] For example, when the determination unit 34 inputs a sub-terahertz wave image into a learning model determined by the determination unit 34 and the learning model outputs a result indicating that a predetermined object is included in the subject 1, the determination unit 34 determines that the predetermined object is included in the subject 1. Furthermore, when the determination unit 34 inputs a sub-terahertz wave image into a learning model determined by the determination unit 34 and the learning model outputs a result indicating that the predetermined object is not included in the subject 1, the determination unit 34 determines that the predetermined object is not included in the subject 1.

[0081] Further, for example, the judgment unit 34 determines a threshold value for determining whether or not the subject 1 contains a specified object based on the subject information and the intensity distribution information, and determines whether or not the subject 1 contains a specified object using the determined threshold value.

[0082] For example, first, the determination unit 34 acquires the position and orientation of the subject 1 from the subject information, and acquires the intensity distribution of the sub-terahertz waves when the predetermined area 22 is irradiated with sub-terahertz waves while the reflector 38 is positioned at the position and in the orientation. As described above, the intensity distribution is measured in advance by simulation, experiment, or the like, and stored in the storage unit 30. Note that, for example, the determination unit 34 may acquire only the position of the subject 1 out of the position and orientation from the subject information, and acquire the intensity distribution of the sub-terahertz waves when the predetermined area 22 is irradiated with sub-terahertz waves while the reflector 38 is positioned at the position.

[0083] For example, next, the determination unit 34 obtains the intensity of the sub-terahertz waves irradiating the subject 1 from the obtained intensity distribution and determines a threshold value based on the obtained intensity. For example, when the intensity of the sub-terahertz waves irradiating the subject 1 is a predetermined first intensity, the determination unit 34 determines to use predetermined upper and lower limit threshold values. Furthermore, for example, when the intensity of the sub-terahertz waves irradiating the subject 1 is a second intensity different from the predetermined first intensity, the determination unit 34 determines to use a first threshold value obtained by multiplying the predetermined upper limit threshold by (second intensity) / (first intensity) as the upper limit threshold, and determines to use a second threshold value obtained by multiplying the predetermined lower limit threshold by (second intensity) / (first intensity) as the lower limit threshold.

[0084] For example, for a portion of the subject 1 depicted in the sub-terahertz wave image where the intensity of the irradiated sub-terahertz waves is a first intensity, the determination unit 34 determines whether the intensity of the sub-terahertz waves is greater than a predetermined upper threshold and whether the intensity of the sub-terahertz waves is less than a predetermined lower threshold. Furthermore, for example, for a portion of the subject 1 depicted in the sub-terahertz wave image where the intensity of the irradiated sub-terahertz waves is a second intensity, the determination unit 34 determines whether the intensity of the sub-terahertz waves is greater than a first threshold and whether the intensity of the sub-terahertz waves is less than a second threshold.

[0085] The output unit 36 ​​acquires the determination result of the determination unit 34 .

[0086] FIG. 6 is a flowchart showing an example of the operation of the determination device 20 of the determination system 10 of FIG.

[0087] 6, the image acquiring unit 26 acquires a sub-terahertz wave image (image acquiring step) (step S1). For example, the image acquiring unit 26 acquires the sub-terahertz wave image as described above.

[0088] The subject information acquisition unit 28 acquires subject information (subject information acquisition step) (step S2). For example, the subject information acquisition unit 28 acquires the subject information as described above.

[0089] The intensity distribution information acquiring unit 32 acquires the intensity distribution information (intensity distribution information acquiring step) (step S3). For example, the intensity distribution information acquiring unit 32 acquires the intensity distribution information as described above.

[0090] The determination unit 34 determines whether or not a predetermined object is included in the subject 1 based on the sub-terahertz wave image, the subject information, and the intensity distribution information (determination step) (step S4). For example, the determination unit 34 determines whether or not a predetermined object is included in the subject 1 as described above.

[0091] The output unit 36 ​​outputs the determination result determined in the determination step (output step) (step S5).

[0092] As described above, the determination device 20 according to the embodiment includes an image acquisition unit 26 that acquires an image based on the sub-terahertz waves irradiated onto a predetermined region 22, a subject information acquisition unit 28 that acquires subject information including position information indicating the position of the subject 1 located in the predetermined region 22, an intensity distribution information acquisition unit 32 that acquires intensity distribution information indicating the intensity distribution in the predetermined region 22 of the sub-terahertz waves irradiated onto the predetermined region 22, a determination unit 34 that determines whether or not the subject 1 includes a predetermined object based on the image, the subject information, and the intensity distribution information, and an output unit 36 ​​that outputs the determination result determined by the determination unit 34.

[0093] According to this, the subject information indicates the position of the subject 1, and the intensity distribution information indicates the intensity of the sub-terahertz waves irradiated onto the subject 1. Therefore, even if there is unevenness in the intensity distribution of the sub-terahertz waves irradiated onto the predetermined region 22, it is possible to appropriately determine whether or not the subject 1 includes a predetermined object according to the intensity of the sub-terahertz waves irradiated onto the subject 1, and therefore it is possible to more accurately determine whether or not the subject 1 includes a predetermined object.

[0094] In addition, the judgment unit 34 corrects the image based on the sub-terahertz waves irradiated onto the specified area 22 based on the subject information and intensity distribution information, and judges whether the subject 1 includes a specified object based on the corrected image.

[0095] According to this, although the intensity distribution of the sub-terahertz waves irradiated onto the specified area 22 varies depending on the position of the subject 1, the image can be corrected based on the intensity distribution of the sub-terahertz waves according to the position of the subject 1, and it can be determined based on the corrected image whether or not the subject 1 contains a specified object, thereby making it possible to determine with even greater accuracy whether or not the subject 1 contains a specified object.

[0096] The subject information further includes orientation information indicating the orientation of the subject 1 .

[0097] According to this, the intensity distribution of the sub-terahertz waves irradiated onto the specified region 22 changes depending on the orientation of the subject 1, but since the orientation of the subject 1 can be determined from the subject information, it is possible to more accurately determine whether or not the subject 1 contains a specified object.

[0098] In addition, the judgment unit 34 determines a learning model for determining whether or not the subject 1 contains a specified object based on the subject information and the intensity distribution information, and determines whether or not the subject 1 contains a specified object using the determined learning model.

[0099] This makes it possible to determine whether or not the subject 1 contains a specified object using a learning model that corresponds to the intensity of the sub-terahertz waves irradiated onto the subject 1, thereby making it possible to more accurately determine whether or not the subject 1 contains a specified object.

[0100] In addition, the judgment unit 34 determines a threshold value for determining whether or not the subject 1 contains a specified object based on the subject information and the intensity distribution information, and determines whether or not the subject 1 contains a specified object using the determined threshold value.

[0101] This allows a determination as to whether or not the subject 1 contains a specified object to be made using a threshold value corresponding to the intensity of the sub-terahertz waves irradiated onto the subject 1, thereby enabling an even more accurate determination as to whether or not the subject 1 contains a specified object.

[0102] The predetermined region 22 is a region sandwiched between a pair of reflectors 14 each of which diffusely reflects sub-terahertz waves.

[0103] This allows the sub-terahertz waves to be diffusely reflected, and by diffusely reflecting the sub-terahertz waves, the sub-terahertz waves can be more uniformly irradiated onto the specified area 22, making it possible to more accurately determine whether or not the subject 1 contains a specified object.

[0104] The apparatus further includes a storage unit 30 that stores intensity distribution information, and an intensity distribution information acquisition unit 32 acquires the intensity distribution information from the storage unit 30 .

[0105] This allows the intensity distribution information to be easily obtained.

[0106] The intensity distribution indicates the intensity of the sub-terahertz wave at each position in the predetermined region 22 .

[0107] This allows the intensity of the sub-terahertz waves at each position in the specified region 22 to be known, and the intensity of the sub-terahertz waves irradiated onto the subject 1 to be known with greater precision, thereby enabling even more accurate determination of whether or not the subject 1 contains a specified object.

[0108] It also includes an image acquisition step (step S1) for acquiring an image based on the sub-terahertz waves irradiated onto the predetermined region 22, a subject information acquisition step (step S2) for acquiring subject information including position information indicating the position of the subject 1 located in the predetermined region 22, an intensity distribution information acquisition step (step S3) for acquiring intensity distribution information indicating the intensity distribution of the sub-terahertz waves irradiated onto the predetermined region 22, a determination step (step S4) for determining whether or not the subject 1 includes a predetermined object based on the image, the subject information, and the intensity distribution information, and an output step (step S5) for outputting the determination result determined by the determination step.

[0109] This provides the same effects as those of the determination device 20 described above.

[0110] While the determination device according to the present disclosure has been described above based on the embodiments, the present disclosure is not limited to these embodiments. As long as it does not deviate from the spirit of the present disclosure, various modifications conceivable by a person skilled in the art to these embodiments and modifications, and configurations constructed by combining components of different embodiments and modifications, are also included within the scope of one or more aspects of the present disclosure.

[0111] For example, the determination system 10 may further include a reflector that connects the upper ends of the pair of reflectors 14 together, and a reflector that connects the lower ends of the pair of reflectors 14 together.

[0112] Furthermore, for example, subject 1 does not have to include a person, and may be luggage, etc. For example, if the luggage, etc. includes a predetermined object and other objects, the intensity of the reflection of the sub-terahertz waves by the other objects will not be the same as the intensity of the reflection of the sub-terahertz waves by the predetermined object, and therefore it can be determined that the luggage, etc. includes the predetermined object.

[0113] Furthermore, for example, the determination system 10 does not need to include all of the components described in the above embodiments, and may be composed of only the components required to perform the desired operation.

[0114] In the above-described embodiments, each component of the determination system may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.

[0115] Each component may be a circuit (or integrated circuit). These circuits may form a single circuit as a whole, or each may be a separate circuit. Each of these circuits may be a general-purpose circuit or a dedicated circuit.

[0116] Furthermore, a comprehensive or specific aspect of the present disclosure may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM. Also, the present disclosure may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a non-transitory recording medium. For example, the present disclosure may be realized as a program for causing a computer to execute control performed by a control unit or the like provided in each component of a determination system.

[0117] Furthermore, the order of the multiple processes in the operation of the determination system described in the above embodiment is an example. The order of the multiple processes may be changed, or the multiple processes may be executed in parallel.

[0118] Furthermore, the above-described embodiments can be modified, substituted, added, omitted, and the like in various ways within the scope of the claims or their equivalents.

[0119] The present disclosure is widely applicable to a determination system or the like that determines whether a subject includes a predetermined object.

[0120] REFERENCE SIGNS LIST 1 subject 2 person 3 predetermined object 10 determination system 12 irradiation unit 14 reflector 16 imaging unit 18 subject detection unit 20 determination device 22 predetermined area 24 light source 26 image acquisition unit 28 subject information acquisition unit 30 storage unit 32 intensity distribution information acquisition unit 34 determination unit 36 ​​output unit 38 reflector

Claims

1. an image acquisition unit that acquires an image based on the sub-terahertz wave irradiated onto a predetermined area; a subject information acquiring unit that acquires subject information including position information indicating a position of a subject located in the predetermined area; an intensity distribution information acquisition unit that acquires intensity distribution information indicating an intensity distribution in the predetermined region of the sub-terahertz wave irradiated onto the predetermined region; a determination unit that determines whether or not the subject includes a predetermined object based on the image, the subject information, and the intensity distribution information. Judgment device.

2. the intensity distribution information indicates a plurality of intensities of the sub-terahertz waves when the sub-terahertz waves irradiated to the predetermined region are reflected by a same object facing a predetermined direction at each of a plurality of positions within the predetermined region; The determination device according to claim 1 .

3. the determination unit corrects the intensity of the sub-terahertz waves for each of a plurality of points of the subject in the image based on the subject information and the intensity distribution information, and determines whether or not the subject includes the predetermined object based on the corrected image. The determination device according to claim 1 or 2.

4. the determination unit determines a learning model for determining whether or not the subject includes the predetermined object by acquiring the intensity of the sub-terahertz waves irradiated at each of a plurality of points on the subject based on the subject information and the intensity distribution information, and determines whether or not the subject includes the predetermined object using the determined learning model. The determination device according to claim 1 or 2.

5. the determination unit has a plurality of learning models corresponding to the intensity of the sub-terahertz waves, and determines the learning model according to the intensity of the acquired sub-terahertz waves. The determination device according to claim 4.

6. the determination unit acquires the intensity of the sub-terahertz waves irradiated at each of a plurality of points of the subject based on the subject information and the intensity distribution information, determines a threshold value for each of the plurality of points of the subject to determine whether or not the subject includes the predetermined object, and determines whether or not the subject includes the predetermined object using the determined threshold value. The determination device according to claim 1 or 2.

7. When the threshold value when the object is irradiated with the sub-terahertz waves at a predetermined intensity is a first threshold value, the determination unit calculates a second threshold value as the threshold value based on the acquired intensity of the sub-terahertz waves, the predetermined intensity, and the first threshold value. The determination device according to claim 6.

8. the predetermined region is a region sandwiched between a pair of reflecting plates each of which diffusely reflects the sub-terahertz wave; The determination device according to claim 1 .

9. A storage unit that stores the intensity distribution information, the intensity distribution information acquisition unit acquires the intensity distribution information from the storage unit. The determination device according to claim 1 .

10. The subject information further includes orientation information indicating an orientation of the subject. The determination device according to claim 1 .

11. Further comprising an output unit that outputs a judgment result judged by the judgment unit. The determination device according to claim 1 .

12. an image acquiring step of acquiring an image based on the sub-terahertz wave irradiated onto a predetermined region; a subject information acquiring step of acquiring subject information including position information indicating a position of a subject located in the predetermined area; an intensity distribution information acquisition step of acquiring intensity distribution information indicating an intensity distribution in the predetermined region of the sub-terahertz wave irradiated to the predetermined region; and determining whether or not the subject includes a predetermined object based on the image, the subject information, and the intensity distribution information. Judgment method.