JP6927914B2 - Image processing equipment, imaging equipment, and moving objects - Google Patents

Description

The present disclosure relates to an image processing device, an imaging device, and a moving body.

Conventionally, it is known that a far-infrared camera captures infrared rays emitted from a subject and extracts a pedestrian subject by the temperature of the subject calculated based on the intensity of the captured infrared rays. It has been proposed to extract pedestrians with high accuracy by estimating the area of the road surface from the thermal image obtained by the far-infrared camera and calculating the temperature that the pedestrian can take based on the temperature of the road surface. (See, for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2012-53724

However, the relationship between the road surface temperature and the temperature that a pedestrian can take may not be constant. Therefore, in the method described in Patent Document 1, the information regarding the temperature of the subject is accurately obtained based on the relationship between the temperature of the road surface and the temperature that can be taken by a pedestrian by using the intensity of the far infrared ray detected by the far infrared ray camera. It becomes difficult to estimate.

An object of the present disclosure is to provide an image processing device, an imaging device, and a moving body that estimate information on the temperature of a subject with high accuracy.

The image processing apparatus according to the embodiment of the present disclosure includes an image acquisition unit and a controller. The image acquisition unit acquires a far-infrared image. The controller sets the subject distance from the imaging position of the far-infrared image to the subject included as an image in the far-infrared image, a predetermined reference distance, and a position separated from the imaging position by the reference distance. Information about the temperature of a reference object having a fixed predetermined radiation coefficient, the signal level in the image of the subject in the far-infrared image, and the imaging region of the reference object in the far-infrared image are predetermined. Information about the temperature of the subject is estimated based on the signal level in the area.

The image pickup apparatus according to the embodiment of the present disclosure includes an image processing apparatus. The image processing device includes an image acquisition unit and a controller. The image acquisition unit acquires a far-infrared image. The controller sets the subject distance from the imaging position of the far-infrared image to the subject included as an image in the far-infrared image, a predetermined reference distance, and a position separated from the imaging position by the reference distance. Information about the temperature of a reference object having a fixed predetermined radiation coefficient, the signal level in the image of the subject in the far-infrared image, and the imaging region of the reference object in the far-infrared image are predetermined. Information about the temperature of the subject is estimated based on the signal level in the area.

The moving body according to the embodiment of the present disclosure includes an image processing device. The image processing device includes an image acquisition unit and a controller. The image acquisition unit acquires a far-infrared image. The controller sets the subject distance from the imaging position of the far-infrared image to the subject included as an image in the far-infrared image, a predetermined reference distance, and a position separated from the imaging position by the reference distance. Information about the temperature of a reference object having a fixed predetermined radiation coefficient, the signal level in the image of the subject in the far-infrared image, and the imaging region of the reference object in the far-infrared image are predetermined. Information about the temperature of the subject is estimated based on the signal level in the area.

According to the image processing device, the image pickup device, and the moving body according to the embodiment of the present disclosure, information on the temperature of the subject can be estimated with high accuracy.

It is a schematic diagram which shows the moving body which includes the subject type estimation system including the image processing apparatus which concerns on this embodiment. It is a functional block diagram which shows the schematic structure of the subject type estimation system shown in FIG. It is a schematic diagram which shows the example of the far-infrared image image | photographed by the image pickup part shown in FIG. It is a flowchart which shows the flow of the subject type estimation processing of the subject type estimation system shown in FIG.

Hereinafter, the image processing apparatus 10 according to the embodiment of the present disclosure will be described with reference to the drawings.

As shown in FIG. 1, the subject type estimation system 1 including the image processing device 10 according to the embodiment of the present disclosure is attached to the moving body 100.

The moving body 100 may include, for example, a vehicle, a ship, an aircraft, and the like. Vehicles may include, for example, automobiles, industrial vehicles, railroad vehicles, living vehicles, fixed-wing aircraft traveling on runways, and the like. Automobiles may include, for example, passenger cars, trucks, buses, motorcycles, trolley buses and the like. Industrial vehicles may include, for example, industrial vehicles for agriculture and construction. Industrial vehicles may include, for example, forklifts and golf carts. Industrial vehicles for agriculture may include, for example, tractors, cultivators, porters, binders, combines, lawnmowers and the like. Industrial vehicles for construction may include, for example, bulldozers, scrapers, excavators, mobile cranes, dump trucks, road rollers and the like. The vehicle may include a vehicle that travels manually. The classification of vehicles is not limited to the above examples. For example, an automobile may include an industrial vehicle that can travel on the road. The same vehicle may be included in multiple categories. Vessels may include, for example, marine jets, boats, tankers and the like. Aircraft may include, for example, fixed-wing aircraft, rotorcraft, and the like.

As shown in FIG. 2, the subject type estimation system 1 includes an imaging device 11 and a distance measuring device 12. The image pickup device 11 includes an image pickup unit 13 and an image processing device 10.

As shown in FIG. 1, the imaging unit 13 is attached to the moving body 100 so that, for example, far-infrared light emitted from the front of the moving body 100 can be imaged. The imaging unit 13 is not limited to the front of the moving body 100, but may be attached to the moving body 100 so that it can image laterally or rearwardly. The imaging unit 13 generates a far-infrared image that captures the far-infrared light emitted from a subject within the imaging range. The image pickup unit 13 is, for example, a far infrared camera.

A reference object 15 is attached to the imaging range of the imaging device 11. Specifically, the reference object 15 is fixed at a predetermined reference distance D1 from the imaging position of the imaging unit 13 on the outer surface of the moving body 100. The reference object 15 is an object having a predetermined emissivity. The predetermined emissivity is, for example, the range that human emissivity can take. The human emissivity is, for example, 0.95-1, although it depends on the condition of the skin, the material of clothes, and the like. The reference object 15 may be, for example, a blackbody which is an object having an emissivity of 1. The temperature of the reference object 15 may be a predetermined temperature included in the range in which the body temperature can be taken. The range of body temperature that can be taken is, for example, 35 to 42 degrees. The reference object 15 may be controlled to be held at a predetermined temperature by an arbitrary temperature control device such as a heater.

The image processing device 10 includes an image acquisition unit 17, an information acquisition unit 18, a memory 19, a controller 20, and an output unit 21.

The image acquisition unit 17 is an interface for acquiring a far-infrared image generated by the image pickup apparatus 11.

The information acquisition unit 18 acquires the subject distance D2. The subject distance D2 is the distance from the imaging position of the far-infrared image measured by the distance measuring device 12 to the subject included as an image in the far-infrared image.

The memory 19 is composed of an arbitrary storage device such as a RAM (Random Access Memory) and a ROM (Read Only Memory). The memory 19 stores _{the intensity I A0} of the far-infrared light emitted from the reference object 15. The memory 19 stores the reference distance D1 from the imaging position in the imaging unit 13 to the reference object 15. The memory 19 stores the distance D22 from the imaging position in the imaging unit 13 to the distance measuring device 12. The far-infrared light intensity I _A0 , the reference distance D1, and the distance D22 are pre-designed values. The far-infrared light intensity I _A0 , the reference distance D1, and the distance D22 may be values calibrated after mounting the subject type estimation system 1 on the moving body 100, or measured values.

The controller 20 includes one or more processors and memory. The controller 20 may include a general-purpose processor that loads a specific program and executes a specific function, and a dedicated processor specialized for a specific process. Dedicated processors may include application specific integrated circuits (ASICs). The processor may include a programmable logic device (PLD). The PLD may include an FPGA (Field-Programmable Gate Array). The controller 20 may be either a SoC (System-on-a-Chip) in which one or a plurality of processors cooperate, and a SiP (System In a Package).

The controller 20 executes processing on the far-infrared image acquired by the image acquisition unit 17. Details of the processing executed by the controller 20 will be described later.

The output unit 21 may output information based on the processing executed by the controller 20 to the distance measuring device 12, the display mounted on the moving body 100, the ECU (Engine Control Unit or the Electric Control Unit), and the like. The ECU can control the traveling of the moving body 100 based on the information output by the output unit 21, for example, by controlling the controlled device used in connection with the moving body 100. The controlled device may include, but is not limited to, for example, an engine, a motor, a transmission, a car air conditioner, a power window, a car navigation system, a car audio, a head-up display, and the like.

The distance measuring device 12 generates information for calculating the subject distance D2, which is the distance from the imaging position of the imaging device 11 to the subject. The information for calculating the subject distance D2 is, for example, the distance D21 from the distance measuring device 12 to the subject, or the subject distance D2 itself. In the configuration in which the information for calculating the subject distance D2 is the distance D21, the distance measuring device 12 measures the distance D21 and generates the measured distance D21 as information for calculating the subject distance D2. In the configuration in which the information for calculating the subject distance D2 is the subject distance D2 itself, the distance measuring device 12 measures the distance D21. The distance measuring device 12 is based on the measured distance D21, the imaging position of the imaging device 11 and the distance D22 between the distance measuring device 12, and the subject distance D2 from the imaging position in the imaging device 11 to the subject. Is calculated. In the example shown in FIG. 1, the distance measuring device 12 is located between the imaging unit 13 and the subject. Therefore, the distance measuring device 12 calculates the subject distance D2, which is the total D21 + D22 of the distance D21 from the distance measuring device 12 to the subject and the distance D22 between the imaging device 11 and the distance measuring device 12.

The distance measuring device 12 may be, for example, RADAR (Radio detection And Ranging), LIDAR (Light Detection and Ranging), or the like. The distance measuring device 12 may be a monocular camera. The distance measuring device 12 to which the monocular camera is applied can calculate the subject distance D2 by a known method based on the image obtained by capturing the subject. Not limited to these, the distance measuring device 12 may measure the distance from the imaging position to the subject by any method.

Here, the process executed by the controller 20 will be described in detail with reference to the drawings.

The controller 20 determines whether or not the image 16im of the target subject 16 is included in the far-infrared image as shown in FIG. 3 captured by the imaging unit 13. When the controller 20 determines that the far-infrared image includes the image 16im of the target subject 16, the controller 20 extracts the image 16im of the target subject 16. The target subject 16 is a subject whose temperature is estimated by the controller 20 as described later.

Specifically, the controller 20 detects an edge in the far-infrared image and extracts a region surrounded by the edge. Then, the controller 20 determines whether or not the region has a predetermined size or more. Further, the controller 20 determines whether or not the difference between the maximum value and the minimum value of the signal level of each pixel included in the region is equal to or less than the threshold value when the region is equal to or larger than a predetermined size. The controller 20 determines that the far-infrared image includes the image 16im of the target subject 16 when there is a region where the difference is equal to or less than the threshold value. When the controller 20 determines that the far-infrared image includes the image 16im of the target subject 16, the controller 20 extracts the image represented in the region as the image 16im of the target subject 16. The method in which the controller 20 extracts the image 16im of the target subject 16 in the far-infrared image is not limited to this, and may be any method.

The controller 20 acquires information for calculating the distance to the target subject 16 from the distance measuring device 12.

Specifically, the controller 20 determines the position of the image 16im of the target subject 16 in the far infrared image. The controller 20 causes the output unit 21 to output the position to the distance measuring device 12. The distance measuring device 12 measures the subject distance D2 from the imaging position to the target subject 16 based on the position in the far infrared image output by the output unit 21. The distance measuring device 12 outputs the measured subject distance D2 to the image processing device 10. When the subject distance D2 is output by the distance measuring device 12, the information acquisition unit 18 acquires the subject distance D2.

The controller 20 may acquire the distances to all the objects within the range measurable by the distance measuring device 12 from the distance measuring device 12. In this case, among the distances to each object measured by the distance measuring device 12, the controller 20 sets the distance to a certain object in the real space corresponding to the position of the image 16im of the target subject 16 in the far infrared image. Extracted as the distance D2.

The controller 20 includes information on the subject distance D2, the reference distance D1, the temperature of the reference object 15, the signal level in the image 16im of the target object 16, and the signal in the region 15im predetermined as the imaging region of the reference object 15. The temperature of the target subject 16 is estimated based on the level. The information about temperature may be temperature. The information about the temperature may be any information that can be converted into a temperature. Hereinafter, the information regarding temperature will be described as being temperature.

Far-infrared light emitted from a subject including the reference object 15 and the target subject 16 is absorbed by the atmosphere. Therefore, the intensity of the far-infrared light is attenuated as the distance through which the far-infrared light propagates increases. _{Specifically, the intensity I A0} of the far-infrared light emitted from _{the reference object 15, the intensity I A1} of the far-infrared light imaged at an imaging position at a reference distance D1 away from the reference object 15, and the far-infrared light due to the atmosphere. The relationship shown in Eq. (1) is established for the external light absorption coefficient α. As described above, the reference object 15 has a predetermined emissivity and is controlled to a predetermined temperature. _{Therefore, the intensity I A0} of the far-infrared light is a known value and is stored in the memory 19 in advance as described above. Further, the intensity I _A1 of the far-infrared light is a value corresponding to a signal level of a region 15im predetermined as an imaging region of the reference object 15 in the far-infrared image. Further, the reference distance D1 is the distance from the imaging position of the imaging unit 13 to the reference object 15 as described above, and is stored in the memory 19 in advance as described above.

α =-(log ₁₀ ( _IA1 / I _A0 )) / D1 equation (1)

_{Further, the intensity I B0} of the far-infrared light emitted from _{the target subject 16, the intensity I B1} of the far-infrared light captured at an imaging position separated from the target subject 16 by the subject distance D2, and the far-infrared light from the atmosphere. The relationship shown in Eq. (2) is established for the absorption coefficient α. The far-infrared light intensity I _B1 is a value corresponding to the signal level in the image of the subject in the far-infrared image. Further, as described above, the subject distance D2 is measured by the distance measuring device 12.

α =-(log ₁₀ ( _IB1 / I _B0 )) / D2 equation (2)

_{Therefore, the intensity I B0} of the far-infrared light emitted from the target subject 16 is derived by the equation (3).

_{When the controller 20 calculates the intensity I B0} of the far-infrared light emitted from the target subject 16, the intensity I _B0 is converted into a temperature, and the converted temperature is estimated to be the temperature of the target subject 16.

When the controller 20 estimates the temperature of the target subject 16, the controller 20 estimates the type of the target subject 16 based on the temperature. Specifically, the controller 20 determines whether or not the temperature of the target subject 16 is within a predetermined range. The predetermined range is a range in which human body temperature can be taken, for example, 35 to 39 degrees. When the temperature of the target subject 16 is within a predetermined range, the controller 20 estimates that the type of the target subject 16 is a human being. When the temperature of the target subject 16 is not within the predetermined range, the controller 20 estimates that the type of the target subject 16 is other than human.

When the temperature of the target subject 16 is within a predetermined range, the controller 20 may presume that the candidate for the type is not the type of the target subject 16 but a human being. In this case, the controller 20 determines whether or not the type of the target subject 16 is a human being based on the shape or behavior of the image 16im of the target subject 16. Specifically, when the shape of the image 16im of the target subject 16 whose type candidate is presumed to be a human is similar to the shape stored in advance, the controller 20 indicates that the type of the target subject 16 is a human. Presumed to be. Further, the controller 20 may estimate whether or not the type of the target subject 16 is a human based on the behavior of the image 16im of the target subject 16 whose type candidate is estimated to be a human. The behavior of the image 16im of the target subject 16 is, for example, a history in which the shape of the image 16im of the target subject 16 changes with time. When the behavior of the image 16im of the target subject 16 is similar to the behavior stored in advance, the controller 20 may determine that the type of the target subject 16 is a human being. The method for determining whether or not the shapes or behaviors are similar may be any method.

When the controller 20 determines the type of the target subject 16, the controller 20 may control the output unit 21 so as to output the type to the display or the ECU mounted on the moving body 100. The controller 20 may control the output unit 21 so as to output the subject distance D2 to the display or the ECU together with the type.

Subsequently, the subject type estimation process of the image processing device 10 of the present embodiment will be described with reference to FIG. When the image processing device 10 acquires a far-infrared image from the imaging unit 13, the image processing device 10 starts the subject type estimation process.

In step S11, the controller 20 determines whether or not the far-infrared image acquired by the image acquisition unit 17 includes the image 16im of the target subject 16. When the controller 20 determines that the far-infrared image includes the image 16im of the target subject 16, the process proceeds to step S12. When the controller 20 determines that the far-infrared image does not include the image 16im of the target subject 16, the controller 20 ends the subject type estimation process.

In step S12, the controller 20 extracts the image 16im of the target subject 16 from the far-infrared image acquired by the image acquisition unit 17. When the controller 20 extracts the image of the target subject 16, the process proceeds to step S13.

In step S13, the controller 20 determines the position of the image 16im of the target subject 16 in the far infrared image. When the controller 20 determines the position of the image 16im of the target subject 16, the process proceeds to step S14.

In step S14, the controller 20 acquires the subject distance D2 measured by the distance measuring device 12 based on the position of the image 16im of the target subject 16. When the controller 20 acquires the subject distance D2, the process proceeds to step S15.

In step S15, the controller 20 determines the subject distance D2, the reference distance D1, the temperature of the reference object 15, the signal level in the image 16im of the target subject 16, and the region 15im predetermined as the imaging region of the reference object 15. The temperature of the target subject 16 is estimated based on the signal level in. When the controller 20 estimates the temperature of the target subject 16, the process proceeds to step S16.

In step S16, the controller 20 determines whether or not the estimated temperature of the target subject 16 is within a predetermined range. When the controller 20 determines that the estimated temperature of the target subject 16 is within a predetermined range, the process proceeds to step S17. When the controller 20 determines that the estimated temperature of the target subject 16 is not within the predetermined range, the process proceeds to step S18.

In step S17, the controller 20 estimates that the type of the target subject 16 is a human being. When the controller 20 estimates that the type of the target subject 16 is a human being, the controller 20 ends the subject type estimation process.

In step S18, the controller 20 estimates that the type of the target subject 16 is not human. When the controller 20 estimates that the type of the target subject 16 is not human, the controller 20 ends the subject type estimation process.

As described above, according to the present embodiment, the image processing apparatus 10 includes the subject distance D2, the reference distance D1, the temperature of the reference object 15, the signal level in the image 16im of the target subject 16, and the reference object 15. The temperature of the target subject 16 is estimated based on the signal level in the region 15 im defined in advance as the imaging region of. Therefore, the image processing device 10 estimates the temperature of the target subject 16 in consideration of the degree of attenuation of the far-infrared light estimated from the temperature of the reference object 15 and the signal level of the imaging region in the far-infrared image. It will be. Therefore, the image processing device 10 can improve the accuracy in estimating the temperature even if the absorption rate of far-infrared light by the atmosphere fluctuates. Further, far-infrared light is absorbed more as the propagating distance becomes longer. Therefore, the image processing device 10 estimates the temperature of the target subject 16 at the subject distance D2 based on the temperature of the reference object 15 at the reference distance D1 from the imaging position, thereby improving the accuracy of the estimation of the temperature. Can be improved.

Further, according to the present embodiment, the temperature of the reference object 15 is a predetermined temperature. As a result, the image processing device 10 can improve the accuracy of measuring the temperature of the target subject 16 with a simple configuration without providing a device for measuring the temperature of the reference object 15.

Further, according to the present embodiment, the image processing device 10 estimates the type of the subject based on the temperature of the subject and the shape or behavior of the image of the subject in the far-infrared image. Specifically, the image processing device 10 extracts the target subject 16 based on the shape or behavior of the image of the subject in the far infrared image, and estimates the type of the target subject 16 based on the temperature of the target subject 16. If the type of the target subject 16 is estimated based only on the shape or behavior of the image 16im of the target subject 16, the shape or behavior is similar to the shape or behavior of each of the predetermined types, but the temperature is predetermined. The target subject 16 that is not within the range defined for the type may be erroneously estimated to be of the predetermined type. For example, the image 16im of the target subject 16 resembles a human shape, but a mannequin or the like whose temperature is not within the range that a human can take may be erroneously presumed to be a human. Therefore, the image processing device 10 estimates the type of the subject based on the temperature of the target subject 16 and the shape or behavior of the image 16im of the target subject 16 in the far-infrared image, and thus the accuracy of the estimation of the type is estimated. Can be improved.

Further, according to the present embodiment, the image processing device 10 estimates whether or not the type of the target subject 16 is a human being, and the emissivity of the reference object 15 is equal to the emissivity of a human being. If the emissivity of the reference object 15 is different from the emissivity of a human being, the relationship between the temperature of the reference object 15 and the signal level in the imaging region of the image is the temperature of the target subject 16 due to the difference in emissivity. It may not be the same as the relationship with the signal level. In this case, the temperature of the target subject 16 may not be accurately estimated based on the signal level of the image of the target subject 16 even in consideration of the relationship between the temperature of the reference object 15 and the signal level of the imaging region of the image. On the other hand, since the emissivity of the reference object 15 is equal to the emissivity of a human being, the relationship between the temperature of the reference object 15 and the signal level of the imaging region of the image is the temperature of the target subject 16 which is a human being and the signal of the image. Applies to relationships with levels. Therefore, the image processing device 10 can improve the accuracy of the temperature estimation by estimating the temperature of the target subject 16 based on the relationship between the temperature of the reference object 15 and the signal level of the image pickup region of the image.

Further, according to the present embodiment, the temperature of the reference object 15 is included in the range in which the body temperature can be taken. The distribution range of the wavelength of infrared light emitted from the subject varies depending on the temperature of the subject. Further, among the infrared light emitted from the subject, the wavelength of the light having the highest intensity differs depending on the temperature of the subject. Therefore, by applying the reference object 15 that emits infrared light having a similar wavelength distribution range and the highest wavelength, the infrared light emitted from humans and the red emitted from the reference object 15 are applied. The characteristics of outside light are similar. Therefore, the image processing device 10 compares the intensity of the infrared light emitted from the subject with the intensity of the infrared light having characteristics similar to those of a human being, so that the temperature of the subject when the subject is a human can be adjusted. The accuracy of the estimation can be improved. Therefore, the image processing device 10 can improve the accuracy of the estimation of the type of the subject by improving the accuracy of the temperature estimation.

Although the present embodiment has been described as a representative example, it will be apparent to those skilled in the art that many modifications and substitutions can be made within the spirit and scope of the present invention. Therefore, the present invention should not be construed as being limited by the embodiments described above, and various modifications or modifications can be made without departing from the claims. For example, it is possible to combine the plurality of constituent blocks described in the embodiments and examples into one, or to divide one constituent block into one.

In the above-described embodiment, the configuration in which the image pickup device 11 and the distance measurement device 12 are separate bodies has been described, but the image pickup device 11 and the distance measurement device 12 may be integrally configured. The image pickup device 11 may include a distance measuring device 12 inside.

In the above-described embodiment, the configuration in which the imaging device 11 includes the imaging unit 13 and the image processing device 10 has been described, and an example in which the imaging unit 13 and the image processing device 10 are separately configured is shown in FIG. However, it is not limited to this. For example, the image pickup unit 13 and the image processing device 10 may be integrally configured.

In the above-described embodiment, the plurality of reference objects 15 may be attached to the imaging range of the imaging unit 13 in the moving body 100. In this case, the plurality of reference objects 15 may be set to different temperatures in a human-possible temperature range. For example, the temperature of the first reference object among the plurality of reference objects 15 may be set to, for example, the maximum temperature in the temperature range. The temperature of the second reference object may be set to, for example, the lowest temperature in the temperature range. In such a configuration, the controller 20 may estimate the temperature of the target subject 16 based on both the first reference object and the second reference object.

For example, the controller 20 calculates the average value of the signal levels of the regions predetermined as the imaging regions of the first reference object and the second reference object. Then, the controller 20 estimates the temperature of the target subject 16 by using the above equations (1) and (2) based on the intensity corresponding to the calculated average value of the signal levels.

Further, for example, the controller 20 may calculate the emissivity α using the above equation (1) based on the first reference object and the second reference object, respectively. _{Then, the controller 20 calculates the intensity I B1} of the infrared light emitted from the target subject 16 using the above equation (2) based on the average value of the emissivity α calculated respectively, and the intensity I _B1 The temperature of the target subject 16 may be estimated by converting.

Further, for example, the controller 20 has the temperature of the first reference object, the signal level in a region predetermined as the imaging region of the first reference object in the far infrared image, and the distance from the imaging position to the first reference object. Based on the distance, the temperature of the target subject 16 is estimated in the same manner as described above. Further, the controller 20 determines the temperature of the second reference object, the signal level in a region predetermined as the imaging region of the second reference object in the far infrared image, and the distance from the imaging position to the second reference object. Based on this, the temperature of the target subject 16 is estimated in the same manner as described above. Then, the controller 20 may estimate the temperature of the target subject 16 based on the temperature estimated based on the first reference object and the temperature estimated based on the second reference object. For example, the controller 20 may use the average temperature of the temperature estimated based on the first reference object and the temperature estimated based on the second reference object as the temperature of the target subject 16.

In the above-described embodiment, the subject type estimation system 1 includes, but is not limited to, the distance measuring device 12. For example, the subject type estimation system 1 does not include the distance measuring device 12, and the controller 20 of the image processing device 10 sets the subject distance D2 by a known method based on the far infrared image acquired by the image acquisition unit 17. It may be calculated. In this case, the controller 20 may estimate the temperature of the target subject 16 by using the subject distance D2 calculated based on the far-infrared image. In this case, the subject type estimation system 1 does not need to include the distance measuring device 12, and can estimate the temperature of the target subject 16 with a simple configuration.

In the above-described embodiment, the information regarding the temperature may be _{the intensity I B0 of far-infrared light.} In this case, the controller 20 may estimate the type of the target subject 16 based on _{the intensity I B0 of the far infrared light emitted from the target subject 16.} Specifically, the controller 20 _{determines whether or not the intensity I B0} is within a predetermined range. The predetermined range is the range of the intensity of far-infrared light that can be emitted from humans. The controller 20 estimates that the type of the target subject 16 is a human when _{the intensity I B0 is within a predetermined range.} The controller 20 estimates that the type of the target subject 16 is not human when _{the intensity I B0 is not within the predetermined range.}

In the above-described embodiment, the memory 19 stores, but is not limited to, _{the intensity I A0} of the far-infrared light emitted from the reference object 15. For example, the memory 19 may store the temperature of the reference object 15. In this case, the controller 20 converts the temperature of the reference object 15 stored in the memory 19 into the intensity I _A0 of the far infrared light. Then, the controller 20 estimates the temperature of the target subject 16 based on _{the converted intensity I A0.}

In the above-described embodiment, the controller 20 extracts the image 16im of the target subject 16 based on the edge of the far-infrared image and the size and signal level of the region surrounded by the edge, but the present invention is not limited to this. The controller 20 may extract an image 16im of the target subject 16 from the subjects extracted as described above based on the shape or behavior of the region surrounded by the edges.

In the above-described embodiment, the controller 20 determines whether or not the type of the target subject 16 is a human being, but this is not the case. For example, the controller 20 may determine whether or not the type of the target subject 16 is a predetermined object that is not a human being. In this case, the controller 20 determines whether or not the estimated temperature of the target subject 16 is within the temperature range that the object can take. Further, the reference object 15 may be controlled within a range in which the temperature of the object can be taken. Further, the emissivity of the reference object 15 may be in the range that the emissivity of the object can take.

1 Subject type estimation system 10 Image processing device 11 Imaging device 12 Distance measuring device 13 Imaging unit 15 Reference object 16 Target subject 17 Image acquisition unit 18 Information acquisition unit 19 Memory 20 Controller 21 Output unit 100 Mobile object

Claims (9)

An image acquisition unit that acquires far-infrared images,
The subject distance from the imaging position of the far-infrared image to the subject included as an image in the far-infrared image, a predetermined reference distance, and a position separated from the imaging position by the reference distance are fixed. Information about the temperature of a reference object having a predetermined radiation coefficient, a signal level in the image of the subject in the far-infrared image, and a region predetermined as an imaging region of the reference object in the far-infrared image. An image processing device comprising a controller that estimates information about the temperature of the subject based on the signal level in. In the image processing apparatus according to claim 1,
An image processing device further including an information acquisition unit that acquires information for calculating the subject distance. In the image processing apparatus according to claim 1,
An image processing device that calculates the distance of the subject based on the far-infrared image. In the image processing apparatus according to any one of claims 1 to 3,
An image processing device in which the temperature of the reference object is a predetermined temperature. In the image processing apparatus according to claim 4,
The controller estimates whether or not the subject type is human, and
An image processing device in which the defined temperature is within a range that the human body temperature can take. In the image processing apparatus according to any one of claims 1 to 5,
The controller is an image processing device that estimates the type of the subject based on the information on the temperature of the subject and the shape or behavior of the image of the subject in the far-infrared image. In the image processing apparatus according to claim 6,
The controller is an image processing device that estimates whether or not the type of the subject is a human, and the emissivity of the reference object is within the range of the emissivity that the human can take. An imaging unit that generates a far-infrared image that captures far-infrared light,
The subject distance from the imaging position of the far-infrared image to the subject included as an image in the far-infrared image, a predetermined reference distance, and a position separated from the imaging position by the reference distance are fixed. Information about the temperature of a reference object having a predetermined radiation coefficient, a signal level in the image of the subject in the far-infrared image, and a region predetermined as an imaging region of the reference object in the far-infrared image. An image pickup apparatus comprising an image processing apparatus including a controller that estimates information about the temperature of the subject based on a signal level. An imaging unit that generates a far-infrared image that captures far-infrared light, a subject distance from the imaging position of the far-infrared image to a subject included as an image in the far-infrared image, and a predetermined reference. Information on the distance, the temperature of a reference object having a predetermined radiation rate fixed at a position separated from the imaging position by the reference distance, the signal level in the image of the subject in the far infrared image, and the far red. A moving body including an image processing device including a controller that estimates information about the temperature of the subject based on a signal level in a region predetermined as an imaging region of the reference object in an external image.

Images