Processing device, processing method, and program

Abstract

A processing device (10) of the present invention comprises a detection unit (11) that detects an object satisfying predetermined disclosure conditions in a processed image, a mask unit (12) that performs masking on the processed image, and a display control unit (13) configured to display the processed image having been entirely subjected to masking on a display device and switches, when the object satisfying the disclosure conditions is detected in the processed image, an image to be displayed on the display device from the processed image having been entirely subjected to masking to a processed image where masking is performed on an area other than an area including the object satisfying the disclosure conditions.

Description

Technical Field

[0001] The present invention relates to a processing device, a processing method, and a recording medium.

Background Art

[0002] For purposes such as privacy protection, a technique for performing image processing so that a person or object shown in an image cannot be identified is desired. Related techniques are disclosed in Patent Documents 1 to 3.

[0003] Patent Document 1 discloses a technique for displaying a mask-processed image in which a mask image covering only the inside of the contour of a person in a processing image is superimposed on a discrimination-reduced image obtained by performing a process for reducing the discriminability of an object on the entire processing image.

[0004] Patent Document 2 discloses a technique for displaying a processed image obtained by performing mask processing only on a detected person area, and when a person who has performed a predetermined action is detected, removing the mask for that person and displaying the processed image in a state where the person can be visually recognized.

[0005] Patent Document 3 discloses a technique for detecting a person registered in advance from a processing image using a face matching technique, performing mask processing on the faces of persons other than the person registered in advance, and displaying the processing image without performing mask processing on the face of the person registered in advance.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0007] When detecting a person in a processed image and performing mask processing only on the detected person's area as in the technologies disclosed in Patent Documents 2 and 3, there is a problem that mask processing is not performed on a person who was not detected in the process of detecting the person, that is, a person who was missed in detection.

[0008] The above problem is solved by performing mask processing on the entire processed image as in the technology disclosed in Patent Document 1. However, if mask processing is always performed on the entire processed image as in the technology disclosed in Patent Document 1, the content of the processed image cannot be fully grasped. For this reason, in the case of the technology disclosed in Patent Document 1, there is a problem that a viewer who views the processed image may overlook a predetermined event shown in the processed image.

[0009] An example of the object of the present invention is to provide a processing device, a processing method, and a storage medium that solve the problem of suppressing the inconvenience that a viewer who views a processed image overlooks a predetermined event shown in the processed image while protecting the privacy of a person shown in the processed image in view of the above-described problems.

Means for Solving the Problem

[0010] According to one aspect of the present invention, detection means for detecting an object that satisfies a predetermined disclosure condition in a processed image; mask means for performing mask processing on the processed image; display control means for displaying the processed image subjected to mask processing on the entire image on a display device, and when the object that satisfies the disclosure condition is detected in the processed image, switching the image to be displayed on the display device from the processed image subjected to mask processing on the entire image to the processed image subjected to mask processing on an area other than the area where the object that satisfies the disclosure condition appears; A processing device having the above is provided.

[0011] According to one aspect of the present invention, a computer detects an object that satisfies a predetermined disclosure condition in a processed image, Perform a masking process on the processed image, Display the processed image with the masking process applied to the whole on a display device. When the object satisfying the disclosure condition is detected within the processed image, switch the image to be displayed on the display device from the processed image with the masking process applied to the whole to the processed image with the masking process applied to the regions other than the region where the object satisfying the disclosure condition appears, from the processed image with the masking process applied to the whole. A processing method is provided.

[0012] According to one aspect of the present invention, A computer, Detection means for detecting an object satisfying a predetermined disclosure condition within a processed image, Masking means for performing a masking process on the processed image, Display control means for displaying the processed image with the masking process applied to the whole on a display device, and when the object satisfying the disclosure condition is detected within the processed image, switching the image to be displayed on the display device from the processed image with the masking process applied to the whole to the processed image with the masking process applied to the regions other than the region where the object satisfying the disclosure condition appears, from the processed image with the masking process applied to the whole. A recording medium recording a program for functioning as such is provided.

Advantages of the Invention

[0013] According to one aspect of the present invention, a processing device, a processing method, and a storage medium are realized that solve the problem of suppressing the inconvenience that a viewer who views a processed image overlooks a predetermined event shown in the processed image while protecting the privacy of the person shown in the processed image.

Brief Description of the Drawings

[0014] The above-described object, as well as other objects, features, and advantages, will become more apparent from the Suitable following embodiments described below and the accompanying drawings.

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0016] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are denoted by the same reference numerals, and the description will be omitted as appropriate.

[0017] <First Embodiment> FIG. 1 is a functional block diagram showing an overview of a processing device 10 according to the first embodiment. The processing device 10 includes a detection unit 11, a mask unit 12, and a display control unit 13.

[0018] The detection unit 11 detects an object that satisfies a predetermined disclosure condition within the processed image. The mask unit 12 performs a masking process on the processed image. The display control unit 13 causes the display device to display the processed image that has been subjected to the masking process overall. Then, when an object that satisfies the disclosure condition is detected within the processed image, the display control unit 13 causes the image to be displayed on the display device to be switched from the processed image that has been subjected to the masking process overall to a processed image in which a masking process is performed on regions other than the region where the object that satisfies the disclosure condition appears, from the processed image that has been subjected to the masking process overall.

[0019] According to the processing device 10 having such a configuration, the problem of suppressing the inconvenience that a viewer who views the processed image overlooks a predetermined event shown in the processed image while protecting the privacy of the person shown in the processed image is solved.

[0020] <Second Embodiment> "Overview" The processing device 10 according to the second embodiment is a more specific implementation of the processing device 10 according to the first embodiment. Here, an overview of the processing device 10 will be described.

[0021] The processed image according to the second embodiment is a moving image composed of a plurality of frame images. Then, the processing device 10 according to the second embodiment is used under the condition that there is sufficient time for the detection process by the detection unit 11 and the masking process by the mask unit 12 from the timing when the frame image is generated to the timing when the frame image is displayed. For example, it is assumed that the captured moving image is reproduced and displayed with a relatively large time lag, or the previously captured moving image is reproduced and displayed at an arbitrary timing after the shooting timing.

[0022] The processing device 10 performs a process of detecting an object that satisfies a predetermined disclosure condition for each of a plurality of frame images. Further, the processing device 10 performs a masking process on each of the plurality of frame images according to the detection result. Specifically, for a frame image in which an object that satisfies the disclosure condition is not detected, the processing device 10 performs a masking process on the entire frame image. On the other hand, for a frame image in which an object that satisfies the disclosure condition is detected, the processing device 10 does not perform a masking process on the area where the object that satisfies the disclosure condition appears in the frame image, but performs a masking process on the other areas. Then, the processing device 10 reproduces and displays a moving image based on the plurality of frame images subjected to such a masking process.

[0023] According to such a processing device 10, reproduction and display of a moving image as shown in FIG. 2 are realized. That is, in a time period in which an object that satisfies the disclosure condition is not detected, an image subjected to a masking process on the whole, such as the n-th frame to the (n + 2)-th frame, is displayed. And in a time period in which an object that satisfies the disclosure condition is detected, an image in which a masking process is not performed on the object that satisfies the disclosure condition but is performed on other areas, such as the (n + 3)-th and (n + 4)-th frames, is displayed.

[0024] "Hardware Configuration" Next, an example of the hardware configuration of the processing device 10 will be described. Each functional unit of the processing device 10 is realized by an arbitrary combination of hardware and software centered around a CPU (Central Processing Unit) of an arbitrary computer, a memory, a program loaded into the memory, a storage unit such as a hard disk that stores the program (in addition to a program stored in advance at the stage of shipping the device, a program downloaded from a storage medium such as a CD (Compact Disc) or a server on the Internet can also be stored), and a network connection interface. And it is understood by those skilled in the art that there are various modification examples for the realization method and device.

[0025] FIG. 3 is a block diagram illustrating the hardware configuration of the processing device 10. As shown in FIG. 3, the processing device 10 includes a processor 1A, a memory 2A, an input / output interface 3A, a peripheral circuit 4A, and a bus 5A. The peripheral circuit 4A includes various modules. The processing device 10 may not have the peripheral circuit 4A. Note that the processing device 10 may be composed of a plurality of physically and / or logically divided devices. In this case, each of the plurality of devices can have the above hardware configuration.

[0026] The bus 5A is a data transmission path for the processor 1A, the memory 2A, the peripheral circuit 4A, and the input / output interface 3A to transmit and receive data to and from each other. The processor 1A is an arithmetic processing device such as a CPU or a GPU (Graphics Processing Unit). The memory 2A is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The input / output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, a camera, etc., and an interface for outputting information to an output device, an external device, an external server, etc. The input device is, for example, a keyboard, a mouse, a microphone, a physical button, a touch panel, etc. The output device is, for example, a display, a speaker, a printer, a mailer, etc. The processor 1A can issue commands to each module and perform operations based on their calculation results.

[0027] "Functional Configuration" Next, the functional configuration of the processing device 10 according to the second embodiment will be described in detail. FIG. 1 shows an example of a functional block diagram of the processing device 10 according to the second embodiment. As shown in the figure, the processing device 10 includes a detection unit 11, a mask unit 12, and a display control unit 13.

[0028] The detection unit 11 detects an object that satisfies a predetermined disclosure condition within the processed image.

[0029] The "processed image" is a moving image composed of a plurality of frame images. The detection unit 11 detects an object that satisfies a predetermined disclosure condition within each of the plurality of frame images. In the following embodiments, an example where the processed image is a single still image will be described.

[0030] The "object" is at least one of a person and an object other than a person.

[0031] The "disclosure condition" is a condition for displaying without applying a mask process. That is, an object that satisfies the disclosure condition is displayed in a state where it can be identified without applying a mask process.

[0032] Specifically, the disclosure condition is · being a person registered in advance, · not being a person registered in advance, · being a person having characteristics of an appearance registered in advance, · being a person who has performed an action registered in advance, · being an object registered in advance, and · being an object held by a person who satisfies the disclosure condition, including at least one of the above. Each will be described below.

[0033] - being a person registered in advance - In this example, information for identifying a person (individual) who does not undergo a mask process, specifically, feature amounts of the appearance, are registered in the processing device 10 in advance. The feature amounts of the appearance are, for example, face information, body shape information, gait information, etc., but are not limited thereto. Then, the detection unit 11 uses a widely known image analysis technique to detect a person who has not undergone a mask process registered in advance from each of the plurality of frame images.

[0034] Note that after the detection unit 11 detects a region where a person appears in the frame image by person detection processing, it may determine whether the person existing in the detected region where the person appears is a person registered in advance using the above-mentioned feature amounts registered in advance. The details of the person detection processing and the collation processing of the feature amounts are not particularly limited, and any technique can be adopted.

[0035] -Not a pre-registered person- In this example, information identifying the person (individual) who performs the masking process, specifically the feature quantities of the appearance, is pre-registered in the processing device 10. Then, the detection unit 11 uses a widely known image analysis technique to detect, from each of a plurality of frame images, the person who performs the pre-registered masking process.

[0036] Note that after the detection unit 11 detects the area where a person appears in the frame image by the person detection process, it may determine whether the person existing in the detected area where the person appears is a pre-registered person using the above pre-registered feature quantities. The details of the person detection process and the collation process of the feature quantities are not particularly limited, and any technique can be adopted.

[0037] -A person with pre-registered appearance features- In this example, a person who does not undergo the masking process is specified by appearance features such as clothing, possessions, and posture. For example, features of what the person is wearing, such as "wearing a mask, sunglasses, and a hat", may be pre-registered. In addition, the posture of the person, such as "lying down", "lying horizontally", "sitting hunched", etc., may be pre-registered. In addition, possession of a predetermined dangerous object, such as "carrying a knife", may be pre-registered.

[0038] The detection unit 11 can detect, from within the frame image, a person having such pre-registered appearance features using widely known person detection techniques, object detection techniques, posture detection techniques, and the like.

[0039] -A person who has performed pre-registered actions- In this example, a person who does not undergo mask processing is specified by an action. For example, actions such as "touched a predetermined object", "abandoned what was being held", "wandered around", "entered a predetermined area", etc. may be registered in advance. The detection unit 11 can detect, from within the frame image, a person who has performed such a pre-registered action by using widely known action analysis techniques.

[0040] -Being a pre-registered object- For example, dangerous objects such as "guns", "knives", etc. may be registered in advance. The detection unit 11 can detect such pre-registered objects from within the frame image by using widely known object detection techniques.

[0041] -Being an object held by a person who satisfies the disclosure conditions- The detection unit 11 detects, within the frame image, an object held by a person who satisfies the above-described disclosure conditions. For example, the detection unit 11 may detect, as an object held by such a person, an object held in the hand, worn on the body, carried on the back, borne, or in contact with, by a person who satisfies the above-described disclosure conditions within the frame image.

[0042] Note that there may be an object that was initially held by a person but later ceased to be held, such as when the person abandoned the object. The detection unit 11 can also detect, within each frame image, an object that was held by a person who satisfies the disclosure conditions but later ceased to be held, as "an object held by a person who satisfies the disclosure conditions", by utilizing object tracking techniques, feature matching techniques, etc.

[0043] The detection unit 11 determines whether a target object that satisfies a predetermined disclosure condition is detected within each frame image ka or not, and outputs information indicating the area within the frame image in which the target object that satisfies the predetermined disclosure condition appears when detected.

[0044] The mask unit 12 performs mask processing on the processing image. The mask unit 12 performs mask processing on each of the plurality of frame images.

[0045] The mask unit 12 performs mask processing on each frame image according to the detection result by the detection unit 11. Specifically, for a frame image in which an object satisfying the disclosure condition is not detected, the mask unit 12 performs mask processing on the entire frame image. On the other hand, for a frame image in which an object satisfying the disclosure condition is detected, the mask unit 12 does not perform mask processing on the area where the object satisfying the disclosure condition appears in the frame image, but performs mask processing on the other areas.

[0046] "Mask processing" is a process that makes it impossible to identify an object in an image. The mask processing may be a process of applying a mosaic to the image using mosaic technology, a process of blurring the image using blurring technology, a process of superimposing a predetermined mask image (such as a single-color mask or a pattern mask) on the image, or other processes.

[0047] Fig. 2 shows an example of a plurality of frame images after mask processing by the mask unit 12. The nth to (n + 2)th frames are frame images in which an object satisfying the disclosure condition is not detected. In these frame images, mask processing is performed on the entire frame image.

[0048] And the (n + 3)th and (n + 4)th frames are frame images in which an object satisfying the disclosure condition is detected. In these frame images, mask processing is not performed on the area where the object satisfying the disclosure condition appears in the frame image, but mask processing is performed on the other areas.

[0049] Note that in the example shown in Fig. 2, the "area where the object satisfying the disclosure condition appears" is a rectangular area, but an area where only the object along the contour of the object appears may be used as the area where the object satisfying the disclosure condition appears. Techniques for detecting the area where the object appears as a rectangular area and techniques for detecting the area where only the object along the contour of the object appears are widely known, so the description here is omitted.

[0050] By the way, as a method of generating a frame image in which masking is not performed on the area where the object satisfying the disclosure condition in the frame image appears, and masking is performed on other areas, (1) after performing masking on the entire frame image, the masking of the area where the object satisfying the disclosure condition in the frame image appears is removed, and (2) masking is performed only on areas other than the area where the object satisfying the disclosure condition in the frame image appears. As in the second embodiment, if there is sufficient time for the detection process by the detection unit 11 and the masking process by the masking unit 12 from the timing when the frame image is generated to the timing when the frame image is displayed, the masking unit 12 may adopt any of these methods.

[0051] The display control unit 13 uses the frame image subjected to the masking process by the masking unit 12 to reproduce and display a moving image. Specifically, the display control unit 13 performs masking on the entire frame image in which the object satisfying the disclosure condition is not detected, and causes the display device to display a moving image in which masking is performed on areas other than the area where the object satisfying the disclosure condition in the frame image in which the object satisfying the disclosure condition is detected appears. The display device is a display, a projection device, or the like.

[0052] With such a display control unit 13, for example, as shown in FIG. 2, a frame image (frames n to (n + 2)) subjected to masking on the entire image is displayed on the display device. When an object satisfying the disclosure condition is detected in the frame image, display control is realized in which the image to be displayed on the display device is switched from the frame image subjected to masking on the entire image to the frame image subjected to masking on areas other than the area where the object satisfying the disclosure condition appears.

[0053] Next, an example of the processing flow of the processing device 10 according to the second embodiment will be described with reference to the flowchart of FIG. 4.

[0054] In S10, the processing device 10 performs mask processing on the entire frame image in which an object satisfying the disclosure condition is not detected, and obtains a moving image obtained by performing mask processing on an area other than the area where the object satisfying the disclosure condition appears in the frame image in which the object satisfying the disclosure condition is detected.

[0055] For example, in advance, a video file in which detection processing by the detection unit 11 and mask processing by the mask unit 12 are performed on all frame images may be generated and stored in a predetermined storage device. Then, the processing device 10 may realize the above acquisition in S10 by acquiring the video file.

[0056] Alternatively, during the shooting of the moving image, the processing device 10 may sequentially acquire the generated frame images. Then, the processing device 10 may realize the above acquisition in S10 by sequentially performing detection processing by the detection unit 11 and mask processing by the mask unit 12 on each of the acquired frame images.

[0057] In S11, the processing device 10 reproduces and displays the moving image acquired in S10. Specifically, the processing device 10 performs mask processing on the entire frame image in which an object satisfying the disclosure condition is not detected, and causes the display device to display a moving image obtained by performing mask processing on an area other than the area where the object satisfying the disclosure condition appears in the frame image in which the object satisfying the disclosure condition is detected.

[0058] "Operation and Effect" According to the processing device 10 of the second embodiment, the same operation and effect as those of the processing device 10 of the first embodiment are realized.

[0059] Also, according to the processing device 10 of the second embodiment, as shown in FIG. 2, in a time period in which an object satisfying the disclosure condition is not detected, an image subjected to mask processing as a whole, such as the nth frame to the (n + 2)th frame, is displayed, and in a time period in which an object satisfying the disclosure condition is detected, an image in which mask processing is not performed on the object satisfying the disclosure condition and mask processing is performed on other areas, such as the (n + 3)th and (n + 4)th frames, is displayed.

[0060] According to the processing device 10 of the second embodiment as described above, only the object that satisfies the disclosure condition is displayed in a state where it can be specified (without mask processing), and the other objects are displayed in a state where they cannot be specified (with mask processing). As a result, while protecting the privacy of the people shown in the moving image, it is possible to suppress the inconvenience that the viewer who views the moving image overlooks a predetermined event shown in the moving image, specifically, an event related to the object that satisfies the disclosure condition.

[0061] Further, according to the processing device 10 of the second embodiment, when an object that satisfies the disclosure condition is not detected, mask processing is performed on the entire frame image, and when an object that satisfies the disclosure condition is detected, mask processing is performed on the area other than the area of the detected object. In this way, in principle, when mask processing is performed by the method of performing mask processing and removing the mask only from the area detected by the detection processing, although the inconvenience of failing to remove the mask from the object from which the mask should be removed due to a detection omission in the detection processing may occur, the inconvenience of failing to mask the object that should not have the mask removed does not occur. For this reason, processing that places more emphasis on privacy protection is realized.

[0062] Further, in the processing device 10 of the second embodiment, the disclosure condition can include at least one of "being a person registered in advance", "not being a person registered in advance", "being a person having a pre-registered appearance feature", "being a person who has performed a pre-registered action", "being a pre-registered object", and "being an object held by a person who satisfies the disclosure condition". According to the processing device 10 of the second embodiment that detects an object to remove the mask using such characteristic disclosure conditions, various objects can be defined as objects to remove the mask. As a result, the range of usage scenarios of the processing device 10 is widened, which is preferable.

[0063] <Third Embodiment> The processed image of the third embodiment is a moving image composed of a plurality of frame images. And the processing device 10 of the third embodiment is used under the condition that there is no time for the detection process by the detection unit 11 and the masking process by the mask unit 12 described in the second embodiment from the timing when the frame image is generated to the timing when the frame image is displayed. For example, it is assumed that the captured moving image is played and displayed in real time with a relatively small time lag.

[0064] Also in the case of the third embodiment, the detection unit 11 detects an object that satisfies a predetermined disclosure condition within each of the plurality of frame images, in the same manner as in the second embodiment. And when the detection unit 11 detects an object that satisfies a predetermined disclosure condition within a certain frame image, it tracks the object as a tracking target within the subsequent frame images. The tracking of the object within the moving image is realized using a widely known tracking technique. And the detection unit 11 outputs information indicating the area where the tracking target detected within the frame image appears.

[0065] The mask unit 12 performs a masking process on each frame image according to the detection result by the detection unit 11. Specifically, the mask unit 12 performs a masking process on the entire frame image for a frame image in which the tracking target (object that satisfies the disclosure condition) is not detected. On the other hand, the mask unit 12 does not perform a masking process on the area where the tracking target (object that satisfies the disclosure condition) appears within the frame image for a frame image in which the tracking target is detected, and performs a masking process on the other areas.

[0066] Note that the process of detecting the tracking target within the frame image has a smaller processing load on the computer and can be completed in a shorter time than the process of detecting an object that satisfies the disclosure condition within the frame image. For this reason, it becomes possible to perform the process of detecting the tracking target by the detection unit 11 and the masking process by the mask unit 12 from the timing when the frame image is generated to the timing when the frame image is displayed.

[0067] The other configurations of the processing apparatus 10 according to the third embodiment are the same as those of the processing apparatus 10 according to the first and second embodiments.

[0068] According to the processing apparatus 10 of the third embodiment, the same operational effects as those of the processing apparatus 10 of the first and second embodiments are achieved. That is, according to the processing apparatus 10 of the third embodiment, for a person who does not satisfy a predetermined disclosure condition among the persons shown in the moving image, mask processing is performed, and for a person who satisfies the predetermined disclosure condition, the moving image can be reproduced and displayed without performing mask processing. mi For a person who does not satisfy a certain disclosure condition among the persons shown in the moving image, mask processing is performed, and for a person who satisfies the predetermined disclosure condition, the moving image can be reproduced and displayed without performing mask processing.

[0069] In the third embodiment, it is assumed that the captured moving image is reproduced and displayed in real time with a relatively small time lag. For this reason, the time from when a certain frame image is generated until it is displayed is relatively small. And it is necessary to execute the processing by the detection unit 11 and the mask unit 12 within such a relatively short time.

[0070] Due to the above-mentioned time limit, even if an object that satisfies the disclosure condition is detected within a certain frame image, it is not possible to remove the mask of the object from that frame image for display. This is because the display timing of that frame image has passed before the processing of detecting an object that satisfies the disclosure condition within that frame image and the mask processing according to the detection result are completed. For this reason, in that frame image, the detected object that satisfies the disclosure condition is displayed with a mask. However, the object can be tracked in subsequent frame images by a tracking technique, and the mask of the object can be removed and displayed in subsequent frame images. Thus, in the case of the third embodiment, it is not possible to remove the mask of an object from the frame image in which the object that satisfies the disclosure condition is detected, but it is possible to remove the mask of the object and display it from any subsequent frame image.

[0071] <Fourth Embodiment> First, the outline of the processing device 10 of the fourth embodiment will be described. The processed image of the fourth embodiment is a "still image". When the processing device 10 receives a display instruction input to display a certain still image, it performs a masking process on the entire still image accordingly and displays the still image after the masking process. Further, the processing device 10 performs a process of detecting an object that satisfies a predetermined disclosure condition within the still image in response to the above display instruction input. Next, when an object that satisfies the predetermined disclosure condition is detected within the still image, the processing device 10 generates a still image in which a masking process is not performed on the area where the object that satisfies the disclosure condition appears and a masking process is performed on the other areas. Then, the processing device 10 switches the image to be displayed from the still image with the masking process performed on the whole to the still image in which the masking process is not performed on the area where the object that satisfies the disclosure condition appears and the masking process is performed on the other areas. As a result, as shown in FIG. 5, first, the still image with the masking process performed on the whole is displayed, and then the display in which the mask of the area where the object that satisfies the disclosure condition appears is removed is realized.

[0072] The flow of the process of the processing device 10 will be described in detail using the flowchart of FIG. 6.

[0073] When the processing device 10 designates a file of a certain still image and receives a display instruction input for displaying the still image, the processes of S20 to S25 in FIG. 6 are performed.

[0074] First, the mask unit 12 performs a masking process on the whole of the designated still image (S20). Then, the display control unit 13 causes the display device to display the still image with the masking process performed on the whole (S21).

[0075] Also, the detection unit 11 analyzes the designated still image and detects an object that satisfies a predetermined disclosure condition within the still image (S22). Note that the process of S22 may be performed after the processes of S20 and S21, or may be performed in parallel with the processes of S20 and S21.

[0076] When an object satisfying the disclosure condition is detected within its still image (Yes in S23), the mask unit 12 generates a still image in which mask processing is not performed on the region where the object satisfying the disclosure condition appears, and mask processing is performed on other regions (S24). For example, the mask unit 12 may realize the generation process in S24 by removing the mask of the region where the object satisfying the disclosure condition appears from the still image with mask processing applied to the whole generated in S20. Alternatively, the mask unit 12 may realize the generation process in S24 by performing mask processing on the regions other than the region where the object satisfying the disclosure condition appears on the still image without mask processing.

[0077] Next, the display control unit 13 causes the image to be displayed on the display device to be switched from the still image with mask processing applied to the whole to the still image in which mask processing is not performed on the region where the object satisfying the disclosure condition appears, and mask processing is performed on other regions. As a result, as shown in FIG. 5, first, the still image with mask processing applied to the whole is displayed, and then, the display in which the mask of the region where the object satisfying the disclosure condition appears is removed is realized.

[0078] Note that when an object satisfying the disclosure condition is not detected within its still image (No in S23), the processes in S24 and S25 are not executed. In this case, the display of the still image with mask processing applied to the whole continues.

[0079] Other configurations of the processing device 10 according to the fourth embodiment are the same as those of the processing device 10 according to the first to third embodiments.

[0080] According to the processing device 10 of the fourth embodiment, the same operational effects as those of the processing device 10 according to the first to third embodiments are realized even when displaying a still image.

[0081] Moreover, according to the processing device 10 of the fourth embodiment, a still image subjected to mask processing as a whole is displayed on the display device. When an object satisfying the disclosure condition is detected in the still image, the image to be displayed on the display device can be switched from the still image subjected to mask processing as a whole to a still image subjected to mask processing in an area other than the area where the object satisfying the disclosure condition appears, from the still image subjected to mask processing as a whole.

[0082] In response to an input for instructing the display of a still image, it is also possible to immediately display a still image (the right still image in FIG. 5) subjected to mask processing that reflects the detection result by the detection unit 11. However, in this case, due to the time required for the detection process by the detection unit 11, the time from the input for instructing the display of the still image until the still image is displayed becomes long. When the time from the input for instructing the display of the still image until the still image is displayed becomes long, there are also users who feel stress. By generating a generated image subjected to mask processing as a whole first in response to an input for instructing the display of a still image as in the processing device 10 of the fourth embodiment, quickly displaying it, and then displaying a still image subjected to mask processing that reflects the detection result by the detection unit 11, the problem of stress on the above users can be reduced.

[0083] <Fifth Embodiment> The detection unit 11 of the processing device 10 of the fifth embodiment determines whether a person existing in the area where the person appears satisfies the disclosure condition after detecting the area where the person appears in the frame image by the person detection process. That is, the detection unit 11 executes at least two steps of "detection of the area where the person appears" and "determination of whether a person existing in the area where the detected person appears satisfies the disclosure condition".

[0084] Then, the mask unit 12 performs a step-by-step mask process on the processed image according to the processing result of each of the above two steps by the detection unit 11.

[0085] First, in response to the detection of an area in which a person is photographed, the masking unit 12 applies masking to areas other than the area in which the detected person is photographed, and also applies masking to parts of the body of the person present in the area in which the detected person is photographed, to generate a processed image in which other parts are not masked. The parts of the body to be masked are parts that can identify a person, such as the "face". Note that the processed image in which an area in which a person is not photographed is entirely masked.

[0086] Next, the mask unit 12 performs mask processing according to the determination result of whether the person present in the area where the detected person is captured satisfies the disclosure condition. Specifically, if the person present in the area where the detected person is captured satisfies the disclosure condition, the mask unit 12 performs mask processing on the area other than the area where the detected person is captured, and generates a processed image in which the area where the detected person is captured is not masked. That is, the mask applied to a part of the body (e.g., face) is removed. Note that, if the person present in the area where the detected person is captured does not satisfy the disclosure condition, the mask unit 12 performs mask processing on the area other than the area where the detected person is captured, and performs mask processing on a part of the body of the person present in the area where the detected person is captured, and generates a processed image in which the mask processing is not performed on the other parts.

[0087] Specific examples of displays realized by the processing device 10 will be shown with reference to Figs. 7 and 8. Fig. 7 shows processing assuming the configuration of the processing device 10 of the third embodiment. As shown in the figure, an area in which a person is photographed is detected. re na During a time period when a person is not detected, an image with the entire image masked is displayed, as in the nth and (n+1)th frames. During a time period when an area in which a person is photographed is detected but it has not been determined whether the person satisfies the disclosure conditions, an image with masking applied to areas other than the area in which the detected person is photographed, as in the (n+2)th frame, is displayed in which masking is applied to parts of the body of the person (e.g., the face) present in the area in which the detected person is photographed, and no masking is applied to other parts.

[0088] Afterwards, if it is determined that the person meets the disclosure conditions, an image is displayed in which masking is applied to areas other than the area where the detected person appears, such as the (n + 3)-th frame, and masking is not applied to the area where the detected person appears. That is, the mask on a part of the person's body (e.g., face) existing in the area where the detected person appears is removed. In FIG. 7, although the display of the image in which masking is applied to areas other than the area where the detected person appears and masking is applied to a part of the person's body (e.g., face) existing in the area where the detected person appears is only for one frame (the (n + 2)-th frame), it may be several frames.

[0089] FIG. 8 shows a process based on the configuration of the processing device 10 of the fourth embodiment. In response to an input of a display instruction to display a still image, a still image with masking applied to the whole is displayed. Next, in response to the detection of the area where a person appears, a still image is displayed in which masking is applied to areas other than the area where the detected person appears, and masking is applied to a part of the person's body (e.g., face) existing in the area where the detected person appears, and no masking is applied to other parts. Afterwards, if it is determined that the person meets the disclosure conditions, an image is displayed in which masking is applied to areas other than the area where the detected person appears, and masking is not applied to the area where the detected person appears. That is, the mask on a part of the person's body (e.g., face) existing in the area where the detected person appears is removed.

[0090] The other configurations of the processing device 10 of the fifth embodiment are the same as those of the processing device 10 of the first to fourth embodiments.

[0091] According to the processing device 10 of the fifth embodiment, the same operational effects as those of the processing device 10 of the first to fourth embodiments are achieved. Further, according to the processing device 10 of the fifth embodiment, at least two steps of "detecting a region in which a person appears" and "determining whether a person existing in the region in which the detected person appears satisfies the disclosure condition" are executed, and step-by-step mask processing can be performed on the processed image according to the processing result of each of the above two steps. According to such a processing device 10, the time during which a display in which mask processing is performed on the entire processed image is performed can be reduced. As a result, the stress on the viewer due to the display of the processed image on which mask processing is performed on the entire image can be reduced.

[0092] In addition, by such a display, while protecting the privacy of the person shown in the processed image, it is possible to notify the viewer that a person is shown in the processed image.

[0093] <Sixth Embodiment> The mask unit 12 of the processing device 10 according to the sixth embodiment performs mask processing not by removing all masks of the object that satisfies the disclosure condition, but by performing mask processing on a part of the object and not performing mask processing on other parts.

[0094] Then, the display control unit 13 causes the display device to display a processed image in which mask processing is performed on a region other than the region in which the object that satisfies the disclosure condition appears, performs mask processing on a region in which the object that satisfies the disclosure condition does not appear, and further performs mask processing on a part of the region in which the object that satisfies the disclosure condition appears, and does not perform mask processing on another part.

[0095] The mask unit 12 performs mask processing on a region in which an object that does not satisfy the disclosure condition appears in the processed image in which a person who satisfies the disclosure condition is detected, and further performs mask processing on a part of the region in which the object that satisfies the disclosure condition appears, and does not perform mask processing on another part. A part (e.g., a part of the body) on which mask processing is performed and a part on which mask processing is not performed in the region in which the object that satisfies the disclosure condition appears may be determined in advance.

[0096] Further, the mask unit 12 may change the portion where the masking process is performed and the portion where the masking process is not performed within the region where the object satisfying the disclosure condition appears, according to the content of the disclosure condition satisfied by the object.

[0097] For example, when the disclosure condition to be satisfied is any one of "being a pre-registered person", "not being a pre-registered person", "being a pre-registered object", and "being an object possessed by a person satisfying the disclosure condition", it is not necessary to perform the masking process on the entire region where the object appears.

[0098] And when the disclosure condition to be satisfied is any one of "being a person having pre-registered appearance features" and "being a person who has performed pre-registered actions", the masking process may be performed by masking the face of the person satisfying the disclosure condition and not masking the other parts of the body and possessions of the person.

[0099] Also, when the disclosure condition to be satisfied is "being a person who has performed pre-registered actions", the portion where the masking process is performed and the portion where the masking process is not performed within the region where the object satisfying the disclosure condition appears may be changed according to the content of the action.

[0100] For example, when the pre-registered action performed by the person satisfying the disclosure condition is "a predetermined part of the body enters the trap region set in the processed image", the mask unit 12 may perform the masking process by not performing the masking process on the predetermined part of the person whose predetermined part of the body has entered the trap region and performing the masking process on the parts other than the predetermined part. This example will be described in detail below.

[0101] As shown in FIG. 9, a partial region in the processed image is preset as the trap region T. For example, a partial region in the processed image where an intrusion prohibited region in the space shown in the processed image or an object that should not be touched existing in the space appears is set as the trap region T. The installation position and biWhen a processed image is generated by a camera with a fixed orientation, the positions of prohibited entry areas within the processed image and objects that must not be touched within the processed image are fixed.

[0102] Predetermined parts of the body that are detected as having entered a trap area are, for example, "arms", "legs", etc. For each trap area, the predetermined parts of the body that are detected as having entered may be different. For example, in the first trap area, it may be detected that an arm has entered, and in the second trap area, it may be detected that a leg has entered.

[0103] In the example of FIG. 9, it is detected that an arm has entered the trap area T. And as shown in FIG. 9, in response to the detection that an arm has entered the trap area T, only the arm of the person is displayed without being masked.

[0104] Also, as shown in FIG. 10, a plurality of trap areas may be set within the processed image. In FIG. 10, two trap areas T1 and T2 are set. The predetermined parts of the body that are detected as having entered each of the plurality of trap areas set within the processed image may be the same or different from each other.

[0105] Also, as shown in FIG. 11, even when a part other than the predetermined part of the body that is detected as having entered the trap area T (in the case of FIG. 11, the arm) enters the trap area T, the mask unit 12 can perform mask processing in such a way that it does not perform mask processing on the predetermined part of the person whose predetermined part of the body has entered the trap area, but performs mask processing on parts other than the predetermined part. In FIG. 11, although parts other than the arm have also entered the trap area T, only the arm is not masked, and mask processing is performed on other parts.

[0106] Other configurations of the processing device 10 of the sixth embodiment are the same as those of the processing device 10 of the first to fifth embodiments.

[0107] According to the processing device 10 of the sixth embodiment, the same operational effects as those of the processing device 10 of the first to fifth embodiments are achieved. Further, according to the processing device 10 of the sixth embodiment, instead of removing all the masks of the object that satisfies the disclosure condition, mask processing can be performed on a part of the object and not on other parts. By using this method, even for an object that satisfies the disclosure condition, it is possible to protect privacy while allowing the viewer to recognize a predetermined event. In addition, since the method of partial masking can be varied according to the content of the disclosure condition, the range of use is widened, which is preferable.

[0108] As described above, the embodiments of the present invention have been described with reference to the drawings. These are examples of the present invention, and various configurations other than the above can also be adopted. The configurations of the above-described embodiments may be combined with each other, or some configurations may be replaced with other configurations. Further, the configurations of the above-described embodiments may be variously modified within a range not departing from the gist. Also, the configurations and processes disclosed in the above-described embodiments and modification examples may be combined with each other.

[0109] Also, in the plurality of flowcharts used in the above description, a plurality of steps (processes) are described in order, but the execution order of the steps executed in each embodiment is not limited to the described order. In each embodiment, the order of the illustrated steps can be changed within a range that does not substantially affect the content. Also, the above-described embodiments can be combined within a range where the contents do not conflict.

[0110] Some or all of the above embodiments can also be described as follows in the appended claims, but are not limited thereto. 1. Detection means for detecting an object that satisfies a predetermined disclosure condition in a processed image; Mask means for performing mask processing on the processed image; Causing the display device to display the processed image that has been subjected to masking processing on the whole, and when the object satisfying the disclosure condition is detected within the processed image, causing the image to be displayed on the display device to be switched from the processed image that has been subjected to masking processing on the whole to the processed image that has been subjected to masking processing on regions other than the region where the object satisfying the disclosure condition appears, a display control means; A processing device having the same. 2. The processed image is a moving image composed of a plurality of frame images, The display control means performs masking processing on the whole of the frame image in which the object satisfying the disclosure condition is not detected, and on the regions other than the region where the object satisfying the disclosure condition appears in the frame image in which the object satisfying the disclosure condition is detected, and causes the moving image obtained by performing masking processing on the whole of the frame image in which the object satisfying the disclosure condition is not detected and on the regions other than the region where the object satisfying the disclosure condition appears in the frame image in which the object satisfying the disclosure condition is detected to be displayed on the display device. The processing device according to 1. 3. The processed image is a still image, The display control means causes the still image that has been subjected to masking processing on the whole to be displayed on the display device in response to an input of a display instruction, and when the object satisfying the disclosure condition is detected within the still image, causes the image to be displayed on the display device to be switched from the still image that has been subjected to masking processing on the whole to the still image that has been subjected to masking processing on regions other than the region where the object satisfying the disclosure condition appears. The processing device according to 1. 4. The disclosure condition is Being a person registered in advance, Not being a person registered in advance, Being a person having characteristics of an appearance registered in advance, Being a person who has performed actions registered in advance, Being an object registered in advance, and Being an object held by a person satisfying the disclosure condition, The processing device according to any one of 1 to 3, including at least one of the above. 5. The display control means As the processed image obtained by performing mask processing on regions other than the region in which the object satisfying the disclosure condition is imaged, the processed image in which a part of the region in which the object satisfying the disclosure condition is imaged is further masked and the other part is not masked is caused to be displayed on the display device, the processing apparatus according to any one of 1 to 4. 6. The mask means The processing apparatus according to 5, wherein the portions to be masked and the portions not to be masked within the region in which the object satisfying the disclosure condition is imaged are changed according to the content of the disclosure condition satisfied by the object. 7. The disclosure condition is that a predetermined part of the body enters a trap region set in the processed image, The mask means does not perform mask processing on the predetermined part of the person in whom the predetermined part of the body has entered the trap region, and performs mask processing on parts other than the predetermined part, the processing apparatus according to 6. 8. A plurality of the trap regions are set in the processed image, The processing apparatus according to 7, wherein the predetermined part of the body is different for each trap region. 9. A computer detects an object satisfying a predetermined disclosure condition in a processed image, performs mask processing on the processed image, causes the processed image masked entirely to be displayed on a display device, and when the object satisfying the disclosure condition is detected in the processed image, causes the image to be displayed on the display device to be switched from the processed image masked entirely to the processed image obtained by performing mask processing on regions other than the region in which the object satisfying the disclosure condition is imaged, processing method. 10. A computer detection means for detecting an object satisfying a predetermined disclosure condition in a processed image, mask means for performing mask processing on the processed image, Causing a display device to display the processed image subjected to the masking process for the whole, and when the object satisfying the disclosure condition is detected in the processed image, causing the image to be displayed on the display device to be switched from the processed image subjected to the masking process for the whole to the processed image subjected to the masking process for a region other than the region where the object satisfying the disclosure condition appears, a display control means A recording medium recording a program causing it to function as such

Explanation of Signs

[0111] 10 Processing device 11 Detection unit 12 Masking unit 13 Display control unit 1A Processor 2A Memory 3A Input / output I / F 4A Peripheral circuit 5A Bus

Claims

1. Detection means for detecting an object that satisfies a predetermined disclosure condition in a processed image, Mask means for performing a masking process on the processed image, The processed image subjected to the overall masking process is displayed on a display device. When the object that satisfies the disclosure condition is detected in the processed image, the image to be displayed on the display device is switched from the processed image subjected to the overall masking process to the processed image in which a masking process is performed on an area other than the area where the object that satisfies the disclosure condition appears. Display control means, having, When the processed image is a still image, In response to an input for instructing the display of a first still image that is one of the still images, The mask means generates a first processed still image obtained by performing a masking process on the entire first still image, the display control means causes the display device to display the first processed still image, and the detection means analyzes the first still image, As a result of the analysis of the first still image, when the object that satisfies the disclosure condition is detected in the first still image, The mask means generates a second processed still image obtained by performing a masking process on an area other than the area where the object that satisfies the disclosure condition appears, and the display control means switches the image to be displayed on the display device from the first processed still image to the second processed still image. Processing device.

2. When the processed image is a moving image composed of a plurality of frame images, The display control means performs a masking process on the entire frame image in which the object that satisfies the disclosure condition is not detected, and the object that satisfies the disclosure condition in the frame image in which the object that satisfies the disclosure condition is detected. The processing device according to claim 1, wherein the moving image obtained by performing a masking process on an area other than the area where the object appears is displayed on the display device.

3. When the processed image is a moving image composed of a plurality of frame images, The mask means generates a first processed frame image obtained by performing a masking process on the entire first frame image, the display control means causes the display device to display the first processed frame image, and the detection means analyzes the first frame image, As a result of the analysis of the first frame image, when the object that satisfies the disclosure condition is detected in the first frame image, The mask means generates a second processed frame image obtained by performing a masking process on an area other than the area where the object appears, based on a second frame image which is the frame image next to the first frame image, and the display control means causes the display device to display the second processed frame image next to the first processed frame image. The processing device according to claim 1.

4. The display control means As the processed image obtained by performing a masking process on an area other than the area where the object satisfying the disclosure condition appears, a processed image obtained by further performing a masking process on a part of the area where the object satisfying the disclosure condition appears and not performing a masking process on another part is caused to be displayed on the display device. The processing device according to any one of claims 1 to 3.

5. The mask means The parts of the area where the object satisfying the disclosure condition appears to be masked and the parts not to be masked are changed according to the content of the disclosure condition satisfied by the object. The processing device according to claim 4.

6. The disclosure condition is that a predetermined part of the body enters a trap area set in the processed image, The mask means does not perform a masking process on the predetermined part of the person whose predetermined part of the body has entered the trap area, and performs a masking process on parts other than the predetermined part. The processing device according to claim 5.

7. A plurality of the trap areas are set in the processed image, For each of the trap areas, the predetermined part of the body is different. The processing device according to claim 6.

8. A computer detects an object satisfying a predetermined disclosure condition in a processed image, performs a masking process on the processed image, displays the processed image masked entirely on a display device, and when the object satisfying the disclosure condition is detected in the processed image, switches the image to be displayed on the display device from the processed image masked entirely to a processed image obtained by performing a masking process on an area other than the area where the object satisfying the disclosure condition appears, When the processed image is a still image, in response to an input of an instruction to display a first still image which is one of the still images, generates a first processed still image obtained by performing a masking process on the entire first still image, causes the first processed still image to be displayed on the display device, and analyzes the first still image, When the object satisfying the disclosure condition is detected in the first still image as a result of the analysis of the first still image, A processing method of generating a second processed still image obtained by masking a region other than the region in which the object satisfying the disclosure condition appears, and switching the image to be displayed on the display device from the first processed still image to the second processed still image.

9. A computer, Detection means for detecting an object satisfying a predetermined disclosure condition in a processed image, Mask means for masking the processed image, Display control means for displaying the processed image masked entirely on a display device, and when the object satisfying the disclosure condition is detected in the processed image, switching the image to be displayed on the display device from the processed image masked entirely to the processed image masked in a region other than the region in which the object satisfying the disclosure condition appears, Functioning as, When the processed image is a still image, In response to an input for instructing display of a first still image which is one of the still images, The mask means generates a first processed still image obtained by masking the entire first still image, the display control means displays the first processed still image on the display device, and the detection means analyzes the first still image, When the object satisfying the disclosure condition is detected in the first still image as a result of the analysis of the first still image, The mask means generates a second processed still image obtained by masking a region other than the region in which the object satisfying the disclosure condition appears, and a program for the display control means to switch the image to be displayed on the display device from the first processed still image to the second processed still image.

Images