Video processing device

Abstract

A video processing device according to one aspect of the present invention includes: a video acquisition unit that acquires video data; an object recognition unit that recognizes an object in the video data; a characteristic acquisition unit that acquires a characteristic of the recognized object; a rule storage unit that stores a rule related to an erasure processing of the object according to the characteristic; an erasure determination unit that executes determination of the erasure processing for the object on the basis of the characteristic of the object and the rule; and an erasure processing unit that executes the erasure processing on the object on the basis of a result of the determination.

Description

Video Processing Device

[0001] One aspect of the present invention relates to a video processing device.

[0002] Diminished Reality (DR) technology, which can hide or highlight real objects using Augmented Reality (AR) technology, is being researched, as in Non-Patent Document 1.

[0003] For example, disappearing reality technology can prevent distractions while driving a car by hiding distracting objects such as prominent signs or oncoming vehicles, or by highlighting important objects such as traffic lights.

[0004] Cheng et al., “Towards Understanding Diminished Reality”, CHI'22: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, Article No. 549, pp. 1-16, April 2022. Joseph Redmon et al., “YOLOv3: An Incremental Improvement”, arXiv preprint, arXiv:1804.02767, 2018. Toshio Mori et al., “Relationship between Visual Impression of Color Texture and Image Information Content”, Textile Product Consumption Science, Vol. 51, No. 5, pp. 433-440, 2010. Yasuhisa Nakano et al., “Psychophysical Measurement Methods”, Vision, Vol. 7, pp. 17-27, 1995.

[0005] For example, by specifying the object to be hidden in advance, such as by setting a rule to "automatically hide or erase signs," it is possible to automatically hide or erase specific objects.

[0006] However, it takes time and effort to set each object to be obscured.

[0007] The present invention has been made in light of the above circumstances, and proposes a technique that enables objects to be automatically hidden and erased relatively easily.

[0008] An image processing device according to one aspect of the present invention includes an image acquisition unit that acquires image data, an object recognition unit that recognizes an object in the image data, a property acquisition unit that acquires the property of the recognized object, a rule storage unit that stores rules relating to the erasure process of the object according to the property, an erasure determination unit that determines the erasure process for the object based on the property of the object and the rule, and an erasure processing unit that performs the erasure process for the object based on the result of the determination.

[0009] According to one aspect of the present invention, there is provided a video processing device that can perform concealment and erasure processing on an object in video data relatively easily.

[0010] FIG. 1 is a block diagram showing an example of the configuration of a video processing device according to a first embodiment. FIG. 2 is a block diagram showing the hardware configuration of the video processing device according to the first embodiment. FIG. 3 is a diagram for explaining the properties of an object. FIG. 4 is a diagram for explaining an overview of the video processing device according to the first embodiment. FIG. 5 is a diagram for explaining an overview of the video processing device according to the first embodiment. FIG. 6 is a flowchart showing an example of the operation of the video processing device according to the first embodiment. FIG. 7 is a block diagram showing an example of the configuration of a video processing device according to a second embodiment. FIG. 8 is a diagram for explaining a visual characteristic model. FIG. 9 is a diagram for explaining an overview of the video processing device according to the second embodiment. FIG. 10 is a flowchart showing an example of the operation of the video processing device according to the second embodiment.

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Hereinafter, elements that are identical or similar to elements already described will be assigned the same or similar reference numerals, and duplicate descriptions will generally be omitted. For example, when there are multiple identical or similar elements, a common reference numeral may be used to describe each element without distinguishing between them, or a subnumber may be used in addition to the common reference numeral to describe each element distinctly.

[0012] (1) First Embodiment A video processing device, a video processing method, and a video processing program according to a first embodiment will be described with reference to FIGS.

[0013] (a) Configuration FIG. 1 is a block diagram showing an example of the configuration of a video processing device according to this embodiment.

[0014] 1 , the video processing device 1 of this embodiment includes an image acquisition unit 10, an object recognition unit 11, a property acquisition unit 12, an obscuration rule storage unit 13, an obscuration determination unit 14, and an obscuration processing unit 15. The video processing device 1 communicates with a camera 2 and a display 3. The camera 2 and the display 3 may be components included in the video processing device 1.

[0015] The image acquisition unit 10 acquires image data IMGa from the camera 2. The image acquisition unit 10 can perform various processes on the image data IMGa. The image acquisition unit 10 sends the acquired image data IMGa to the object recognition unit 11, the property acquisition unit 12, and the erasure processing unit 15, which are located downstream.

[0016] The camera 2 captures an image of a space and generates image data IMGa based on the captured image. The camera 2 can generate the image data IMGa of a moving image or a still image. For example, the image data IMGa is real-time image data.

[0017] The object recognition unit 11 receives the image data IMGa from the image acquisition unit 10. The object recognition unit 11 recognizes various objects in the image data IMGa. For example, the object recognition unit 11 recognizes objects in the image data IMGa using various object detection technologies such as YOLO (You Only Look Once). The object recognition unit 11 sends object recognition results regarding the recognized objects to the property acquisition unit 12.

[0018] The property acquisition unit 12 receives the image data IMGa from the image acquisition unit 10 and the object recognition results from the object recognition unit 11. For example, the property acquisition unit 12 receives the image range of each recognized object from the object recognition unit 11 as input data. The property acquisition unit 12 analyzes the objects included in each image range. The property acquisition unit 12 acquires the properties of each recognized object based on the analysis process of the objects within the image range. For example, the property acquisition unit 12 acquires values ​​indicating the properties of the objects using a color space evaluation technique such as CIELAB. The property acquisition unit 12 sends the properties of each object to the concealment / erasure determination unit 14.

[0019] The erasure rule storage unit 13 stores a plurality of erasure rules (also called image processing rules or DR rules) RL, which include whether or not to erase an object for each property and the method of erasure for each property. For example, the erasure rules RL are created manually. Note that in this embodiment, as will be described later, the erasure rules RL are not limited to rules for erasing objects, but may also include rules for highlighting objects.

[0020] The erasure determination unit 14 receives the object properties from the property acquisition unit 12 and the erasure rule RL from the erasure rule storage unit 13. Based on the erasure rule RL, the erasure determination unit 14 determines whether or not an object in the video data IMGa is to be erased (or highlighted), and the method of erasure (or highlighting). The erasure determination unit 14 sends the determination result to the erasure processing unit 15.

[0021] The erasure processing unit 15 receives the video data IMGa from the video acquisition unit 10 and the judgment result of whether or not an object has been erased from the erasure determination unit 14. Based on the judgment result, the erasure processing unit 15 performs erasure processing on the object to be erased (or highlighted) in the video data IMGa. After the erasure processing, the erasure processing unit 15 sends the video data IMGz including the object that has been subjected to the erasure processing to the display 3.

[0022] The display 3 receives the video data IMGz from the concealment / concealment processing unit 15. The display 3 displays the video data IMGz. If the video data IMGz includes a concealed object, the display 3 displays the video data IMGz in a state in which the specific object has been concealed to the user. The display 3 is, for example, a head-mounted display or a flat panel display.

[0023] FIG. 2 is a block diagram showing the hardware configuration of the video processing device 1 of this embodiment.

[0024] The video processing device 1 can be configured as a computer. The video processing device 1 does not need to be configured as a single computer, and may be configured by multiple computers.

[0025] 2, the video processing device 1 includes a processor 100, a ROM 110, a RAM 120, a storage 130, and an interface 140. These hardware components are connected via a bus.

[0026] The processor 100 is a processing circuit capable of executing various programs (software, applications). The processor 100 includes a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processor 100 performs various calculation processes on the image data IMG (IMGa, IMGz) and a certain image range extracted from the image data IMG. The processor 100 controls the overall operation of the image processing device 1. Note that multiple processors 100 may be provided within the image processing device 1.

[0027] The ROM 110 is a non-volatile semiconductor memory such as an EEPROM (registered trademark), and stores programs and control data for controlling the video processing device 1.

[0028] The RAM 120 is a volatile semiconductor memory such as a dynamic RAM (DRAM) or a static RAM (SRAM). The RAM 120 is used as a working area for the processor 100. The RAM 120 temporarily stores image data IMG, various data and parameters used by the processor 100, and the like.

[0029] The storage 130 is a non-volatile storage device such as a hard disk drive (HDD), a solid state drive (SSD), or a memory card. The storage 130 stores various types of information, various types of data, and various types of parameters. The storage 130 has a database configured by a collection of certain types of data. For example, the storage 130 functions as the erasure rule storage unit 13. The storage 130 stores the erasure rule RL. Programs and control data may also be stored in the storage 130.

[0030] The storage 130 stores a program (video processing program) relating to the video processing method executed by the video processing device 1 of the present embodiment. The video processing method of the embodiment will be described later. The video processing program includes multiple program codes corresponding to multiple processes of the video processing method of the embodiment. The video processing program causes the processor 100 to execute various processes for video processing. The video processing program may be stored in the ROM 110 or the RAM 120.

[0031] The interface 140 includes various connectors, various ports, a signal processing circuit, a communication module, etc. The interface 140 connects the camera 2 and the display 3 to the image processing device 1. The interface 140 is responsible for inputting and outputting information and data, various processes on information and data, and various controls for acquiring information and data. The interface 140 can transfer signals, information, and data between the image processing device 1 and other devices 2 and 3 by communication via a wireless or wired network. The interface 140 sends various data and signals from the other devices 2 and 3 to the processor 100. The interface 140 sends various data and signals from the processor 100 or the RAM 120 to the other devices 2 and 3.

[0032] These hardware configurations 100, 110, 120, 130, and 140 can realize the software configurations (functional blocks) 10, 11, 12, 13, 14, and 15 of the video processing device 1 of this embodiment.

[0033] The specific hardware configuration of the video processing device 1 may be such that components are omitted, replaced, or added as appropriate depending on the embodiment.

[0034] FIG. 3 is a schematic diagram for explaining the properties of objects in the image data IMGa in the image processing device 1 of this embodiment.

[0035] The image processing device 1 of this embodiment manages information relating to the properties of a plurality of objects. The information relating to the properties of the objects is stored in the RAM 120 or the storage 130, for example.

[0036] As shown in Fig. 3, each object is assigned an identification number (ID) for management purposes. The video processing device 1 of this embodiment handles the type, saturation, brightness, hue, size, texture, speed, saliency map, etc. of an object having a certain identification number as properties for the obscuration process. For example, the texture further includes parameters such as contrast, correlation, entropy, and angular second moment as object properties.

[0037] The parameter values ​​of these properties are obtained by well-known image processing of the image data IMGa, such as YOLO and CIELAB. For example, the size of an object is obtained within the range of the object using the coordinates of the x-axis, y-axis, w-axis, and h-axis in the image data as parameters. The type of object is obtained using techniques such as AI image recognition. Values ​​such as saturation, brightness, and hue are obtained based on the results of various analytical processes on multiple pixels in the image data IMGa.

[0038] These properties are acquired for each of the objects in the image data IMG.

[0039] FIG. 4 is a schematic diagram for explaining an overview of the video processing in the video processing device 1 of this embodiment.

[0040] As shown in FIG. 4, various properties of one or more objects 200, 201, 202 in the image data IMGa are analyzed using techniques such as YOLO or CIELAB.

[0041] For example, by analyzing the image data IMGa, the object 200 is recognized as a type of “automobile.” The object 200 recognized as an automobile is analyzed to have a saturation value of “6” and a contrast value of “9.”

[0042] The object 201 is recognized as a type of “signal.” The object 201 recognized as a signal is analyzed to have a saturation value of “4,” a contrast value of “6,” and so on.

[0043] The object 202 is recognized as a type of “signboard.” The object 202 recognized as a signboard is analyzed to have a saturation value of “2,” a contrast value of “3,” and so on.

[0044] Regarding the properties of the objects 200, 201, and 202, thresholds for erasing the objects are set in advance as erasing rules RL.

[0045] There are various methods for erasing an object, such as making it transparent, making it an outline, blurring it, reducing saturation, reducing contrast, etc. These erasing methods or the strength of the erasing can be included in the erasing rule RL.

[0046] For example, a user 900 viewing video data tends to be visually distracted.

[0047] For such a user 900, for example, according to the concealment rule RL, if the saturation values ​​of the multiple objects 200, 201, and 202 in the video data IMGa are 7 or greater, the video processing device 1 processes the video data IMGa to reduce the saturation of the corresponding objects. Also, according to the concealment rule RL, if the contrast values ​​of the multiple objects 200, 201, and 202 in the video data IMGa are 8 or greater, the video processing device 1 processes the video data IMGa to outline the corresponding objects.

[0048] Based on such concealment and erasure rules RL, the video processing device 1 converts the automobile 200 in the video data IMGa into a contour line. As a result, video data IMGz is generated in which the object (automobile) 210 has been subjected to concealment and erasure processing. The generated video data IMGz is displayed on the display 3. A user 900 who tends to be visually distracted observes the video data IMGz in which the automobile 210 has been converted into a contour line.

[0049] By hiding or erasing the object 210 (200) in the image data IMGz in this way, the image processing device 1 of this embodiment can prevent the user 900 from being distracted.

[0050] FIG. 5 is a schematic diagram for explaining another outline of the video processing in the video processing device 1 of this embodiment.

[0051] As shown in FIG. 5, the image processing device 1 of this embodiment may process the image data IMGa based on the concealment / disappearance rule RL so as to emphasize a specific object in the image data IMGa.

[0052] The user 900 has a visual impairment such as low vision.

[0053] For example, in accordance with the concealment rule RL, for the user 900, if the object type is a signal for the plurality of objects 200, 201, and 202 in the video data IMGa, the video processing device 1 executes a concealment process (enhancement process) on the video data IMGa so as to enlarge the corresponding object. Also, for example, in accordance with the concealment rule RL, for the plurality of objects 200, 201, and 202 in the video data IMGa, if the contrast value of the object type is 6 or less, the video processing device 1 processes the video data IMGa so as to sharpen the corresponding object.

[0054] For example, the image processing device 1 recognizes the type of the object 201 in the image data IMGa as a signal. The contrast value of the object 201 is "6".

[0055] The video processing device 1 enlarges and sharpens the object (signal) 201 in the video data IMGa. As a result, video data IMGz is generated in which the object (signal) 220 has been subjected to enhancement processing. The generated video data IMGz is displayed on the display 3. A visually impaired user 900 observes the video data IMGz in which the object 220 has been enlarged and sharpened.

[0056] By emphasizing the object 220 (201) in the video data IMGz in this way, the video processing device of this embodiment can assist users with visual impairments.

[0057] In this embodiment, the erasure process including the erasure and emphasis of an object is also called DR process.

[0058] As described above, the video processing device 1 of this embodiment determines and executes the hiding or highlighting of the objects 200, 201, and 202 in the video data IMGz based on the hiding and highlighting rule RL set in advance.

[0059] (b) Operation An example of the operation of the video processing device of this embodiment will be described with reference to Fig. 6. Here, Figs. 1 to 5 will also be referenced as appropriate. Note that in this embodiment, the operation of the video processing device 1 corresponds to a video processing method. Alternatively, the operation of the video processing device 1 corresponds to processing executed by a video processing program.

[0060] FIG. 6 is a flowchart showing an example of the operation of the video processing device 1 of this embodiment.

[0061] As shown in FIG. 6, the video processing device 1 of this embodiment starts various processes for hiding and / or highlighting an object on real-time video data.

[0062] In step S1 , the image processing device 1 acquires, via the image acquisition unit 10 , image data IMGa captured by the camera 2 .

[0063] In step S2, the image processing device 1 recognizes one or more objects 200, 201, 202 in the image data IMGa through analysis processing using YOLO or the like in the object recognition unit 11.

[0064] In step S3, the image processing device 1 acquires the properties of each of the recognized objects 200, 201, and 202 through analysis processing using CIELAB or the like in the property acquisition unit 12.

[0065] The video processing device 1 acquires the concealment rule RL from the concealment rule storage unit 13 .

[0066] In step S4, the image processing device 1 determines, using the concealment / erasure determination unit 14, whether or not the recognized objects 200, 201, and 202 in the image data IMGa will be concealed (or highlighted) and the method of concealment (or highlighting) based on the preset concealment / erasure rule RL and the properties of each of the acquired objects 200, 201, and 202.

[0067] For example, the video processing device 1 acquires various parameters (e.g., type, saturation, contrast, etc.) corresponding to the properties of each object 200, 201, 202 in the video data IMGa. The video processing device 1 compares the acquired parameter values ​​with thresholds for various parameters in the concealment / concealment rule RL using the concealment / concealment determination unit 14. The video processing device 1 determines whether to conceal (or emphasize) the object to be determined based on the comparison result between the parameter value and the threshold. The video processing device 1 also determines the concealment method or concealment strength of the object to be determined based on the comparison result between the parameter value and the threshold. For example, if the value of a certain parameter of the object to be determined is equal to or greater than a threshold, the video processing device 1 determines the object to be concealed and selects contouring as the process for the object to be determined. For example, if the value of a certain parameter of the object to be determined is equal to or less than a threshold, the video processing device 1 determines the object to be emphasized and selects sharpening as the process for the object to be determined.

[0068] In step S5, the image processing device 1 performs an erasure process (for example, making transparent, contouring, blurring, reducing saturation, and / or reducing contrast) on the object to be erased by the erasure processing unit 15 based on the determination result of the erasure determination unit 14. Alternatively, the image processing device 1 performs an emphasis process (for example, enlarging and / or sharpening) on ​​a certain object by the erasure processing unit 15 based on the determination result of the erasure determination unit 14.

[0069] The video processing device 1 sends the video data IMGz after the concealment processing to the display 3. The user 900 views, via the display 3, the video data IMGz in which the specific object 200 has been concealed or highlighted.

[0070] As described above, the video processing device 1 of this embodiment can provide video data generated by video processing using DR technology based on the pre-set rule RL.

[0071] (c) Summary The video processing device 1 of this embodiment executes processing to hide or highlight objects in the video data IMG based on rules RL that are set in advance according to the properties of the objects.

[0072] This allows the video processing device 1 of this embodiment to automatically hide or highlight specific objects in the video data IMG without manually setting each object to be hidden or highlighted one by one.

[0073] Therefore, the video processing device 1 of this embodiment can relatively easily perform various processes using DR technology on objects in video data.

[0074] (2) Second Embodiment A video processing device, a video processing program, and a video processing program according to a second embodiment will be described with reference to FIGS.

[0075] (a) Configuration An example of the configuration of the video processing device of this embodiment will be described with reference to FIG.

[0076] The video processing device of this embodiment takes into consideration the visual characteristics of the user and executes processing to hide (or highlight) objects in video data.

[0077] FIG. 7 is a block diagram showing an example of the configuration of the video processing device 1 of this embodiment.

[0078] As shown in FIG. 7, the video processing device 1 of this embodiment includes a visual characteristic model storage unit 17 .

[0079] The visual characteristic model storage unit 17 stores the visual characteristic model MD. The visual characteristic model MD includes a model related to the visual characteristic of the user. The visual characteristic model MD may also include a model related to the visual characteristic of each property of an object.

[0080] For example, the visual characteristic model storage unit 17 stores, as the visual characteristic model MD, a model relating to the likelihood of the user becoming distracted, etc. Furthermore, the visual characteristic model storage unit 17 stores, as the visual characteristic model MD, a model relating to visual characteristics such as the user's visual sensitivity to various parameters such as the saturation, brightness, hue, and contrast of an object.

[0081] The visual characteristic model MD can be obtained by performing a regression analysis using learning data with the property values ​​as explanatory variables and the distraction level as the target variable, and calculating the parameters of each property.

[0082] 8 is a diagram showing an example of a visual characteristic model, in which an example of a visual characteristic model of a certain user is shown.

[0083] For example, regression coefficients of a user's likelihood of distraction for each object property are set as parameters of the user's visual characteristic model MD for various properties such as object size, saturation, brightness, and hue based on well-known techniques.

[0084] The user visual characteristic model MD may be a model based on the characteristics of each specific user, or may be a model based on generalized characteristics of multiple users.

[0085] The visual characteristic model storage unit 17 sends the stored visual characteristic model MD to the concealment / disappearance determination unit 14 .

[0086] The concealment / disappearance determination unit 14 receives the visual characteristic model MD from the visual characteristic model storage unit 17. The concealment / disappearance determination unit 14 determines whether or not each object in the video data IMGa is concealed and the method of concealment / disappearance based on the visual characteristic model MD.

[0087] FIG. 9 is a schematic diagram for explaining an overview of the video processing (DR processing) in the video processing device 1 of this embodiment.

[0088] As in the above-described embodiments, the image processing device 1 of this embodiment acquires various parameters of the properties of the objects 200, 201, and 202 in the image data IMGa by analyzing the image data IMGa.

[0089] Based on the visual characteristic model MD, the video processing device 1 acquires the visual characteristics of the user 900. For example, the user 900 has a characteristic with a saturation value of "0.5" and a characteristic with a contrast value of "0.7".

[0090] The video processing device 1 calculates an evaluation value for each of the objects 200, 201, and 202 regarding the presence or absence of occlusion (or emphasis) based on the various acquired parameters and the user's visual characteristic model MD.

[0091] For example, an object 200 recognized as a car has an evaluation value of "9.3." For example, an object 201 recognized as a traffic light has an evaluation value of "6.2." For example, an object 202 recognized as a signboard has an evaluation value of "3.1."

[0092] The video processing device 1 determines whether or not each of the objects 200, 201, and 202 is obscured or obscured based on the obscuration rule RL and the calculated evaluation value by the obscuration determination unit 14. For example, the video processing device 1 obscures or obscures an object having an evaluation value of 9 or more based on a threshold value set in the obscuration rule RL.

[0093] In the example of FIG. 9, the video processing device 1 converts the object (car) 200 into a contour line based on the determination result of the concealment / disappearance determination unit 14 .

[0094] The strength of the obscuration may be controlled according to the type of object and the magnitude of the evaluation value. Furthermore, the object in the video data IMGa may be emphasized by processing such as enlargement and / or sharpening according to the visual characteristic model MD and the evaluation value.

[0095] The video processing device 1 may include both the concealment / disappearance rule storage unit 13 and the visual characteristic model storage unit 17 .

[0096] (b) Operation An example of the operation of the video processing device of this embodiment will be described with reference to Fig. 10. As described above, the operation of the video processing device corresponds to various processes executed by a video processing method or a video processing program.

[0097] FIG. 10 is a flowchart showing an example of the operation of the video processing device 1 of this embodiment.

[0098] As shown in FIG. 10, the video processing device 1 executes the processes from step S1 to step S3, similarly to the first embodiment.

[0099] The video processing device 1 acquires a visual characteristic model MD of a certain user from the visual characteristic model storage unit 17 .

[0100] In step S4A, the video processing device 1 determines whether or not the recognized objects 200, 201, and 202 in the video data IMGa are obscured and how they are obscured, based on the user's visual characteristic model MD and the properties of the objects.

[0101] For example, the video processing device 1 calculates an evaluation value according to the visual characteristic model MD for each of the objects 200, 201, and 202 in the video data IMGa. The video processing device 1 determines whether the calculated evaluation value satisfies the conditions for the erasure process. For example, if the evaluation value of the object to be determined is equal to or greater than a threshold, the video processing device 1 determines that the object to be determined should be erased (or highlighted).

[0102] Thereafter, in step S5, the video processing device 1 performs a process of erasing or highlighting the target object. The video processing device 1 sends the video data IMGz after the erasure process to the display 3. The user 900 views the video data IMGz in which the specific object 200 has been erased (or highlighted) via the display 3.

[0103] As described above, the video processing device 1 of this embodiment can provide video data generated by video processing using DR technology based on the user's visual characteristic model MD.

[0104] (c) Summary The video processing device according to the first embodiment described above can automatically hide or highlight a specific object by specifying in advance the properties of the object to be hidden or hidden based on preset rules.

[0105] However, it can be relatively difficult to set the properties of each object to be obscured.

[0106] The video processing device 1 of this embodiment performs a process of hiding or erasing an object in video data based on a model of the user's visual characteristics.

[0107] This allows the video processing device of this embodiment to automatically hide or highlight objects in video data relatively easily.

[0108] Therefore, the video processing device of this embodiment can relatively easily perform various processes using DR technology on objects in video data.

[0109] (3) Others: The present invention is not limited to the above-described embodiments, and various modifications can be made 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.

[0110] REFERENCE SIGNS LIST 1...Video processing device 2...Camera 3...Display 10...Video acquisition unit 11...Object recognition unit 12...Property acquisition unit 13...Concealment and erasure rule storage unit 14...Concealment and erasure determination unit 15...Concealment and erasure processing unit 17...Visual characteristic model storage unit 100...Processor 110...ROM 120...RAM 130...Storage 140...Interface 200, 201, 202...Object 900...User IMGa, IMGz...Video data RL...Concealment and erasure rule MD...Visual characteristic model

Claims

1. A video processing device comprising: a video acquisition unit that acquires video data; an object recognition unit that recognizes objects in the video data; a property acquisition unit that acquires the properties of the recognized object; a rule storage unit that stores rules regarding the erasure process of the object according to the properties; a concealment determination unit that determines the concealment process for the object based on the properties of the object and the rules; and a concealment processing unit that executes the concealment process for the object based on the result of the determination.

2. The video processing device according to claim 1, wherein the occlusion / erasure determination unit determines whether or not to occlude or erase the object based on a result of comparison between the value indicating the property of the object and a first threshold value.

3. The image processing device according to claim 1, wherein the obscuration processing includes highlighting the object, the obscuration determination unit determines whether to highlight the object based on the property of the object and the rule, and the obscuration processing unit performs highlighting of the object based on the result of the determination.

4. The video processing device according to claim 3, wherein the concealment / cancellation determination unit determines whether or not to emphasize the object based on a result of comparison between the value indicating the property of the object and a second threshold value.

5. A video processing device comprising: a video acquisition unit that acquires video data; an object recognition unit that recognizes an object in the video data; a property acquisition unit that acquires the properties of the recognized object; a model storage unit that stores a visual characteristic model of a user; a concealment / erasure determination unit that performs a determination of concealment processing for the object based on the properties of the object and the visual characteristic model; and a concealment / erasure processing unit that performs the concealment / erasure processing based on the result of the determination.

6. The video processing device according to claim 5, wherein the occlusion / erasure determination unit determines whether or not to occlude the object based on a first evaluation value obtained from a calculation result between the parameter indicating the property and the visual characteristic model.

7. The image processing device according to claim 6, wherein the obscuration processing includes emphasizing the object, and the obscuration determination unit determines whether or not to emphasize the object based on a second evaluation value obtained from a calculation result between a parameter indicating the property and the visual characteristic model.

Images