Video processing device

Abstract

This video processing device includes: an object detection unit that detects an object from a captured video; a diminishment parameter determination unit that determines a diminishment parameter with respect to the object; a diminished video presentation unit that generates a diminished video by performing a diminishing process on the captured video image on the basis of the diminishment parameter, and presents the diminished video to a user; a user state acquisition unit that acquires state information of the user who has viewed the diminished video; and an optimal diminishment parameter estimation unit that estimates a diminishment parameter for improving the state of the user on the basis of the state information of the user.

Description

Video Processing Device

[0001] The present invention relates to a video processing device.

[0002] One video processing method is a diminished reality technology that visually conceals an object in a video by superimposing a background image or an effect such as blurring on the object. Hereinafter, video processing using the diminished reality technology will be referred to as "diminished processing." For example, Non-Patent Document 1 proposes a method of using a diminished processing to conceal unnecessary objects on a work desk in a video, thereby helping a user who watches the video to improve their concentration on their work.

[0003] Yi Fei Cheng, et al. "Towards Understanding Diminished Reality" Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, 2022Joseph Redmon, et al. "You Only Look Once: Unified, Real-Time Object Detection." Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, p.779-788Bobak Shahriari, et al. "Taking the Human Out of the Loop: A Review of Bayesian Optimization." Proceedings of the IEEE, Vol. 104, No. 1, January, 2016, p.148-175

[0004] When performing object erasure processing, the user who watches the video manually adjusts the degree of erasure for each object, which places a heavy burden (labor and time) on the user for the erasure processing.

[0005] The present invention has been made in light of the above circumstances, and its purpose is to provide a video processing device that can reduce the burden on the user in relation to the erasure process by acquiring the state of the user who has viewed the video that has been subjected to the erasure process and determining the degree of erasure of the object to be subjected to the erasure process based on the state of the user.

[0006] According to one aspect of the present invention, the video processing device includes an object detection unit that detects an object from a captured video, an erasure parameter determination unit that determines an erasure parameter for the object, a erasure video presentation unit that generates an erasure video by performing an erasure process on the captured video based on the erasure parameter and presents the erasure video to a user, a user status acquisition unit that acquires status information of a user who has viewed the erasure video, and an optimal erasure parameter estimation unit that estimates an erasure parameter that will improve the user's status based on the user's status information.

[0007] According to the present invention, by acquiring the state of the user who has viewed the video that has been subjected to the erasure process, it is possible to determine the degree of erasure of the object that will be subjected to the erasure process based on the state of the user, and it is possible to provide a video processing device that can reduce the burden on the user regarding the erasure process.

[0008] Fig. 1 is a block diagram showing an example of the functional configuration of a video processing device according to an embodiment. Fig. 2 is a flowchart showing an example of a concealment process in the video processing device according to an embodiment. Fig. 3 is a table showing a first example of concealment parameters and user status information in the video processing device according to an embodiment. Fig. 4 is a table showing a second example of concealment parameters and user status information in the video processing device according to an embodiment. Fig. 5 is a table showing a third example of concealment parameters and user status information in the video processing device according to an embodiment. Fig. 6 is a block diagram showing an example of the hardware configuration of the video processing device according to an embodiment.

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. The image processing device according to the embodiment is a device that performs image processing (disappearance processing) using distorted reality technology. In the following description, components having the same functions and configurations will be assigned the same reference numerals.

[0010] 1. Functional Configuration First, an example of the functional configuration of a video processing device 1 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of the functional configuration of a video processing device 1 according to an embodiment.

[0011] As shown in FIG. 1 , the image processing device 1 includes an imaging unit 11, an object detection unit 12, an occlusion parameter determination unit 13, an occlusion image presentation unit 14, a user state acquisition unit 15, a result storage unit 16, and an optimal occlusion parameter estimation unit 17.

[0012] The imaging unit 11 acquires video to be subjected to the erasure process. The imaging unit 11 includes, for example, an imaging device (such as a camera) for acquiring video. Hereinafter, the video acquired by the imaging unit 11 will be referred to as "captured video." The captured video is video that has not been subjected to the erasure process. The imaging unit 11 transmits the captured video to the object detection unit 12. The imaging unit 11 may store the captured video in the result storage unit 16. The imaging unit 11 may also present the captured video to the user via a display device (not shown). Note that the video processing device 1 does not need to include the imaging unit 11. In this case, the captured video is input to the video processing device 1 from outside.

[0013] The object detection unit 12 detects (extracts) objects in the captured video. Note that it is sufficient for the object to have a specific shape that can be identified in the captured video. The object detection unit 12 estimates at least one of the type, position, or size of the object in the captured video. Note that the method of detecting objects in the object detection unit 12 is not limited. For example, the algorithm described in Non-Patent Document 2 may be used as the object detection method. The object detection unit 12 transmits the captured video and information regarding the type, position, size, etc. of each object (hereinafter also referred to as "object information") to the occlusion parameter determination unit 13.

[0014] The erasure parameter determination unit 13 determines erasure parameters. The erasure parameters are values ​​indicating the degree of erasure processing (concealment, erasure, or transparency intensity) set for each object. The erasure parameter determination unit 13 sets the erasure parameters for each object. For example, the erasure parameters set by the erasure parameter determination unit 13 are used to generate training data for erasure parameter optimization. Therefore, the erasure parameters determined by the erasure parameter determination unit 13 may be any value. For example, the erasure parameters for each object may be set based on object information, etc., or may be set randomly. Hereinafter, a set of erasure parameters set for each object will also be referred to as a "erasure parameter group." The erasure parameter determination unit 13 may set multiple different erasure parameters for one object. In other words, the erasure parameter determination unit 13 may generate multiple erasure parameter groups for one captured image. The erasure parameter determination unit 13 transmits the captured image and the corresponding erasure parameter group to the erasure image presentation unit 14.

[0015] The erasure image presenting unit 14 performs erasure processing on the captured image based on the erasure parameters. Hereinafter, the image subjected to the erasure processing will be referred to as the "erasure image." In other words, the erasure image presenting unit 14 generates the erasure image by superimposing a background image or effects such as blurring on each object in the image based on the erasure parameter group. The erasure image presenting unit 14 may generate a different erasure image for each erasure parameter group. The erasure image presenting unit 14 presents the erasure image to the user via a display device. Note that the method for generating the erasure image is not limited. For example, the method described in Non-Patent Document 1 may be used as the method for generating the erasure image. The erasure image presenting unit 14 transmits the erasure image and the corresponding erasure parameter group to the user state acquiring unit 15. Furthermore, the erasure image presenting unit 14 stores the erasure image and the corresponding erasure parameter group in the result storage unit 16.

[0016] The user state acquisition unit 15 acquires information about the state of the user who viewed the obscured image (hereinafter, also referred to as "user state information"). That is, the user state acquisition unit 15 acquires user state information corresponding to the obscured image parameter group. The user state information includes the user state to be improved by the obscured image processing and a numerical value representing the user state (hereinafter, referred to as "user state value"). The user state may include the user's concentration level, the user's comfort level, or the user's lack of discomfort with the obscured image. For example, the user state value is expressed as a value between 0 and 1. For example, if the user's state is concentration level, a higher user state value is acquired as the user's concentration level increases. The method for acquiring the user state information is not limited. The user state acquisition unit 15 may acquire the user's state information by directly inputting it via an input device (not shown), or may estimate it from the user's biological information (such as information on heart rate or brain waves). The user state acquisition unit 15 stores the user's state information in the result storage unit 16.

[0017] The result storage unit 16 stores the obscuration parameters for each object and the user's state information for each obscuration image. That is, the result storage unit 16 stores the user's state information for each obscuration parameter group. The obscuration parameter groups and the corresponding user's state information stored in the result storage unit 16 are transmitted to the optimal obscuration parameter estimation unit 17.

[0018] The optimal obscuration parameter estimation unit 17 estimates optimal obscuration parameters (hereinafter also referred to as "optimal obscuration parameters") that improve the user's state from the obscuration parameter group and the user's state information. That is, the optimal obscuration parameter estimation unit 17 optimizes the obscuration parameters based on the user's state information. The optimal obscuration parameter estimation unit 17 estimates optimal obscuration parameters for each object using a combination of multiple obscuration parameter groups and user state information as training data. For example, Bayesian optimization, as described in Non-Patent Document 3, may be used as a method for optimizing the obscuration parameters. Bayesian optimization can calculate a black-box function. Therefore, the optimal obscuration parameter estimation unit 17 uses the state information of multiple users to calculate a function f such that the user state value = f (obscuration parameter for each object), and can estimate optimal obscuration parameters for each object that improve the user's state (maximize the user state value). The optimal obscuration parameter estimation unit 17 transmits the optimized obscuration parameter group to the obscuration image presentation unit 14.

[0019] The erasure image presenting unit 14 executes the erasure process using the erasure parameter group received from the optimal erasure parameter estimating unit 17, and presents the generated erasure image to the user.

[0020] In addition, in order to optimize the occlusion parameters (improve the accuracy of Bayesian optimization), the video processing device 1 may repeat the steps of estimating the optimal occlusion parameters, presenting the occlusion video based on the estimated optimal occlusion parameters, and acquiring the user's state information regarding the occlusion video. The repetitive process may have an upper limit number of repetitions set based on the number of times the estimation of the optimal occlusion parameters is performed, or it may be determined whether or not to repeat the process based on the determination result of whether or not the user state value is equal to or greater than a predetermined determination value.

[0021] 2. Erasing Process Next, an example of the erasing process will be described with reference to Fig. 2. Fig. 2 is a flowchart showing an example of the erasing process.

[0022] 2, first, the imaging unit 11 acquires a captured image (S1). The imaging unit 11 may present the captured image to the user via a display device.

[0023] Next, the object detection unit 12 detects (extracts) objects in the acquired captured video (S2). The object detection unit 12 can detect multiple objects from the captured video. The object detection unit 12 generates object information related to the detected objects.

[0024] Next, the erasure parameter determination unit 13 sets erasure parameters for each object (S3). That is, the erasure parameter determination unit 13 generates an erasure parameter group. Note that the erasure parameter determination unit 13 may generate multiple erasure parameter groups.

[0025] Next, the erasure image presenting unit 14 generates an erasure image based on the erasure parameter group and presents the generated erasure image to the user (S4). For example, when the erasure parameter determining unit 13 generates a plurality of erasure parameter groups, the erasure image presenting unit 14 generates an erasure image for each of the erasure parameter groups.

[0026] Next, the user status acquisition unit 15 acquires status information of the user who viewed the obscured image (S5). The user status acquisition unit 15 acquires user status information for each obscured image, i.e., for each obscured parameter group. Note that the video processing device 1 may repeat steps S3 to S5 to acquire multiple obscured parameter groups and status information of multiple users corresponding to the multiple obscured parameter groups.

[0027] Next, the optimal elimination parameter estimation unit 17 estimates the optimal elimination parameters of each object based on the state information of the plurality of users (S6). Note that the number of pieces of state information of the users used for estimating the optimal elimination parameters can be set arbitrarily.

[0028] Next, the disappearing image presenting unit 14 generates a disappearing image based on the optimal disappearing parameters received from the optimal disappearing parameter estimating unit 17, and presents the generated disappearing image to the user (S7).

[0029] The video processing device 1 checks whether the number of repetitions of steps S5 to S7 has reached a preset upper limit (S8). The number of repetitions may be 0. That is, the estimation of the optimal concealment parameter in the optimal concealment parameter estimation unit 17 may be completed in one time.

[0030] If the number of repetitions has not reached the upper limit (S8_No), the image processing device 1 returns to step S5. The user state acquisition unit 15 acquires state information of the user who viewed the occlusion image based on the optimal occlusion parameter. Proceeding to step S6, the optimal occlusion parameter estimation unit 17 adds the newly acquired user state information to the training data and executes estimation of the optimal occlusion parameter of each object.

[0031] If the number of repetitions reaches the upper limit (S8_Yes), the video processing device 1 ends the erasure process.

[0032] 3. Specific Examples of Concealment Parameters and User Status Information Three examples of concealment parameters and user status information are given below.

[0033] 3.1 First Example First, the first example will be described with reference to Fig. 3. Fig. 3 is a table showing a first example of obscuration parameters and user state information. Each row of the table indicates an obscuration parameter group number, an obscuration parameter for each object, and a user state value.

[0034] In this example, the occlusion parameter is set to a value between 0 and 1 for each object. For example, when the occlusion parameter is 0, occlusion processing is not performed on the target object. That is, the target object is not occluded. Also, when the occlusion parameter is 1, occlusion processing is performed on the target object so that the object becomes completely invisible.

[0035] As the user's state information, for example, a user state value corresponding to the user's concentration level is acquired as a value between 0 and 1. For example, if the user is not able to concentrate at all on the obscured image, the user state value is 0. If the user is able to concentrate maximally on the obscured image, the user state value is 1.

[0036] 3, the object detection unit 12 detects, for example, four objects 1 to 4 from the captured video. The elimination parameter determination unit 13 generates, for example, three elimination parameter groups.

[0037] The obscuration parameter determination unit 13 sets the obscuration parameters of object 1, object 2, object 3, and object 4 to 0.1, 0.5, 0.3, and 0.5, respectively, in obscuration parameter group 1. In this case, the user state acquisition unit 15 acquires 0.4 as the user's concentration level for obscuration parameter group 1.

[0038] The obscuration parameter determination unit 13 sets the obscuration parameters of object 1, object 2, object 3, and object 4 to 0.3, 0.1, 0.5, and 0.8, respectively, in obscuration parameter group 2. In this case, the user state acquisition unit 15 acquires 0.7 as the user's concentration level for obscuration parameter group 2.

[0039] The obscuration parameter determination unit 13 sets 0.4, 0.6, 0.7, and 0.3 as obscuration parameters for object 1, object 2, object 3, and object 4, respectively, in obscuration parameter group 3. In this case, the user state acquisition unit 15 acquires 0.3 as the user's concentration level for obscuration parameter group 3.

[0040] The optimal obscuration parameter estimation unit 17 uses the three obscuration parameter groups shown in FIG. 3 and the user's state information as training data to estimate the optimal obscuration parameters for each object that maximize the user's concentration.

[0041] 3.2 Second Example Next, a second example will be described with reference to Fig. 4. Fig. 4 is a table showing a second example of obscuration parameters and user state information. Each row in the table indicates an obscuration parameter group number, an obscuration parameter related to an object to be obscured, and a user state value.

[0042] In this example, the height and width (horizontal width) of the object to be concealed (erased) are set as the concealment parameters. In this case, whether or not to conceal the object is determined based on the height and width of the object. For example, if at least one of the height and width of the object is equal to or greater than (or less than) the concealment parameter, the object is concealed.

[0043] As in the first example, a user state value for the user's concentration level is acquired as a value between 0 and 1, inclusive, as user state information.

[0044] As shown in FIG. 4, the concealment parameter determination unit 13 generates, for example, three concealment parameter groups, as in the first example.

[0045] The occlusion parameter determination unit 13 sets the height and width of the object to be occluded to 30 and 20, respectively, in occlusion parameter group 1. In this case, the user state acquisition unit 15 acquires 0.4 as the user's concentration level for occlusion parameter group 1.

[0046] The concealment parameter determination unit 13 sets the height and width of the object to be concealed to 5 and 10, respectively, in concealment parameter group 2. In this case, the user state acquisition unit 15 acquires 0.7 as the user's concentration level for concealment parameter group 2.

[0047] The occlusion parameter determination unit 13 sets the height and width of the object to be occluded to 20 and 100, respectively, in occlusion parameter group 3. In this case, the user state acquisition unit 15 acquires 0.3 as the user's concentration level for occlusion parameter group 3.

[0048] The optimal occlusion parameter estimation unit 17 estimates the optimal occlusion parameters for each object that maximizes the user's concentration, using the three occlusion parameter groups shown in Fig. 4 and the user's state information as training data. That is, it estimates the size of the object to be occluded. In the case of the method according to this example, the items set as the occlusion parameters are not limited to the height and width of the object, but may also be other feature quantities such as the RGB value, saturation, brightness, or roundness of the object.

[0049] 3.3 Third Example Next, a third example will be described with reference to Fig. 5. In the third example, a case will be described in which multiple user states are set as user state information. Fig. 5 is a table showing a third example of obscuration parameters and user state information. Each row of the table indicates the obscuration parameter group number, the obscuration parameter for each object, the user state value of the user's concentration level, the user state value of the user's comfort level, and the total value of the user state values.

[0050] In this example, similarly to the first example, the obscuration parameter is set to a value between 0 and 1 for each object.

[0051] For example, the user's concentration level and the user's comfort level are set as the user's state information. Three or more items related to the user's state may be set. The user state value for the user's concentration level is acquired as a value between 0 and 1. Similarly, the user state value for the user's comfort level is acquired as a value between 0 and 1.

[0052] 5, the object detection unit 12 detects, for example, four objects 1 to 4 from the captured video. The elimination parameter determination unit 13 generates, for example, three elimination parameter groups.

[0053] The concealment parameter determination unit 13 sets the concealment parameters of object 1, object 2, object 3, and object 4 to 0.1, 0.5, 0.3, and 0.5, respectively, in concealment parameter group 1. In this case, the user state acquisition unit 15 acquires 0.4 as the user concentration level and 0.2 as the user comfort level for concealment parameter group 1. The sum of the user concentration level and the user comfort level is 0.6.

[0054] The concealment parameter determination unit 13 sets the concealment parameters of object 1, object 2, object 3, and object 4 to 0.3, 0.1, 0.5, and 0.8, respectively, in concealment parameter group 2. In this case, the user state acquisition unit 15 acquires 0.7 as the user concentration level and 0.1 as the user comfort level for concealment parameter group 2. The sum of the user concentration level and the user comfort level is 0.8.

[0055] The concealment parameter determination unit 13 sets the concealment parameters of object 1, object 2, object 3, and object 4 to 0.4, 0.6, 0.7, and 0.3, respectively, in concealment parameter group 3. In this case, the user state acquisition unit 15 acquires 0.3 as the user concentration level and 0.5 as the user comfort level for concealment parameter group 3. The sum of the user concentration level and the user comfort level is 0.8.

[0056] The optimal concealment parameter estimation unit 17 uses the three concealment parameter groups shown in FIG. 5 and the user's state information as training data to estimate optimal concealment parameters that maximize the sum of the user's concentration level and user's comfort level.

[0057] 4. Hardware Configuration Next, an example of the hardware configuration of the video processing device 1 will be described with reference to Fig. 6. Fig. 6 is a block diagram showing an example of the hardware configuration of the video processing device 1.

[0058] As shown in FIG. 6, the video processing device 1 includes a video processing unit 20, an imaging device 31, a display device 32, an input device 33, and an output device .

[0059] The image processing unit 20 is, for example, a computer, and includes a processor 21, a read-only memory (ROM) 22, a random access memory (RAM) 23, a storage medium 24, and an input / output interface 25.

[0060] The processor 21, ROM 22, RAM 23, storage medium 24, and input / output interface 25 are electrically connected to one another via a bus 26. The processor 21, ROM 22, RAM 23, storage medium 24, and input / output interface 25 transmit and receive data or control signals via the bus 26.

[0061] The processor 21 is configured by a general-purpose hardware processor including, for example, a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), etc. The processor 21 controls the entire video processing unit 20.

[0062] The ROM 22 is a non-volatile memory. For example, the ROM 22 is an erasable programmable read-only memory (EPROM). The ROM 22 is a non-transitory storage medium that stores firmware, programs, and the like. For example, the processor 21 loads firmware from the ROM 22 into the RAM 23 and executes the firmware.

[0063] The RAM 23 is a volatile memory, such as a dynamic random access memory (DRAM) or a static random access memory (SRAM). The RAM 23 temporarily stores programs used in processing by the processor 21 and data used to execute the programs. The processor 21 executes the programs in the RAM 23 to perform operations on the data in the RAM 23 and store the results of the operations in the RAM 23.

[0064] The storage medium 24 is composed of a nonvolatile memory such as a hard disk drive (HDD) or a solid state drive (SSD). The storage medium 24 non-temporarily stores programs executed by the processor 21 and data required for executing the programs. For example, the storage medium 24 stores a concealment processing program for executing the concealment processing. The concealment processing program causes the video processing unit 20 to execute at least some of the functions of the components of the video processing device 1, namely, the imaging unit 11, the object detection unit 12, the concealment parameter determination unit 13, the concealment image presentation unit 14, the user state acquisition unit 15, and the optimal concealment parameter estimation unit 17. The storage medium 24 also stores data used in the concealment processing, such as the captured video, the concealment image, object information, concealment parameters, and user state information. In other words, the storage medium 24 functions as the result storage unit 16.

[0065] The program executed by the video processing unit 20 may be provided to the video processing unit 20 via a readable non-transitory storage medium (not shown). Such a storage medium is called a non-transitory computer-readable storage medium. Non-transitory computer-readable storage media include disks such as flexible disks, optical disks (CD-ROM, CD-R, DVD-ROM, DVD-R, etc.), and magneto-optical disks (MO, etc.), as well as semiconductor memories.

[0066] The input / output interface 25 is connected to the image capturing device 31, the display device 32, the input device 33, and the output device 34. The input / output interface 25 enables input of captured images from the image capturing device 31, display of images on the display device 32, input of information from the input device 33, and output of information to the output device 34. For example, the input / output interface 25 may be a wired interface or a wireless interface. A wired interface includes a port to which a device is connected. For example, a wireless interface has a function that satisfies communication standards such as Bluetooth (registered trademark) and WiFi (registered trademark).

[0067] The image capturing device 31 includes a camera. A user uses the image capturing device 31 to capture an image.

[0068] The display device 32 includes a display (such as an LCD (Liquid Crystal Display), an EL (Electroluminescence) display, or a cathode ray tube.) The display device 32 can display captured images, obscured images, obscured parameters, user status information, and the like.

[0069] The input device 33 may include a keyboard, a mouse, a touch panel, a receiving device, a disk drive, etc. The input device 33 is not limited to these, and may include any other input device.

[0070] The output device 34 may include a transmitting device, a disk drive, etc. The output device 34 is not limited to these and may include any other output device. The input device 33 and the output device 34 may be configured as an input / output device having the functions of both the input device 33 and the output device 34.

[0071] When the video processing device 1 (video processing unit 20) starts up, the processor 21 executes a program in the ROM 22 and loads and starts up an operating system (OS) in the RAM 23. Under control of the OS, the processor 21 monitors input instructions, connections to external devices, and the like. Under control of the OS, the processor 21 also sets up a program area and a data area in the RAM 23. In response to an instruction to start up the video processing device 1, the processor 21 loads a concealment processing program from the storage medium 24 into the program area of ​​the RAM 23 and loads data used to execute the concealment processing program from the storage medium 24 into the data area of ​​the RAM 23. The processor 21 calculates data in the data area according to the concealment processing program and writes the calculation results to the data area. Through these operations, the processor 21, RAM 23, storage medium 24, input / output interface 25, and bus 26 work together to execute at least some of the functions of the components of the video processing device 1.

[0072] 5. Effects of the Embodiment With the configuration according to this embodiment, the video processing device 1 can detect an object in a captured video and estimate at least one of the object's type, position, and size. The video processing device 1 can set an occlusion parameter for each detected object. The video processing device 1 can generate an occlusion-erased video based on the occlusion parameter and present the occlusion-erased video to the user. The video processing device 1 can acquire state information of a user who has viewed the occlusion-erased video. The video processing device 1 can set at least one of the user's concentration level, user comfort level, and perceived discomfort with the occlusion-erased video as the user's state. The video processing device 1 can then optimize the occlusion parameters of an object to be occlusion-erased based on the user's state information. That is, by acquiring state information of a user who has viewed the video to which the occlusion-erased process has been applied, the video processing device 1 can determine the occlusion parameters of an object to be occlusion-erased based on the user's state information. This eliminates the need for the user to manually set the occlusion parameters. Therefore, the video processing device 1 can reduce the burden on the user associated with the occlusion-erased video.

[0073] The present invention is not limited to the above-described embodiments. Various modifications are possible in the implementation stage without departing from the spirit of the invention. Furthermore, the embodiments may be implemented in appropriate combinations, in which case the combined effects can be obtained. Furthermore, the above-described embodiments include various inventions, and various inventions can be extracted by combining selected elements from the disclosed elements. For example, if the problem can be solved and the desired effect can be obtained even if some elements are deleted from all elements shown in the embodiments, the configuration from which these elements are deleted can be extracted as an invention.

[0074] DESCRIPTION OF SYMBOLS 1...Video processing device 11...Image capture unit 12...Object detection unit 13...Occlusion parameter determination unit 14...Occlusion video presentation unit 15...User state acquisition unit 16...Result storage unit 17...Optimal occlusion parameter estimation unit 20...Video processing unit 21...Processor 22...ROM 23...RAM 24...Storage medium 25...Input / output interface 26...Bus 31...Photographing device 32...Display device 33...Input device 34...Output device

Claims

1. A video processing device comprising: an object detection unit that detects an object from a captured video; an obscuration parameter determination unit that determines obscuration parameters of the object; an obscuration image presentation unit that generates obscuration images by performing obscuration processing on the captured video based on the obscuration parameters and presents the obscuration images to a user; a user status acquisition unit that acquires status information of the user who has viewed the obscuration images; and an optimal obscuration parameter estimation unit that estimates the obscuration parameters that will improve the status of the user based on the status information of the user.

2. The video processing device according to claim 1, wherein the object detection unit estimates at least one of the type, position, and size of the object.

3. The image processing device according to claim 1, wherein the state information of the user includes at least one of the user's concentration level, the user's comfort level, and the user's sense of discomfort regarding the obscured image.

4. The video processing device according to claim 1, wherein the optimal occlusion parameter estimation unit estimates the occlusion parameters that improve the states of the users by Bayesian optimization based on the state information of the users corresponding to the objects.

Images