JP2020077399A - Information processing device - Google Patents

Abstract

To solve a problem such that it is difficult to smoothly pass a gate.SOLUTION: An information processing device 200 comprises: image processing means 220 for extracting a feature quantity of an object in a photographed image obtained by photographing a region before passage of a gate to store collation information concerning collation of the object based on the feature quantity; distance estimation means 230 for estimating a distance from the gate to the object in the photographed image; and collation means 240 for performing collation determination based on the estimated distance and collation information in which the object that estimated the distance is stored.SELECTED DRAWING: Figure 9

Description

  The present invention relates to an information processing device, an information processing system, a program, and an information processing method.

  As a means for restricting and managing persons who enter and leave a specific place such as an office or an event venue, a collation system that collates whether or not the person who is going to pass is a person who is registered in advance is used. In particular, in recent years, with the development of person face recognition technology, a walk-through face recognition system has been used that performs face recognition from a person's face image taken by a camera installed at a gate.

JP, 2016-083225, A

  Here, in the walk-through face authentication system, it is necessary to open and close the gates by collating the people lined up in the gates in order so that the people can smoothly pass through the gates. However, there are various persons who try to pass through the gate, and it is difficult to properly determine the order. As a result, there arises a problem that it is difficult to smoothly pass through the gate.

  Therefore, an object of the present invention is to solve the above-mentioned problem that it is difficult to smoothly pass through a gate.

An information processing apparatus which is one mode of the present invention,
An image processing unit that extracts a feature amount of a target in a captured image of a pre-passage area of the gate, and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
With
Take the configuration.

Further, the information processing system which is one embodiment of the present invention,
Imaging means for acquiring a photographed image of the area before passing through the gate,
An image processing unit that extracts a feature amount of the target in the captured image and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
With
Take the configuration.

In addition, the program which is one mode of the present invention,
In the information processing device,
An image processing unit that extracts a feature amount of a target in a captured image of a pre-passage area of the gate, and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
To realize
Take the configuration.

In addition, the information processing method, which is an aspect of the present invention,
The feature amount of the target in the captured image of the pre-passage area of the gate is extracted, and matching information regarding matching of the target based on the characteristic amount is stored,
Estimate the distance from the gate to the object in the captured image,
A collation determination is performed based on the estimated distance and the stored collation information of the target whose distance is estimated,
Take the configuration.

  The present invention can provide an information processing device capable of smoothly passing through a gate by being configured as described above.

It is a figure which shows the use condition of the face authentication system in Embodiment 1 of this invention. It is a block diagram showing a configuration of a face authentication system according to the first exemplary embodiment of the present invention. It is a figure which shows the imaging condition by the face recognition system disclosed in FIG. It is a figure which shows the use condition of the face authentication system disclosed in FIG. 3 is a flowchart showing a processing operation by the face authentication system disclosed in FIG. 1. 3 is a flowchart showing a processing operation by the face authentication system disclosed in FIG. 1. It is a block diagram which shows the structure of the face authentication system in Embodiment 2 of this invention. It is a block diagram which shows the structure of the information processing system in Embodiment 3 of this invention. It is a block diagram which shows the structure of the information processing apparatus in Embodiment 3 of this invention.

<Embodiment 1>
A first embodiment of the present invention will be described with reference to FIGS. FIG. 1 is a diagram showing a usage situation of the face authentication system. FIG. 2 is a diagram showing the configuration of the face authentication system. 3 to 6 are diagrams for explaining the processing operation of the face authentication system.

[overall structure]
The face authentication system 10 (information processing system) according to the present invention is a system used for restricting or managing entrance and exit of a person (target) in a specific place such as an office or an event venue. For example, the imaging device C that constitutes the face authentication system 10 is installed in the vicinity of the location of the gate for each gate that is opened and closed when a person enters and leaves.

  In the example shown in FIG. 1, a plurality of gates G are arranged adjacent to each other in parallel, and a person passes in the direction indicated by the arrow from the right side of FIG. 1 toward each gate G. Therefore, the right side region of FIG. 1 for each gate G is a front side region (front side region) where a person passes through the gate. In addition, in the front passage area of each gate G, the lanes through which the person trying to pass the gate G side by side passes are located in parallel corresponding to each gate G. Each lane may or may not be partitioned by some member. Further, although the case where a plurality of gates G are arranged adjacent to each other is illustrated in the present embodiment, the number of gates G may be only one.

  In the situation shown in FIG. 1, the imaging device C that constitutes the face authentication system 10 according to the present embodiment is installed in the vicinity of each corresponding gate G and on the right side when viewed from a person who faces each gate G. However, the installation position of the imaging device is not limited to the position shown in FIG. 1, and may be installed at any position such as on the left side of the gate or above the gate. The face authentication system 10 also includes a display device D near each imaging device C.

  Then, the face authentication system 10 captures an image of a person who faces the gate G by using the image capturing apparatus C provided therein. Then, the face image of the person shown in the photographed image is collated to determine whether or not the person is a pre-registered person, and if the collation is successful, the gate G is opened so that the person can pass through. Hereinafter, the configuration of the face authentication system 10 will be described in detail.

[Face recognition system configuration]
The face authentication system 10 according to the present embodiment is an information processing apparatus including an arithmetic device and a storage device that are integrally configured with an imaging device C (camera) and a display device D (display). To put it the other way around, the image pickup apparatus C is equipped with an information processing apparatus and a display apparatus D each having an arithmetic unit for performing face recognition processing and a storage unit. However, the face authentication system 10 is not necessarily limited to being configured integrally with the imaging device C and the display device D. For example, the imaging device C, the display device D, and the information processing device that processes a captured image may be configured by different devices, and may be installed at different locations.

  Specifically, as shown in FIG. 2, the face authentication system 10 includes an image pickup device C and a display device D, and a feature amount extraction unit 11 and a distance measurement unit that are constructed by executing a program by an arithmetic device. It includes a unit 12, a collation unit 13, and a gate control unit 14. The face authentication system 10 also includes a feature amount storage unit 15 and a matching data storage unit 16 built in a storage device.

  The imaging device C (imaging unit) includes a camera and a camera control unit that acquires a captured image of a front side area of the gate G, that is, a front gate area of a corresponding lane at a predetermined frame rate. Then, in the imaging device C, as shown in FIG. 1, for example, the range sandwiched by the reference Ca lines is the imaging region. For example, when there are three persons P10, P11, P12 in the lane as shown in FIG. 1, the captured image captured by the image capturing apparatus C is as shown in FIG. Note that the captured image is set to be substantially in focus within a range of a preset distance in the perspective direction with respect to the imaging device C.

  When the captured image is captured by the imaging device C, the feature amount extraction unit 11 (image processing means) extracts a person in the captured image and first performs a process of extracting the feature amount of the person. Specifically, the feature amount extraction unit 11 extracts a person in the captured image, targets all the extracted persons, and generates a feature amount necessary for matching from the face area of the person. The feature amount is information used by the collation unit 13 to calculate a collation score such as the degree of similarity with the feature amount of a person registered in the collation data storage unit 16 in advance and perform the collation process. The feature amount may be a feature amount used in the existing face matching technique or a feature amount calculated by another method.

  Then, the feature amount extraction unit 11 stores the extracted feature amount in the feature amount storage unit 15 as information related to person matching, that is, information used for matching processing (matching information). At this time, the feature amount is stored in the feature amount storage unit 15 in association with the information for identifying the person in the captured image. Although the person in the captured image may be tracked in the subsequent captured image, in that case, the tracked person and the feature amount in the feature amount storage unit 15 are associated with each other.

  Further, the feature amount extraction unit 11 may extract feature amounts from different captured images for one person and store a plurality of feature amounts. Further, the feature amount extraction unit 11 may store only one feature amount when the feature amount is extracted from different captured images. That is, when the feature amount is extracted each time a captured image is acquired for the same person, only one feature amount may be updated and stored. For example, the quality of the extracted feature amount may be determined, and only one feature amount having the highest quality may be stored in association with the person.

  The feature amount extraction unit 11 may perform the matching process using the matching unit 13 described below. In this case, the feature amount extraction unit 11 issues a collation instruction to the collation unit 13, and performs the collation process between the feature amount of the person in the captured image extracted as described above and the person registered in advance. Then, the characteristic amount extraction unit 11 may acquire the collation result by the collation unit 13 and store the collation result in the characteristic amount storage unit 15 as collation information regarding collation of a person. At this time, the feature amount is stored in the feature amount storage unit 15 in association with the information for identifying the person in the captured image. Although the person in the captured image may be tracked in the subsequent captured image, in that case, the tracked person and the matching result in the feature amount storage unit 15 are associated with each other. At this time, the feature amount extraction and collation processing may be performed on a plurality of captured images, and in that case, only one collation result may be updated and stored in association with the person.

  The distance measuring unit 12 (distance estimating means) measures the distance from the gate G to the person in the captured image from which the feature amount is extracted as described above. At this time, in this embodiment, the distance from the gate G to the person is measured using the image portion of the person in the captured image. Specifically, the distance is measured as follows.

  The distance measuring unit 12 first sets a reference value necessary for measuring the distance to a person in a captured image. Specifically, the distance measuring unit 12 extracts the image portion of the face area of the person to be processed from the captured image. The extraction of the face area of the person is performed, for example, by determining the position and color of the moving person with respect to the entire image. Then, the distance measuring unit 12 performs attribute analysis processing for determining the attribute of a person from the image portion of the face area. Here, the attributes of a person are, for example, sex, age (age, adult, child), race, and the like.

  In the attribute analysis process, for example, the attribute discrimination information that is information necessary for discriminating the attribute is extracted from the image portion of the face area, and the extracted attribute discrimination information and the attribute discrimination reference information registered in advance are extracted. By comparison, the attributes of the person are determined. Here, the attribute discrimination information is information that represents a physical feature that generally appears in the face area of a person for each attribute such as gender and age. Since the attribute analysis process for determining the attribute such as the gender and age (age) of a person can be realized by the existing technology, detailed description of the process will be omitted. Further, the distinguishable attribute is not limited to the above-mentioned attribute, and may be any attribute.

  Then, the distance measuring unit 12 sets a reference value corresponding to the determined attribute of the person. Here, the reference value is registered in advance in a storage device equipped in the face authentication system 10. For example, in the present embodiment, the reference value of the eye-to-eye distance representing the distance between the eyes of a person is Registered in. As an example, when a certain number is registered as the eye-to-eye distance which is the reference value of the attribute such as "male", the eye-to-eye distance which is the reference value of the attribute such as "female" is smaller than the reference value of male. Is set. In addition, for example, when a certain numerical value is registered as the eye-to-eye distance which is a reference value of an attribute such as “adult” from the age of 15 to 60s, the criterion of the attribute such as “child” whose age is less than 15 years is registered. The eye-to-eye distance, which is a value, is set to a value smaller than the standard value for adults. In this way, the reference value is a value according to the general physical constitution of the attributes of the person. Then, the distance measuring unit 12 sets the reference value registered corresponding to the attribute determined for the person extracted from the captured image, as the reference value of the person.

  Further, the distance measuring unit 12 measures the distance to the person by using the reference value set for the person as described above. Specifically, the distance measuring unit 12 first detects, as the target information indicating the feature of the person in the captured image, the inter-eye distance indicating the distance between the eyes of the person from the image portion of the face area of the person. For example, the eye-to-eye distances of the persons P10, P11, and P12 in the captured image are detected as indicated by reference signs d10, d11, and d12 in FIG. Then, the detected eye-to-eye distances d10, d11, d12 are compared with the reference values set for the persons P10, P11, P12, and the distance from the gate G to each person is measured. For example, the distance from the gate G to the person is measured from the difference between the eye distances detected from the person with respect to the reference value set for the person and the ratio of the difference. The distance measuring unit 12 may measure the relative distance of the person in the captured image, that is, the order with respect to the gate G as the distance with respect to the gate G.

  Here, an example of distance measurement from the gate G to the persons P10, P11, P12 will be described. In the example of FIG. 1, persons P10, P11, and P12 are arranged in order toward the gate G, and the captured image is captured as shown in FIG. At this time, if the physiques and face sizes of the persons P10, P11, P12 are substantially the same, the eye-to-eye distances d10, d11, d12 of the persons P10, P11, P12 are generally d10> d11>. It becomes d12. On the other hand, if the person P10 is a child and the persons P11 and P12 are adults, it is generally considered that the child's face is small and the eye-to-eye distance is short. The result is d11> d12> d10. In such a situation, in the present embodiment, the attribute of the person P10 is determined to be “child”, a reference value of a small value is set, and the distance is measured using the reference value and the detected eye-to-eye distance d10. It Then, the attributes of the persons P11 and P12 are determined to be “adult”, a reference value that is larger than the reference value of the child is set, and the distance is measured using the reference value and the detected eye-to-eye distances d11 and d12. To be done. As a result, as shown in FIG. 4, the distances D10, D11, D12 to the respective persons can be measured so that the persons P10, P11, P12 are arranged in order with respect to the gate G, as in the actual order for the gate G.

  Then, the distance measuring unit 12 associates the measured distance with the person in the captured image, so that the distance is also associated with the feature amount of the same person stored in the feature amount storage unit 15. Although the person in the captured image may be tracked in the subsequent captured image, in that case, the distance to the tracked person is measured in the same manner as above, and the distance associated with the person is updated. .. Note that the association of persons in captured images that are temporally before and after can be realized by tracking feature points or the like.

  The method for detecting the eye-to-eye distance by the distance measuring unit 12 is not limited to the method described above, and any method may be used. Further, the distance measuring unit 12 may measure the distance by detecting the size of other parts of the person or other characteristics as the target information, instead of the inter-eye distance. In this case, the reference value described above is also a value corresponding to the target information.

  Here, the distance measuring unit 12 is not necessarily limited to measuring the distance from the gate G to the person. For example, the distance measuring unit 12 may estimate the relative positional relationship between the persons with respect to the gate. As an example, the distance measuring unit 12 estimates the proximity of each person to the gate, that is, the perspective relationship between the persons with respect to the gate G, based on the target information such as the above-mentioned eye distance and the reference value. Good.

  The matching unit 13 (matching unit) performs matching processing between a person in a captured image and a person registered in advance. At this time, the matching unit 13 performs the matching process based on the distance to the person measured as described above. For example, in the matching unit 13, the person is located in a predetermined range located at a preset distance from the gate G set immediately before the gate G, and the person is located closest to the gate G in the captured image. If so, the collation process for such a person is performed. Note that the matching unit 13 may perform the matching process of a person when the person is located in a predetermined range located at a preset distance from the gate G set immediately before the gate G, Alternatively, the matching process of the person may be performed based on another criterion according to the distance to the person. Further, when the distance measuring unit 12 estimates only the relative positional relationship between the persons with respect to the gate G as described above, the collation unit 13 determines that the person closest to the gate G is determined from the positional relationship. You may perform a collation process.

  The matching process by the matching unit 13 is performed using the feature amount stored in the feature amount storage unit 15 of the person who is the processing target based on the distance as described above. That is, the collation unit 13 does not newly generate the feature amount from the face area of the person in the captured image, but registers the feature amount stored in the feature amount storage unit 15 and the collation data storage unit 16 in advance. Matching is performed by calculating a matching score such as the similarity between the feature amount of the person and determining whether the matching score is higher than a threshold value. If the matching score is higher than the threshold value, it is determined that the matching is successful, and the person trying to pass through the gate G is determined to be the person who is registered in advance. Any matching method may be used.

  Note that the collation unit 13 has already performed the collation process on the person who is the processing target based on the distance according to the instruction from the feature amount extraction unit 11 as described above, and the collation result is stored in the feature amount storage unit 15. If it is stored, only the verification result is confirmed. That is, the matching unit 13 checks the success or failure of the matching result, which is the matching information stored for the person who has been processed according to the distance, and determines whether the matching is successful.

  The gate control unit 14 (gate control means) first determines whether or not a person can pass through the gate G based on the matching result by the matching unit 13. Specifically, it is determined that a person whose matching by the matching unit 13 has succeeded can be passed. Further, the gate control unit 14 has a function of displaying the collation result, that is, the success or failure of the collation on the display device D. Further, the gate control unit 14 also has a gate control function of opening and closing the gate G, and controls a person who is determined to be able to pass through to open the gate G.

  The display device D is arranged with its display surface facing the front passage area of the gate G so that a person passing through the gate G can visually recognize it. However, the display device D does not necessarily have to be equipped.

[motion]
Next, the operation of the face authentication system 10 described above will be described with reference to the flowcharts of FIGS. Here, the operation of the face authentication system 10 corresponding to the gate G will be described, and a case where a person is lined up with respect to the gate G as shown in FIGS. 3 and 4 will be described as an example.

  The imaging device C corresponding to the gate G continues to capture an image of the area before passing through the gate G. Then, the face authentication system 10 always performs the following processing on the captured image.

  First, the feature amount extraction unit 11 extracts persons (targets) P10, P11, P12 to be processed from the captured image (step S1). Then, if the feature amount extraction unit 11 can extract the feature amount of the extracted person from the situation of the captured image (Yes in step S2), the feature amount extraction unit 11 generates the feature amount required for matching from the face area of the person (step S2). Step S3). Then, the feature amount extraction unit 11 stores the extracted feature amount in the feature amount storage unit 15 in association with the person in the captured image. In addition, when it is not possible to sufficiently generate the characteristic amount of the person from the captured image, such as when the captured image does not clearly show the face area of the person or the front of the face is not reflected (No in step S2). A feature amount is generated for the subsequent captured image.

  Then, the distance measuring unit 12 measures the distance from the gate G to the person in the captured image from which the feature amount is extracted (step S4). Here, the process of measuring the distance by the distance measuring unit 12 will be described with reference to the flowchart of FIG.

  The distance measuring unit 12 performs attribute analysis processing on the image portion of the face area of the person in the captured image to determine the attribute of the person. For example, in the example of FIGS. 1 and 3, it is assumed that the attribute of the person P10 is determined to be a child and the attributes of the persons P11 and P12 are determined to be an adult. Then, the distance measuring unit 12 sets the reference value stored in advance in the face authentication system 10 in correspondence with the determined attribute of the person as the reference value of the person (step S11). For example, in the example of FIGS. 3 and 4, a reference value corresponding to a child is set for the person P10, and a reference value corresponding to an adult is set for the persons P11 and P12.

  Subsequently, the distance measuring unit 12 measures the size of a predetermined part which is a feature of the person as target information necessary for measuring the distance to the gate G of the person in the captured image, here, the distance between the eyes of the person. Is detected (step S12). For example, the eye-to-eye distances of the persons P10, P11, and P12 are detected as indicated by reference signs d10, d11, and d12 in FIG.

  Then, the distance measuring unit 12 compares, for each person, the reference value set for each person P10, P11, P12 as described above and the eye-to-eye distance d10, d11, d12 of each person P10, P11, P12. Then, the distance from the gate G to each person P10, P11, P12 is measured (step S13). For example, in the example of FIG. 3B, the eye distance d11 of the person P11 is the second largest from the gate among the three persons, but the reference values set for the persons P10, P11, and P12 are different. Therefore, the distances D10, D11, and D12 to each person are measured so that the persons P10, P11, and P12 are in the order as shown in FIG.

  Then, the collation unit 13 performs the collation process for each person based on the distance to each person P10, P11, P12 measured as described above. At this time, when the person is located at a preset distance from the gate G set immediately before the gate G and the person is located closest to the gate G in the captured image, Such a person matching process is performed (Yes in step S5, step S6). Therefore, in the example of FIG. 4, the matching process of the person P10 closest to the gate G is performed. Specifically, the collation unit 13 stores the feature amount stored in the feature amount storage unit 15 in association with the person in the captured image to be subjected to the collation process and the person registered in the collation data storage unit 16 in advance. This is performed by calculating a matching score such as the similarity between the feature amount and the matching score and determining whether the matching score is higher than a threshold value (step S6). If the matching score is higher than the threshold value, the matching is successful (Yes in step S7), and the person trying to pass through the gate G is determined to be the person who is registered in advance.

  As a result of the matching processing by the matching unit 13, if the matching of the person P10 located immediately before the gate G succeeds (Yes in step S7), the gate control unit 14 permits the person P10 to pass through the gate G and opens the gate G. Control (step S8). At this time, the gate control unit 14 displays on the display device D whether the passage is possible or not.

  As described above, according to the face authentication system 10 of the present embodiment, the feature amount is extracted in advance from the face area of the person in the area before passing through the gate G, and the matching process is performed immediately before the gate. The gate can be opened and closed appropriately. As a result, a person can smoothly pass through the gate G.

  In addition, the feature amount of the person is extracted and stored not only immediately before the gate G but also from a captured image taken at an arbitrary timing when the person moves toward the gate G. Therefore, the feature amount with high reliability can be extracted and the accuracy can be improved. It is possible to collate well. As a result, a person can smoothly pass through the gate G.

  Note that, in the above, the case where the target trying to pass through the gate G is a person is illustrated, but the object is not limited to a person and may be any object. For example, it may be an object such as luggage. Accordingly, the information used to measure the distance from the gate G, such as the above-described reference value and target information indicating the target feature, may be information indicating any feature that can be detected from the object. Further, when performing the matching process, any feature amount that can be detected from the object may be used.

<Embodiment 2>
Next, a second embodiment of the present invention will be described with reference to FIG. FIG. 7 is a block diagram showing the configuration of the face authentication system.

  The face authentication system 10 according to the present embodiment has almost the same configuration as that of the above-described first embodiment, but measures the distance from the gate G to the person without using a captured image for extracting the feature amount. It is a structure. Hereinafter, mainly the configuration different from that of the first embodiment will be described in detail.

  As shown in FIG. 7, the face authentication system 10 according to the present embodiment includes a distance measuring device E in addition to the face authentication system 10 described in the first embodiment. The range finder E is, for example, an infrared depth sensor, and is present in the pre-passage area of the gate G using the measured depth, which is information different from the captured image for extracting the feature amount of the person as described above. It is a device that can measure the distance to a person who does.

  The distance-measuring device E is, for example, near each corresponding gate G, and is installed on the right side or above the gate when viewed from a person who faces each gate G, like the image pickup device C. Further, if the distance measuring device E is composed of one device, one is installed, and if it is composed of a plurality of devices, a plurality of devices are installed. The distance measuring device E may be a device that measures the distance to a person by another method.

  Then, the distance measuring unit 12 in the present embodiment acquires the depth measured from the distance measuring device E and associates it with the person in the captured image. For example, the distance measuring unit 12 identifies the depth for each position in the pre-passage area of the gate G and associates it with the position of the captured image. Thereby, the distance to each person located in the captured image can be specified, and the distance can be associated with the person. In this way, as in the first embodiment, the measured distance can be associated with the feature amount of the same person stored in the feature amount storage unit 15.

  Although the person in the captured image may be tracked in the subsequent captured image, in that case, the distance to the tracked person is measured in the same manner as described above, and the distance associated with the person is updated. To do. Note that the association of persons in captured images that are temporally before and after can be realized by tracking feature points or the like.

  Then, the matching unit 13 in the present embodiment performs the matching process based on the distance to the person measured as described above. The matching process is similar to that of the first embodiment, and when a person is positioned immediately before the gate G, the feature amount stored for the person is read and the matching process is performed.

  Here, the distance measuring device E and the distance measuring unit 12 are not necessarily limited to measuring the distance from the gate G to the person. For example, the distance measuring device E and the distance measuring unit 12 may estimate the relative positional relationship between the persons with respect to the gate. That is, the distance measuring device E and the distance measuring unit 12 may estimate the perspective relationship between the persons with respect to the gate G. Then, the matching unit 13 may perform the matching process on the person closest to the gate G based on the estimated relative positional relationship between the persons with respect to the gate G.

  Even in the above manner, it is possible to appropriately open and close the gate with respect to the person in front of the gate, and it is possible to realize the smooth passage of the person through the gate G.

<Embodiment 3>
Next, a third embodiment of the present invention will be described with reference to FIGS. FIG. 8 is a block diagram showing the configuration of the information processing system according to the third embodiment. FIG. 9 is a block diagram showing the arrangement of the information processing apparatus according to the third embodiment. In this embodiment, the outline of the configuration of the face authentication system described in the first and second embodiments is shown.

As shown in FIG. 8, the information processing system 100 according to the present embodiment is
An image pickup means 110 for obtaining a photographed image of the area before passing through the gate;
An image processing unit 120 for extracting the feature amount of the target in the photographed image and storing the matching information used for matching the target based on the feature amount;
Distance estimating means 130 for estimating a distance from the gate to an object in the captured image,
Collation means 140 for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
With
Take the configuration.

Further, in the present embodiment, the image pickup means 110 may be removed from the information processing system 100 shown in FIG.
That is, the information processing device 200 according to the present embodiment is
An image processing unit 220 that extracts a feature amount of a target in a captured image of a pre-passage area of a gate and stores matching information used to match the target based on the feature amount,
Distance estimating means 230 for estimating a distance from the gate to an object in the captured image,
Collation means 240 for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
With
Take the configuration.

  The image processing means 120, 220, the distance estimation means 130, 230, and the matching means 140, 240 described above may be constructed by an arithmetic unit executing a program, or may be constructed by electronic circuits. It may be one.

The information processing system 100 or the information processing apparatus 200 having the above configuration is
The feature amount of the target in the captured image of the pre-passage area of the gate is extracted, and the matching information used for matching the target based on the feature amount is stored,
Estimate the distance from the gate to the object in the captured image,
A collation determination is performed based on the estimated distance and the stored collation information of the target whose distance is estimated,
It operates to perform the process.

  According to the information processing system 100 or the information processing apparatus 200 described above, the feature amount is extracted in advance from the face area of the person in the pre-passage region of the gate, or the matching process is performed in advance by using the feature amount. Since the collation determination is performed immediately before, it is possible to appropriately open and close the gate for the person. Further, since the characteristic amount of the person is extracted and stored from the photographed image photographed at an arbitrary timing when the person moves toward the gate, the highly reliable characteristic amount can be extracted and the matching can be performed accurately. As a result, a person can smoothly pass through the gate.

<Appendix>
The whole or part of the exemplary embodiments disclosed above can be described as the following supplementary notes. Hereinafter, the outline of the configurations of the information processing apparatus, the information processing system, the program, and the information processing method according to the present invention will be described. However, the present invention is not limited to the following configurations.

(Appendix 1)
An image processing unit that extracts a feature amount of a target in a captured image of a pre-passage area of the gate, and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
Information processing device equipped with.

(Appendix 2)
The information processing apparatus according to attachment 1,
The matching means performs matching processing on the basis of the estimated distance, with the characteristic amount that is the stored matching information of the target for which the distance is estimated, and a previously registered characteristic amount,
Information processing device.

(Appendix 3)
The information processing device according to attachment 2,
The collation unit performs collation processing of the stored feature amount of the target located at a preset distance with respect to the gate and a preregistered feature amount;
Information processing device.

(Appendix 4)
The information processing apparatus according to attachment 2 or 3,
The collation unit performs collation processing of the stored feature amount of the target located closest to the gate and a pre-registered feature amount,
Information processing device.

(Appendix 5)
The information processing apparatus according to attachment 1,
The image processing means performs a collation process between the stored feature amount and a feature amount registered in advance, and stores a collation result as the collation information,
The collation unit performs collation determination based on the estimated distance and a collation result that is the collation information stored in the target that estimated the distance,
Information processing device.

(Appendix 6)
The information processing apparatus according to any one of appendices 1 to 5,
The image processing means extracts the feature amount of the target from a plurality of the captured images, and updates and stores the matching information of the target based on the feature amount.
Information processing device.

(Appendix 7)
The information processing apparatus according to any one of appendices 1 to 6,
The distance estimating means estimates a distance to an object existing in a pre-passage area of the gate by using information different from the captured image for extracting the feature amount,
Information processing device.

(Appendix 8)
The information processing apparatus according to any one of appendices 1 to 6,
The distance estimating means estimates a distance to the target using an image portion of the target in the captured image,
Information processing device.

(Appendix 9)
The information processing apparatus according to attachment 8,
The distance estimating unit determines an attribute of a target in the captured image, sets a reference value corresponding to the attribute, and estimates a distance to the target in the captured image using the reference value.
Information processing device.

(Appendix 10)
The information processing apparatus according to attachment 9,
The distance estimation means detects target information representing a characteristic of a target in the captured image, and estimates a distance to the target in the captured image based on the reference value and the target information.
Information processing device.

(Appendix 11)
The information processing apparatus according to attachment 10,
The distance estimating means detects, as the target information, the size of a predetermined part of the target in the captured image, and based on the size of the predetermined part of the target with respect to the reference value, up to the target in the captured image. Estimate the distance,
Information processing device.

(Appendix 12)
Imaging means for acquiring a photographed image of the area before passing through the gate,
An image processing unit that extracts a feature amount of the target in the captured image and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
Information processing system equipped with.

(Appendix 12.1)
The information processing system according to attachment 12,
The collation unit performs collation processing of the stored feature amount of the target located at a preset distance with respect to the gate and a preregistered feature amount;
Information processing system.

(Appendix 12.2)
The information processing system according to appendix 12 or 12.1,
The collation unit performs collation processing of the stored feature amount of the target located closest to the gate and a pre-registered feature amount,
Information processing system.

(Appendix 13)
In the information processing device,
An image processing unit that extracts a feature amount of a target in a captured image of a pre-passage area of the gate, and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
A program for realizing.

(Appendix 13.1)
The program according to Appendix 13,
The collation unit performs collation processing of the stored feature amount of the target located at a preset distance with respect to the gate and a preregistered feature amount;
program.

(Appendix 13.2)
The program according to supplementary note 13 or 13.1,
The collation unit performs collation processing of the stored feature amount of the target located closest to the gate and a pre-registered feature amount,
program.

(Appendix 14)
The feature amount of the target in the captured image of the pre-passage area of the gate is extracted, and matching information regarding matching of the target based on the characteristic amount is stored,
Estimate the distance from the gate to the object in the captured image,
A collation determination is performed based on the estimated distance and the stored collation information of the target whose distance is estimated,
Information processing method.

(Appendix 15)
The information processing method according to attachment 14,
On the basis of the estimated distance, a matching process is performed between the feature amount, which is the stored match information of the target whose distance is estimated, and a feature amount registered in advance.
Information processing method.

(Appendix 16)
The information processing method according to attachment 15,
A matching process is performed between the stored feature amount of the target located at a preset distance with respect to the gate and a feature amount registered in advance;
Information processing method.

(Appendix 17)
The information processing method according to appendix 15 or 16,
A matching process is performed between the stored feature amount of the target located closest to the gate and a pre-registered feature amount,
Information processing method.

(Appendix 18)
The information processing method according to any one of appendices 15 to 17,
Estimating a distance to an object existing in the pre-passage area of the gate using information different from the captured image for extracting the feature amount;
Information processing method.

(Appendix 19)
The information processing method according to any one of appendices 15 to 17,
Estimating the distance to the target using the image portion of the target in the captured image,
Information processing method.

(Appendix 19.1)
The information processing method according to attachment 19,
The attribute of the target in the captured image is determined, a reference value corresponding to the attribute is set, and the distance to the target in the captured image is estimated using the reference value.
Information processing device.

(Appendix 19.2)
The information processing method according to appendix 19.1,
Detecting target information representing a characteristic of a target in the captured image, and estimating a distance to the target in the captured image based on the reference value and the target information,
Information processing method.

(Appendix 19.3)
The information processing method according to appendix 19.2,
Detecting the size of a predetermined part of the target in the captured image as the target information, and estimating the distance to the target in the target image based on the size of the predetermined part of the target with respect to the reference value,
Information processing method.

  The above-mentioned program is stored in a storage device or a computer-readable recording medium. For example, the recording medium is a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, and a semiconductor memory.

  Although the invention of the present application has been described with reference to the exemplary embodiments and the like, the invention of the present application is not limited to the above-described exemplary embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

10 Face Authentication System 11 Feature Extraction Unit 12 Distance Measuring Unit 13 Collating Unit 14 Gate Control Unit 15 Feature Amount Storage Unit 16 Matching Data Storage Unit 100 Information Processing System 200 Information Processing Device 110 Imaging Unit 120, 220 Image Processing Unit 130, 230 Distance estimating means 140, 240 Collating means C Imaging device D Display device E Distance measuring device G Gate

Claims (19)

An image processing unit that extracts a feature amount of a target in a captured image of a pre-passage area of the gate, and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
Information processing device equipped with. The information processing apparatus according to claim 1, wherein
The collation unit performs collation processing of the feature amount, which is the stored collation information of the target for which the distance is estimated, and a feature amount registered in advance, based on the estimated distance.
Information processing device equipped with. The information processing apparatus according to claim 2, wherein
The collation unit performs collation processing of the stored feature amount of the target located at a preset distance with respect to the gate and a preregistered feature amount;
Information processing device. The information processing apparatus according to claim 2 or 3, wherein
The collation unit performs collation processing of the stored feature amount of the target located closest to the gate and a pre-registered feature amount,
Information processing device. The information processing apparatus according to claim 1, wherein
The image processing means performs a collation process between the stored feature amount and a feature amount registered in advance, and stores a collation result as the collation information.
The collation unit performs collation determination based on the estimated distance and a collation result that is the collation information stored in the target that estimated the distance,
Information processing device. The information processing apparatus according to any one of claims 1 to 5,
The image processing means extracts the feature amount of the target from a plurality of the captured images, and updates and stores the matching information of the target based on the feature amount.
Information processing device. The information processing apparatus according to any one of claims 1 to 6,
The distance estimating means estimates a distance to an object existing in a pre-passage area of the gate by using information different from the captured image for extracting the feature amount,
Information processing device. The information processing apparatus according to any one of claims 1 to 6,
The distance estimating means estimates a distance to the target using an image portion of the target in the captured image,
Information processing device. The information processing apparatus according to claim 8,
The distance estimating unit determines an attribute of a target in the captured image, sets a reference value corresponding to the attribute, and estimates a distance to the target in the captured image using the reference value.
Information processing device. The information processing apparatus according to claim 9,
The distance estimation means detects target information representing a characteristic of a target in the captured image, and estimates a distance to the target in the captured image based on the reference value and the target information.
Information processing device. The information processing apparatus according to claim 10, wherein
The distance estimating means detects, as the target information, the size of a predetermined part of the target in the captured image, and based on the size of the predetermined part of the target with respect to the reference value, up to the target in the captured image. Estimate the distance,
Information processing device. Imaging means for acquiring a photographed image of the area before passing through the gate,
An image processing unit that extracts a feature amount of the target in the captured image and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
Information processing system equipped with. In the information processing device,
An image processing unit that extracts a feature amount of a target in a captured image of a pre-passage area of the gate, and stores matching information regarding matching of the target based on the feature amount,
Distance estimation means for estimating the distance from the gate to the object in the captured image,
Collation means for performing collation determination based on the estimated distance and the stored collation information of the target whose distance is estimated,
A program for realizing. The feature amount of the target in the captured image of the pre-passage area of the gate is extracted, and matching information regarding matching of the target based on the characteristic amount is stored,
Estimate the distance from the gate to the object in the captured image,
A collation determination is performed based on the estimated distance and the stored collation information of the target whose distance is estimated,
Information processing method. The information processing method according to claim 14, wherein
On the basis of the estimated distance, a matching process is performed between the feature amount, which is the stored match information of the target whose distance is estimated, and a feature amount registered in advance.
Information processing method. The information processing method according to claim 15, wherein
A matching process is performed between the stored feature amount of the target located at a preset distance with respect to the gate and a feature amount registered in advance;
Information processing method. The information processing method according to claim 15 or 16, wherein
A matching process is performed between the stored feature amount of the target located closest to the gate and a pre-registered feature amount,
Information processing method. The information processing method according to any one of claims 15 to 17, wherein
Estimating a distance to an object existing in the pre-passage area of the gate using information different from the captured image for extracting the feature amount;
Information processing method. The information processing method according to any one of claims 15 to 17, wherein
Estimating the distance to the target using the image portion of the target in the captured image,
Information processing method.

Images