Information processing device, information processing method, and program

Abstract

The present technology pertains to an information processing device, an information processing method, and a program that make it possible to reduce power consumed in authentication using a plurality of imaging devices. The information processing apparatus performs an imaging apparatus search process of searching for an imaging apparatus suitable for authentication of a target among non-activated imaging apparatuses that have not been activated, based on a position and an angle of the target estimated from an image captured by an activated imaging apparatus, which is an activated imaging apparatus among a plurality of imaging apparatuses; and activating the camera device found by searching. This technology can be applied to a face authentication system.

Description

Technical Field

[0001] The present technology relates to an information processing device, an information processing method, and a program, and particularly to an information processing device, an information processing method, and a program that allow reduction in power consumption in authentication using a plurality of imaging devices. Background Art

[0002] It is known that in facial recognition, using a plurality of cameras to capture facial images from various angles can improve recognition accuracy (see Patent Document 1).

[0003] Reference List

[0004] Patent Literature

[0005] [Patent Document 1]

[0006] JP 2004-192378A. Summary of the invention

[0007] Technical issues

[0008] Meanwhile, in usage scenarios such as a face recognition gate and a surveillance camera, since it is not known when a target for face recognition will appear, each camera must continuously perform a process of detecting a target.

[0009] If such a use case is implemented by using multiple cameras, the multiple cameras are continuously activated and perform face detection processing on each camera image, even if no object is detected most of the time. This is quite inefficient in terms of power consumption and device durability.

[0010] The present technology has been developed in view of such circumstances, and aims to reduce power consumption in authentication using a plurality of cameras.

[0011] Solution to the problem

[0012] According to one aspect of the present technology, an information processing device includes a control unit configured to perform the following camera device search processing: based on the position and angle of the target estimated from an image captured by an activated camera device which is an activated camera device among multiple cameras, searching for a camera device suitable for authentication of the target among inactivated cameras that have not yet been activated, and activating the camera device found by the search.

[0013] According to one aspect of the present technology, based on the position and angle of a target estimated from an image captured by an activated camera that is an activated camera among multiple cameras, a camera device suitable for authentication of the target is searched among inactivated cameras that have not yet been activated, and the camera device found by the search is activated. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a diagram of a configuration example of the appearance of a facial recognition system according to the first embodiment of the present technology.

[0015] Figure 2 yes Figure 1 A block diagram of an example of a functional configuration of a facial recognition system in FIG.

[0016] Figure 3 A configuration example of the camera configuration DB is shown.

[0017] Figure 4 An example of capturing an image by a camera module is shown.

[0018] Figure 5 It is used to illustrate Figure 1 Flowchart of the processing of the facial recognition system in FIG.

[0019] Figure 6 It is used to illustrate Figure 5 Flowchart of the camera module search process in step S11.

[0020] Figure 7 is Figure 6 FIG. 1 is a view of an example of the facial region detected in step S31.

[0021] Figure 8 3 is a diagram showing an example of the position and angle of the face estimated in step S33.

[0022] Fig. 9 yes Figure 6 FIG. 1 is a view of an example of the optimal camera module search in step S34.

[0023] Fig.10 It is used to illustrate Figure 5 Flowchart of the authentication process in step S12.

[0024] Fig.11 It is a schematic diagram of operations in a camera module and an information processing device of a facial recognition system.

[0025] Fig.12 This is a diagram for explaining how to set up a normally-on camera device.

[0026] Fig.13A configuration example of the appearance of a human authentication system according to a second embodiment of the present technology is shown.

[0027] Fig.14 yes Fig.13 A block diagram of an example of a functional configuration of a human authentication system in FIG.

[0028] Fig.15 is a diagram of a configuration example of a lens-less imaging device that forms an image without a lens.

[0029] Fig.16 is a view of a configuration example of the appearance of a wearable device according to a third embodiment of the present technology.

[0030] Fig.17 is a block diagram of a configuration example of a computer. DETAILED DESCRIPTION

[0031] Hereinafter, a mode for implementing the present technology will be described. The description will be made in the following order.

[0032] 1. First Embodiment (Face Recognition System)

[0033] 2. Second Embodiment (Human Body Authentication System)

[0034] 3. Third embodiment (wearable device)

[0035] 4. Others

[0036] 1. First Embodiment (Face Recognition System)

[0037] <Configuration of facial recognition system>

[0038] Figure 1 It is a diagram of a configuration example of the appearance of a facial recognition system according to the first embodiment of the present technology.

[0039] Figure 1 A in FIG. 1 is a front view of the appearance of the facial recognition system. Figure 1 B in FIG. 1 is a side view of the appearance of the facial recognition system.

[0040] Figure 1 The facial recognition system 1 in FIG. 1 is configured to include a door 12 provided with a plurality of camera modules 11 - 1 to 11 - 12 . The door 12 is usually locked and is unlocked when authentication is successfully performed by the facial recognition system 1 .

[0041] Camera modules 11-1 to 11-12 are arranged in three horizontal rows and four vertical columns on door 12. Camera module 11-1 is arranged on the left side in the bottom row. Camera module 11-2 is arranged at the center in the bottom row. Camera module 11-3 is arranged on the right side in the bottom row.

[0042] The camera module 11-4 is disposed on the left side in the second row from the bottom. The camera module 11-5 is disposed at the center in the second row from the bottom. The camera module 11-6 is disposed on the right side in the second row from the bottom.

[0043] The camera module 11-7 is disposed on the left side in the second row from the top. The camera module 11-8 is disposed at the center in the second row from the top. The camera module 11-9 is disposed on the right side in the second row from the top.

[0044] The camera module 11-10 is arranged on the left side in the top row. The camera module 11-11 is located in the center in the top row. The camera module 11-12 is arranged on the right side in the top row. When there is no need to distinguish the individual camera modules 11-1 to 11-12, these camera modules will be collectively referred to as the camera module 11.

[0045] At least one of the camera modules 11 (in Figure 1 In the embodiment, the camera module 11-8) is a normally-on camera and is always activated. The normally-on camera is preset in the camera module 11. The camera modules 11 other than the normally-on camera are usually in a stopped state. The stopped state may be a power-off state or a sleep state in which only some functions are activated.

[0046] The camera module 11 - 8 , which is an always-on camera, captures an image of the face of a user standing in front of the door 12 to enter the house, and waits for authentication by the facial recognition system 1 .

[0047] Figure 1 The imaging range 2 captured by the camera module 11-8 is shown, and the camera module is a normally-on camera. Figure 1 , represented by the base of the triangle with the camera module 11 - 8 at the vertex.

[0048] The camera module 11-8 extracts feature values ​​of the user's face using the captured image. However, in this example, the camera module 11-8 cannot capture the user's face at the center of its imaging range. Therefore, the accuracy of the feature values ​​extracted using the image captured by the camera module 11-8 may not be high.

[0049] Therefore, the facial recognition system 1 searches for any other camera module 11 that can capture an image of the user's face from the most frontal position based on the position and angle of the user's face estimated using the image captured by the activated camera module 11-8 (activated camera), and activates the camera module 11 found by the search. In this way, the camera module 11 suitable for authentication of the user's face is activated.

[0050] Then, the facial recognition system 1 controls the activated camera module 11 to extract feature values ​​of the user's face and authenticates the user's face based on facial feature value information indicating feature values ​​of the user's face provided by the camera module 11. When the user's face is authenticated, the door 12 that is normally locked is unlocked.

[0051] <Functional configuration of facial recognition system>

[0052] Figure 2 yes Figure 1 A block diagram of an example of a functional configuration of a facial recognition system in FIG.

[0053] exist Figure 2 In the embodiment, the facial recognition system 1 is configured to include a camera module 11 - 1 , a camera module 11 - 2 , . . . , an information processing device 21 , and a locking mechanism 22 .

[0054] The camera module 11 is configured to include an imaging unit 31 , a detection and estimation unit 32 , and a control unit 33 .

[0055] The imaging unit 31 captures an image of a subject and outputs a camera input image obtained by capturing the image of the subject to the detection and estimation unit 32 .

[0056] The detection and estimation unit 32 performs processing on the camera input image supplied from the imaging unit 31. The detection and estimation unit 32 is configured to include a face detection unit 42, a face part detection unit 43, a face image normalization unit 45, and a face feature value extraction unit 46.

[0057] The face detection unit 42 detects a face region from the camera input image supplied from the imaging unit 31 , and outputs the camera input image and face region information indicating the detected face region to the face part detection unit 43 .

[0058] Based on the camera input image and the facial region information provided by the facial detection unit 42, the facial part detection unit 43 detects facial part points indicating the positions of four facial features (ie, both eyes, nose and mouth) according to the facial region detected by the facial detection unit 42.

[0059] The face part detection unit 43 outputs the camera input image, the face region information, and the face part point information indicating the detected face part points to the position and angle estimation unit 44 and the face image normalization unit 45 .

[0060] The position and angle estimation unit 44 estimates the position of the face and the angle of the face using the camera input image, the face region information, and the face part point information supplied from the face part detection unit 43 .

[0061] The position and angle estimation unit 44 transmits information indicating the estimated position and angle of the face to the information processing device 21 to which its own camera ID (identifier) ​​is attached.

[0062] The facial image normalization unit 45 normalizes the facial image using the camera input image, facial region information, and facial part point information provided by the facial part detection unit 43. The facial image normalization unit 45 outputs the normalized facial image, facial region information, and facial part point information as the normalized facial image to the facial feature value extraction unit 46.

[0063] The facial feature value extraction unit 46 extracts facial feature values ​​using the normalized facial image, facial region information, and facial part point information provided by the facial image normalization unit 45. The facial feature value extraction unit 46 transmits facial feature value information indicating the extracted facial feature values ​​to the information processing device 21 together with its own camera ID.

[0064] The control unit 33 controls the various parts of the camera module 11 in response to the control from the information processing device 21. The control unit 33 also activates or stops the camera module 11 in response to the control from the information processing device 21. The activation of the camera module 11 may refer to the activation of each part of the camera module 11, that is, the activation of the imaging unit 31 and the detection and estimation unit 32, or the activation of the detection and estimation unit 32 when the imaging unit 31 has been activated.

[0065] The information processing apparatus 21 is configured to include an optimum camera configuration search unit 51 , a camera configuration DB (database) 52 , a facial feature value integration unit 53 , a facial matching unit 54 , and a registered facial feature value DB 55 .

[0066] The optimal camera configuration search unit 51 searches for a camera module 11 that is capable of capturing an image of the detected face from the most frontal position among the non-activated camera modules 11 by referring to the information indicating the position and angle of the face provided by the position and angle estimation unit 44 and the camera ID, and the information registered in the camera configuration DB 52.

[0067] The optimum camera configuration search unit 51 controls the control unit 33 of the camera module 11 found by the search to activate the camera module 11 .

[0068] The camera configuration DB 52 registers information on each camera module 11 .

[0069] The facial feature value integration unit 53 controls the control unit 33 of the activated camera module 11 to perform facial feature value extraction.

[0070] The facial feature value integration unit 53 performs integration of facial feature values ​​based on the facial feature value information and the camera ID provided by the facial feature value extraction unit 46. For example, the integration of facial feature values ​​is performed by summing and averaging the facial feature values. The facial feature value integration unit 53 outputs integrated facial feature value information indicating the integrated facial feature values ​​to the face matching unit 54.

[0071] The facial matching unit 54 refers to the information registered in the camera configuration DB 52, and matches the integrated facial feature value indicated by the integrated facial feature value information provided by the facial feature value integration unit 53 with the registered facial feature value registered in the registered facial feature value DB 55. The facial feature values ​​are matched by taking the dot product of two arrays, the integrated facial feature value and the registered facial feature value.

[0072] If the match is successful, the face matching unit 54 determines that the user's face has been successfully authenticated and unlocks the locking mechanism 22. If the match is successful, the face matching unit 54 also controls the control unit 33 of the camera module 11 other than the normally-on camera to stop the corresponding camera module 11.

[0073] The locking mechanism 22 is provided at the door 12. The locking mechanism 22 is locked by closing the door 12, and is unlocked in response to control of the face matching unit 54.

[0074] exist Figure 2 In the face recognition system 1 , the detection and estimation unit 32 is provided in each camera module 11 , but the detection and estimation unit 32 may be provided in the information processing device 21 .

[0075] <Configuration of Camera Configuration DB>

[0076] Figure 3 is a diagram showing a configuration example of a camera configuration DB.

[0077] The camera configuration DB 52 is configured to include information about each camera module 11, including camera ID, adjacent camera ID, installation position X, installation position Y, roll camera angle, pitch camera angle, yaw camera angle, and information about normally-on cameras and activation status.

[0078] The camera ID indicates identification information of the camera module 11. Figure 3 In this case, the camera device ID is 1.

[0079] The adjacent camera ID indicates identification information of the camera module 11 adjacent to the camera module 11 indicated by the camera ID. Figure 3 In this case, the adjacent camera device IDs are 2 and 4.

[0080] The installation position X and Y indicate the X coordinate and Y coordinate of the installation position of the camera module 11 indicated by the camera ID. For example, the lower left corner of the door 12 is used as the origin. Figure 3 In this case, the installation positions X and Y are 30 cm and 120 cm respectively.

[0081] The roll camera angle, the pitch camera angle, and the yaw camera angle represent the corresponding installation angles, roll, pitch, and yaw, of the camera module 11 indicated by the camera ID, respectively. Figure 3 , the roll camera angle, the pitch camera angle, and the yaw camera angle are all 0 degrees.

[0082] The information about the normally-on camera indicates whether the camera module 11 indicated by the camera ID is a normally-on camera. Figure 3 In the case of , the camera module 11 indicated by the camera ID is not a normally-on camera, and therefore the normally-on camera is set to No.

[0083] The activation state is information indicating the activation state of the camera module 11 indicated by the camera ID. Figure 3 In the case of , the activation state of the camera module 11 indicated by the camera ID is off. When the camera module 11 is activated, the activation state becomes on.

[0084] <Image Captured by Camera Module>

[0085] Figure 4 An example of an image captured by the camera module 11 is shown.

[0086] In the facial recognition system 1, when a user stands in front of the door 12 and waits to be authenticated by the facial recognition system 1 in order to enter the house, the activated camera module 11 captures the image of the user, as described above with reference to Figure 1 In Figure 4 In the example, the user is shown wearing a mask.

[0087] Figure 4 A in FIG. 6 shows an image 61 captured by the camera module 11 - 8 . In the center of the image 61 , the area between the eyebrows of the user's face captured from the front is shown.

[0088] Figure 4B in FIG. 6 shows an image 62 captured by the camera module 11-5. Since the camera module 11-5 is located directly below the camera module 11-8 at the door 12, the center of the image 62 shows the nose of the user's face captured from the front.

[0089] Figure 4 C in FIG. 1 shows an image 63 captured by the camera module 11 - 4 and an image 64 captured by the camera module 11 - 6 .

[0090] Since the camera module 11 - 4 is located on the left side of the camera module 11 - 5 at the door 12 , the center of the image 63 shows an image of the nose of the user's face captured diagonally from the left side.

[0091] Since the camera module 11 - 6 is located on the right side of the camera module 11 - 5 at the door 12 , the center of the image 64 shows an image of the nose of the user's face captured diagonally from the right side.

[0092] <Processing of facial recognition system>

[0093] Figure 5 It is used to illustrate Figure 1 Flowchart of the processing of the facial recognition system in FIG.

[0094] In combination with Figure 5 The description will refer to Figure 4 .

[0095] For example, a user stands in front of the door 12 to enter the house and waits for authentication by the facial recognition system 1 .

[0096] In step S11 , the facial recognition system 1 performs a camera module detection process.

[0097] At the start of the process, only at least one normally-on camera module 11 (eg, camera module 11-8) is activated. The position and angle of the user's face are estimated from the image captured by the camera module 11-8.

[0098] In the camera module search process, camera modules 11 to be activated (inactivated cameras) are activated until a camera module 11 capable of capturing a user's facial image from the most frontal position is found through a search based on the estimated position and angle of the user's face.

[0099] For example, according to the image 61A ( Figure 4 A) estimates the position and angle of the user's face, and searches to find the camera module 11-5 that can capture an image of the user's face from the most frontal position, such as image 61B ( Figure 4 As shown in B).

[0100] In step S12 , the facial recognition system 1 performs facial recognition processing.

[0101] The facial recognition system 1 first performs facial recognition using the camera module 11 found and activated by the search in step S11. If authentication using the activated camera module 11 is unsuccessful, the facial recognition system 1 sequentially activates the camera modules 11 surrounding the camera module 11 found in step S11, starting with the camera module 11 closest to the front, until facial recognition succeeds. The image captured by the activated camera module 11 is added as an image for authentication processing.

[0102] If, for example, an image captured by the camera module 11-5 is used as an image for authentication processing and authentication is unsuccessful, the camera module 11-4 near the camera module 11-5 is activated and the image 63 captured by the activated camera module 11-4 is added as an image for authentication processing.

[0103] If authentication is unsuccessful even in this case, the camera module 11 - 6 near the camera module 11 - 5 is activated, and the image 64 captured by the activated camera module 11 - 6 is added as an image for authentication processing.

[0104] As described above, images captured by the camera module 11 at different positions are added as images used for authentication processing, thereby increasing the accuracy of face authentication.

[0105] For example, by adding facial images captured from multiple angles by different camera modules 11 to increase information about the face, the quality of facial images with occlusions (e.g. Figure 4 Authentication accuracy of the face wearing a mask as shown in .

[0106] When the face authentication process is successful, the process proceeds to step S13.

[0107] In step S13, the facial recognition system 1 stops the camera modules 11 except the normally-on camera modules. Figure 5 The processing in is completed.

[0108] <Camera Module Search Process>

[0109] Figure 6 It is used to illustrate Figure 5 Flowchart of the camera module search process in step S11.

[0110] When the processing starts, the imaging unit 31 of the camera module 11 (e.g., the camera module 11-8) as a normally-on camera captures an image of the user's face to generate a camera input image, and outputs the generated camera input image to the face detection unit 42.

[0111] In step S31 , the face detection unit 42 detects the face area of ​​the user in the camera input image. The camera input image and the detected face area information are output to the face part detection unit 43 .

[0112] In step S32, the face part detection unit 43 detects face part points in the face region detected by the face detection unit 42. The face part detection unit 43 outputs the camera input image, the face region information, and the face part point information to the position and angle estimation unit 44.

[0113] In step S33, the position and angle estimation unit 44 estimates the position and angle of the face based on the camera input image, the facial region information, and the facial part point information. The position and angle estimation unit 44 outputs information on the estimated position and angle of the face and the camera ID of the camera module 11-8 to the optimal camera configuration search unit 51 of the information processing device 21.

[0114] In step S34 , the optimal camera configuration search unit 51 searches for the optimal camera module 11 based on the information on the position and angle of the face provided by the position and angle estimation unit 44 and the camera ID of the camera module 11 - 8 , and the information registered in the camera configuration DB 52 .

[0115] In step S35 , the optimum camera configuration search unit 51 determines whether the camera module 11 found by the search is a new camera module 11 that has not yet been activated.

[0116] If it is determined in step S35 that the camera module 11 found by the search is a new camera module 11 that has not yet been activated, the process proceeds to step S36.

[0117] In step S36 , the optimum camera configuration search unit 51 controls the control unit 33 of the new camera module 11 to activate the new camera module 11 .

[0118] The imaging unit 31 of the camera module 11 as the normally-on camera and the new camera module 11 each generates a camera input image by capturing an image of the user's face, and outputs the generated camera input image to the face detection unit 42. Then, the process returns to step S31, and the subsequent processes are repeated in the activated camera module 11 and the information processing device 21.

[0119] If it is determined in step S35 that the camera module 11 found by the search is not a new camera module 11 that has not been activated, then Figure 6 The camera device module search process is completed.

[0120] <Detection of facial area and facial part points>

[0121] Figure 7 Shown in Figure 6 An example of the facial area detected in step S31.

[0122] Similar to Figure 1 , Figure 7 An imaging range 2 captured by the imaging unit 31 of the camera module 11 - 8 which is a normally-on camera is shown. Figure 7 A face region 71 detected in the camera input image in imaging range 2 is also shown.

[0123] The camera input image in the imaging range 2 is supplied from the imaging unit 31 to the face detection unit 42. The face detection unit 42 detects the face region 71 of the user in the camera input image in the imaging range 2. The face part detection unit 43 detects face part points in the face region 71 detected by the face detection unit 42.

[0124] exist Figure 6 In the camera module search process shown, the detection process of the face area 71 in the camera input image captured by the camera module 11 and the detection process of the face part points may be repeated until the face part points are detected.

[0125] <Estimation of Facial Position and Facial Angle>

[0126] Figure 8 It is used to illustrate Figure 6 FIG. 5 is a diagram showing an example of the position and angle of the face estimated in step S33 .

[0127] Similar to Figure 7 , Figure 8 There is shown a facial area 71 detected in a camera input image of camera module 11-8, which is a normally-on camera.

[0128] The position and angle estimation unit 44 is supplied with the camera input image, the information on the face region 71 , and the face part point information supplied by the face part detection unit 43 .

[0129] When only one camera module 11 is activated, the position and angle estimation unit 44 estimates the distance d and the height h of the user's face based on the size of the face area 71 .

[0130] Furthermore, the position and angle estimation unit 44 estimates the face angle a (dashed arrow) indicating the angle of the face when the horizontal direction is 0 degrees based on the face part point information. Figure 8 In this case, the facial angle a is 0 degrees.

[0131] Furthermore, when there are a plurality of activated camera modules 11 , the 3D position and angle of the face are estimated using stereoscopic vision based on the face part point information provided by each camera module 11 .

[0132] In this case, for example, all detected pieces of facial part point information from the activated camera module 11 can be collected in the position and angle estimation unit 44 of a single camera module 11, and the 3D position and angle of the face can be estimated using stereoscopic vision based on the collected multiple pieces of facial part point information.

[0133] In addition, the camera module 11 that estimates the 3D position and angle of the face using stereoscopic vision may be an always-on camera, or may be any camera module 11 other than an always-on camera. In addition, the position and angle estimation unit in the information processing device 21 may be configured to estimate the 3D position and angle of the face based on a plurality of pieces of facial part point information using stereoscopic vision.

[0134] <Search for the best camera module>

[0135] Fig. 9 It is used to illustrate Figure 6 FIG. 1 is a diagram showing an example of how to search for an optimal camera module in step S34.

[0136] Fig. 9 As shown above, Figure 8 The estimated facial angle a (dashed arrow) and the angles a2, a5, a8 and a11 of the camera modules 11-2, 11-5, 11-8 and 11-11 relative to the user's face, respectively.

[0137] The optimal camera configuration search unit 51 can determine the angles a2, a5, a8 and a11 of the camera modules 11-2, 11-5, 11-8 and 11-1 relative to the user's face, respectively, based on the information about the position and angle a of the face provided by the position and angle estimation unit 44, the camera ID of the camera module 11-1 and the information registered in the camera configuration DB 52.

[0138] The optimal camera configuration search unit 51 can search for the optimal camera module for facial recognition by searching for the camera module 11-5 having the minimum angle difference (e.g., angle a5 indicated by a thick line) from the facial angle a estimated by the position and angle estimation unit 44 among these angles. Fig. 9 The angle of the face in the vertical direction is shown, while the angle of the face in the horizontal direction is estimated in the same manner, and the estimated angle of the face is used to search for the camera module.

[0139] Subsequently, as described above, if the camera module 11 - 5 determined to be the optimal camera module through the search is a new camera module 11 that has not yet been activated, the optimal camera configuration search unit 51 activates the camera module 11 .

[0140] <Authentication Process>

[0141] Fig.10 It is used to illustrate Figure 5 Flowchart of the authentication process in step S12.

[0142] In step S51 , one of the activated camera modules 11 is extracted. The imaging unit 31 of the extracted camera module 11 captures an image of the user's face to generate a camera input image, and outputs the generated camera input image to the face detection unit 42 .

[0143] In step S52, the face detection unit 42 detects the face region of the user in the camera input image supplied from the imaging unit 31. The camera input image and the face region information indicating the detected face region are output to the face part detection unit 43.

[0144] In step S53, the face part detection unit 43 detects face part points in the face region detected by the face detection unit 42. The face part detection unit 43 outputs the camera input image, the face region information, and the face part point information indicating the detected face part points to the face image normalization unit 45.

[0145] In step S54, the facial image normalization unit 45 normalizes the facial image using the camera input image, facial region information, and facial part point information provided by the facial part detection unit 43. The facial image normalization unit 45 outputs the normalized facial image, facial region information, and facial part point information to the facial feature value extraction unit 46.

[0146] In step S55, the facial feature value extraction unit 46 extracts facial feature values ​​using the normalized facial image, facial region information, and facial part point information provided by the facial image normalization unit 45. The facial feature value extraction unit 46 sends facial feature value information indicating the extracted facial feature values ​​to the facial feature value integration unit 53 of the information processing device 21 together with its own camera ID.

[0147] In step S56, the facial feature value integration unit 53 determines whether the camera module 11 extracted in step S51 is the last camera module 11 that has not been extracted among the activated camera modules 11. If it is determined in step S56 that the extracted camera module 11 is not the last camera module 11, the process returns to step S51, and the subsequent processes are repeated.

[0148] If it is determined in step S56 that the extracted camera module 11 is the last camera module 11 , the process proceeds to step S57 .

[0149] In step S57, the facial feature value integration unit 53 performs facial feature value integration based on the facial feature value information and the camera ID provided by the facial feature value extraction units 46 of all activated camera modules 11. The facial feature value integration unit 53 outputs integrated facial feature value information indicating the integrated facial feature values ​​to the face matching unit 54.

[0150] In step S58, the face matching unit 54 refers to the information registered in the camera configuration DB 52 and performs matching between the integrated facial feature value indicated by the integrated facial feature value information provided by the facial feature value integration unit 53 and the registered facial feature value registered in the registered facial feature value DB 55.

[0151] In step S59, the facial matching unit 54 determines whether the match is successful. For example, if the similarity of the match between the integrated facial feature value and the registered facial feature value is greater than or equal to a prescribed threshold, the match is determined to be successful. When it is determined in step S59 that the match is successful, Fig.10 The authentication process is completed.

[0152] Meanwhile, when it is determined in step S59 that the matching is unsuccessful, the process proceeds to step S60.

[0153] In step S60, the face matching unit 54 determines whether the number of activated camera modules 11 has reached the set maximum camera module number. If it is determined in step S60 that the number of activated camera modules 11 has not reached the maximum camera module number, the process proceeds to step S61.

[0154] In step S61, the optimal camera configuration search unit 51 searches for an optimal camera module among the camera modules 11 that have not yet been activated. That is, the optimal camera configuration search unit 51 searches for a camera module 11 among the camera modules 11 that have not yet been activated that has the smallest angle difference with respect to the detected face.

[0155] In step S62, the optimum camera configuration search unit 51 activates the camera module 11 found by the search. Then, the process returns to step S51, and the subsequent processes are repeated.

[0156] If it is determined in step S60 that the number of activated camera modules 11 has reached the maximum number of camera modules, the authentication is unsuccessful, and Fig.10 The authentication process is completed.

[0157] <Advantageous Effects of the Present Technology>

[0158] Fig.11 1 is a schematic diagram for explaining the operations of the camera module 11 and the information processing device 21 in the face recognition system 1.

[0159] exist Fig.11 In the face recognition system 1, each camera module 11-1 to 11-3 executes Fig.10 In the information processing device 21, the processing of steps S52 to S55 is performed. Fig.10 The processing in steps S56 and S57.

[0160] In the conventional system, even the camera module 11 that does not need to be activated is activated. Therefore, for example, if the camera module 11-3 on the left side captures only a part of the user's outline because the user stands at the right end in front of the door 12, the camera module 11-3 is wasted for Fig.10 The power of the processing in steps S52 to S55.

[0161] In contrast, according to the present technology, only the camera module 11-1 that captures the frontal image of the user's face and the camera module 11-2 required for authentication in the surrounding area are activated to perform Fig.10 The processing in steps S52 to S55.

[0162] That is, according to the present technology, the camera module 11-3 that is not required for authentication is not activated, so that the camera module 11-3 can be saved. Fig.10 The power consumption of the processing in steps S52 to S55.

[0163] In the above example, the always-on camera is preset. The always-on camera may be set when the facial recognition system 1 is shipped or when the facial recognition system 1 is installed, or may be automatically set by the facial recognition system 1 .

[0164] <Setting of the normally open camera device>

[0165] Fig.12 1 is a diagram for explaining an example of how to set a normally-on camera device.

[0166] exist Fig.12 On the left side of FIG. 1 , an example is shown in which, after the facial recognition system 1 is installed, all camera modules 11 are set as normally-on cameras in order to determine which camera module 11 will be set as a normally-on camera.

[0167] The information processing device 21 of the facial recognition system 1 records the number of times and date and time each camera module 11 has been used for authentication, and based on the recorded number of times or date and time, only sets the camera module 11 that has been used for authentication a certain number of times as a normally-on camera.

[0168] exist Fig.12 On the right side of FIG. 1 , an example is shown in which camera modules 11 - 2 , 11 - 5 , and 11 - 9 that have been used for authentication a certain number of times are set as normally-on cameras.

[0169] In this way, simply installing the facial recognition system 1 enables the system to adapt to various users, such as tall users and users who often use wheelchairs.

[0170] Normally open cameras can be set and switched at different times.

[0171] <2. Second Embodiment (Human Body Authentication System)>

[0172] <Configuration of human authentication system>

[0173] Fig.13 A configuration example of the appearance of a human authentication system according to a second embodiment of the present technology is shown.

[0174] Fig.13 A human body authentication system 101 installed in, for example, an unmanned convenience store is shown.

[0175] The human authentication system 101 is configured to include camera modules 111 - 1 to 111 - 10 and a human detection sensor 112 .

[0176] The camera modules 111 - 1 to 111 - 8 are installed on the walls and shelves so that the camera modules can capture images of the aisles r1 to r8 and images of customers (users) in the aisles.

[0177] The camera module 111-1 is installed on a wall or a shelf so that the camera module can capture an image of aisle r1. The camera module 111-2 is installed on a wall or a shelf that can capture an image of aisle r2. The camera module 111-3 is installed on a wall or a shelf that can capture an image of aisle r3. The camera module 111-4 is installed on a wall or a shelf that can capture an image of aisle r4.

[0178] Camera module 111-5 is mounted on a wall or shelf that can capture an image of aisle r5. Camera module 111-6 is mounted on a wall or shelf so that the camera module can capture an image of aisle r6. Camera module 111-7 is mounted on a wall or shelf so that the camera module can capture an image of aisle r7. Camera module 111-8 is mounted on a wall or shelf so that the camera module can capture an image of aisle r8.

[0179] The camera modules 111-9 and 111-10 can capture a 360-degree image and are installed on the ceiling. When there is no need to distinguish the individual camera modules 111-1 to 111-10, these camera modules are collectively referred to as a camera module 111.

[0180] At least one of the camera modules 111 (in Fig.13 In the case of the camera module 111-1, 111-2, 111-9 and 111-10) are used as normally-open camera devices that are always activated. The camera module 111 other than the normally-open camera device is usually in a stopped state, similar to Figure 1 The camera module 11 in.

[0181] The camera module 111 serving as a normally-on camera may be configured to be activated in response to a signal from the human detection sensor 112 .

[0182] At least one of the camera modules 111-1 and 111-2 used as the normally-on camera captures an image of the body of a user who has entered the store. At least one of the camera modules 111-9 and 111-10 used as the normally-on camera captures an image of the body of a user who has entered the store. The camera modules 111 other than the normally-on camera are activated in response to the control of the human body authentication system 101, and capture images of the human bodies of users in the corresponding aisles.

[0183] The human detection sensor 112 detects a user entering the store and sends a signal indicating the detection to the normally-on camera.

[0184] The human authentication system 101 registers feature values ​​extracted from a human body image captured by at least one of the normally-on camera modules 111 - 1 and 111 - 2 .

[0185] The human authentication system 101 continues to detect the user's body using the human body image captured by at least one of the camera modules 111 - 9 and 111 - 10 that function as an always-on camera and estimate the position and angle of the user's body using the captured human body image.

[0186] Furthermore, the human authentication system 101 searches for an inactivated camera module 111 among the camera modules 111 that can capture an image of the user's body from the most frontal position according to the estimated position and angle of the user's body.

[0187] The human body authentication system 101 activates the camera module 111 found by searching, controls the activated camera module 111, extracts the user's human body feature value, and authenticates the user's human body. When the user's body is authenticated, information such as products that the authenticated user has taken from the shelf or purchased at the checkout is associated with the user.

[0188] The human body authentication system 101 performs the processing for each user. For example, if there are multiple users in a store and the camera module 111 has been activated by another user other than the target user, the image captured by the camera module 111 activated by the other user can be used to authenticate the body of the target user.

[0189] It is also possible to set a stop time for stopping the camera module 111 other than the normally-on camera. For example, the stop time from the activation start to the stop time can be set.

[0190] As described above, in the human authentication system 101, unnecessary camera modules 111 are not activated, so that human authentication can be continuously performed, and, for example, a product picked up by a user can be detected using a minimum camera module configuration.

[0191] <Functional configuration of human authentication system>

[0192] Fig.14 yes Fig.13 A block diagram of an example of a functional configuration of a human authentication system shown in FIG.

[0193] exist Fig.14 In the embodiment, the human body authentication system 101 is configured to include camera modules 111 - 1 , 111 - 2 . . . , a human body detection sensor 112 , and a server 121 .

[0194] The camera module 111 is configured to include an imaging unit 131 and a control unit 132 .

[0195] The imaging unit 131 captures an image of a subject, and outputs a camera input image obtained by capturing the image of the subject to the detection and estimation unit 141 of the server 121 .

[0196] The control unit 132 controls the imaging unit 131 of the camera module 111 in response to the control from the server 121. The control unit 132 activates or stops the camera module 111 in response to the control from the server 121.

[0197] The server 121 is configured to include a detection and estimation unit 141 , an optimal camera configuration search unit 142 , a camera configuration DB 143 , a human feature value integration unit 144 , a human matching unit 145 , and a registered human feature value DB 146 .

[0198] Note that the detection and estimation unit 141, the optimal camera configuration search unit 142, the camera configuration DB 143, the human feature value integration unit 144, the human matching unit 145, and the registered human feature value DB 146 are identical to Figure 2 The detection and estimation unit 32, the optimal camera configuration search unit 51, the camera configuration DB 52, the facial feature value integration unit 53, the facial matching unit 54 and the registered facial feature value DB 55 are basically the same and perform the same processing, except that the processing target is the user's body instead of the user's face.

[0199] The detection and estimation unit 141 is configured to include a human body detection unit 151 , a human body part detection unit 152 , a position and angle estimation unit 153 , a human body image normalization unit 154 , and a human body feature value extraction unit 155 .

[0200] The human body detection unit 151, the human body part detection unit 152, the position and angle estimation unit 153, the human body image normalization unit 154 and the human body feature value extraction unit 155 perform the same Figure 2 The face detection unit 42, face part detection unit 43, position and angle estimation unit 44, face image normalization unit 45 and face feature value extraction unit 46 perform essentially the same processing, the only difference being that the processing target is the user's body instead of their face.

[0201] exist Fig.14 In the human body authentication system 101, the detection and estimation unit 141 is provided on the server 121, but the detection and estimation unit 141 may be provided in each camera module 111, similar to the one according to the first embodiment described above. Figure 1 Facial recognition system1.

[0202] The lens-less camera to be described may be used as the imaging unit 31 of the camera module 11 according to the above-described first embodiment, or as the imaging unit 131 of the camera module 111 according to the second embodiment.

[0203] <Configuration of lensless imaging device>

[0204] Fig.15 A configuration example in which a lens-less imaging device forms an image without using a lens is shown.

[0205] exist Fig.15 In the figure, the lens-less camera device 171 is configured to include an optical element plate 181, a light-transmitting portion 182, and an imaging device 183.

[0206] The optical element plate 181 is a thin plate having a transparent area through which light passes and an opaque area that blocks light. The optical element plate 181 is arranged at a position corresponding to the imaging device 183 and opposite to the light receiving surface of the imaging device 183.

[0207] The light-transmitting portion 182 has a light-transmitting area (micropore) through which light passes and is formed on the optical element plate 181. The light-transmitting portion 182 has a transparent area in a form corresponding to various types of lensless imaging optical elements, such as a pinhole, a zone plate like a Fresnel zone plate, and a photon sieve.

[0208] The imaging device 183 includes optical elements that form an optical image of a subject. The imaging device 183 may be a CMOS (Complementary Metal Oxide Semiconductor) image sensor, a CCD (Charge Coupled Device) image sensor, or any other type of device.

[0209] The lensless imaging device 171 as described above transmits light through the light transmitting portion 182 and forms an image on the imaging device 183 .

[0210] use Fig.15 The lens-less camera 171 in FIG. 1 as an imaging unit of the camera module according to the present technology can capture an image through a hole (eg, a hole having a diameter of 1 mm or less) that is invisible to a user.

[0211] For example, in Figure 1 In the case of the facial recognition system 1 in , this can enable the user to unlock the door simply by approaching the door without being aware of the camera device, so that the user can enjoy the service (i.e., unlocking the door) using a more natural user interface (UI).

[0212] Normally, if the user is not aware of the camera, authentication becomes difficult because the user does not turn to the camera, but by arranging multiple cameras according to the first embodiment and the second embodiment of the present technology, authentication can be smoothly implemented even if the user is not aware of the camera. In addition, even when multiple cameras are set, the present technology makes it possible to reduce power consumption.

[0213] <3. Third Embodiment (Wearable Device)>

[0214] Fig.16 is a view of a configuration example of the appearance of a wearable device according to a third embodiment of the present technology.

[0215] Fig.16 The wearable device 201 in FIG. 2 is a wrist-type wearable device.

[0216] exist Fig.16 In the embodiment, the wearable device 201 is configured to include camera modules 211 - 1 to 211 - 6 , a display unit 212 and a wristband 213 .

[0217] Camera modules 211-1 to 211-6 are provided on the surface of the display unit 212. The camera module 211-1 is provided at the center of the top row on the surface of the display unit 212. The camera module 211-2 is provided on the left side of the second row from the top of the display unit 212. The camera module 211-3 is provided on the right side of the second row from the top of the surface of the display unit 212.

[0218] The camera module 211-4 is located on the left side in the third row from the top of the surface of the display unit 212. The camera module 211-5 is located on the right side of the third row from the top of the surface of the display unit 212. The camera module 211-6 is located at the center of the bottom row on the surface of the display unit 212. When there is no need to distinguish the camera modules 211-1 to 211-6 individually, these camera modules are collectively referred to as camera modules 211.

[0219] At least one camera module 211 (in Fig.16 In this case, the camera module 211-1) is a normally-on camera and is always activated.

[0220] The camera module 211 - 1 , which functions as an always-on camera, captures an image of a QR code.

[0221] exist Fig.16 , an imaging range 215 captured by the camera module 211-1 used as a normally-on camera is shown. The imaging range 215 is represented by Fig.16, which is represented by the base of the triangle formed by the camera module 211 - 1 at the vertex.

[0222] The wearable device 201 uses the same mechanism as the first embodiment to search for other camera modules 211 capable of reading the QR code based on the relative position and angle of the QR code estimated using the image captured by the camera module 211-1, and activates the camera module 211 found by the search.

[0223] The wearable device 201 then controls the activated camera module 211 to identify the QR code captured by the image and performs processing such as payment based on the identified QR code.

[0224] In the wearable device 201 configured as described above, if Fig.15 If the lensless camera 171 in FIG. 1 is used as the camera module 211 , the user may not be able to correctly read the QR code because the position of the camera module 211 is unknown.

[0225] However, by arranging a plurality of camera modules 211 and activating the camera according to this embodiment, it is possible to appropriately activate only the camera in a position that enables the camera to read and recognize the QR code. In this way, the QR code can be read while reducing battery consumption.

[0226] The configuration according to the third embodiment is substantially the same as that of the first embodiment. However, according to the third embodiment, a SoC (System on Chip) mounted on the wearable device 201 is used instead of Figure 1 The information processing device 21 in.

[0227] In combination Fig.16 In the description, a QR code is used, but the present technology can also be applied to other codes.

[0228] <4. Others>

[0229] <Advantageous Effects of the Present Technology>

[0230] As described above, according to the present technology, based on the position and angle of the object estimated from the image captured by the activated camera among multiple cameras, a camera search process is performed to search for a camera suitable for authenticating the object among the inactivated cameras, and then the camera found by the search is activated.

[0231] In this way, power consumption can be reduced.

[0232] In the above description, target objects to be authenticated (recognized) include faces, human bodies, and QR codes, but the present technology can be applied to recognition of any type of object.

[0233] <Computer Configuration Example>

[0234] The above-mentioned series of processing can also be executed by hardware or software. When the series of processing is executed by software, a program for the software is embedded in dedicated hardware to be installed from a program recording medium to a computer or a general-purpose personal computer.

[0235] Fig.17 : is a block diagram showing a configuration example of computer hardware that executes the above-described series of processes using a program.

[0236] A CPU (Central Processing Unit) 301 , a Read Only Memory (ROM) 302 , and a Random Access Memory (RAM) 303 are connected to one another via a bus 304 .

[0237] The input / output interface 305 is also connected to the bus 304. An input unit 306 including a keyboard or a mouse and an output unit 307 including a display or a speaker are connected to the input / output interface 305. In addition, a storage unit 308 including a hard disk or a nonvolatile memory, a communication unit 309 including a network interface, and a drive 310 driving a removable medium 311 are connected to the input / output interface 305.

[0238] In the computer configured as described above, for example, the CPU 301 loads a program stored in the storage unit 308 onto the RAM 303 via the input / output interface 305 and the bus 304 and executes the program to perform the above-described series of processing steps.

[0239] For example, the program executed by the CPU 301 is recorded on the removable medium 311 , or provided through a wired or wireless transmission medium such as a local area network, the Internet, or digital broadcasting to be installed in the storage unit 308 .

[0240] Note that the program executed by the computer may be a program that chronologically executes processing in the order described in this specification, or may be a program that executes processing in parallel or at necessary timing such as call timing.

[0241] Meanwhile, in this specification, a system is a collection of multiple constituent elements (devices, modules (components), etc.), and all constituent elements may or may not be located in the same housing. Therefore, multiple devices housed in separate housings and connected via a network, and a device in which multiple modules are housed in one housing are both systems.

[0242] Furthermore, the advantages described in this specification are merely exemplary and not restrictive, and other advantages may be obtained.

[0243] The embodiment of the present technology is not limited to the above-described embodiment, and various changes can be made without departing from the gist of the present technology.

[0244] For example, the present technology may be configured as cloud computing in which a function is shared and jointly processed by multiple devices over a network.

[0245] Furthermore, each step described in the above flowchart may be performed by one device or by a plurality of devices in a shared manner.

[0246] Furthermore, in the case where one step includes a plurality of processes, the plurality of processes included in one step may be executed by one device or may be executed by a plurality of devices in a shared manner.

[0247] <Configuration combination example>

[0248] The present technology may also have the following configurations.

[0249] (1) An information processing device, comprising a control unit, configured to perform the following camera search processing: based on a position and an angle of a target estimated from an image captured by an activated camera which is an activated camera among a plurality of cameras, searching for a camera suitable for authentication of the target among inactivated cameras which have not yet been activated, and activating the camera found by the search.

[0250] (2) An information processing device according to (1), wherein, when the camera device found through the search is the activated camera device, the control unit ends the camera device search process, and, when the camera device found through the search is an inactivated camera device, activates the camera device found through the search and repeats the camera device search process.

[0251] (3) An information processing device according to (1) or (2), wherein the control unit performs the following authentication processing: matching between a target in an image captured by the activated camera device and a target in a registered image, and, when the matching is unsuccessful, searching the inactivated camera devices for a camera device suitable for authentication of the target, and activating the camera device found by the search.

[0252] (4) An information processing device according to (3), wherein when the number of activated cameras reaches a specified number, the control unit ends the authentication process, and, when the number of activated cameras does not reach the specified number, activates the camera found through the search and repeats the authentication process.

[0253] (5) The information processing device according to (3), wherein:

[0254] At least one of the activated camera devices is a normally-on camera device that is always activated, and

[0255] When the authentication process ends, the control unit stops the activated imaging devices other than the normally-on imaging device.

[0256] (6) The information processing device according to (5), wherein the control unit sets the always-on camera according to the number of times the plurality of cameras have been used or the date and time when the plurality of cameras have been used for the authentication process.

[0257] (7) The information processing device according to (3), wherein at least one of the activated camera devices is a normally-on camera device, and

[0258] The control unit sets a time until the activated image pickup devices other than the normally-on image pickup device are stopped.

[0259] (8) The information processing device according to any one of (1) to (7), including the plurality of imaging devices.

[0260] (9) The information processing device according to (8), wherein each of the plurality of imaging devices includes:

[0261] an imaging unit configured to capture an image of the target, and

[0262] An estimation unit is configured to estimate a position and an angle of the target based on the captured image.

[0263] (10) The information processing device according to (9), wherein the imaging unit of the inactivated imaging device is activated while the estimation unit is inactivated, and

[0264] The control unit activates the estimation unit of the camera found by the search.

[0265] (11) The information processing device according to (9), wherein

[0266] The imaging unit and the estimation unit of the non-activated camera are not activated, and

[0267] The control unit activates the imaging unit and the estimation unit of the camera found by the search.

[0268] (12) The information processing device according to (9), wherein

[0269] The plurality of cameras each include an imaging unit configured to capture an image of the object.

[0270] (13) The information processing device according to (12), wherein

[0271] The imaging unit of the non-activated camera device is not activated, and

[0272] The control unit activates the imaging unit of the camera found by the search.

[0273] (14) The information processing device according to (12), further including an estimation unit configured to estimate the position and angle of the target based on the captured image.

[0274] (15) The information processing device according to any one of (1) to (14), wherein the plurality of imaging devices are lens-less imaging devices.

[0275] (16) The information processing device according to any one of (1) to (15), wherein the target is a face or a human body.

[0276] (17) The information processing device according to any one of (1) to (15), wherein the target is a code.

[0277] (18) An information processing method, comprising: performing the following camera device search processing by an information processing device: based on the position and angle of a target estimated from an image captured by an activated camera device which is an activated camera device among multiple cameras, searching for a camera device suitable for authentication of the target among inactivated cameras that have not yet been activated, and activating the camera device found by the search.

[0278] (19) A program for causing a computer to function as a control unit, the control unit being configured to perform the following camera device search processing: based on the position and angle of a target estimated from an image captured by an activated camera device which is an activated camera device among a plurality of cameras, searching for a camera device suitable for authentication of the target among inactivated cameras that have not yet been activated, and activating the camera device found by the search.

[0279] Reference numerals list

[0280] 1Facial Recognition System

[0281] 11. 11-1 to 11-12 Camera device module

[0282] 12 doors

[0283] 21Information processing device

[0284] 22 Locking mechanism

[0285] 31 Imaging Unit

[0286] 32 Detection and estimation units

[0287] 33Control Unit

[0288] 42Face detection unit

[0289] 43Face part detection unit

[0290] 44Face Image Normalization Unit

[0291] 45Facial feature value extraction unit

[0292] 46Facial position and angle estimation unit

[0293] 51 Best Camera Equipment Search Unit

[0294] 52 Camera device configuration DB

[0295] 53Facial feature value integration unit

[0296] 54Face matching unit

[0297] 55 Registered facial feature value DB

[0298] 101 Human Authentication System

[0299] 111, 111-1 to 111-10 Camera devices

[0300] 112 Human body detection sensor

[0301] 121 Server

[0302] 131 Imaging Unit

[0303] 132 Control Unit

[0304] 141 Detection and Estimation Unit

[0305] 142 Best Camera Configuration Search Unit

[0306] 143 Camera device configuration DB

[0307] 144 Human body characteristic value integration unit

[0308] 145 Human Body Matching Unit

[0309] 146 Registered human feature value DB

[0310] 151 Human body detection unit

[0311] 152 Human body part detection unit

[0312] 153 Position and angle estimation unit

[0313] 154 Human Image Normalization Unit

[0314] 155 Human feature value extraction unit

[0315] 171Lens-less camera device

[0316] 181 Optical Component Board

[0317] 182 light-transmitting part

[0318] 183 Imaging Device

[0319] 201 Wearable Devices

[0320] 211, 211-1 to 211-6, 212 display unit

[0321] 213 wristband

Claims

1. An information processing device, comprising a control unit, wherein the control unit is configured to perform the following camera search processing: based on the position and angle of a target estimated from an image captured by an activated camera device which is an activated camera device among multiple cameras, searching for a camera device suitable for authentication of the target among inactivated cameras that have not yet been activated, and activating the camera device found by the search.

2. The information processing device according to claim 1, wherein: When the camera device found through the search is the activated camera device, the control unit ends the camera device search process, and, when the camera device found through the search is the inactivated camera device, activates the camera device found through the search and repeats the camera device search process.

3. The information processing device according to claim 2, wherein: The control unit performs the following authentication processing: matching between a target in an image captured by the activated camera device and a target in a registered image, and, when the matching is unsuccessful, searching for a camera device suitable for authentication of the target in the inactivated camera devices, and activating the camera device found by the search.

4. The information processing device according to claim 3, wherein: When the number of activated cameras reaches a prescribed number, the control unit ends the authentication process, and, when the number of activated cameras does not reach the prescribed number, activates the camera found by the search and repeats the authentication process.

5. The information processing device according to claim 3, wherein: At least one of the activated camera devices is a normally-on camera device that is always activated, and When the authentication process ends, the control unit stops the activated imaging devices other than the normally-on imaging device.

6. The information processing device according to claim 5, wherein: The control unit sets the normally-on camera according to the number of times the plurality of camera have been used or the date and time at which the plurality of camera have been used for the authentication process.

7. The information processing device according to claim 3, wherein: At least one of the activated camera devices is a normally-on camera device, and The control unit sets a time until which the activated image pickup devices other than the normally-on image pickup device are stopped. The information processing device according to claim 1 , comprising the plurality of imaging devices.

9. The information processing device according to claim 8, wherein: Each of the plurality of camera devices comprises: an imaging unit configured to capture an image of the target, and An estimation unit is configured to estimate a position and an angle of the target based on the captured image.

10. The information processing device according to claim 9, wherein: The imaging unit of the inactive camera is activated and the estimation unit is not activated, and The control unit activates the estimation unit of the camera found by the search.

11. The information processing device according to claim 9, wherein The imaging unit and the estimation unit of the non-activated camera are not activated, and The control unit activates the imaging unit and the estimation unit of the camera found by the search.

12. The information processing device according to claim 8, wherein The plurality of cameras each include an imaging unit configured to capture an image of the object.

13. The information processing device according to claim 12, wherein The imaging unit of the non-activated camera device is not activated, and The control unit activates the imaging unit of the camera found by the search. 14 . The information processing device according to claim 12 , further comprising an estimation unit configured to estimate a position and an angle of the target based on the captured image.

15. The information processing device according to claim 1, wherein: The plurality of imaging devices are lens-less imaging devices.

16. The information processing device according to claim 1, wherein: The target is a face or a human body.

17. The information processing device according to claim 1, wherein: The target is yards.

18. An information processing method, comprising performing the following camera device search processing by an information processing device: based on the position and angle of a target estimated from an image captured by an activated camera device which is an activated camera device among multiple cameras, searching for a camera device suitable for authentication of the target among inactivated cameras that have not yet been activated, and activating the camera device found by the search.

19. A program for causing a computer to function as a control unit, the control unit being configured to perform the following camera device search processing: based on a position and an angle of a target estimated from an image captured by an activated camera device which is an activated camera device among a plurality of cameras, searching for a camera device suitable for authentication of the target among inactivated cameras that have not yet been activated, and activating the camera device found by the search.

Images