Method for processing visual content

Abstract

The invention relates to a method for processing visual content (Cont), the method comprising a step (E1) of generating metadata (Meta) associated with the visual content (Cont), the generating step comprising a step (E11) of segmenting the visual content (Cont) into a plurality of zones (Z1-Z6), a step (E12) of determining descriptors (Desc) for the zones from the plurality of zones (Z1-Z6), the descriptors (Desc) of a zone comprising a parameter (P) for the acceptability of the zone to receive a visual element. The processing method further comprises a step of associating zone descriptors (Desc) with the visual content as metadata (Meta) for the visual content.

Description

DESCRIPTION Title of the invention: Method for processing visual content

[0001] Technical field

[0002] The present invention relates to the field of communications between electronic devices, such as servers or terminals (or between people using these electronic devices) and more particularly to the exchange of visual content between two electronic devices, said visual content comprising a visual element intended to be displayed superimposed on this visual content.

[0003] Visual content here means purely visual content (such as an image or video) as well as audiovisual or multimedia content comprising at least one visual component such as an image or video.

[0004] Methods for creating freely configurable and modular graphical interfaces are known. These graphical interfaces are essentially composed of fixed or dynamic multimedia objects, texts or actuators.

[0005] In these processes, a visual element may be placed on an image area that is not suitable for good readability of this visual element. Thus, if the visual element is positioned on a face, this presence may promote a potential reading error by the user.

[0006] There is therefore a need to propose a processing method which makes it possible to improve the rendering of visual elements superimposed on an image.

[0007] Summary of the invention

[0008] An object of the invention relates to a method for processing visual content comprising a generation of metadata associated with said visual content, said generation comprising a segmentation of the visual content into a plurality of zones, a determination of zone descriptors of the plurality of zones, the descriptors of a zone comprising a parameter of acceptability of said zone to receive a visual element, an association with said visual content of the zone descriptors, as metadata of said visual content.

[0009] The present application relates in particular to a method for processing visual content, said processing method comprising: - a generation of metadata associated with said visual content, said generation comprising: • a segmentation of the visual content (Cont) into a plurality of zones, said segmentation taking into account the semantic elements detected in said visual content; • a determination of descriptors of zones of the plurality of zones, the descriptors of a zone comprising an acceptability parameter of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one of said semantic elements detected on said zone; - an association with said visual content of the zone descriptors, as metadata of said visual content.

[0010] The processing method analyzes the visual content in order to define preservation zones in which no visual element can be superimposed on the image and / or zones of acceptance of visual elements that can be superimposed on the image. These zones are characterized either by the presence of a strong semantic element (face, main element of a landscape, etc.) or, on the contrary, they constitute neutral zones, i.e. zones containing no semantic element or no semantic element identified as strong. Each zone thus forms a visual unit identifying said zone and grouping together all the properties concerning it. This visual unit can result, for example, from the shape of the zone, the color of the zone, the texture of the zone or the semantic element associated with this zone. In other words, these zones have similar colors (gradient of the same color, etc.), the same resolution or the same level of blur or even the same texture within the same area.

[0011] Each zone is assigned descriptors that define it, both from a structural point of view and in terms of the content carried. These zone descriptors are integrated into the metadata associated with the visual content, thus ensuring their preservation during storage and / or transmission of the visual content through a communication channel. This communication channel is suitable for transmitting different streams that can carry different types of data. This allows for optimal rendering or adaptation on a remote user terminal. The user experience when viewing visual content can thus be improved.

[0012] In an alternative embodiment, taken alone or in combination, the segmentation comprises a layered decomposition by depth of the visual content.

[0013] In an alternative embodiment, taken in isolation or in combination, an area comprises a majority of pixels of the same color and / or the same texture and / or corresponds to a visual rendering of a specific part of an individual.

[0014] In an alternative embodiment, taken alone or in combination, the visual content being a video, the segmentation of the visual content into a plurality of zones is carried out over the entire video.

[0015] In an alternative embodiment, taken in isolation or in combination, the visual content being a video, the segmentation of the visual content into a plurality of zones is carried out by video sequences cutting said video.

[0016] In an alternative embodiment, taken in isolation or in combination, the zones obtained by segmentation have different depths.

[0017] In an alternative embodiment, taken in isolation or in combination, said acceptability parameter of an area takes into account a semantic importance of at least one of said detected semantic elements present in said area.

[0018] Another object of the invention relates to a method of associating, with visual content, a visual element to be displayed superimposed on said visual content, said association method comprising, obtaining metadata associated with said visual content, said metadata comprising descriptors of the zones of a plurality of zones segmenting said visual content, said descriptors of a zone comprising an acceptability parameter of said zone to receive a visual element, a selection of at least one zone of said plurality of zones to receive the visual element according to said acceptability parameters of said descriptors of the plurality of zones, an association with said visual element of said at least one selected zone.

[0019] The present application relates in particular to a method of associating, with visual content, a visual element to be displayed superimposed on said visual content, said association method comprising: - obtaining metadata associated with said visual content, said metadata comprising descriptors of the zones of a plurality of zones segmenting said visual content, said descriptors of a zone comprising an acceptability parameter of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one semantic element on said zone; - a selection of at least one zone of said plurality of zones to receive the visual element according to said acceptability parameters of said descriptors of the plurality of zones;

[0020] - an association with said visual element of said at least one selected zone. In an alternative embodiment, taken in isolation or in combination, the selection takes into account a spatial occupation of the visual element and / or a color of said visual element.

[0021] Another subject of the invention relates to a data flow between a first electronic device and a second electronic device, said at least one data flow comprising visual content segmented into a plurality of zones, metadata associated with said visual content, said metadata comprising descriptors of zones of the plurality of zones, the descriptors of a zone comprising an acceptability parameter of said zone to receive a visual element.

[0022] Said data stream may in particular be adapted for the display of visual content on said second electronic device.

[0023] The present application relates in particular to a data flow between a first electronic device and a second electronic device, said at least one data flow comprising: - visual content segmented into a plurality of zones; - metadata associated with said visual content, said metadata comprising descriptors of zones of the plurality of zones, the descriptors of a zone comprising an acceptability parameter of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one semantic element on said zone.

[0024] In an alternative embodiment, taken in isolation or in combination, said at least one data stream comprises a first visual element in association and a designation of at least a first of said areas of said visual content for receiving said first visual element, said first area taking into account said acceptability parameters of said descriptors of the plurality of areas.

[0025] Another subject of the invention relates to a method of displaying visual content, said display method comprising obtaining a stream, said stream comprising visual content segmented into a plurality of zones, metadata associated with said visual content, said metadata comprising descriptors of zones of the plurality of zones, the descriptors of a zone comprising a acceptability parameter of said area to receive a visual element, an identification of an area suitable for receiving a first visual element among said plurality of areas, a display of the visual content on a display device of an electronic device, said displayed visual content comprising the first visual element positioned on the identified area. In an alternative embodiment, taken alone or in combination, the display method comprises a reception of said first visual element and a designation of at least a first of said areas of said visual content, said first area taking into account said acceptability parameters of said descriptors of the plurality of areas, the identification taking into account said designated first area.

[0026] In an alternative embodiment, taken in isolation or in combination, the method comprises a graphic adaptation of the visual content according to characteristics of said display device of said electronic device, the identification comprising, when said metadata comprises descriptors of at least two zones whose acceptability parameters correspond to zones adapted to receive said first visual element, a selection of the zone in said at least two zones taking into account said graphic adaptation.

[0027] In an alternative embodiment, taken in isolation or in combination, prior to the display of the visual content, the visual element is adapted to the identified area.

[0028] The present application relates in particular to a method for displaying visual content, said display method comprising: - obtaining a flow, said flow comprising: • visual content segmented into a plurality of zones; • metadata associated with said visual content, said metadata comprising descriptors of zones of the plurality of zones, the descriptors of a zone comprising an acceptability parameter of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one semantic element on said zone; - a display of the visual content on a display device of an electronic device, said displayed visual content comprising a first visual element, said first visual element being positioned on an area of ​​said plurality of areas identified taking into account the acceptability parameters of said plurality of areas.

[0029] In an alternative embodiment, taken alone or in combination, the display method comprises receiving said first visual element and a designation of said first zone.

[0030] In an alternative embodiment, taken in isolation or in combination, the display method comprises a graphic adaptation of the visual content according to characteristics of said display device of said electronic device, and, when said metadata comprises descriptors of at least two zones whose acceptability parameters correspond to zones adapted to receive said first visual element, a selection of said first zone from among said at least two zones taking into account said graphic adaptation.

[0031] In an alternative embodiment, taken alone or in combination, the display method comprises, prior to the display of the visual content, said first visual element is adapted to the identified area.

[0032] This application also relates to electronic devices implementing the processing, association and / or display methods described above.

[0033] In particular, the present application relates to an electronic device comprising at least one microprocessor suitable for processing visual content comprising: - a generation of metadata associated with said visual content, said generation comprising: • a segmentation of the visual content into a plurality of zones, said segmentation taking into account the semantic elements detected in said visual content; • a determination of descriptors of zones of the plurality of zones, the descriptors of a zone comprising an acceptability parameter of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one of said semantic elements detected on said zone; - an association with said visual content of the zone descriptors, as metadata of said visual content.

[0034] The present application also relates to an electronic device comprising at least one microprocessor adapted to: - obtaining metadata associated with visual content, said metadata comprising descriptors of the zones of a plurality of zones segmenting said visual content, said descriptors of an area comprising a parameter of acceptability of said area to receive a visual element; - a selection, as a function of said acceptability parameters of said descriptors of the plurality of zones, of at least one zone of said plurality of zones to receive a first visual element to be displayed superimposed on said visual content; - an association with said first visual element of said at least one selected zone.

[0035] The present application also relates to an electronic device comprising at least one microprocessor adapted to: - obtaining a flow, said flow comprising: • visual content segmented into a plurality of zones; • metadata associated with said visual content, said metadata comprising descriptors of zones of the plurality of zones, the descriptors of a zone comprising an acceptability parameter of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one semantic element on said zone; - a display of the visual content and a first visual element, associated with said visual content, on a display device of an electronic device, said first visual element being positioned on an area positioned superimposed on an area of ​​said plurality of areas identified taking into account the acceptability parameters of said plurality of areas.

[0036] Description of figures

[0037] Other characteristics and advantages of the invention will appear during the reading of the detailed description which follows for the understanding of which reference will be made to the appended drawings in which:

[0038] Figure 1 illustrates a data stream, according to at least some embodiments of the invention, exchanged between two electronic devices;

[0039] Figure 2 illustrates at least some embodiments of a method for processing visual content according to the invention;

[0040] Figure 3 illustrates at least some embodiments of the processing method of Figure 2 for visual content segmented into a foreground and a second plane disposed behind the foreground;

[0041] Figure 4 illustrates at least some embodiments of the display method of Figure 3 centered on a foreground of the visual content;

[0042] Figure 5 illustrates at least some embodiments of the display method of Figure 3 centered on a second plane of the visual content;

[0043] Figure 6 illustrates a segmentation of visual content obtained by the processing method of Figures 2 to 5;

[0044] Figure 7 illustrates at least some embodiments of a method for displaying visual content according to the invention;

[0045] Figure 8 illustrates the visual content visible on the user terminal of Figure 1 with a visual element displayed in a selected area;

[0046] Figure 9 illustrates, according to at least some embodiments of the invention, a transfer of data between three electronic devices;

[0047] Figure 10 illustrates a data transfer between three electronic devices, according to another embodiment of the invention.

[0048] Description of embodiments

[0049] Figure 1 illustrates the exchanges between a first electronic device, here a server 10 and a second electronic device, here a user terminal 20. The server 10 is adapted to provide at least one enriched multimedia stream FW following, for example, the reception of a content request Req coming from the user terminal 20. This user terminal 20 is adapted to display visual content Cont and a visual element from the stream FW.

[0050] More particularly, this at least one FW rich media stream includes: - multimedia data; - Meta metadata; - at least one visual Text element. This visual element can correspond to a text message written by a sender. - at least one List zone adapted to receive the Text visual element. Alternatively, this at least one List zone corresponds to at least one zone where the rendering of the visual element is prohibited.

[0051] Multimedia data Data is the data that can be directly used by the user terminal 20 to display the visual content Cont.

[0052] Meta metadata is data associated with multimedia data, this metadata comprising Desc descriptors of areas. Each area corresponds to a part of an image forming the visual content, each area constituting a visual unit. The Desc descriptor of an area comprises the characteristics of the area such as a shape, a size and / or a positioning in the visual content. The shape of the area is, for example, polygonal. Alternatively, the Desc descriptors of an area comprise data associated with a vector system. The area descriptors also comprise an acceptability parameter P of an area to receive a visual element.

[0053] The Text visual element is intended to appear on a portion of at least one image that comprises the visual content. It may include at least one character string, and / or a graphic element (for example, an emoticon or an actuator (such as a clickable button).

[0054] The at least one List zone represents the zone(s) of the image which can display the visual element Text, i.e. those whose descriptors have acceptability parameters P which allow a readable display of the visual element Text on these zones.

[0055] It will now be noted that the visual content Cont and the metadata that describes it can be transmitted in the same stream or in separate streams, for example in association with each other. In the same way, the visual element Text and the selected areas can be transmitted in separate streams, for example in association with each other. Depending on the embodiments, the visual element Text and the visual content Cont can be transmitted in separate streams or in the same stream (or associated streams).

[0056] The image areas are defined from a processing method illustrated in Figures 2 to 5.

[0057] This method of processing the visual content Cont illustrated, more particularly, in figure 2, comprises a step E1 of generating Meta metadata associated with the visual content Cont.

[0058] This E1 generation step may include: - a step E11 of segmenting the visual content into a plurality of zones Z; - a step E12 of determining descriptors Desc for each zone of the plurality of zones.

[0059] The processing method may also comprise a step E2 of selecting at least one zone of the plurality of zones capable of receiving the visual element Text. This selection step 2 is carried out from zone acceptability parameters P. These acceptability parameters P are determined during the step E12 of determining descriptors Desc. The selection step E2 is thus capable of constituting a list List of one or more zones suitable for receiving the visual element Text.

[0060] The processing method may finally comprise a step E3 of transmitting the stream to the user terminal 20, this stream containing the visual content Cont and the Meta metadata associated with said visual content.

[0061] The segmentation step E11 and the determination step E12 of step E1 of the processing method are more particularly detailed in Figure 3.

[0062] The segmentation step E11 includes a step E111 of decomposition of the content into layers by depth. Thus from the general visual content Cont, it is possible to obtain a foreground visual content Cont PP and background visual content Cont sp . The top visual content Cont PP and the background visual content Cont sp form the visual content Cont. From the foreground Cont PP , it is possible to determine foreground areas, in a step E112. In the same way, from the background Cont sp , it is possible to determine background areas, in a step E113.

[0063] These different foreground and background areas can, for example, be determined using image processing or video processing algorithm(s). These image processing or video processing operations can, for example, be based on computer vision analysis techniques, known as "Computer Vision", in particular OpenCV, Tesseract, Google Cloud Vision or Amazon Rekognition techniques.

[0064] In some embodiments, the foreground visual content Cont PP and / or background visual content Cont sp may be subject to pre-treatments. These pre-treatments may include, but are not limited to, at least one of the following operations: - a conversion of color spaces; - binary coloring; - a standardization or maximization of color, brightness or contrast thresholds; - a combination of at least two of the above operations.

[0065] The performance of E11 segmentation may vary depending on the implementation. For example, the segmentation step may be performed by the Grabcut function in the case where the visual content Cont is an image. In the case where the visual content is a video, the layered segmentation may be performed by the BackgroundSubtractorMOG function.

[0066] Figure 4 illustrates more specifically the segmentation of foreground visual content Cont PP . In the illustrated example, this segmentation can use in step E1121 a face detection function and a surface detection function. The face detection can for example rely on Haar cascade classifications from predefined models. The surface detection can for example be based (at least mainly) on the colorimetric simplification of K-Means Clustering.

[0067] Figure 5 illustrates more specifically the segmentation of background visual content Cont sp This segmentation can for example use a surface detection function in step E1131.

[0068] Note that other functions for segmentation can be used, such as a texture detection function or a text detection function. Texture detection can, for example, rely on clustering methods using Local Binary Patterns. Text detection can, for example, rely on the TextDetectionModel classes of the Deep Neural Network brick of OpenCV.

[0069] Figure 6 illustrates an example of segmentation carried out from the visual content Cont. The visual content Cont is thus segmented into a first zone Z1, a second zone Z2, a third zone Z3, a fourth zone Z4, a fifth zone Z5 and a sixth zone Z6.

[0070] The first zone Z1 belongs to the foreground of the visual content Cont. This zone Z1 has a generally circular shape. This zone Z1 is centered on the head of an animal, here a dog.

[0071] The second zone Z2 belongs to the foreground of the visual content Cont. This zone Z2 has a rectangular shape. This zone Z2 is centered on the animal's body.

[0072] The third zone Z3 belongs to the foreground of the visual content Cont. This third zone Z3 has a triangular shape. This zone Z3 is centered on a part of a vehicle, here a door handle.

[0073] The fourth zone Z4 belongs to the second plane of the visual content Cont. This fourth zone Z4 has a parallelepiped shape. This zone Z4 is centered on a part of the road.

[0074] The fifth zone Z5 belongs to the second plane of the visual content Cont. This fifth zone Z5 has a generally trapezoidal shape. This zone Z5 is centered on a roadside.

[0075] The sixth zone Z6 belongs to the second plane of the visual content Cont. This sixth zone Z6 has a generally rectangular shape. This zone Z6 is centered on the sky.

[0076] Other area shapes may be considered, for example area shapes compatible with at least one image description standard (such as a shape described using at least one "Image region" type metadata from the IPTC (International Press Telecommunications Council) Photo Metadata Standard.

[0077] In the same way that the segmentation operation can be dissociated between the foreground and the background, the step E12 of determining descriptors can be divided into a step E121 of determining foreground descriptors and a step E122 of determining background descriptors, as can be seen in Figure 3. Alternatively, this determination step E12 may not take into account the depth of the image.

[0078] In Figure 4, this step E121 comprises a step E1211 of determining acceptability parameters of the foreground zones Z1-Z3. Thus, in the exemplary embodiment of Figure 6, it is defined that the first zone Z1 centered on the dog's head cannot receive a visual element. For example, if a text were placed in this zone Z1, it would blur the animal's head, which would add confusion to the overall understanding of the visual content Cont. The accessibility parameter of zone Z1 would take the value 0. In the same way, the third zone Z3 is not suitable for receiving a visual element. This zone Z3 is, in fact, too small. The accessibility parameter of zone Z3 would take the value 0. The second zone Z2 is larger. It could receive a visual element, particularly in its lower part. The accessibility parameter of zone Z2 would take the value 1.These accessibility parameter values ​​are associated with the foreground areas in step E1212. It is then possible to create a first list Listl of foreground areas that can receive a visual element. This first list Listl. would group together the zones whose accessibility parameter is equal to 1, i.e. here the second zone Z2.

[0079] The value of the accessibility parameter of an area depends on the size of the area, the themes of the area or the colors of the area and can for example be a numerical value varying between 0 and 1.

[0080] Step E1212 of Figure 4 allows the extraction of complementary parameters from zones Z1 to Z3 such as luminance, dominant color, etc.

[0081] In the same way, in Figure 5, step E122 comprises a step E1221 for determining acceptability parameters of the background zones Z4-Z5. Thus, in the exemplary embodiment of Figure 6, it is defined that the fourth zone Z4 centered on the road cannot receive a visual element. This zone Z4 is, in fact, too small. The accessibility parameter of the zone Z4 would take the value 0. The fifth zone Z5 covering the roadway is larger. It could receive a visual element. The accessibility parameter of this zone Z5 would take the value 1. In the same way, the sixth zone Z6 covering the sky could receive a visual element. The accessibility parameter of the zone Z6 would also take the value 1. It is then possible to constitute a second list List2 of background zones that can receive a visual element.This second list Listl would group together the zones whose accessibility parameter is equal to 1, i.e. here the fifth zone Z5 and the sixth zone Z6.

[0082] Step E1222 of Figure 5 allows the extraction of complementary parameters from zones Z4 to Z6 such as luminance, dominant color, etc.

[0083] As can be seen in Figure 3, all the zone descriptions are aggregated in an aggregation step E123. This step also makes it possible to constitute the list of zones List suitable for receiving a visual element. This list List is a combination of the first list List1 and the second list List2.

[0084] The various descriptors of zones Z1-26 are then formatted in the metadata in step E124. In a step E125, the metadata is added to the multimedia data Data, to the visual element Text, to the list of zones List in order to constitute the FW stream. It should be noted that depending on the embodiments, the metadata may be structured according to a proprietary format or according to a market standard, for example the IPTC Photo Metadata Standard. In particular, the added Meta metadata may for example be integrated into a data field or structure left free from a standard, or in a dedicated, mandatory or optional field of a standard. For example, in some embodiments, zone descriptors may be prefixed with a particular prefix (or "namespace"), such as a proprietary prefix. Thus, in the example below the following prefix "OrangeXmpExt" is used for zone descriptors OrangeXmpExt:RegionColor [Region color] <external>definition of color information associated with an ImageRegion (IPTC standard) OrangeXmpExt: rcColor [Text<>] table of the main dominant colors in [A]RGB format "# [AA]RRGGBB" OrangeXmpExt: rcLum [Real<>] average luminance of the region Example of additional metadata: OrangeXmpExt:RegionColor[1] / OrangeXmpExt:rcColor[1]= #ffeee7e5 OrangeXmpExt:RegionColor[1] / OrangeXmpExt:rcColor[2]= #ff98a27f OrangeXmpExt:RegionColor[1] / OrangeXmpExt:rcColor[3]= #ff637971 OrangeXmpExt: RegionColor[1] / OrangeXmpExt:rcLum[3]= 0.809861

[0085] Figure 7 illustrates a method of displaying visual content Cont on the receiving terminal 20.

[0086] This method comprises a step E'1 of receiving the enriched multimedia stream FW. As already specified, the stream FW comprises in particular, in the illustrated example, the visual element as well as the list List of zones suitable for receiving the visual element. This list List here comprises the second zone Z2, the fifth zone Z5 and the sixth zone Z6.

[0087] In a step E'3, an area is selected from the list List. This selected area may be an area recommended by the server 10. Alternatively, the user terminal 20 may modify the recommended area. This is particularly the case if there is a step E'2 of graphic adaptation of the visual content Cont according to characteristics of the receiving terminal 20. Indeed, this graphic adaptation may reduce certain areas of the visual content Cont which no longer allow certain visual elements to be received.

[0088] In step E'4, the visual element is adapted to the selected area. This adaptation may be an adaptation of size, font or color.

[0089] In a step E'5, the visual content cont is displayed with the visual element positioned on the selected area.

[0090] Such a display is illustrated in particular in Figure 8. In this Figure 8, the visual element is the word: "HELLO". It is displayed in white and bold, in the fifth zone Z5 of the visual content Cont.

[0091] The invention also relates to a method for associating, with the visual content Cont, the visual element Text to be displayed superimposed on said visual content. This association method comprises obtaining the Meta metadata associated with the visual content Cont. This obtaining may correspond to a generation of the Meta metadata as described above. Alternatively, it may be metadata already generated and stored, for example in association with the visual content, and obtaining the Meta metadata may correspond to reading this data from a storage space.

[0092] As already specified, the Meta metadata includes the Desc descriptors of the zones of the plurality of zones Z1 -Z6 segmenting said visual content Cont. These Desc descriptors include the parameter P of acceptability of said zone concerned to receive a visual element (any).

[0093] The association method also comprises the selection E2 of at least one zone Z2, Z5, Z6 of said plurality of zones Z1 -Z6 to receive the visual element (Text) considered (for example received from the terminal) as a function of the acceptability parameters P of the descriptors of the plurality of zones.

[0094] The method thus allows an association with said visual element of said at least one selected zone.

[0095] In an alternative embodiment, the selection E2 takes into account a spatial occupation (in terms of pixels for example) of the visual element Text and / or a color of said visual element Text.

[0096] It will be noted that the association method is for example implemented in the server 10 of FIG. 1. It may for example be a method executed by an online application accessible to a terminal of a user wishing to attach (in superposition) a visual element to existing visual content. In such embodiments, the method may comprise a reception of the visual element to be associated (for example in the request Req sent by the user terminal) described in connection with FIG. 1.

[0097] It should be noted that alternatively, the terminal wishing to attach the visual element to the visual content may be different from the terminal on which the visual content and the associated visual element are intended to be displayed.

[0098] In some embodiments, the association method may be implemented in an electronic terminal (for example, the terminal of a user wishing to attach (overlay) a visual element to existing visual content). In such embodiments, the method may comprise receiving the visual content and its metadata (including the area descriptors described above) prior to associating the visual content and the visual element and possibly transmitting, after association, the visual content and the visual element to another terminal for display.

[0099] In some embodiments, the area descriptors of a visual content may be generated prior to and independent of any association with a visual element and integrated into the metadata of the visual content. This generation of metadata may occur during the creation of the visual content and / or at a later time, for example when it is added to an image bank. The generated metadata may be stored in association with the visual content for later use.

[0100] In the example illustrated in Figure 10, the generation can for example be carried out on a first electronic device, the storage being (for simplicity of the example) also implemented on this first device. The method of associating a visual element with visual content stored on the first device can be implemented on a second electronic device 10' for example at the initiative of the second electronic device or on request for example from a third-party device) and include a reception of the visual content and its metadata (including the zone descriptors) prior to the association. The visual content and the visual element once associated via their metadata as described above can be transmitted to a terminal 20 for rendering of the visual content and the visual element in superposition as described above.

[0101] Figure 9 illustrates an alternative embodiment in which at least three electronic devices 10, 10', 20 are used for the exchange of flows.

[0102] In this embodiment, the user terminal 20 sends its request Req to an intermediate electronic device 10'. This intermediate device 10' is adapted to query the server 10 via an adapted request Req'. In return, the server 10 provides data such as the visual content Data, the metadata Meta. As already specified, this metadata Meta includes the acceptability parameters P, the visual element Text, and the areas suitable for receiving the visual element.

[0103] The 10' intermediate electronic equipment transmits the various data (Data, Meta) in the form of one or more streams to the user terminal 20.< / external>

Claims

CLAIMS 1. Method for processing visual content (Cont), said processing method comprising: - a generation (E1) of metadata (Meta) associated with said visual content (Cont), said generation comprising: • a segmentation (E11) of the visual content (Cont) into a plurality of zones (Z1-Z6), said segmentation taking into account the semantic elements detected in said visual content; • a determination (E12) of descriptors (Desc) of zones of the plurality of zones (Z1 -Z6), the descriptors (Desc) of a zone comprising a parameter (P) of acceptability of said zone to receive a visual element (Text), said acceptability parameter taking into account the presence or absence of at least one of said semantic elements detected on said zone; - an association with said visual content of the zone descriptors (Desc), as metadata (Meta) of said visual content.

2. Processing method according to claim 1, in which the segmentation (E11) comprises a decomposition into layers by depth of the visual content (Cont).

3. Processing method according to any one of claims 1 or 2, in which an area comprises a majority of pixels of the same color and / or the same texture and / or corresponds to a visual rendering of a specific part of an individual.

4. Processing method according to any one of claims 1 to 3, in which the visual content (Cont) being a video, the segmentation (E2) of the visual content (Cont) into a plurality of zones is carried out over the entire video.

5. Processing method according to any one of claims 1 to 4, in which the visual content (Cont) being a video, the segmentation (E2) of the visual content into a plurality of zones is carried out by video sequences cutting said video.

6. Processing method according to any one of claims 1 to 5, in which the zones (Z1-26) obtained by segmentation have different depths.

7. Treatment method according to claim 1 according to any one of claims 1 to 6, wherein said parameter of acceptability of an area takes into account of semantic importance of at least one of said detected semantic elements present in said area; 8. Method of associating, with visual content, a visual element (Text) to be displayed superimposed on said visual content, said association method comprising: - obtaining metadata (Meta) associated with said visual content (Cont), said metadata comprising descriptors (Desc) of the zones of a plurality of zones (Z1-Z6) segmenting said visual content (Cont), said descriptors (Desc) of a zone comprising a parameter (P) of acceptability of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one semantic element on said zone; - a selection (E2) of at least one zone (Z2, Z5, Z6) of said plurality of zones (Z1-Z6) to receive the visual element (Text) according to said acceptability parameters (P) of said descriptors of the plurality of zones; - an association with said visual element of said at least one selected zone.

9. Association method according to claim 8, in which the selection (E2) takes into account a spatial occupation of the visual element (Text) and / or a color of said visual element (Text).

10. Data flow between a first electronic device (10) and a second electronic device (20), said at least one data flow (FW) comprising: - visual content (Cont) segmented into a plurality of zones (Z1 -Z6); - metadata (Meta) associated with said visual content (Cont), said metadata comprising descriptors (Desc) of zones of the plurality of zones (Z1-Z6), the descriptors (Desc) of a zone comprising a parameter (P) of acceptability of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one semantic element on said zone.

11. Data stream according to claim 10, wherein said at least one data stream comprises a first visual element and a designation of at least a first of said areas of said visual content for receiving said first visual element (Text), said first area taking into account said acceptability parameters (P) of said descriptors of the plurality of areas.

12. Method for displaying visual content (Cont), said display method comprising: - obtaining (E'1) a flow (FW), said flow comprising: • visual content (Cont) segmented into a plurality of zones (Z1-Z6); • metadata (Meta) associated with said visual content (Cont), said metadata comprising descriptors (Desc) of zones of the plurality of zones (Z1-Z6), the descriptors (Desc) of a zone comprising a parameter (P) of acceptability of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one semantic element on said zone; - a (E'5) display of the visual content (Cont) on a display device of an electronic device (20), said displayed visual content (Cont) comprising a first visual element (Text), said first visual element being positioned on an area of ​​said plurality of areas identified taking into account the acceptability parameters of said plurality of areas.

13. Method for displaying visual content (Cont) according to claim 12, said display method comprising: - a reception of said first visual element (Text) and a designation of said first zone.

14. Display method according to any one of claims 12 or 13, wherein the method comprises a (E'2) graphic adaptation of the visual content (Cont) according to characteristics of said display device of said electronic device (20), and, when said metadata comprise descriptors of at least two zones whose acceptability parameters correspond to zones adapted (Z2, Z5, Z6) to receive said first visual element (Text), a selection (E'3) of said first zone from among said at least two zones taking into account said graphic adaptation.

15. Display method according to any one of claims 12 to 14, in which prior to the display (E'5) of the visual content (Cont), said first visual element is adapted (E'4) to the identified zone.

16. Electronic device comprising at least one microprocessor suitable for processing visual content (Cont) comprising: - a generation (E1) of metadata (Meta) associated with said visual content (Cont), said generation comprising: • a segmentation (E11) of the visual content (Cont) into a plurality of zones (Z1-Z6), said segmentation taking into account the semantic elements detected in said visual content; • a determination (E12) of descriptors (Desc) of zones of the plurality of zones (Z1 -Z6), the descriptors (Desc) of a zone comprising a parameter (P) of acceptability of said zone to receive a visual element (Text), said acceptability parameter taking into account the presence or absence of at least one of said semantic elements detected on said zone; - an association with said visual content of the zone descriptors (Desc), as metadata (Meta) of said visual content.

17. Electronic device comprising at least one microprocessor adapted to: - obtaining metadata (Meta) associated with visual content (Cont), said metadata comprising descriptors (Desc) of the zones of a plurality of zones (Z1-Z6) segmenting said visual content (Cont), said descriptors (Desc) of a zone comprising a parameter (P) of acceptability of said zone to receive a visual element; - a selection (E2), as a function of said acceptability parameters (P) of said descriptors of the plurality of zones, of at least one zone (Z2, Z5, Z6) of said plurality of zones (Z1-Z6) to receive a first visual element (Text) to be displayed superimposed on said visual content; - an association with said first visual element of said at least one selected zone.

18. Electronic device comprising at least one microprocessor adapted to display, on a display device of said electronic device, visual content (Cont), said display method comprising: - obtaining (E'1) a flow (FW), said flow comprising: • visual content (Cont) segmented into a plurality of zones (Z1 -Z6); • metadata (Meta) associated with said visual content (Cont), said metadata comprising descriptors (Desc) of zones of the plurality of zones (Z1-Z6), the descriptors (Desc) of a zone comprising a parameter (P) of acceptability of said zone to receive a visual element, said acceptability parameter taking into account the presence or absence of at least one semantic element in said area; - a (E'5) display of the visual content (Cont) and of a first visual element, associated with said visual content, on a display device of an electronic device (20), said first visual element (Text) being positioned on an area positioned superimposed on an area of ​​said plurality of areas identified taking into account the acceptability parameters of said plurality of areas.

Images