Image processing device, image processing method, and image processing program

Abstract

This image processing device comprises: a light-emitting unit that irradiates a subject with near-infrared light; a light-emission control unit that controls the light-emission amount of the light-emitting unit on the basis of the distance between the subject and the light-emitting unit; and a detection unit that detects feature points on the basis of the captured image of the subject irradiated with the near-infrared light.

Description

[Technical field]

[0001] The present invention relates to an image processing device, an image processing method, and an image processing program. [Background technology]

[0002] Various technologies have been proposed for displaying 3D images on displays. Among them, there are also proposals for naked-eye 3D display that does not require tools such as glasses. For example, there is a Light Field display, which is typified by the lenticular method, as a display for naked-eye 3D display.

[0003] When displaying a stereoscopic image on a Light Field display, the viewpoint positions of the left and right of the user are detected, optimal light rays are focused at the viewpoint positions, and an image for the right eye and an image for the left eye are generated. For example, as a technology for detecting the viewpoint position, Patent Document 1 describes a technique for detecting a feature point of an image and tracking the feature point as a gaze position. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2004-195141 A [Non-patent literature]

[0005] [Non-Patent Document 1] Jean-Yves Bouguet "Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the algorithm" Intel Corporation Microprocessor Research Labs (2000) OpenCV Documents Summary of the Invention [Problem to be solved by the invention]

[0006] However, in the above-mentioned conventional technology, there is room for improvement in the process of tracking the user's viewpoint position.

[0007] Therefore, the present disclosure provides an image processing device, an image processing method, and an image processing program that can appropriately track the user's gaze point position. [Means for solving the problem]

[0008] In order to solve the above problems, an image processing device according to one embodiment of the present disclosure includes a light-emitting unit that irradiates an object with near-infrared light, a light-emitting control unit that controls the amount of light emitted by the light-emitting unit based on a distance value between the object and the light-emitting unit, and a detection unit that detects feature points based on an image of the object irradiated with the near-infrared light. [Brief description of the drawings]

[0009] [Figure 1] 1 is a diagram showing an example of the appearance of an information processing device according to an embodiment of the present invention; [Diagram 2] 1 is a block diagram showing an example of a system configuration of an information processing device according to an embodiment of the present invention. [Diagram 3] 1 is a block diagram showing an example of the configuration of a tracking device according to an embodiment of the present invention. [Figure 4] FIG. 11 is a diagram illustrating an example of current specifying information. [Diagram 5] FIG. 2 is a diagram for explaining a captured image according to the present embodiment. [Figure 6] 13A to 13C are diagrams for explaining other processes of the selection unit according to the embodiment. [Figure 7] 4 is a flowchart showing a processing procedure of the tracking device of the present embodiment. [Figure 8] FIG. 2 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the tracking device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the following embodiments, the same components are designated by the same reference numerals, and duplicated descriptions will be omitted.

[0011] The present disclosure will be described in the following order. 1. Embodiment 1.1 Example of the appearance of information processing equipment 1.2 Example of system configuration of information processing device 1.3 Example of tracking device configuration 1.4 Tracking Device Processing Procedures 1.5 Effects of tracking devices 2. Hardware Configuration 3. Conclusion

[0012] [1. Embodiment] [1.1 Example of the appearance of information processing device] 1 is a diagram showing an example of the appearance of an information processing device 1 according to this embodiment. The information processing device 1 is, for example, about the same size as a notebook personal computer, but can also be made smaller or larger.

[0013] The information processing device 1 has a base 2 and a display 3 standing upward from the base 2. The information processing device 1 has a camera 4 above the display 3, and is configured so that the camera 4 can capture an image of a user positioned in front of the display 3. The information processing device 1 also has a near-infrared light emitting device 5 disposed therein, which irradiates the user with near-infrared light.

[0014] The information processing device 1 is capable of displaying, for example, a lenticular stereoscopic image on the display 3. In general, the viewpoint position of a naked-eye user who is not using glasses or the like for stereoscopic display is detected using an image captured by a camera 4. Images (parallax images) for the right and left eyes are generated using light rays that are focused at the respective viewpoint positions on the left and right, and the generated images are displayed on the display 3 equipped with a lenticular lens. This enables the user to view a stereoscopic image without using glasses, a HUD (Head Up Display), or the like.

[0015] [1.2 Example of system configuration of information processing device] 2 is a block diagram showing an example of a system configuration of an information processing device 1 according to this embodiment. The information processing device 1 generally includes a tracking device 100 and a parallax image processing unit 20. The tracking device 100 outputs information indicating a user's viewpoint position, for example, two-dimensional coordinates of the viewpoint position, to the subsequent parallax image processing unit 20. Details of the configuration, operation example, etc. of the tracking device 100 will be described later. The tracking device 100 is an example of an "image processing device".

[0016] The parallax image processing unit 20 has a spatial viewpoint coordinate generation unit 21, a parallax image generation unit 22, and a parallax image display unit 23. The spatial viewpoint coordinate generation unit 21 converts two-dimensional coordinates indicating the viewpoint position output from the tracking device 100 into viewpoint coordinates in a spatial position by applying a known method, and generates viewpoint coordinates in space. The parallax image generation unit 22 generates a stereoscopic image by generating light rays (images) corresponding to the viewpoint coordinates in space. The parallax image display unit 23 is a device that presents a stereoscopic video by continuously displaying the parallax images generated by the parallax image generation unit 22, and corresponds to the display 3 described above.

[0017] [1.3 Tracking device configuration example] Fig. 3 is a block diagram showing an example of the configuration of a tracking device according to this embodiment. As shown in Fig. 3, this tracking device 100 has a distance measurement unit 110, a light emission control unit 120, a wavelength control unit 130, a near-infrared light emitter 140, a wavelength selection unit 140a, an image sensor 150, a center of gravity detection unit 150a, a face detection unit 160, and a selection unit 170. Although not shown in the figure, it is assumed that a user is located in front of the near-infrared light emitter 140.

[0018] 3 shows an example in which the distance measuring unit 110, the light emission control unit 120, the wavelength control unit 130, the near-infrared light emitter 140, the wavelength selection unit 140a, the image sensor 150, the center of gravity detection unit 150a, the face detection unit 160, and the selection unit 170 are included in the tracking device 100, but is not limited to this. For example, the distance measuring unit 110, the light emission control unit 120, and the near-infrared light emitter 140 may be included in other units.

[0019] The distance measuring unit 110 is a processing unit that calculates a distance value between the near-infrared light emitter 140 and a target object (user). The distance measuring unit 110 outputs the distance value to the light emission control unit 120.

[0020] For example, the distance measuring unit 110 calculates a distance value based on the face detection result of the face detection unit 160. The face detection result includes the coordinates of the user's left eye and the coordinates of the user's right eye. The distance between the coordinates of the left eye and the coordinates of the right eye is expressed as the "interocular distance." The distance measuring unit 110 calculates the distance value using a conversion table that defines the relationship between the interocular distance and the distance value. It is assumed that the relationship between the interocular distance and the distance value has been set by prior calibration.

[0021] The light emission control unit 120 is a processing unit that controls the amount of light emitted by the near-infrared light emitter 140 based on the distance value. The light emission control unit 120 specifies the magnitude of a current according to the distance value, and outputs a current (or voltage) of the specified magnitude to the near-infrared light emitter 140.

[0022] The light emission control unit 120 specifies the magnitude of the current according to the distance value by using the current specifying information that defines the relationship between the distance value and the magnitude of the current. FIG. 4 is a diagram showing an example of the current specifying information. Here, the current specifying information is shown by a two-axis graph. The vertical axis corresponds to the magnitude of the current, and the horizontal axis corresponds to the distance value. Amax indicates the upper limit of the current. Amax satisfies the photobiological safety standards JIS C 7550 and IEC 62471. That is, even if the near-infrared light emitting unit 140 irradiates near-infrared light with a current of less than Amax, the user is safe. For example, the light emission control unit 120 specifies the magnitude of the current according to the distance value by following the current specifying information in FIG. 4, and when the magnitude of the current is greater than a threshold (Amax), it can be said that the specified magnitude of the current is corrected to a magnitude less than the threshold.

[0023] 4, according to the current definition information, the greater the distance value (the greater the distance between the user and the near-infrared light emitter 140), the greater the magnitude of the current. When the distance value exceeds d, the magnitude of the current becomes Ad. The current value Ad is a value less than the current value Amax and is set in advance.

[0024] The wavelength control unit 130 is a processing unit that controls the wavelength of the near-infrared light irradiated by the near-infrared light emitting unit 140. For example, the wavelength control unit 130 selects a wavelength based on the face detection result of the face detection unit 160, the center of gravity detection result of the center of gravity detection unit 150a, and the captured image output from the image sensor 150. First, the wavelength control unit 130 binarizes the captured image to generate a binary image. As a result, pixels in dark parts of the captured image become "1" and pixels in bright parts become "0".

[0025] The wavelength control unit 130 sets a partial region on the binary image based on the face detection result of the face detection unit 160 and the centroid detection result of the centroid detection unit 150a. The partial region is assumed to include at least both of the user's eyes. The wavelength control unit 130 calculates the ratio of pixels whose value is "1" (pixels in dark areas) among all pixels included in the partial region. When the ratio of pixels whose value is "1" is equal to or greater than a predetermined ratio, the wavelength control unit 130 selects a wavelength such that the ratio of pixels whose value is "1" is less than the predetermined ratio.

[0026] For example, there are a plurality of wavelength selection candidates. The wavelengths of the selection candidates are assumed to be within the near-infrared wavelength range (0.75 to 1.4 μm). The wavelength control unit 130 selects one of the selection candidate wavelengths and outputs the selection result to the wavelength selection unit 140a of the near-infrared light emission unit 140.

[0027] Incidentally, the wavelength control unit 130 may select a wavelength based on a table in which the user's characteristics are associated with selection candidates. The user's characteristics correspond to the user's race, eye color, etc. It is assumed that information regarding the user's characteristics is designated in advance by an input device (not shown) or the like.

[0028] The near-infrared light emitter 140 is a device that irradiates the user with near-infrared light. The near-infrared light emitter 140 corresponds to the near-infrared light emitting device 5 described in Fig. 1. The wavelength of the near-infrared light emitted by the near-infrared light emitter 140 is switched by a wavelength selection unit 140a.

[0029] The irradiation intensity of the near-infrared light emitted by the near-infrared light emitter 140 depends on the magnitude of the current (voltage) output from the light emission control unit 120. That is, the larger the current, the greater the irradiation intensity of the near-infrared light emitted by the near-infrared light emitter 140.

[0030] The wavelength selection unit 140a is a processing unit that switches the wavelength of the near-infrared light emitted by the near-infrared light emission unit 140 based on the result of the wavelength selection output from the wavelength control unit .

[0031] The image sensor 150 is, for example, a complementary metal oxide semiconductor (CMOS) sensor. Other sensors such as a charge coupled device (CCD) may be used as the image sensor 150. The image sensor 150 captures an image of a user positioned in front of the display 3, more specifically, the periphery of the user's face, and acquires the captured image. The captured image acquired by the image sensor 150 is output after being A / D (Analog to Digital) converted.

[0032] Although not shown in the figure, an A / D converter or the like may be mounted on the image sensor 150, or may be provided between the image sensor 150 and the face detection unit 160. Note that the image sensor 150 according to the embodiment is configured to be capable of capturing images at a high frame rate. As an example, the image sensor 150 is capable of capturing images at 1000 fps (frames per second) or more. In the embodiment, the image sensor 150 is described as being capable of capturing images at 1000 fps.

[0033] Here, the captured image includes an IR band captured image and a visible light captured image. In the following description, an IR band captured image is referred to as an "IR captured image." A visible light captured image is referred to as a "visible light captured image."

[0034] Fig. 5 is a diagram for explaining captured images according to this embodiment. In the example shown in Fig. 5, the visible light captured image is a visible light captured image 30a, and the IR captured image is an IR captured image 30b.

[0035] The face detection unit 160 performs face detection based on the captured image (visible light captured image) acquired by the image sensor 150, and detects the user's face frame, left eye coordinates, and right eye coordinates. The face detection unit 160 outputs the face detection result to the distance measurement unit 110, the center of gravity detection unit 150a, and the selection unit 170. The face detection unit 160 can detect the face (face frame, left eye coordinates, right eye coordinates) using a known method such as a method using image features.

[0036] The face detection unit 160 may not be able to detect the left or right eye from the captured image if the distance between the user and the image sensor 150 is too far. If the face detection unit 160 fails to detect the left or right eye, it outputs face frame information to the distance measurement unit 110, the center of gravity detection unit 150a, and the selection unit 170 as a face detection result.

[0037] The image sensor 150 includes a center of gravity detection unit 150a. The center of gravity detection unit 150a is a processing unit that detects the center of gravity of the pupils and irises within the face frame based on the face detection result output from the face detection unit 160. For example, the center of gravity detection unit 150a uses the face detection result as a clue to identify the positions of the pupils and irises on the captured image (IR captured image) and calculates the center of gravity positions of the pupils or irises of the left and right eyes. The center of gravity detection unit 150a outputs the center of gravity detection result to the wavelength control unit 130 and the selection unit 170. The center of gravity detection unit 150a may be located outside the image sensor 150.

[0038] The selection unit 170 is a processing unit that selects either the face detection result or the center of gravity detection result based on the distance value output from the distance measurement unit 110. For example, the selection unit 170 selects the face detection result when the distance value is equal to or greater than a threshold. The selection unit 170 outputs the coordinates of the left eye and the coordinates of the right eye included in the face detection result to the parallax image processing unit 20 as information on the viewpoint position.

[0039] On the other hand, if the distance value is less than the threshold, the selection unit 170 selects the center of gravity detection result. The selection unit 170 outputs information about the center of gravity (the center of gravity of the pupil or the iris) to the parallax image processing unit 20 as information about the viewpoint position.

[0040] Meanwhile, the selection unit 170 may set a first threshold value and a second threshold value and select either the face detection result or the center of gravity detection result. FIG. 6 is a diagram for explaining other processing of the selection unit 170 according to the embodiment. The axis shown in FIG. 6 is an axis corresponding to the distance value. A first threshold value and a second threshold value are set on the axis corresponding to the distance value, and the first threshold value is smaller than the second threshold value.

[0041] The selection unit 170 selects the center of gravity detection result when the distance value acquired from the distance measurement unit 110 is less than the first threshold value. The selection unit 170 selects the face detection result when the distance value acquired from the distance measurement unit 110 is equal to or greater than the second threshold value.

[0042] When the distance value acquired from the distance measuring unit 110 is equal to or greater than the first threshold and less than the second threshold, the selection unit 170 refers to the face detection result and determines whether or not the left eye coordinates and the right eye coordinates have been detected by the face detection unit 160. When the left eye coordinates and the right eye coordinates have been detected by the face detection unit 160, the selection unit 170 selects the face detection result. When either the left eye coordinates or the right eye coordinates has not been detected, the selection unit 170 selects the center of gravity detection result.

[0043] [1.4 Tracking device processing procedure] Next, the processing procedure of the tracking device 100 of this embodiment will be described. Fig. 7 is a flowchart showing the processing procedure of the tracking device of this embodiment. The processing procedure described in Fig. 7 shows an example of a processing procedure for adjusting the light of the near-infrared light emitter 140 in conjunction with a distance value. The distance measuring unit 110 of the tracking device 100 calculates the distance value based on the interocular distance (step S101).

[0044] If the distance value is not within the switching distance range (step S102, No), the light emission control unit 120 of the tracking device 100 ends the process. On the other hand, the light emission control unit 120 calculates the magnitude of the current (current value) according to the distance value.

[0045] If the current value is not equal to or less than the current value Amax (step S104, No), the light emission control unit 120 outputs a current and voltage corresponding to the current value Ad to the near-infrared light emitter 140 (step S105), and proceeds to step S107. On the other hand, if the current value is equal to or less than the current value Amax (step S104, Yes), the light emission control unit 120 outputs a current and voltage corresponding to the distance value to the near-infrared light emitter 140 (step S106), and proceeds to step S107.

[0046] The wavelength selection unit 140a of the tracking device 100 determines whether or not to switch the wavelength based on the selection result of the wavelength control unit 130 (step S107). If the wavelength selection unit 140a decides to switch the wavelength (step S107, Yes), it changes the wavelength (step S108) and proceeds to step S109. On the other hand, if the wavelength selection unit 140a decides not to switch the wavelength (step S107, No), it proceeds to step S109.

[0047] The near-infrared light emitter 140 irradiates near-infrared light according to the current (voltage) input to the emission controller 120 and the wavelength selected by the wavelength selector 140a (step S109). The center of gravity detector 150a of the tracking device 100 outputs the center of gravity detection result to the selector 170 (step S110).

[0048] [1.5 Effect of tracking devices] Next, the effects of the tracking device 100 according to this embodiment will be described. The tracking device 100 controls the amount of light emitted by the near-infrared light emitter 140 based on the distance value between the user and the near-infrared light emitter 140, and detects the feature points of the user based on the image captured by the image sensor 150. This allows the user's viewpoint position to be tracked appropriately.

[0049] As the distance value increases, tracking device 100 increases the irradiation intensity of near-infrared light emitter 140. This makes it possible to accurately detect the user's viewpoint position even if the distance to the user increases.

[0050] When adjusting the magnitude of the current input to the near-infrared light emitter 140 based on the distance value, the tracking device 100 prevents the magnitude of the current from exceeding an upper limit value. This prevents the irradiation intensity of the near-infrared light emitter 140 from becoming too high, and meets the requirements of the photobiological safety standards JIS C 7550 and IEC 62471. In addition, it is possible to control the irradiation of near-infrared light so that the user's face does not become overexposed.

[0051] When the distance value is less than the threshold, the tracking device 100 selects the center of gravity detection result as the viewpoint position, and when the distance value is equal to or greater than the threshold, the tracking device 100 selects the face detection result as the viewpoint position. This allows more responsive center of gravity position information to be used when the user is nearby. Also, when the user is far away, the face detection result can be used to perform fast and stable viewpoint tracking.

[0052] [2. Hardware configuration] The tracking device according to each embodiment described above is realized, for example, by a computer 200 configured as shown in Fig. 8. The tracking device 100 according to the embodiment will be described below as an example. Fig. 8 is a hardware configuration diagram showing an example of a computer 200 that realizes the functions of the tracking device. The computer 200 has a CPU 201 that executes various arithmetic processes, an input device 202 that accepts data input from a user, and a display 203. The computer 200 also has an interface 204 for connecting to various devices.

[0053] The interface 204 is connected to a near-infrared light emitting device, a camera (image sensor), a parallax image processing unit, and the like.

[0054] The hard disk device 206 has an image processing program 206a. The CPU 201 reads out the image processing program 206a and loads it in the RAM 205. The image processing program 206a functions as an image processing process 205a.

[0055] The processing of the image processing process 205a corresponds to the processing of the distance measurement section 110, the emission control section 120, the wavelength control section 130, the wavelength selection section 140a, the center of gravity detection section 150a, the face detection section 160, and the selection section 170 described in FIG.

[0056] It should be noted that image processing program 206a does not necessarily have to be stored in hard disk device 206 from the beginning. For example, each program may be stored in a "portable physical medium" such as a flexible disk (FD), CD-ROM, DVD disk, magneto-optical disk, or IC card that is inserted into computer 200. Then, computer 200 may read and execute image processing program 206a.

[0057] [3. Conclusion] The image processing device has a light emitting unit, a light emitting control unit, and a detection unit. The light emitting unit irradiates an object with near-infrared light. The light emitting control unit controls the amount of light emitted by the light emitting unit based on a distance value between the object and the light emitting unit. The detection unit detects feature points based on a captured image of the object irradiated with the near-infrared light. The detection unit detects feature points related to the face of the object based on the captured image. The left eye and right eye of the object are detected as feature points based on the captured image. This makes it possible to appropriately track the user's viewpoint position.

[0058] The image processing device further includes a center of gravity detection unit that detects the center of gravity of the pupil or iris of the object. With this, even if the imaging device cannot detect the feature amount of the object, the center of gravity of the pupil or iris of the object can be detected and the user's viewpoint position can be tracked.

[0059] The image processing device includes a distance measuring unit, and the distance measuring unit further includes a distance measuring unit that calculates a distance value based on the distance between feature points included in the captured image. This makes it possible to calculate the distance value from the captured image without using a distance sensor or the like.

[0060] The light emission control unit of the image processing device specifies the magnitude of the current according to the distance value, and controls the amount of light emitted by the light emission unit by outputting a current of the specified magnitude to the light emission unit. The light emission control unit of the image processing device specifies the magnitude of the current according to the distance value, and when the magnitude of the current is greater than a threshold value, corrects the specified magnitude of the current to a magnitude less than the threshold value, and outputs a current of the corrected magnitude to the light emission unit. This makes it possible to irradiate near-infrared light of a safe intensity to the user.

[0061] The image processing device has a selection unit, and the selection unit selects one of the detection results of the detection unit and the center of gravity detection unit. The selection unit selects one of the detection results of the detection unit and the center of gravity detection unit based on the detection results of the detection unit and the center of gravity detection unit. This makes it possible to quickly and stably track the user's viewpoint position.

[0062] The selection unit outputs the selected detection result to a device that generates a stereoscopic image, thereby making it possible to display an appropriate stereoscopic image to the user.

[0063] The image processing device further includes a wavelength control unit that controls the wavelength of the near-infrared light emitted by the light emitting unit based on the detection result of the detection unit, thereby making it possible to stably execute the process of detecting the center of gravity of the pupil or iris of the object.

[0064] It should be noted that the effects described in this specification are merely examples and are not limiting, and other effects may also be obtained.

[0065] The present technology can also be configured as follows. (1) A light emitting unit that irradiates a target object with near-infrared light; a light emission control unit that controls an amount of light emitted by the light emission unit based on a distance value between the object and the light emission unit; a detection unit that detects feature points based on a captured image of the object irradiated with the near-infrared light; An image processing device comprising: (2) The image processing device according to (1), wherein the detection unit detects feature points relating to the face of the object based on the captured image. (3) The image processing device according to (2) above, wherein the detection unit detects the left eye and the right eye of the object as feature points based on the captured image. (4) The image processing device according to (3) above, further comprising a center of gravity detection unit for detecting the center of gravity of the pupil or iris of the object. (5) The image processing device according to (4) above, further comprising a distance measuring unit that calculates the distance value based on a distance between feature points included in the captured image. (6) The image processing device described in (1) is characterized in that the light emission control unit specifies a magnitude of a current corresponding to the distance value and controls the amount of light emitted by the light emission unit by outputting a current of the specified magnitude to the light emission unit. (7) The image processing device described in (6) is characterized in that the light emission control unit determines a magnitude of current corresponding to the distance value, and if the magnitude of current is greater than a threshold, corrects the determined magnitude of current to a magnitude less than the threshold, and outputs a current of the corrected magnitude to the light emission unit. (8) The image processing device described in (5) is characterized in that it further has a selection unit that selects either the detection result of the detection unit or the detection result of the center of gravity detection unit based on the distance value. (9) The image processing device described in (8) is characterized in that the selection unit selects one of the detection results of the detection unit and the detection result of the center of gravity detection unit based on the detection result of the detection unit and the detection result of the center of gravity detection unit. (10) The image processing device according to any one of (1) to (8), wherein the selection unit outputs the selected detection result to a device that generates a stereoscopic image. (11) The image processing device according to any one of (1) to (10), further comprising a wavelength control unit that controls the wavelength of the near-infrared light irradiated by the light emitting unit based on the detection result of the detection unit. (12) The computer controlling the amount of light emitted by the light-emitting device based on a distance value between the object and the light-emitting device that irradiates the object with near-infrared light; Detecting feature points based on a captured image of the object irradiated with the near-infrared light. The image processing method to perform the process. (13) Computer, a light emission control unit that controls an amount of light emitted by a light emitting device that irradiates near-infrared light onto the object based on a distance value between the object and the light emitting device; A detection unit that detects feature points based on a captured image of the object irradiated with the near-infrared light. An image processing program to make it function as a [Explanation of symbols]

[0066] 100 Tracking Device 110 Ranging section 120 Light emission control unit 130 Wavelength control section 140 Near-infrared light emitting unit 140a Wavelength selection section 150 Image Sensor 150a Center of gravity detection unit 160 Face detection unit 170 Selection Section

Claims

1. A face detection unit that detects feature points related to the face of a target person based on a visible light image captured by an image sensor; a center of gravity detection unit that detects a center of gravity of a pupil or an iris of the object based on the visible light captured image; a distance measuring unit that calculates a distance between the object and a near-infrared light emitting unit that irradiates the object with near-infrared light based on the distance between the feature points; a selection unit that selects a viewpoint position of the object corresponding to either one of the detection results of the face detection unit and the detection result of the center of gravity detection unit based on the distance value; a light emission control unit that controls the amount of light emitted by the near-infrared light emitter based on the distance value; An image processing device comprising:

2. The image processing device according to claim 1, characterized in that the light emission control unit specifies a magnitude of a current corresponding to the distance value and outputs a current of the specified magnitude to the near-infrared light emission unit, thereby controlling the amount of light emitted by the near-infrared light emission unit.

3. The image processing device described in claim 2, characterized in that the light emission control unit specifies a magnitude of a current corresponding to the distance value, and if the magnitude of the current is greater than a threshold value, corrects the specified magnitude of the current to a magnitude less than the threshold value, and outputs a current of the corrected magnitude to the near-infrared light emission unit.

4. 2. The image processing device according to claim 1, wherein the selection unit selects one of the detection results of the face detection unit and the detection result of the center of gravity detection unit based on the detection result of the face detection unit and the detection result of the center of gravity detection unit.

5. The image processing device according to claim 1 , wherein the selection unit outputs the selected detection result to a device that generates a stereoscopic image.

6. 2. The image processing apparatus according to claim 1, further comprising a wavelength control unit that controls a wavelength of the near-infrared light emitted by the near-infrared light emitting unit based on a detection result of the face detection unit.

7. The computer Detecting facial feature points of the target person based on the visible light captured image acquired by the image sensor; Detecting a center of gravity of a pupil or an iris of the object based on the visible light captured image; calculating a distance value between the object and a near-infrared light emitting unit that irradiates the object with near-infrared light based on the distance between the feature points; selecting a viewpoint position of the object corresponding to either one of the face detection result and the center of gravity detection result based on the distance value; The amount of light emitted by the near-infrared light emitting unit is controlled based on the distance value. An image processing method to perform the processing.

8. Computer, a face detection unit that detects feature points related to the face of a target person based on a visible light captured image acquired by an image sensor; a center of gravity detection unit that detects a center of gravity of a pupil or an iris of the object based on the visible light captured image; a distance measuring unit that calculates a distance between the object and a near-infrared light emitting unit that irradiates the object with near-infrared light based on the distance between the feature points; a selection unit that selects a viewpoint position of the object corresponding to either one of the detection results of the face detection unit and the detection result of the center of gravity detection unit based on the distance value; a light emission control unit that controls the amount of light emitted by the near-infrared light emitting unit based on the distance value; An image processing program to make it function as a

Images