Information processing device, information processing method and storage medium

Abstract

To provide a device that tracks a physical area in an image.SOLUTION: A device comprises: a memory that stores one or more commands; and a processor configured to execute the one or more commands, acquire a first image including one or more faces imaged at a first point in time by one or more cameras, each corresponding to one person among one or more persons, detect a first person from among the one or more persons by performing a face recognition operation for the one or more faces in the first image acquired from the camera, detect a physical area corresponding to a face area of the first person, and track a physical area in a second image captured by the one or more cameras at a second point in time after the first time. Tracking the physical area in the second image includes: associating the face area in the first image with the physical area in the first image; and comparing the physical area in the second image with the physical area in the first image.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and a storage medium. Specifically, the present disclosure relates to an information processing apparatus, an information processing method, and a storage medium that perform authentication of a person using an image captured by a camera.

Background Art

[0002] In recent years, in facilities such as airports, gate devices that control passages through which users such as security inspection areas may pass have been provided. In a conventional gate device, a face authentication operation may be performed by comparing a face image acquired from a camera with a face image acquired from a registered image such as a passport. However, in a conventional gate device, in order to perform a face authentication operation, it is necessary for a facility staff member to operate a camera to capture a face image of a passenger or a visitor. This method of performing face authentication causes a delay because each passenger or visitor needs to stop in front of the camera one by one. Therefore, it is difficult for passengers or visitors to pass through the gate device quickly.

Summary of the Invention

Problems to be Solved by the Invention

[0003] In view of the above problems, one or more aspects of the present disclosure enable a user such as a passenger or a visitor to pass through a gate device without having to stop in front of a camera, and thus provide a gate device, a control method of the gate device, and a storage medium for reducing a delay of the user.

Means for Solving the Problems

[0004] According to one aspect of the present disclosure, a memory storing one or more instructions, and a processor configured to execute the one or more instructions to obtain a first image including one or more faces captured at a first time by one or more cameras, each corresponding to one person among one or more persons, perform a face recognition operation on the one or more faces in the image obtained from the camera, detect a first person from among the one or more persons, detect a body region corresponding to the face region of the first person, track the body region in a second image captured by the one or more cameras at a second time after the first time, and output information for controlling to open the barrier based on a determination that the body region is approaching the barrier. An apparatus is provided that includes the above components.

[0005] According to another aspect of the present disclosure, a memory storing one or more instructions, and a processor configured to execute the one or more instructions to obtain a first image including a plurality of faces captured at a first time by one or more cameras, each corresponding to a plurality of persons, perform a face recognition operation on the plurality of faces in the first image, detect a first person from among the plurality of persons, detect a body region corresponding to the face region of the first person, track the body region in a second image captured by the one or more cameras at a second time after the first time, and output information for controlling to open the barrier based on a determination that the body region is approaching the barrier. An apparatus is provided that includes the above components.

[0006] According to another aspect of the present disclosure, there is provided an apparatus comprising: a memory storing one or more instructions; and a processor configured to execute the one or more instructions to obtain an image captured by a camera, the image including a plurality of faces each corresponding to a plurality of persons approaching a barrier and each including features, detect a first person as the person closest to the camera among the plurality of persons based on the size of the features for the first person, and output information for controlling the barrier based on a result of comparison between the face information of the first person from the obtained image and a plurality of registered information each corresponding to a person registered before obtaining the image. BRIEF DESCRIPTION OF THE DRAWINGS

[0007]

Figure 1A

Figure 1B

Figure 2

Figure 3

Figure 4A

Figure 4B

Figure 4C

Figure 4D

Figure 5

Figure 6

Figure 7A

Figure 7B

Figure 8

Figure 9

Embodiments for Carrying Out the Invention

[0008] One or more exemplary embodiments of the present disclosure will be described below with reference to the drawings. Throughout the drawings, the same reference numerals are assigned to the same or corresponding components, and the description thereof may be omitted or simplified.

[0009] FIGS. 1A and 1B show an example of a gate apparatus 1 according to a non-limiting and exemplary embodiment. As shown in FIG. 1A, the gate apparatus 1 may include a gate 2 provided in the passage 3 to control the traffic passing through the passage 3. The gate apparatus 1 may further include a camera 4 and an information processing apparatus 5 for performing face recognition of a user walking through the passage 3. According to one embodiment, the information processing apparatus 5 may acquire a first image of a person or user (U) at a first position P1 while the person is approaching the gate 2. The first image may be captured by the camera 4 at a first time (t1). The first image may include one or more faces of a person near the gate apparatus, and each of the one or more faces corresponds to one user among a plurality of users.

[0010] According to an embodiment, the information processing device 5 may be configured to detect a first user from among a plurality of users by performing a face recognition operation on the face in the first image. For example, the face recognition operation may be a part of the authentication operation that is wholly or partly performed by the information processing device 5 configured to authenticate the face of a user as a person permitted to pass through the gate, called the user to be authenticated (U).

[0011] According to an embodiment, the information processing device 5 may detect the area of the user to be authenticated (U) as a body area. This body area can be associated with the face area of the user to be authenticated (U). By associating the body area of the user to be authenticated (U) with the corresponding face area, the user to be authenticated (U) can be tracked by tracking the body area. When the user is at the second position P2 of the passage, a second image can be acquired by the camera 4. The second image may be captured at a second time (t2) following the first time (t1), and may be captured by the same camera 4, or may be captured by an imaging device different from the camera 4 that captured the first image. The second image may include the body area, but may not include the face area of the user to be authenticated (U). This may be due to the movement of the user to be authenticated (U) between time t1 and time t2, or because the face of the user to be authenticated (U) is not facing the camera 4 sufficiently at time t2, or the face is unclear in the second image, or does not exist in the second image at time t2. Since the body part area is associated with the user to be authenticated (U), the user to be authenticated (U) can be tracked in the second image even when the face area does not exist in the second image. The information processing device 5 may output information for controlling the opening of the gate 2 based on a determination that the tracked body area is approaching an obstacle. In this way, the information processing device 5 does not need to repeatedly authenticate the user after the user has been authenticated as a permitted person. For example, since the body area of the user to be authenticated is being tracked, the gate 2 may be opened even when the person is not facing the camera 4 at position P2.

[0012] In FIG. 1B, when the information processing device 5 determines that the body region tracked in the second image at position P2 is not associated with the face region of the user authenticated in the first image, the information processing device 5 can be configured to prevent the gate 1 from opening. For example, when the information processing device 5 cannot perform a face recognition operation on the face in the first image acquired from the camera 4, the information processing device 5 may not track the body region corresponding to the face in the first image. Therefore, the information processing device 5 does not open the gate 1 unless an additional face recognition operation is performed on the user and the user is not authenticated.

[0013] FIG. 2 is a functional block diagram of an information processing apparatus 10 according to an exemplary embodiment. The information processing apparatus 10 may be part of the automatic gate apparatus 1. According to one embodiment, the information processing apparatus may include one or more processors (such as the CPU 102 or other processors in FIG. 9) and a memory (such as the RAM 104 or other memory in FIG. 9). The information processing apparatus 10 may have an image acquisition unit 121, a detection unit 122, an extraction unit 123, an association unit 125, a controller 126, a display image generation unit 127, and a storage unit 129. According to one embodiment, the CPU 102 may execute one or more instructions stored in the memory to implement various units. The units and the operations performed by the units are provided for illustrative purposes, but the present disclosure is not limited to the operations performed by the units or the units. According to other embodiments, the novel features of the present disclosure may be performed by various combinations of the above-described units and other units.

[0014] According to one embodiment, the image acquisition unit 121 may acquire an image from the camera 4, the detection unit 122 may detect a person in the image acquired from the camera 4, the extraction unit 123 may extract features such as face features and body features in the image, the association unit 125 may associate the extracted face features and body features with each other, the controller 126 may control to open and close the gate 2, the display image generation unit 127 may generate information to be displayed on the display 110 (shown in FIG. 9), and the storage unit 129 may store information.

[0015] FIG. 3 is a flowchart showing an outline of the processing performed by the information processing apparatus 10 according to an exemplary embodiment. With reference to FIGS. 1 and 2, an outline of the processing performed by the information processing apparatus 10 will be described along the flowchart of FIG. 3.

[0016] In S310 of FIG. 3, the information processing apparatus 10 may acquire a first image from the camera 4. According to one embodiment, the method of acquiring the first image may include the following operations performed by the image acquisition unit 121. For example, the image acquisition unit 121 acquires a first image from the camera 4. This process may correspond to the diagram of FIG. 4A. FIG. 4A shows the first image captured at the first time and stored in the storage unit 129. According to one embodiment, the acquired first image may include a face of a recognition target. The target may be approaching the gate 1 (shown in FIGS. 1A and 1B). According to other embodiments, the acquired first image may include a plurality of faces each corresponding to a target among a plurality of recognition targets. According to one embodiment, the recognition target may be a person.

[0017] In S320 of FIG. 3, the information processing apparatus 10 detects a person in the first image. This process corresponds to the diagram of FIG. 4B. According to one embodiment, the information processing apparatus 10 may detect a person by performing face recognition on the first image.

[0018] The method of performing face recognition may include the following operations performed by the detection unit 122 and the extraction unit 123. For example, the extraction unit 123 extracts face features from the first image acquired by the image acquisition unit 121, the detection unit 122 acquires the face features extracted by the extraction unit 123, and detects whether the face features match one of the plurality of registered face features. Each of the plurality of registered face features may correspond to the face of a person among the plurality of previously registered persons. The registered face features may be stored in the storage unit 129.

[0019] In S330, the information processing apparatus 10 tracks the body region in the second image captured at the second time. This process corresponds to the figure in FIG. 4C. According to one embodiment, the information processing apparatus 10 may track the body region in the second image by associating the face region in the first image with the body region in the first image and matching the body region in the second image with the body region in the first image.

[0020] According to one embodiment, the method of performing body tracking may include the following operations performed by the image acquisition unit 121, the detection unit 122, the extraction unit 123, and the association unit 125. For example, the extraction unit 123 may extract the body region of the target in the first image. The operation of extracting the body region may be performed after the detection unit detects the match between the face features in the first image and the registered face features. According to another embodiment, the operation of extracting the body region may be performed before the detection unit detects the match between the face features in the first image and the registered face features, or may be performed simultaneously while the detection unit detects the match between the face features in the first image and the registered face features.

[0021] According to one embodiment, the association unit 125 associates the extracted body region with the face region in the first image. For example, the association unit 125 analyzes one or more characteristics of the face region and the body region to determine that the body region corresponds to the face region. For example, when the association unit 125 determines that one or more characteristics of the face region are similar to one or more features of the body region, the association unit 125 may associate the face region with the body region. According to another embodiment, the association unit 125 may determine that the body region corresponds to the face region based on the proximity between the face region and the body region.

[0022] According to one embodiment, the association unit 125 may store the associated face region and body region in the storage unit 129. For example, as shown in FIG. 5, the storage unit 129 may store the face region and the body region in association with the identification information of the detected person. The associated face region and body region may be temporarily stored in the storage unit 129.

[0023] According to one embodiment, the image acquisition unit 121 may acquire a second image captured by the camera 4 at a second time. The second time is different from the first time. According to one embodiment, the second time is after the first time. According to one embodiment, the second image may be captured by an image acquisition device such as a camera different from the camera that captures the first image.

[0024] According to one embodiment, the extraction unit 123 may extract features of the body region in the second image, the detection unit 122 may obtain the features of the body region in the second image from the extraction unit 123, and detect whether the features of the body region in the second image match the features of the body region stored in the storage unit 129. Therefore, when the body region in the second image matches the body region obtained from the storage unit 129, the detection unit 122 may obtain the identification of the object previously detected in the first image. Therefore, the information processing apparatus 10 may track the object using the body regions extracted from the first image and the second image.

[0025] According to another embodiment, the information processing apparatus 10 may perform a body tracking operation when the face features in the second image cannot be detected. This process may correspond to the diagram of FIG. 4D. For example, the extraction unit 123 may extract the face features in the second image, the detection unit 122 may obtain the face features in the second image from the extraction unit 123, and determine that the face features do not have sufficient information for face recognition. For example, when a person approaching the camera is not facing the camera, the detection unit 122 may determine that sufficient face features cannot be extracted from the person's face. According to one embodiment, the detection unit 122 may determine that the information is insufficient for face detection when the person's face deviates from the camera by more than 45 degrees.

[0026] In S340, the information processing apparatus 10 may output information for controlling gate 2 based on the tracked movement of the body area. This process may correspond to the diagrams in FIGS. 1A and 1B. According to one embodiment, the method of controlling the gate may be performed by the controller 126. For example, the controller 126 may obtain from the detection unit 122 information indicating whether the features of the body area in the second image match the features of the body area obtained from the storage unit 129. If they match, the controller 126 may output a control signal for opening gate 2 as shown in FIG. 1A. On the other hand, if they do not match, the controller 126 may maintain gate 2 in a closed state as shown in FIG. 1B.

[0027] FIGS. 4A to 4D show an example of the processing performed by the information processing apparatus according to the present embodiment. In FIG. 4A, the information processing device 1 acquires an image 401. According to one embodiment, the acquired image may be displayed on the display 402.

[0028] In FIG. 4B, the information processing apparatus 10 may detect a person in the first image. According to one embodiment, the information processing apparatus 10 may detect a person by performing face recognition on the first image. For example, the information processing apparatus may extract the face features of the face area 403 in the first image and detect whether the face features match one of the registered face features among the plurality of registered face features.

[0029] In FIG. 4C, the information processing apparatus 10 may associate the face area 403 with the body area 404 in the first image. According to one embodiment, the information processing apparatus 10 may store the associated face area 403 and body area 404 in the storage unit 129.

[0030] In FIG. 4D, the information processing apparatus 10 may track the body region 405 in the second image by matching the features of the body region 405 in the second image with the features of the body region in the first image stored in the storage unit 29. Thus, even when the face feature 406 in the second image is not available, the information processing apparatus 10 may perform the body tracking operation.

[0031] FIG. 5 shows a data structure that associates face feature information 501 and body feature information 502 with each other. For example, the face feature information 501 and the body feature information 502 may be associated with each other by identification information 503 and stored in the storage unit 129. The identification information 503 may be further used to identify whether the associated face feature information 501 and body feature information 502 correspond to an authenticated person.

[0032] FIG. 6 is a flowchart showing an overview of the processing performed by the information processing apparatus 10 according to another exemplary embodiment. With reference to FIGS. 1 and 2, an overview of the processing performed by the information processing apparatus 10 will be described along the flowchart of FIG. 6.

[0033] In S610 of FIG. 6, the information processing apparatus 10 may acquire a first image from the camera 4 (as shown in FIGS. 1A and 1B). According to one embodiment, the method of acquiring the first image may include the following operations performed by the image acquisition unit 121. For example, the image acquisition unit 121 may acquire a first image from the camera 4. The acquired first image may include a plurality of faces each corresponding to a target among a plurality of recognition targets. According to one embodiment, the recognition target may be a person.

[0034] In S620 of FIG. 6, the information processing apparatus 10 may identify the front person in the first image, that is, the person closest to the imaging device among the plurality of persons. This process may correspond to the diagrams of FIGS. 7A and 7B.

[0035] According to one embodiment, the method for identifying a front person may include the following operations performed by the detection unit 122 and the extraction unit 123. For example, the extraction unit 123 may extract a plurality of face features corresponding to one of the plurality of faces in the first image each obtained by the image acquisition unit 121. According to one embodiment, the detection unit 122 may obtain the plurality of face features extracted by the extraction unit 123 and identify the face feature corresponding to the person closest to the camera. Among the plurality of people approaching the camera, this person closest to the camera may be identified as the front person. According to one embodiment, the detection unit 122 may identify the front person by comparing the sizes corresponding to each of the plurality of face features. For example, the detection unit 122 may compare the areas occupied by each of the plurality of face features and determine the face feature having the largest area among the plurality of features as the face feature closest to the camera. According to another embodiment, the detection unit 122 may compare the distances between two feature points in each of the plurality of face features and determine the face feature having the largest distance among the plurality of features as the face feature closest to the camera. For example, the distance may be the distance between two eyes in the face feature.

[0036] In S630, the information processing apparatus 10 may perform face recognition on the front person by comparing the information of the face features of the front person with the plurality of registered information. According to one embodiment, the method for performing face recognition may include the following operations performed by the detection unit 122. For example, the detection unit 122 may obtain the face features of the front person extracted by the extraction unit 123 and detect whether the face features match one of the plurality of registered face features. Each of the plurality of registered face features may correspond to the face of a person among the plurality of previously registered people. The registered face features may be stored in the storage device 106.

[0037] In S640, the information processing apparatus 10 may output information for controlling the gate 114 based on the result of face recognition. This process may correspond to the diagrams in FIGS. 1A and 1B. According to one embodiment, the method of controlling the gate may be performed by the controller 126. For example, the controller 126 may obtain from the detection unit 122 information indicating whether the facial features of the person in front match a plurality of previously registered facial features. If they match, the controller 126 may output a control signal for opening the gate 2 as shown in FIG. 1A. On the other hand, if they do not match, the controller 126 may maintain the gate 2 in a closed state as shown in FIG. 1B.

[0038] FIGS. 7A-7B show an example of the process performed by the information processing apparatus for identifying a person in front according to the present embodiment.

[0039] In FIG. 7A, the information processing apparatus 10 may acquire the image 701 and extract a plurality of facial features (702a, 702b, and 702c), each corresponding to one of the plurality of faces in the image 701. The information processing apparatus 10 may identify the person in front by comparing the sizes of the features corresponding to each of the plurality of facial features (702a, 702b, and 702c). For example, as shown in FIG. 7B, the information processing apparatus 10 may compare the areas occupied by each of the plurality of facial features, and determine that the facial feature 702b having the largest area among the plurality of features is the facial feature closest to the camera.

[0040] FIG. 8 is a flowchart showing an overview of the process performed by the information processing apparatus 10 according to another embodiment. With reference to FIGS. 1 and 2, the overview of the process performed by the information processing apparatus 10 will be described along the flowchart of FIG. 8.

[0041] In S810 of FIG. 8, the information processing apparatus 10 may acquire a first image from the camera 4. According to one embodiment, the image acquisition unit 121 may acquire a first image from the camera 4. The acquired first image may be captured at a first time and stored in the storage unit 129. According to one embodiment, the acquired first image may include a face of a recognition target. The target may be approaching the gate 2. According to other embodiments, the acquired first image may include a plurality of faces each corresponding to a face among a plurality of recognition targets. According to one embodiment, the recognition target may be a person.

[0042] In S820 of FIG. 8, the information processing apparatus 10 may identify a front person in the first image. According to one embodiment, the detection unit 122 may extract a plurality of face regions corresponding to one of the plurality of faces in the first image acquired by the image acquisition unit 121 respectively. According to one embodiment, the detection unit 122 may acquire the plurality of face regions extracted by the extraction unit 123 and identify the face region corresponding to the person closest to the camera. Among the plurality of people approaching the camera, this person closest to the camera may be identified as the front person. According to one embodiment, the detection unit 122 may identify the front person by comparing the sizes corresponding to each of the plurality of face regions. For example, the detection unit 122 may compare the areas occupied by each of the plurality of face regions and determine the face region having the largest area among the plurality of features as the face region closest to the camera. According to another embodiment, the detection unit 122 may compare the distances between two feature points in each of the plurality of face regions and determine the face region having the largest distance among the plurality of regions as the face region closest to the camera. For example, the distance may be the distance between two eyes in the face region.

[0043] In S830 of FIG. 8, the information processing apparatus 10 may extract face features and body features of the front person in the first image. According to other embodiments, the information processing apparatus 10 may extract a plurality of face features and body features from the first image respectively.

[0044] In S840 of FIG. 8, the information processing apparatus 10 may perform face recognition on the face features of the person in front. For example, the extraction unit 123 may extract the face features of the person in front in the acquired first image, and the detection unit 122 may acquire the face features extracted by the extraction unit 123 and detect whether the face features match one of the plurality of registered face features. Each of the plurality of registered face features may correspond to the face of a person among the plurality of previously registered persons. The registered face features may be stored in the storage device 106.

[0045] In S850 of FIG. 8, the information processing apparatus 10 may extract the body features of the person in front in the first image and associate the face features with the body features. According to one embodiment, the operation of extracting the body features may be performed after the face recognition operation in S840. According to another embodiment, the operation of extracting the body features may be performed before the detection unit detects the match between the face features in the first image and the registered face features, or may be performed simultaneously while the detection unit detects the match between the face features in the first image and the registered face features.

[0046] According to one embodiment, the association unit 125 may associate the extracted body features with the face features in the first image. For example, the association unit 125 may determine that the body features correspond to the face features by analyzing one or more characteristics of the face features and the body features. For example, when the association unit 125 determines that one or more characteristics of the face features are similar to one or more features of the body features, the association unit 125 may associate the face features with the body features. According to another embodiment, the association unit 125 may determine that the body features correspond to the face features based on the proximity between the face features and the body features.

[0047] According to one embodiment, the association unit may store the associated face features and body features in the storage unit 129. For example, as shown in FIG. 5, the storage unit 129 may store the face features and body features together with the identification information of the detected person. According to one embodiment, the associated face features and body features may be temporarily stored in the storage unit 129.

[0048] In S860 of FIG. 8, the information processing apparatus 10 may acquire a second image. According to one embodiment, the image acquisition unit 121 may acquire a second image captured by the camera 4 at a second time. The second time is different from the first time. According to one embodiment, the second time is after the first time. According to one embodiment, the second image may be captured by a camera different from the camera that captures the first image. According to other embodiments, the acquired first image may include a plurality of faces in which each face of the plurality of recognition targets corresponds to the target. According to one embodiment, the recognition target may be a person.

[0049] In S870 of FIG. 8, the information processing apparatus 10 may extract body features from the second image. According to one embodiment, the extraction unit 123 may extract the body features in the second image, and the detection unit 122 may acquire the body features in the second image from the extraction unit 123.

[0050] In S880 of FIG. 8, the information processing apparatus 10 may compare the body features extracted from the second image with the body features stored in the storage unit 129. According to one embodiment, the detection unit 122 may compare the body features in the second image with the body features stored in the storage unit 129.

[0051] In S890 of FIG. 8, the information processing apparatus 10 may identify previously recognized face features based on the result of the comparison in S880. According to one embodiment, when the body features in the second image match the body features acquired from the memory unit 129, the detection unit 122 may acquire the identification of the target previously recognized in the first image. Therefore, the information processing apparatus 10 may identify previously recognized face features. On the other hand, when neither the body features in the second image nor the body features acquired from the memory unit 129 match, the detection unit 122 may determine that the body features in the second image do not correspond to the face features previously recognized in the first image.

[0052] In S891 of FIG. 8, when the previously recognized face features are identified in S890, the information processing apparatus 10 may be controlled to open the gate 114. According to one embodiment, the controller 126 may acquire from the detection unit 122 information indicating whether the body features in the second image match the body features acquired from the memory unit 129. When they match, the controller 126 may output a control signal for opening the gate 2.

[0053] In S892 of FIG. 8, when the previously recognized face features are not identified in S890, the information processing apparatus 10 may be enabled to close the gate 2. According to one embodiment, when neither the body features in the second image nor the body features acquired from the memory unit 129 match, the controller 126 may maintain the gate 2 in a closed state.

[0054] FIG. 9 is a block diagram showing an example of the hardware configuration of the automatic gate apparatus 1. The automatic gate apparatus 1 can automatically perform face recognition on a person approaching the gate, and can pass the person without requesting the person to stop for authentication even when the person is not always facing the camera while approaching the gate.

[0055] As shown in FIG. 9, the automatic gate device 1 includes a CPU 102, a RAM 104, a storage device 106, an input device 108, a display 110, a camera 112, a gate 114, and a communication unit 116. The CPU 102, RAM 104, storage device 106, input device 108, display 110, camera 112, gate 114, and communication unit 116 are connected to a bus line 118.

[0056] The CPU 102 may operate by executing a program stored in the storage device 106 and function as a control unit that controls the operation of the entire automatic gate device 1. Further, the CPU 102 may execute an application program stored in the storage device 106 to perform various processes as the automatic gate device 1. The RAM 104 may provide a memory field necessary for the operation of the CPU 102.

[0057] The storage device 106 may be composed of a storage medium such as a non-volatile memory or a hard disk drive and function as a storage unit. The storage device 106 may store a program executed by the CPU 102 and data referred to by the CPU 102 when the program is executed.

[0058] The input device 108 may be, for example, a touch panel built into the display 110. The input device 108 may function as an input unit that receives input from a user.

[0059] The display 110 may function as a display unit that displays various windows to a user who uses the automatic gate device. For example, the display 110 may display a guidance window showing how to use the automatic gate device 1 or a notification window to the user.

[0060] The camera 112 may image one person or multiple persons. The image may include the face area and body area of one or more persons. For example, the camera 112 may image the front area of the automatic gate device 1 and, when detecting the face of a user standing in front of the automatic gate device 1 in the continuously or periodically captured images, may be a digital camera that images the face of the user 1 and acquires the face image.

[0061] According to one embodiment, when personal authentication of a person is successful in the automatic gate device 1, the gate 114 changes from a closed state for the standby mode that blocks the passage of the person to an open state that permits the passage of the person. The type of the gate 114 is not particularly limited, and may be, for example, a flap gate in which one or more flaps provided on one or both sides of the passage open and close, or a turnstile gate in which three bars rotate.

[0062] The communication unit 116 may be connected to a network and may transmit and receive data via the network. The communication unit 116 communicates with a server or the like under the control of the CPU 102.

[0063] The present disclosure is not limited to the above-described exemplary embodiments, and can be appropriately changed without departing from the spirit of the present disclosure.

[0064] In each of the above-described exemplary embodiments, the information processing apparatus and system used for face recognition for gate control have been described as examples. However, the present disclosure can also be applied by appropriately changing the configuration of one or more exemplary embodiments to the fields of face recognition and body tracking other than gate control.

[0065] The scope of one or more exemplary embodiments also includes a processing method of storing, in a storage medium, a program for operating the configuration of the exemplary embodiment so as to realize the functions of the above-described exemplary embodiment, reading out the program stored in the storage medium as code, and executing the program on a computer. That is, a computer-readable storage medium is also included in the scope of each exemplary embodiment. Further, not only the storage medium in which the above-described program is stored, but also the program itself is included in each exemplary embodiment. Further, one or more components included in the above-described exemplary embodiments may be circuits such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA) configured to realize the functions of the respective components.

[0066] As the storage medium, for example, a floppy (registered trademark) disk, a hard disk, an optical disk, a magneto-optical disk, a compact disk (CD)-ROM, a magnetic tape, a non-volatile memory card, a ROM, or the like can be used. Further, the scope of each of the exemplary embodiments is not limited to an example in which processing is performed by an individual program stored in a storage medium, and includes an example in which processing is performed while operating on an operating system (OS) and in cooperation with the functions of other software and add-in boards.

[0067] The service implemented by the functions of the one or more exemplary embodiments described above can be provided to users in the form of software as a service (SaaS).

[0068] Note that all of the above-described exemplary embodiments are merely examples of embodiments for implementing the present disclosure, and the technical scope of the present disclosure should not be construed in a limited manner by these exemplary embodiments. That is, the present disclosure can be implemented in various forms without departing from its technical idea or its main features.

[0069] Further, the above-described exemplary embodiments may be fully or partially described by the following supplementary notes without being limited thereto.

[0070] (Appendix 1) A memory for storing one or more instructions, executing the one or more instructions to, obtain a first image including one or more faces captured at a first time by one or more cameras, each corresponding to one person among one or more persons, detect a first person from among the one or more persons by performing a face recognition operation on the one or more faces in the image obtained from the camera, detect a body region corresponding to the face region of the first person, track the body region in a second image captured by the one or more cameras at a second time after the first time, output information for controlling to open the barrier based on a determination that the body region is approaching the barrier a processor configured as such, and a device comprising the same.

[0071] (Appendix 2) Performing the face recognition operation includes extracting face features corresponding to the one or more faces from the first image, and detecting whether the face features match one of a plurality of registered face features, The device according to Appendix 1, comprising the same.

[0072] (Appendix 3) Tracking the body region in the second image includes associating the face region in the first image with the body region in the first image, and matching the body region in the second image with the body region in the first image, The device according to Appendix 1, comprising the same.

[0073] (Appendix 4) Outputting information for controlling the barrier includes Outputting a control signal for opening the gate based on a match between a feature of the body region in the second image and a feature of one of the plurality of body regions stored in the storage. The apparatus according to appended claim 1.

[0074] (Appended claim 5) The apparatus according to appended claim 4, wherein each of the plurality of body regions is pre-associated with a respective face region from one or more previously captured images.

[0075] (Appended claim 6) The apparatus according to appended claim 1, wherein the one or more faces include a plurality of faces captured by the one or more cameras at the first time, and the plurality of faces respectively correspond to a plurality of persons.

[0076] (Appended claim 7) The apparatus according to appended claim 1, wherein the body region is detected after the first person is detected by face recognition.

[0077] (Appended claim 8) The apparatus according to appended claim 1, wherein the body region is detected before the first person is detected by face recognition.

[0078] (Appended claim 9) The apparatus according to appended claim 1, wherein the body region is detected simultaneously with the detection of the first person by face recognition.

[0079] (Appended claim 10) A memory storing one or more instructions; Executing the one or more instructions to Obtain an image captured by a camera, which corresponds to each of a plurality of persons approaching a barrier and includes a plurality of faces each including a feature; Detect a first person as the person closest to the camera among the plurality of persons based on the size of the feature for the first person; A processor configured to output information for controlling the barrier based on a result of comparison between the face information of the first person from the acquired image and a plurality of registered information corresponding to the persons registered before acquiring the image An apparatus comprising the same

[0080] (Appendix 11) The apparatus according to Appendix 10, wherein the size of the feature corresponds to the area of the face region

[0081] (Appendix 12) The apparatus according to Appendix 10, wherein the size of the feature corresponds to the distance between the eyes

[0082] (Appendix 13) Obtaining a first image including one or more faces captured at a first time by one or more cameras, each corresponding to one person among one or more persons Detecting a first person from among the one or more persons by performing a face recognition operation on the one or more faces in the image acquired from the camera, and detecting a body region corresponding to the face region of the first person Tracking the body region in a second image captured by the one or more cameras at a second time after the first time Outputting information for controlling the barrier to be opened based on a determination that the body region is approaching the barrier A method including the same

[0083] (Appendix 14) Causing a computer to Obtaining a first image including one or more faces captured at a first time by one or more cameras, each corresponding to one person among one or more persons Detecting a first person from among the one or more persons by performing a face recognition operation on the one or more faces in the image acquired from the camera; detecting a body region corresponding to the face region of the first person; Tracking the body region in a second image captured by the one or more cameras at a second time after the first time; Outputting information for controlling the barrier to be opened based on a determination that the body region is approaching the barrier; A program for causing the above to be executed.

[0084] (Appendix 15) Obtaining an image captured by a camera that corresponds to each of a plurality of persons approaching a barrier and includes a plurality of faces each including features; Detecting a first person as the person closest to the camera among the plurality of persons based on the size of the features for the first person; Outputting information for controlling the barrier based on a result of comparison information between the face of the first person from the obtained image and a plurality of registered information corresponding to persons registered before obtaining the image; A method including the above.

[0085] (Appendix 16) Causing a computer to Obtain an image captured by a camera that corresponds to each of a plurality of persons approaching a barrier and includes a plurality of faces each including features; Detect a first person as the person closest to the camera among the plurality of persons based on the size of the features for the first person; Output information for controlling the barrier based on a result of comparison between information of the face of the first person from the obtained image and a plurality of registered information corresponding to persons registered before obtaining the image; A program for causing the above to be executed.

[0086] This application claims the benefit of priority based on U.S. Provisional Patent Application No. 62 / 910,751, filed on October 4, 2019, the entire disclosure of which is incorporated herein by reference.

Claims

1. A memory storing one or more instructions, executing the one or more instructions to obtain a first image including one or more faces captured at a first time by one or more cameras, each face corresponding to one person among one or more persons, detect a first person from among the one or more persons by performing a face recognition operation on the one or more faces in the first image obtained from the camera, detect a body region corresponding to the face region of the first person, track the body region in a second image captured by the one or more cameras at a second time after the first time a processor configured as such, and comprising, tracking the body region in the second image is associating the face region in the first image with a body region in the first image, and comparing the body region in the second image with the body region in the first image An apparatus including.

2. Performing the face recognition operation is extracting face features corresponding to the one or more faces from the first image, and detecting whether the face features match one of a plurality of registered face features The apparatus according to claim 1, including.

3. The apparatus according to claim 1, wherein each of a plurality of body regions stored in a storage unit is previously associated with a respective face region from one or more previously captured images.

4. The apparatus according to claim 1, wherein the one or more faces include a plurality of faces captured at the first time by the one or more cameras, and the plurality of faces respectively correspond to a plurality of persons.

5. The apparatus according to claim 1, wherein the body region is detected after the first person is detected by face recognition.

6. The apparatus according to claim 1, wherein the body region is detected before the first person is detected by face recognition.

7. The apparatus according to claim 1, wherein the body region is detected simultaneously with the detection of the first person by face recognition.

8. A computer, obtaining a first image including one or more faces captured at a first time by one or more cameras, each face corresponding to one person among one or more persons, Detecting a first person from among the one or more persons by performing a face recognition operation on the one or more faces in the first image acquired from the camera; Detecting a body region corresponding to the face region of the first person; Tracking the body region in a second image captured by the one or more cameras at a second time after the first time; including; tracking the body region in the second image includes: associating the face region in the first image with a body region in the first image; comparing the body region in the second image with the body region in the first image. A method. **Claim 9** Causing a computer to: acquire a first image including one or more faces captured at a first time by one or more cameras, each corresponding to one person among one or more persons; detect a first person from among the one or more persons by performing a face recognition operation on the one or more faces in the first image acquired from the camera; detect a body region corresponding to the face region of the first person; track the body region in a second image captured by the one or more cameras at a second time after the first time; and execute, tracking the body region in the second image includes: associating the face region in the first image with a body region in the first image; comparing the body region in the second image with the body region in the first image. A program. **Claim 10** Obtaining a first image and a second image captured at a time later than the time when the first image was captured, detecting a first person having the face by performing a face recognition operation on the face captured in the first image, associating, in the first image, the face region of the first person with the body region of the first person, and comparing the body region in the first image with the body region of the first person captured in the second image. A processor.

Images