Information processing device, information processing method, and recording medium

Abstract

This information processing device comprises: an acquisition means for acquiring, on the basis of a camera image generated by a camera provided at a position where a specific body part of a pedestrian serving as an imaging target can be imaged and distance information from the position of the specific body part to the camera, transition information that indicates the transition of the position of the specific body part in the three-dimensional space; an angle estimation means for estimating, on the basis of the transition information, a camera angle which is an angle formed by the optical axis of the camera and an axis parallel to the traveling direction of the pedestrian; a position estimation means for estimating the transition of the positions of the eyes of the pedestrian on the basis of the transition information and the camera angle; and an image acquisition means for acquiring, on the basis of the estimated transition of the positions of the eyes, an eye image obtained by imaging the eyes.

Description

Information Processing Apparatus, Information Processing Method, and Recording Medium

[0001] This disclosure relates to the technical field of information processing apparatuses, information processing methods, and recording media.

[0002] Techniques for imaging a part of a living body (e.g., face, iris, etc.) used in biometric authentication processing are known. For example, Patent Document 1 discloses acquiring movement information regarding movement in at least a part of an object, estimating periodicity regarding movement in at least a part of the object based on the movement information, and controlling a camera that images the object based on the periodicity.

[0003] Japanese Patent No. 7371762

[0004] This disclosure aims to provide an information processing apparatus, an information processing method, and a recording medium for improving the related techniques described above.

[0005] One aspect of the information processing apparatus of this disclosure includes an acquisition unit that acquires transition information indicating the transition of the position of a specific part in a three-dimensional space based on a camera image generated by a camera installed at a position where a specific part of a pedestrian as an imaging target can be imaged and distance information from the position of the specific part to the camera; an angle estimation unit that estimates a camera angle, which is an angle formed by an axis parallel to the traveling direction of the pedestrian and the optical axis of the camera, based on the transition information; a position estimation unit that estimates the transition of the position of the eyes of the pedestrian based on the transition information and the camera angle; and an image acquisition unit that acquires an eye image obtained by imaging the eyes based on the estimated transition of the position of the eyes.

[0006] One aspect of the information processing method disclosed herein includes: obtaining transition information showing the change in the position of a specific part of a pedestrian, which is the target of imaging, based on a camera image generated by a camera installed at a position capable of imaging a specific part of the pedestrian, and distance information from the position of the specific part to the camera; estimating a camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; estimating the change in the position of the pedestrian's eyes based on the transition information and the camera angle; and obtaining an eye image of the eyes based on the estimated change in the position of the eyes.

[0007] One aspect of the recording medium of this disclosure contains a computer program that causes a computer to execute an information processing method including: acquiring a camera image generated by a camera installed at a position capable of imaging a specific part of a pedestrian who is the subject of imaging, and transition information showing the change in the position of the specific part in three-dimensional space based on distance information from the position of the specific part to the camera; estimating a camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; estimating the change in the position of the pedestrian's eyes based on the transition information and the camera angle; and acquiring an eye image of the eyes based on the estimated change in the position of the eyes.

[0008] This is a block diagram illustrating an example of the configuration of the information processing device related to this disclosure. This is a flowchart illustrating an example of the flow of information processing operations in the information processing device related to this disclosure. This is a block diagram illustrating an example of the configuration of the information processing device related to this disclosure. This is a schematic diagram illustrating an example of a scenario in which the information processing device related to this disclosure is applied. This is a schematic diagram illustrating an example of a scenario in which the information processing device related to this disclosure is applied. This is a flowchart illustrating an example of the flow of information processing operations in the information processing device related to this disclosure. This is a diagram illustrating an example of information processing operations in the information processing device related to this disclosure. This is a diagram illustrating an example of information processing operations in the information processing device related to this disclosure. This is a block diagram illustrating an example of the configuration of the information processing device related to this disclosure. This is a block diagram illustrating an example of the configuration of the information processing device related to this disclosure.

[0009] The following describes embodiments of the information processing device, information processing method, and recording medium with reference to the drawings. [1: First Embodiment]

[0010] A first embodiment relating to an information processing device, an information processing method, and a recording medium will be described with reference to Figures 1 and 2. In the following description, the first embodiment relating to an information processing device, an information processing method, and a recording medium will be described using the information processing device 10.

[0011] The information processing device 10 controls the imaging of pedestrians' eyes. As shown in Figure 1, the information processing device 10 comprises an acquisition unit 11, an angle estimation unit 12, a position estimation unit 13, and an image acquisition unit 14. The operations performed by the information processing device 10 will be explained with reference to the flowchart in Figure 2.

[0012] As shown in Figure 2, the acquisition unit 11 acquires transition information showing the transition of the position of a specific part of the pedestrian in three-dimensional space (step S11). The pedestrian is the subject of imaging. The specific part may be a part whose position changes in the same way as the pedestrian's eyes. Therefore, the specific part may be the pedestrian's eyes.

[0013] The acquisition unit 11 acquires transition information based on the camera image and distance information. The camera image is an image generated by a camera installed at a position capable of capturing a specific part of a pedestrian. In other words, the camera image includes information about the position of the specific part of the pedestrian in a two-dimensional space perpendicular to the optical axis of the camera. The distance information is information indicating the distance from the position of the specific part of the pedestrian to the camera. In other words, the distance information includes information about the position of the specific part of the pedestrian in the optical axis direction of the camera. Therefore, the acquisition unit 11 can acquire transition information based on the camera image and distance information. The transition information may be, for example, time-series data in three-dimensional coordinates.

[0014] The angle estimation unit 12 estimates the camera angle based on the transition information acquired by the acquisition unit 11 (step S12). The camera angle is the angle between the axis parallel to the pedestrian's direction of travel and the optical axis of the camera.

[0015] The position estimation unit 13 estimates the change in the pedestrian's eye position based on the change information and camera angle (step S13). The image acquisition unit 14 acquires an eye image of the pedestrian based on the estimated change in the pedestrian's eye position (step S14).

[0016] Thus, the information processing device 10 performs an information processing method that includes acquiring transition information showing the change in the position of a specific part of a pedestrian in three-dimensional space, based on a camera image generated by a camera installed at a position capable of capturing a specific part of the pedestrian that is the target of imaging, and distance information from the position of the specific part of the pedestrian to the camera; estimating the camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; estimating the change in the position of the pedestrian's eyes based on the transition information and the camera angle; and acquiring an eye image of the pedestrian's eyes based on the estimated change in the position of the pedestrian's eyes.

[0017] The information processing device 10 described above may be implemented by a computer reading a computer program recorded on a recording medium. In this case, the computer program may cause the computer to execute an information processing method that includes: acquiring transition information showing the change in the position of a specific part of a pedestrian in three-dimensional space, based on a camera image generated by a camera installed at a position capable of imaging a specific part of the pedestrian, and distance information from the position of the specific part of the pedestrian to the camera; estimating the camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; estimating the change in the position of the pedestrian's eyes, based on the transition information and the camera angle; and acquiring an eye image of the pedestrian's eyes, based on the estimated change in the position of the pedestrian's eyes. [Technical Effects] Since the information processing device 10 according to this disclosure estimates the camera angle, it can estimate the change in the position of the pedestrian's eyes as seen from the camera with greater accuracy compared to the case where the camera angle is not estimated. [2: Second Embodiment]

[0018] A second embodiment relating to an information processing device, an information processing method, and a recording medium will be described with reference to Figures 3 to 10. Hereinafter, the second embodiment relating to the information processing device, an information processing method, and a recording medium will be described using the information processing device 20. Note that, in the second embodiment, explanations that overlap with the description of the first embodiment described above will be omitted as appropriate. [2-1: Configuration of the Information Processing Device 20]

[0019] The configuration of the information processing device 20 will be explained with reference to Figure 3. Figure 3 is a block diagram showing the configuration of the information processing device 20.

[0020] As shown in Figure 3, the information processing device 20 comprises an arithmetic unit 21 and a storage device 22. Furthermore, the information processing device 20 may also include a communication device 23, an input device 24, and an output device 25. However, the information processing device 20 does not have to include the communication device 23 and at least one of the input device 24 and the output device 25. The arithmetic unit 21, the storage device 22, the communication device 23, the input device 24, and the output device 25 may be connected via a data bus 26.

[0021] The arithmetic unit 21 includes at least one processor (i.e., one or more processors) as hardware. The processor may include, for example, a processor conforming to a von Neumann computer architecture. A processor conforming to a von Neumann computer architecture may include at least one of a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processor may also include, for example, a processor conforming to a non-von Neumann computer architecture. A processor conforming to a non-von Neumann computer architecture may include at least one of an FPGA (Field Programmable Gate Array) and an ASIC (Application Specific Circuit).

[0022] The arithmetic unit 21 reads a computer program 221 which includes at least one of computer program code and computer program instructions. For example, the arithmetic unit 21 may read a computer program 221 stored in a storage device 22. For example, the arithmetic unit 21 may read a computer program 221 stored in a computer-readable and non-temporary recording medium using a recording medium reader (not shown) provided in the information processing device 20. The computer program 221 read from the recording medium may be stored in the storage device 22. The arithmetic unit 21 may obtain (i.e., download or read) a computer program 221 from a device (not shown) located outside the information processing device 20 via a communication device 23 (or other communication device). The downloaded computer program 221 may be stored in the storage device 22.

[0023] The arithmetic unit 21 executes the loaded computer program 221. As a result, logical functional blocks for executing the information processing that the information processing device 20 should perform are realized within the arithmetic unit 21. In other words, the arithmetic unit 21, together with the storage device 22 on which the computer program 221 is recorded (in other words, together with the storage device 22 and the computer program 221 recorded in the storage device 22), can function as a controller or computer for realizing logical functional blocks for executing the processing that the information processing device 20 should perform. That is, together with at least one processor in the arithmetic unit 21, the memory (recording medium) in the storage device 22 and the computer program 221 are configured so that the information processing device 20 performs the information processing that the information processing device 20 should perform.

[0024] Furthermore, the recording medium for recording the computer program 221 executed by the arithmetic unit 21 may include at least one of the following: optical discs such as CD-ROM, CD-R, CD-RW, flexible disk, MO, DVD-ROM, DVD-RAM, DVD-R, DVD+R, DVD-RW, DVD+RW, and Blu-ray (registered trademark); magnetic media such as magnetic tape; magneto-optical disks; semiconductor memory such as USB memory; and any other medium capable of storing a program. The recording medium may also include equipment capable of recording computer programs (for example, general-purpose or dedicated equipment on which the computer program 221 is implemented in an executable state in at least one form such as software and firmware). Furthermore, each process and function included in the computer program 221 may be realized by logical processing blocks implemented within the arithmetic unit 21 (i.e., the processor) when the arithmetic unit 21 executes the computer program 221, or by hardware such as a predetermined gate array (FPGA (Field Programmable Gate Array), ASIC (Application Specific Integrated Circuit)) provided by the arithmetic unit 21, or in a form in which logical processing blocks and partial hardware modules that realize some elements of the hardware are mixed.

[0025] The storage device 22 includes at least one memory capable of storing desired data. In other words, the storage device 22 includes at least one memory containing desired data. For example, the storage device 22 may store a computer program 221 executed by the arithmetic unit 21. In this case, the storage device 22 (memory) may be used as the recording medium described above for recording the computer program 221 executed by the arithmetic unit 21. The storage device 22 may temporarily store data that the arithmetic unit 21 temporarily uses when the arithmetic unit 21 is executing the computer program 221. The storage device 22 may store data that the information processing device 20 stores long-term. The storage device 22 may include at least one of RAM (Random Access Memory), ROM (Read Only Memory), hard disk drive, magneto-optical disk drive, SSD (Solid State Drive), and disk array drive. In other words, the storage device 22 may include a non-temporary recording medium.

[0026] The communication device 23 may be capable of communicating with devices outside the information processing device 20. The communication device 23 may use either wired or wireless communication.

[0027] The input device 24 is a device capable of receiving information input to the information processing device 20 from an external source. The input device 24 may include an operating device (e.g., a keyboard, mouse, touch panel, etc.) that can be operated by the user of the information processing device 20. The input device 24 may include a recording medium reader capable of reading information recorded on a recording medium that can be attached to and detached from the information processing device 20, such as a USB (Universal Serial Bus) memory. When information is input to the information processing device 20 via the communication device 23 (in other words, when the information processing device 20 acquires information via the communication device 23), the communication device 23 may function as an input device.

[0028] The output device 25 is a device capable of outputting information to the outside of the information processing device 20. The output device 25 may output visual information such as characters and images, auditory information such as sounds, or tactile information such as vibrations. The output device 25 may include, for example, at least one of a display, a speaker, a printer, and a vibration motor. The output device 25 may also be capable of outputting information to a recording medium that can be attached to or detached from the information processing device 20, such as a USB memory stick. When the information processing device 20 outputs information via the communication device 23, the communication device 23 may function as an output device.

[0029] Figure 3 shows an example of a logical functional block implemented in the arithmetic unit 21 to perform eye image acquisition and iris authentication. As shown in Figure 3, the arithmetic unit 21 may include a transition information acquisition unit 211, an angle estimation unit 212, a position estimation unit 213, an eye image acquisition unit 214, and an iris authentication unit 215. The "transition information acquisition unit 211" is a component corresponding to the "acquisition unit 11" in the first embodiment described above, the "angle estimation unit 212" is a component corresponding to the "angle estimation unit 12" in the first embodiment described above, the "position estimation unit 213" is a component corresponding to the "position estimation unit 13" in the first embodiment described above, and the "eye image acquisition unit 214" is a component corresponding to the "image acquisition unit 14" in the first embodiment described above. The transition information acquisition unit 211 may include a camera image acquisition unit 2111 and a distance information acquisition unit 2112. The angle estimation unit 212 may include a period estimation unit 2121 and a moving average calculation unit 2122.

[0030] The information processing device 20 may be able to communicate with the camera 101, distance sensor 102, and iris camera 103 shown in Figures 4 and 5 via the communication device 23. Alternatively, the information processing device 20 may be equipped with the camera 101, distance sensor 102, and iris camera 103. [2-2: Overview of scenarios in which the information processing device 20 is applied]

[0031] The information processing device 20 captures images of pedestrians and performs biometric authentication. The information processing device 20 may acquire eye images of pedestrians as they walk towards the iris camera 103 and perform iris authentication using the eye images. The information processing device 20 may be applied, for example, to an authentication system that performs walk-through authentication.

[0032] As shown in Figure 4, pedestrians may walk along the shooting lane L. The direction of travel of pedestrians may be in the direction of the shooting lane L. As shown in Figure 4, the shooting lane L may be provided horizontally.

[0033] As shown in Figure 4, the camera 101 is positioned to capture specific parts of the pedestrian being photographed. The camera 101 may capture the entire body of the pedestrian. The camera 101 may capture only a part of the pedestrian. The camera 101 may continuously capture images to generate time-series data of camera images including specific parts of the pedestrian.

[0034] Camera 101 may be positioned such that its optical axis is horizontal. In other words, camera 101 may be positioned so that its optical axis coincides with an axis parallel to the direction of travel of the pedestrian. Camera 101 may be installed inside the housing 100. Camera 101 may be a visible light camera. Camera 101 may also be a near-infrared camera. Furthermore, there may be one camera 101 or multiple cameras 101.

[0035] The information processing device 20 acquires an eye image captured from the pedestrian's eyes. As described above, the specific part of the pedestrian may be a part that changes position in the same way as the pedestrian's eyes. The specific part of the pedestrian may be the pedestrian's head. The specific part of the pedestrian may be a part of the pedestrian's head. The specific part of the pedestrian may be the pedestrian's eyes. Below, as an example, we will explain the case where the specific part of the pedestrian is the pedestrian's eyes.

[0036] The distance sensor 102 generates distance information from a specific part of the pedestrian being imaged to the camera 101. The relative positions of the distance sensor 102 and the camera 101 may be fixed. The distance sensor 102 may be installed inside the housing 100. For example, the camera 101 and the distance sensor 102 may be fixed to the housing 100, and the relative positional relationship between the camera 101 and the distance sensor 102 may remain unchanged.

[0037] The iris camera 103 captures images of the pedestrian's eyes. The iris camera 103 is positioned to capture images of the pedestrian's eyes. The field of view of the iris camera 103 may be narrower than that of the camera 101. The iris camera 103 may be installed inside the housing 100. That is, as shown in Figure 4, the camera 101 and the iris camera 103 may be housed in the same housing. The relative positions of the iris camera 103 and the camera 101 may be fixed. For example, the camera 101 and the iris camera 103 may be fixed to the housing 100, and the relative positional relationship between the camera 101 and the iris camera 103 may remain unchanged. The iris camera 103 may be a near-infrared camera. The iris camera 103 may also be a visible light camera. Furthermore, there may be one iris camera 103 or multiple iris cameras 103.

[0038] If the optical axis of camera 101 is horizontal, then estimating the position of a pedestrian's eyes based on the assumption that the optical axis of camera 101 is horizontal will not likely result in the estimated eye position being different from the actually measured eye position. However, even if the optical axis of camera 101 was horizontal at the time of installation, it is possible that the optical axis of camera 101 may become non-horizontal after installation, as shown in Figure 5. For example, if the housing 100 tilts as shown in Figure 5, the orientation of camera 101 will tilt, and the optical axis of camera 101 will no longer be horizontal.

[0039] Even if the optical axis of camera 101 is not horizontal, if the position of the pedestrian's eyes is estimated assuming that the optical axis of camera 101 is horizontal, the estimated eye position may differ from the actually measured eye position. In this case, it becomes difficult to obtain an eye image suitable for iris authentication at the imaging point (i.e., the focal plane FP) of the iris camera 102. [2-3: Information processing method executed by information processing device 20]

[0040] The information processing device 20 in this embodiment takes into account the orientation of the optical axis of the camera 101 and estimates the position of the pedestrian's eyes as seen from the camera 101. That is, it estimates the position of the pedestrian's eyes as seen from the mechanism installed inside the housing 100. In other words, the information processing device 20 in this embodiment accurately estimates the positional changes of a specific part included in the image generated by the camera 101, even if the camera 101 is tilted. As a result, the information processing device 20 acquires an eye image suitable for iris authentication at the imaging point of the iris camera 102 (i.e., the focal plane FP) and performs iris authentication.

[0041] The information processing method performed by the information processing device 20 will be explained with reference to Figures 6 to 10. Figure 6 is a flowchart showing an example of the flow of the information processing method performed by the information processing device 20. Figures 7 to 10 are diagrams illustrating the information processing method performed by the information processing device 20.

[0042] The camera image acquisition unit 2111 acquires the camera image generated by the camera 101. The distance information acquisition unit 2112 acquires the distance information generated by the distance sensor 102. As shown in Figure 6, the transition information acquisition unit 211 acquires transition information based on the information acquired by the camera image acquisition unit 2111 and the distance information acquisition unit 2112 (step S21). The transition information shows the transition in three-dimensional space of the position of a specific part of the pedestrian that is the target of imaging (in this embodiment, the eyes).

[0043] The transition information may include three-dimensional coordinate information in time series. Further, the transition information may include information regarding the speed, acceleration, etc. of the movement. Also, the transition information acquisition unit 211 may acquire information other than the transition information. For example, an acceleration sensor may be provided inside the housing 100. In this case, the transition information acquisition unit 211 may acquire the detection result detected by the acceleration sensor.

[0044] Assume that the vertical movement of the pedestrian's eyes is periodic. The cycle estimation unit 2121 estimates the walking cycle of the pedestrian (step S22). The cycle estimation unit 2121 may estimate the walking cycle of the pedestrian from the transition of the position of a specific part of the pedestrian on the shooting lane L. The cycle estimation unit 2121 may obtain the walking cycle of the pedestrian based on the time series data of the position of a specific part of the pedestrian on the shooting lane L.

[0045] The cycle estimation unit 2121 may estimate the walking cycle using a preset rule. Or, the cycle estimation unit 2121 may estimate the walking cycle using a learned estimation engine.

[0046] When averaging the eye height in one cycle of the walking cycle, the eye height with respect to the traveling direction of the pedestrian ignoring the vertical movement of the eyes can be obtained. The moving average calculation unit 2122 calculates the average of the eye positions in one cycle of the walking cycle and obtains the moving average of the position of a specific part of the pedestrian (step S23). The moving average calculation unit 2122 may calculate the average value of the eye positions for one cycle in a sliding window method.

[0047] The angle estimation unit 212 estimates the camera angle based on the moving average (step S24). The angle estimation unit 212 may estimate the camera angle based on the transition information of the eye positions of the pedestrian for more than one and a half steps.

[0048] The solid line of the graph θ0 shown in FIG. 7 illustrates the transition of the height of a specific part when the camera angle is 0 degrees. Also, the solid line of the graph θ6 shown in FIG. 7 illustrates the transition of the height of a specific part when the camera angle is 6 degrees. That is, FIG. 7 illustrates that when the camera angle with respect to the horizontal plane changes, even if the transition of the height of the pedestrian's eyes is the same, the way the transition of the pedestrian's eyes is seen from the camera 101 changes. The graph θ0 shown in FIG. 7 illustrates the transition (solid line) of the height of a specific part and the moving average (dotted line) when the camera angle is 0 degrees. As illustrated by the dotted line of the graph θ0 shown in FIG. 7, when the camera angle is 0 degrees, the slope of the moving average is 0 degrees. Also, the graph θ6 shown in FIG. 7 illustrates the transition (solid line) of the height of a specific part and the moving average (dotted line) when the camera angle is 6 degrees. As illustrated by the dotted line of the graph θ6 shown in FIG. 7, when the camera angle is 6 degrees, the slope of the moving average is 6 degrees.

[0049] The position estimation unit 213 estimates the transition of the position of the pedestrian's eyes based on the transition information and the camera angle (step S25). The position estimation unit 213 may estimate how the position in the eye height direction changes. Also, the position estimation unit 213 may estimate how the position of the eyes in the horizontal plane changes. The position estimation unit 213 may obtain the amount of movement of the eyes with respect to the traveling direction of the pedestrian.

[0050] The position estimation unit 213 may estimate a model representing the position of the eyes (referred to as an "eye position model"). The eye position model may represent how the height of the pedestrian's eyes changes according to walking. The eye position model may represent how the height of the pedestrian's eyes captured by the camera 101 changes. Therefore, the eye position model may include a term related to the camera angle. Also, the eye position model may include a term related to the periodic movement of the eye position according to walking.

[0051] The eye position model may be represented, for example, by the following [Equation 1]: [Equation 1] y = Asin{(2π / T)t + α} + Bt + β In [Equation 1], y is the height of the eye, A is the amplitude, T is the period, t is a variable related to time, B is a coefficient related to the camera angle, and α and β are constant terms. The first term on the right-hand side of [Equation 1] is an example of a term related to the periodic movement of the eye position in response to walking, and the second term on the right-hand side of [Equation 1] is an example of a term related to the camera angle.

[0052] The eye image acquisition unit 214 acquires an eye image of the pedestrian's eye at the imaging point (i.e., the focal plane FP) of the iris camera 102 based on the estimated movement of the pedestrian's eye position (step S26). The eye image acquisition unit 214 may acquire an eye image from the iris camera 103. The eye image acquisition unit 214 may control the imaging range of the iris camera 103 based on the estimated height of the pedestrian's eye. The eye image acquisition unit 214 may determine how much to tilt the optical axis of the iris camera 103 relative to the optical axis of the camera 101. The eye image acquisition unit 214 may control the tilt of the optical axis of the iris camera 103 and take images. Note that the optical axis of the camera 101 and the optical axis of the iris camera 103 may be optical axes outside the housing 100. For example, the optical axis of the iris camera 103 may have different orientations inside and outside the housing 100 due to a reflective member such as a mirror.

[0053] The above describes an embodiment in which the position estimation unit 213 estimates how the position of the eye changes in the height direction and controls the tilt direction of the iris camera 103. In other words, in this embodiment, the tilt of the optical axis of the camera 101 in the vertical plane was estimated. In this embodiment, only the control of the tilt direction of the iris camera 103 was described, but the tilt of the optical axis of the camera 101 in the horizontal plane can be estimated in the same way, and the control of the pan direction of the iris camera 103 can be carried out in the same way.

[0054] Referring to Figures 8 to 10, we compare the case where the camera angle is estimated and the change in the pedestrian's eye position is estimated considering the camera angle, with the case where the change in the pedestrian's eye position is estimated without considering the camera angle. This can also be rephrased as a comparison between the case where the eye position model includes the second term on the right-hand side of [Equation 1] and the case where the eye position model does not include the second term on the right-hand side of [Equation 1].

[0055] For example, the transition information acquisition unit 211 may acquire information on the transition of a pedestrian's eyes from the camera 101 to a point 2200 mm away. In contrast, the position estimation unit 213 may estimate, for example, the height of the pedestrian's eyes at the focal plane FP 1700 mm away from the camera 101.

[0056] Graph θ0 in Figure 8 illustrates the estimated eye height when the camera angle is 0 degrees (dark line), the estimated eye height when the camera angle is not considered (light line), and the measured eye height (dot). When the camera angle is 0 degrees, the estimated results when the camera angle is considered (dark line) and the estimated results when the camera angle is not considered (light line) are close to the measured value (dot).

[0057] Furthermore, the facial image F0 in Figure 8 illustrates the imaging range of the iris camera 103 (solid line) based on estimation results that take into account the camera angle at the focal plane of the iris camera 103, and the imaging range of the iris camera 103 (dashed line) based on estimation results that do not take into account the camera angle at the focal plane of the iris camera 103. When the camera angle is 0 degrees, the imaging range of the iris camera 103 when the camera angle is taken into account (solid line) and the imaging range of the iris camera 103 when the camera angle is not taken into account (dashed line) are approximately the same.

[0058] Graph θ3 in Figure 9 illustrates the estimated result considering the camera angle (dark line), the estimated result without considering the camera angle (light line), and the measured value (point) when the camera angle is 3 degrees. When the camera angle is 3 degrees, the estimated result considering the camera angle (dark line) is close to the measured value (point), but the estimated result without considering the camera angle (light line) is far from the measured value (point).

[0059] Furthermore, the facial image F3 in Figure 9 illustrates the imaging range of the iris camera 103 (solid line) based on estimation results that take into account the camera angle at the focal plane of the iris camera 103, and the imaging range of the iris camera 103 (dashed line) based on estimation results that do not take into account the camera angle at the focal plane of the iris camera 103. When the camera angle is 3 degrees, the imaging range of the iris camera 103 when the camera angle is taken into account (solid line) will be different from the imaging range of the iris camera 103 when the camera angle is not taken into account (dashed line).

[0060] Graph θ6 in Figure 10 illustrates the estimated result considering the camera angle (dark line), the estimated result without considering the camera angle (light line), and the measured value (point) when the camera angle is 6 degrees. When the camera angle is 6 degrees, the estimated result considering the camera angle (dark line) is close to the measured value (point), but the estimated result without considering the camera angle (light line) is even further from the measured value (point) than when the camera angle is 3 degrees.

[0061] Furthermore, the facial image F6 in Figure 10 illustrates the imaging range of the iris camera 103 (solid line) based on estimation results that take into account the camera angle at the focal plane of the iris camera 103, and the imaging range of the iris camera 103 (dashed line) based on estimation results that do not take into account the camera angle at the focal plane of the iris camera 103. When the camera angle is 6 degrees, the imaging range of the iris camera 103 when the camera angle is taken into account (solid line) and the imaging range of the iris camera 103 when the camera angle is not taken into account (dashed line) are even more different than when the camera angle is 3 degrees.

[0062] The iris authentication unit 215 authenticates the pedestrian's iris using the eye image acquired by the eye image acquisition unit 214 (step S27). The iris authentication unit 215 may perform iris authentication by extracting feature quantities from the iris region included in the eye image acquired by the eye image acquisition unit 214 and comparing the extracted feature quantities with registered feature quantities. [2-4: Technical Effects]

[0063] For example, a walk-through iris recognition system detects pedestrians using a wide-angle camera and then adjusts the narrow field of view of a camera used for iris imaging to capture the pedestrian's iris. When imaging the iris using an iris recognition system, it is necessary to predict the height at which the pedestrian's eyes are located at the imaging point (i.e., the focal plane FP). Predicting the eye position requires camera position and orientation information, and this information is often used when the camera is installed. On the other hand, the camera's position and orientation may change during the operation of the iris recognition system. For example, if a person or object bumps into the camera, the camera's position and orientation may change. As a result, problems such as failure to capture eye images and failure of iris recognition may occur. In order to perform iris recognition, it is necessary to accurately predict the height at which the pedestrian's eyes are located at the imaging point, even if the camera's position and orientation change during the operation of the iris recognition system.

[0064] The information processing device 20 described in this disclosure estimates the camera angle, so even if, for example, a person or luggage bumps into the camera during the operation of the iris authentication system and the camera's position and orientation changes, it can accurately estimate the change in the position of the pedestrian's eyes as seen from the camera. As a result, the information processing device 20 can appropriately perform iris authentication. [3: Third Embodiment]

[0065] A third embodiment relating to an information processing device, an information processing method, and a recording medium will be described with reference to Figure 11. In the following description, the third embodiment relating to an information processing device, an information processing method, and a recording medium will be described using the information processing device 30. In the third embodiment, explanations that overlap with the descriptions of the first and second embodiments described above will be omitted as appropriate. In the drawings, parts common to the first and second embodiments will be denoted by the same reference numerals.

[0066] As shown in Figure 11, the arithmetic unit 21 of the information processing device 30 includes, as logical functional blocks, a transition information acquisition unit 311, an angle estimation unit 312, a position estimation unit 213, an iris authentication unit 215, another iris authentication unit 215, and a tilt detection unit 316.

[0067] In this embodiment, when the tilt of the optical axis of the camera 101 is detected, the angle estimation unit 312 estimates the camera angle. The tilt detection unit 316 may detect the possibility that the optical axis of the camera 101 is tilted by detecting the occurrence of a trigger event. In other words, the tilt detection unit 316 may detect that it is necessary to estimate the camera angle by detecting the occurrence of a trigger event. [Detection Example 1]

[0068] In detection example 1, a trigger event is considered to have occurred when the housing 100 is subjected to an impact. An acceleration sensor may be provided inside the housing 100. The transition information acquisition unit 311 may acquire the detection result detected by the acceleration sensor. In detection example 1, the tilt detection unit 316 may detect that the change in acceleration detected by the acceleration sensor inside the housing 100 exceeds a threshold, and that it is necessary to estimate the camera angle. [Detection Example 2]

[0069] The transition information acquisition unit 311 may acquire transition information by detecting the pedestrian's eyes from the camera image. In detection example 2, a trigger event is considered to have occurred in at least one of the following cases: when the detection of the pedestrian's eyes fails, or when it takes more than a predetermined time to detect the pedestrian's eyes. In detection example 2, the tilt detection unit 316 may detect that the detection of the pedestrian's eyes has failed, or that it has taken more than a predetermined time to detect the pedestrian's eyes, and detect that it is necessary to estimate the camera angle. [Detection Example 3]

[0070] In detection example 2, a trigger event is assumed to have occurred when iris authentication becomes more prone to failure. In detection example 3, the tilt detection unit 316 may detect that the frequency of iris authentication failures exceeds a threshold and that camera angle estimation is required. [Technical Effects]

[0071] The information processing device 30 according to this disclosure estimates the camera angle when it is necessary to estimate the camera angle, thereby reducing the processing load. [4: Fourth Embodiment]

[0072] A fourth embodiment relating to an information processing device, an information processing method, and a recording medium will be described with reference to Figure 14. In the following description, the fourth embodiment relating to an information processing device, an information processing method, and a recording medium will be described using the information processing device 40. In the fourth embodiment, explanations that overlap with the descriptions of the first to third embodiments described above will be omitted as appropriate. In the drawings, parts common to the first to third embodiments will be denoted by the same reference numerals.

[0073] As shown in Figure 12, the arithmetic unit 21 of the information processing device 40 includes, as logical functional blocks, a transition information acquisition unit 211, an angle estimation unit 412, a position estimation unit 413, an eye image acquisition unit 214, an iris authentication unit 215, and a tilt detection unit 316. The storage device 22 of the information processing device 40 may also store the camera angle 422 of the camera 101. Note that the camera angle of the camera 101 may be stored in a storage device other than the storage device 22. For example, the camera angle of the camera 101 may be stored in a storage device provided by an external device to the information processing device 20. The following describes the case where the camera angle 422 of the camera 101 is stored in the storage device 22.

[0074] In the fourth embodiment, the angle estimation unit 412 may estimate the camera angle of camera 101 based on the movement information of a predetermined number of pedestrians when a trigger event described in the third embodiment occurs. The angle estimation unit 412 may also store the estimated camera angle of camera 101 in the camera angle 422 in the storage device 22. The position estimation unit 413 may estimate the movement of the pedestrian's eye position based on the movement information and the camera angle 422 in the storage device 22.

[0075] The predetermined number may be 1. In this case, when a trigger event occurs, the angle estimation unit 412 may estimate the camera angle of camera 101 based on the movement information of one pedestrian and store the estimation result in the camera angle 422 in the storage device 22. The camera angle 422 in the storage device 22 may be corrected to "0", for example, when the posture of camera 101 is corrected.

[0076] The predetermined number may be two or more. In this case, when a trigger event occurs, the angle estimation unit 412 may estimate the camera angle of camera 101 based on the transition information of two or more predetermined pedestrians and store the estimation result in the camera angle 422 in the storage device 22. For example, the angle estimation unit 412 may estimate the camera angle of camera 101 for each predetermined number of pedestrians and store a representative value of the predetermined number of camera angles in the camera angle 422 in the storage device 22. The representative value of the predetermined number of camera angles may be determined based on the distribution of the predetermined number of camera angles. The representative value of the predetermined number of camera angles may also be the average result of the predetermined number of camera angles. By using multiple estimation results, an improvement in the accuracy of the camera angle can be expected. [Technical Effects]

[0077] As described above, the camera angle changes due to events such as a person or luggage bumping into the camera. Therefore, the changed camera angle often remains unchanged until the next event. The information processing device 40 disclosed herein retains the estimated camera angle and does not require the estimation of the camera angle for each pedestrian, thus reducing the processing load. [5: Note]

[0078] The embodiments described above may also be described as follows, but are not limited thereto. [Appendix 1] An information processing apparatus comprising: an acquisition means for acquiring transition information showing the transition of the position of a specific part of a pedestrian, which is the target of imaging, based on a camera image generated by a camera installed at a position capable of imaging a specific part of the pedestrian, and distance information from the position of the specific part to the camera; an angle estimation means for estimating a camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; a position estimation means for estimating the transition of the position of the pedestrian's eyes, based on the transition information and the camera angle; and an image acquisition means for acquiring an eye image of the eyes based on the estimated transition of the position of the eyes. [Appendix 2] The information processing apparatus according to Appendix 1, wherein the angle estimation means estimates the walking cycle of the pedestrian from the transition of the position of the specific part, calculates the average of the position of the specific part in one cycle of the walking cycle to obtain a moving average of the position of the specific part, and estimates the camera angle based on the moving average. [Note 3] The position estimation means estimates a model representing the position of the eye, and the model includes a term relating to the camera angle, as described in Note 1. [Note 4] The angle estimation means estimates the camera angle when a trigger event occurs, as described in Note 1. [Note 5] The camera housing is provided with an acceleration sensor, and the trigger event is the detection that the change in acceleration by the acceleration sensor exceeds a threshold, as described in Note 4. [Note 6] The acquisition means detects the specific part from the camera image and acquires the transition information, and the trigger event is the detection of at least one of the failure to detect the specific part and the detection of a predetermined time or longer in detecting the specific part, as described in Note 4. [Note 7] The information processing device according to Note 4, further comprising an authentication means for iris authentication using the eye image. [Note 8] The trigger event is the detection that the frequency of iris authentication failures exceeds a threshold, as described in Note 7.[Note 9] The angle estimation means is an information processing device according to Note 4, wherein when the trigger event occurs, the angle estimation means estimates the camera angle based on the transition information of a predetermined number of pedestrians. [Note 10] The information processing device according to Note 9, further comprising a camera angle storage means for storing the camera angle, wherein the position estimation means estimates the transition of the pedestrian's eye position based on the transition information and the camera angle stored in the camera angle storage means. [Note 11] An information processing method comprising: acquiring transition information showing the transition of the position of a specific part in three-dimensional space based on a camera image generated by a camera installed at a position capable of imaging a specific part of a pedestrian that is the target of imaging, and distance information from the position of the specific part to the camera; estimating a camera angle which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera based on the transition information; estimating the transition of the pedestrian's eye position based on the transition information and the camera angle; and acquiring an eye image of the eye based on the estimated transition of the eye position. [Note 12] A recording medium on which a computer program is recorded that causes a computer to execute an information processing method including: acquiring transition information showing the transition of the position of a specific part in three-dimensional space based on a camera image generated by a camera installed at a position capable of imaging a specific part of a pedestrian who is the target of imaging, and distance information from the position of the specific part to the camera; estimating a camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; estimating the transition of the position of the pedestrian's eyes based on the transition information and the camera angle; and acquiring an eye image of the eyes based on the estimated transition of the position of the eyes.

[0079] This disclosure may be modified as appropriate, insofar as it does not contradict the gist or idea of ​​the invention as can be inferred from the claims and the specification as a whole, and information processing devices, information processing methods, and recording media with such modifications are also included in the technical idea of ​​this disclosure.

[0080] 10, 20, 30, 40 Information processing device 11 Acquisition unit 12, 212, 312, 412 Angle estimation unit 13, 213, 413 Position estimation unit 14 Image acquisition unit 100 Housing 101 Camera 102 Distance sensor 103 Iris camera 211, 311 Transition information acquisition unit 2111 Camera image acquisition unit 2112 Distance information acquisition unit 2121 Period estimation unit 2122 Moving average calculation unit 214 Eye image acquisition unit 215 Iris authentication unit 316 Tilt detection unit

Claims

1. An information processing device comprising: acquisition means for acquiring transition information showing the transition of the position of a specific part of a pedestrian, which is the target of imaging, based on a camera image generated by a camera installed at a position capable of imaging a specific part of the pedestrian, and distance information from the position of the specific part to the camera; angle estimation means for estimating the camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; position estimation means for estimating the transition of the position of the pedestrian's eyes, based on the transition information and the camera angle; and image acquisition means for acquiring an eye image of the eyes based on the estimated transition of the eye position.

2. The information processing apparatus according to claim 1, wherein the angle estimation means estimates the walking cycle of the pedestrian from the change in the position of the specific part, calculates the average of the position of the specific part over one cycle of the walking cycle to obtain a moving average of the position of the specific part, and estimates the camera angle based on the moving average.

3. The information processing apparatus according to claim 1, wherein the position estimation means estimates a model representing the position of the eye, and the model includes a term relating to the camera angle.

4. The information processing apparatus according to claim 1, wherein the angle estimation means estimates the camera angle when a trigger event occurs.

5. The camera housing is provided with an acceleration sensor, and the trigger event is the detection of a change in acceleration detected by the acceleration sensor exceeding a threshold, as described in claim 4.

6. The information processing apparatus according to claim 4, wherein the acquisition means detects the specific part from the camera image and acquires the transition information, and the trigger event is the detection of at least one of the failure to detect the specific part and the detection of a predetermined time or longer in detecting the specific part.

7. The information processing apparatus according to claim 4, comprising authentication means for iris authentication using the aforementioned eye image.

8. The information processing apparatus according to claim 7, wherein the trigger event is the detection that the frequency of iris authentication failures exceeds a threshold.

9. The information processing apparatus according to claim 4, wherein the angle estimation means estimates the camera angle based on the transition information of a predetermined number of pedestrians when the trigger event occurs.

10. The information processing apparatus according to claim 9, comprising a camera angle storage means for storing the camera angle, wherein the position estimation means estimates the change in the position of the pedestrian's eyes based on the change in information and the camera angle stored in the camera angle storage means.

11. An information processing method comprising: acquiring transition information showing the change in the position of a specific part of a pedestrian, which is the target of imaging, based on a camera image generated by a camera installed at a position capable of imaging a specific part of the pedestrian, and distance information from the position of the specific part to the camera; estimating a camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; estimating the change in the position of the pedestrian's eyes based on the transition information and the camera angle; and acquiring an eye image of the eyes based on the estimated change in the position of the eyes.

12. A recording medium on which a computer program is stored that causes a computer to execute an information processing method including: acquiring transition information showing the change in the position of a specific part of a pedestrian, which is the target of imaging, based on a camera image generated by a camera installed at a position capable of imaging a specific part of the pedestrian, and distance information from the position of the specific part to the camera; estimating a camera angle, which is the angle between an axis parallel to the direction of travel of the pedestrian and the optical axis of the camera, based on the transition information; estimating the change in the position of the pedestrian's eyes, based on the transition information and the camera angle; and acquiring an eye image of the eyes, based on the estimated change in the position of the eyes.

Images