Method and computer system for user interaction with a video

Abstract

Title: Method and Computer System for User Interaction with a Video. The invention relates to a method (10) enabling at least one user to interact with at least one multimedia content including a video. The method (10) is configured to track the entity present in the video and generates (104) an interactivity mask that is superimposed on the video. The tracker follows the entity in real time and its position is calculated (105) in the interactivity mask, including spatial and temporal coordinates. The position of the tracker is recorded (108) at each instant in the video when the entity is visible. A function can be assigned (109) to the tracker and activated (201) by the user via an interface. Figure for the abstract: Fig. 4.

Description

Title of the invention: Method and computer system for user interaction with a video technical field

[0001] The present invention relates to the technical field of web development applied to video, particularly in the context of e-commerce and information. STATE OF THE ART

[0002] Numerous solutions exist in the field of interactive video. For example, Amazon Prime X-ray®, MindStamp®, and Vimeo® already allow a certain form of interactivity in videos by offering clickable elements that are either fixed or appear at a specific time in the video. However, these solutions do not allow users to track objects present in the video or provide relevant contextual information.

[0003] Current solutions therefore lack the ability to track objects present in the video and to provide relevant contextual information. Users are thus limited in their ability to interact with video content.

[0004] The present invention therefore aims to overcome, at least in part, the aforementioned disadvantages of these prior art solutions.

[0005] The other objects, features and advantages of the present invention will become apparent from an examination of the following description and accompanying drawings. It is understood that other advantages may be incorporated. SUMMARY

[0006] To achieve this objective, according to one embodiment, an interaction method is provided between at least one user and at least one multimedia content comprising a video, which video presents visual representations of entities. This method is configured to be executed by at least one computer interaction system.

[0007] According to one embodiment, the present invention relates to a method which comprises two main phases: a monitoring phase and an interaction phase.

[0008] The tracking phase includes, or even consists of, selecting, by a selection module, at least one entity present in the video. Then, a determination module determines the matrix position of the entity in the video according to a predetermined list of times T when the entity is visible. Preferably, this predetermined list of times T is a subset of each time T when the entity is visible in the video. A tracking module then assigns a tracer to the entity, which The tracking module monitors the matrix position of the entity in real time at every instant T when the entity is visible in the video. It also generates an interactive mask that overlays the video and includes the tracker. The tracker's position within the interactive mask is calculated at every instant T, using at least three coordinates (X, Y, and T). The X and Y coordinates correspond to a first and second spatial coordinate, respectively, while the T coordinate corresponds to a temporal coordinate. The tracker's position is recorded at every instant T when the entity is visible in the video. Finally, the tracking module defines the tracker's X and Y coordinates as percentages of the video's width and height, respectively.

[0009] The interaction phase includes the selection of said tracer by a user using an interface, and then the activation of at least one functionality of said tracer by the user using said interface.

[0010] According to one embodiment, the present invention thus relates to a method of interaction of at least one user with at least one multimedia content comprising at least one video, said video comprising at least one visual representation of at least one entity, said method being configured to be executed by at least one computer interaction system, said method comprising: a. a follow-up phase including: i. select, by at least one selection module, at least said entity, said entity being present in at least a plurality of images of said video; ii. determine, by at least one determination module, the matrix position of said entity in the video according to a predetermined list of instants T of the video where said entity is visible in said video; iii. assign, by at least one tracking module, at least one tracker to said entity, said tracker being configured to track, preferably in real time, the matrix position of said entity at each instant T of the video where said entity is visible in said video; iv. generate, by said tracking module, at least one interactivity mask, said interactivity mask being configured to overlay said video, said interactivity mask including said tracker; v. calculate, by said tracking module, the position of said tracker in said interactivity mask at each instant T of the video, said position comprising at least three coordinates (X, Y and T), the first coordinate X corresponding to a first coordinate spatial, the second Y coordinate corresponding to a second spatial coordinate, and the third T coordinate corresponding to a temporal coordinate; vi. define, by said tracking module, the first X coordinate of said plotter as a percentage of the width of said video; vii. define, by said tracking module, the second Y coordinate of said plotter as a percentage of the height of said video; viii. record, by said tracking module, the position of said tracker at each instant T of the video where said entity is visible in said video; ix. assign, by said tracking module, at least one functionality to said tracker; x. to follow, by said tracking module, said entity by said tracker at each instant T of the video; b. an interaction phase comprising at least: i. select said plotter by at least one user using at least one interface; ii. activate at least one feature of said tracker by said user using at least said interface.

[0011] Advantageously, this interactivity mask includes the tracker and allows for the creation of a more intuitive and immersive user interface. The tracker's ability to follow the entity's matrix position in real time ensures more precise and efficient interaction by adapting the position and size of the interactivity mask to the entity's movement.

[0012] Furthermore, the technical advantages of this interaction method are numerous. The automatic selection and tracking of an entity within a video simplifies the interaction process for the user, eliminating the need to manually search for visual elements within the video. The dynamic generation of an interactivity mask that overlays the video creates a more intuitive and immersive user interface, allowing users to select and interact directly with the video's visual elements.

[0013] The present invention also relates to a computer program product intended to execute complex processes. According to one embodiment, this program product is designed to be stored on a non-transient memory medium, such as hard drives or memory cards.

[0014] According to this design, the program product includes instructions that are intended to be executed by at least one of a processor and a computer. When carried out, these instructions allow the execution of a process according to the specifications defined in the present invention.

[0015] In particular, this program product is designed to execute processes that involve the use of computer resources such as RAM, processors, and input / output devices. The instructions of the program product are therefore designed to be interpreted by a computer or processor, which executes the process accordingly.

[0016] In this sense, the program product is a powerful tool designed to automate complex tasks and provide accurate and rapid results.

[0017] Thus, the present invention also relates to a computer program product, preferably stored on a non-transient memory medium, comprising instructions which, when executed by at least one of a processor and a computer, executes the process according to the present invention.

[0018] One of the possible features of this product is its ability to be saved on non-transient storage media, such as hard drives or memory cards. This allows for greater flexibility and ease of use, as the program can be easily copied, moved, and stored. Furthermore, the presence of instructions within the program ensures high precision and speed of execution, as the steps to be followed are clearly defined and can be executed without error.

[0019] The present invention relates to a non-transient memory medium for storing information permanently and reliably. This medium is designed to meet the specific needs of a computer program product, which requires a large storage capacity and high reliability.

[0020] According to one embodiment, the non-transient memory carrier comprises at least one computer program product. This product is designed to be executed by a computer and requires a certain amount of storage space to function correctly. The non-transient memory carrier is designed to store this computer program product permanently, for example, without the possibility of modification or editing.

[0021] The non-transient memory medium is characterized by its ability to store information in a durable and environmentally resistant manner. It is designed for use in a wide range of applications, particularly in the fields of computing, the present invention, and science.

[0022] Thus, the present invention also relates to a non-transient memory support comprising at least one computer program product according to the present invention.

[0023] According to one embodiment, the present invention relates to a non-transient memory medium for storing and managing programmed computer products. This Memory support is designed to offer large storage capacity and high speed of access to stored information.

[0024] The invention relates to a computer interaction system allowing at least one user to interact with at least one multimedia content, including in particular a video. This video contains visual representations of entities, which are tracked by the computer system.

[0025] According to one embodiment, the present invention relates to a computer interaction system comprising four main components: a selection module, a determination module, a tracking module, and an interface. The selection module is configured to choose at least one entity present in several frames of the video. Preferably, the determination module determines the matrix position of the entity in the video according to a predetermined list of time points T, called key moments or key instants. According to another embodiment, the determination module determines the matrix position of the entity in the video at each time point T when the entity is visible.

[0026] The tracking module assigns a tracker to the entity, which tracks the entity's matrix position in real time at each instant T when the entity is visible. The interactivity mask generated by the tracking module is overlaid on the video and contains the tracker. The tracker's position in the interactivity mask is calculated at each instant T, comprising at least three coordinates (X, Y, and T). The X and Y coordinates correspond respectively to a first and second spatial coordinate, while the T coordinate corresponds to a temporal coordinate.

[0027] The tracking module also defines the X and Y coordinates of the tracker as a percentage of the video's width and height, respectively. The tracker's position is determined at each instant T when the entity is visible, and a function is assigned to the tracker. The user can select the tracker and activate an associated function through the interface.

[0028] Thus, the present invention also relates to a computer system for interaction between at least one user and at least one multimedia content comprising at least one video, said video comprising at least one visual representation of at least one entity, said computer system comprising at least: a. a selection module, said selection module being configured to select at least said entity, said entity being present in at least a plurality of images of said video; b. a determination module, said determination module being configured to determine the matrix position of said entity in the video according to a predetermined list of times T in the video where said entity is visible in said video; Preferably, this predetermined list of T-times is a subset of each T-time where the entity is visible in the video; c. a tracking module, said tracking module being configured to: i. assign at least one tracker to said entity, said tracker being configured to track, preferably in real time, the matrix position of said entity at each instant T of the video where said entity is visible in said video; ii. generate at least one interactivity mask, said interactivity mask being configured to overlay said video, said interactivity mask including said tracker; iii. calculate the position of said tracer in said interactivity mask at each instant T of the video, said position comprising at least three coordinates (X, Y and T), the first coordinate X corresponding to a first spatial coordinate, the second coordinate Y corresponding to a second spatial coordinate, and the third coordinate T corresponding to a temporal coordinate; iv. define the first X coordinate of said plotter as a percentage of the width of said video; v. define the second Y coordinate of said plotter as a percentage of the height of said video; vi. record the position of said tracer at each instant T of the video where said entity is visible in said video; vii. assign at least one functionality to said tracer; viii. to track said entity by said tracker at each instant T of the video; d. an interface, said interface being configured to allow: i. the selection of said plotter by at least one user using at least said interface; ii. the activation of at least one feature of said tracker by said user using at least said interface.

[0029] Thus, according to the present invention, the computer system can comprise several modules.

[0030] The first module is responsible for selecting the entity to be tracked in the video. This module is configured to identify and select at least one entity present in a plurality of video frames. Once the entity is selected, the computer system can determine its matrix position in the video in real time.

[0031] The second module is responsible for tracking the entity through the video. This module assigns a tracker to the entity and tracks its matrix position at each instant T in the video where the entity is visible. The tracker is configured to overlay the video, thus creating an interactivity mask that allows the user to follow the entity through the video.

[0032] The computer system can also calculate the position of the plotter within the interactive mask in real time, enabling more precise interaction with the entity. Furthermore, the computer system can define the spatial and temporal coordinates of the entity, allowing for a better understanding of its behavior in the video.

[0033] Finally, the computer system includes an interface that allows the user to select the plotter and activate features related to the entity. This interface can be used to activate features such as pausing or replaying the video, as well as to interact with the entity more extensively.

[0034] Thanks to these modules and functionalities, the computer system allows for a more immersive and precise interaction with multimedia content, which can improve the user experience and offer new opportunities for users. BRIEF DESCRIPTION OF THE FIGURES

[0035] The aims, objects, features and advantages of the invention will become clearer from the detailed description of an embodiment thereof, which is illustrated by the following accompanying drawings in which:

[0036] [Fig.1] Fig.1 illustrates steps of the process according to an embodiment of the present invention.

[0037] [Fig.2] Figure [Fig.2] illustrates a computer system according to one embodiment of the present invention.

[0038] [Fig.3] Fig.3 illustrates a video comprising entities according to a mode of realization of the present invention.

[0039] [Fig.4] [Fig.4] illustrates a plotter for each entity of [Fig.3] according to a mode of the realization of the present invention.

[0040] [Fig. 5] Figure 5 illustrates a functionality of a first plotter according to a mode of realization of the present invention.

[0041] [Fig.6] Figure [Fig.6] illustrates a functionality of a second plotter according to a mode of realization of the present invention.

[0042] [Fig.7] Fig.7 illustrates a functionality of a third plotter according to a mode of realization of the present invention.

[0043] The drawings are given by way of example and are not limiting of the invention. They constitute schematic representations of principle intended to facilitate understanding of the invention and are not necessarily to scale with practical applications. In particular, the dimensions are not representative of reality. DETAILED DESCRIPTION

[0044] Before proceeding with a detailed review of embodiments of the invention, optional features that may be used in combination or alternatively are listed below:

[0045] According to one example, the plotter is generated dynamically, preferably based on the position and / or size of the entity.

[0046] This allows the plotter to be adapted to various conditions and to provide a more accurate representation of the position and / or size of the entity.

[0047] This dynamic generation allows for more precise tracking, as it takes into account the entity's movement and any changes in its shape or size. This is particularly important when dealing with entities subject to significant variations in their physical characteristics, such as objects undergoing deformation or transformation.

[0048] Furthermore, this technical advantage allows the tracker to be more responsive to changes in the environment, enabling more effective monitoring of the entity's movements and behavior. This responsiveness is essential in applications where the entity's position and size must be monitored accurately in real time, such as in computer monitoring systems, for example, but not limited to these applications.

[0049] Furthermore, the dynamic generation of the plotter allows for more efficient use of computing resources, as it can adjust its processing power to meet the changing requirements of the tracking task. This efficiency is particularly important in applications where processing power is limited, such as in embedded computer systems or mobile devices.

[0050] Overall, the technical advantage of generating the plotter dynamically provides a more accurate, responsive and efficient way of tracking entities, making it an essential feature for many applications.

[0051] According to one example, the interactivity mask is generated dynamically, preferably based on the dimensions of the video and / or the entity.

[0052] The technical advantage of dynamically generating the interactivity mask lies in its ability to adapt to the specific characteristics of the video and / or the entity being processed. This allows for more precise and efficient interaction with the user, as the mask is tailored to the unique characteristics of the content.

[0053] For example, when processing a video of varying dimensions, the dynamic generation of the mask allows it to adjust its shape and size accordingly, ensuring that interactive elements are correctly aligned and easily accessible. This results in a more intuitive and engaging user experience, as the user can interact seamlessly with the video without being distracted by irrelevant or misplaced information.

[0054] Furthermore, the dynamic generation of the mask also allows for real-time adjustments based on changes in the video content or user behavior. This enables the computer system to react quickly and accurately to changing circumstances, providing a more responsive and interactive overall experience.

[0055] Furthermore, the ability to dynamically generate the mask in response to the dimensions of the video and / or the entity eliminates the need for manual configuration or adjustment, thereby reducing the complexity and effort required to configure and operate the computer system. This allows users to focus more easily on their goals and objectives, rather than getting bogged down in technical details.

[0056] Overall, the dynamic generation of the interactivity mask offers a series of technical advantages that allow for more efficient and engaging interactions with digital content.

[0057] According to one example, the tracker is visible to the user, preferably at every instant T of the video.

[0058] The visibility of the tracker to the user at every moment T of the video provides several technical advantages.

[0059] One of these advantages is that it allows for real-time monitoring and tracking of the tracked object or subject. This enables more precise and continuous tracking, as the user can see the tracker's position and movement in real time. For example, but not limited to, in a surveillance application, this functionality would allow security personnel to react quickly to any changes in the location or behavior of the tracked person.

[0060] Furthermore, the tracker's visibility reduces the need for manual data entry or interpretation, which can be time-consuming and prone to errors. Since the tracker's position is visible at all times, the user can simply observe the tracker's movement and make decisions based on this information, without having to manually analyze the tracking data.

[0061] Overall, the visibility of the tracker provides users with a more intuitive and efficient way to track objects or subjects, enabling better decision-making, improved communication, and a reduction in errors.

[0062] According to one example, said functionality includes at least one of the following functionalities: opening an Internet page, adding an item to a basket; calling a telephone number, sending an email, displaying a name, displaying information related to said entity, etc.

[0063] The technical advantages of the present invention include the ability to seamlessly integrate various functionalities, allowing users to access and interact with a wide range of information and services.

[0064] For example, the procedure allows users to open a web page, add items to an online shopping cart, or make phone calls. This integration facilitates a more streamlined and efficient user experience, as users can perform multiple tasks without having to navigate through different interfaces or applications.

[0065] Furthermore, the present invention makes it possible to display relevant information relating to a specific entity, such as a person's name, contact details, or profile. This functionality allows users to quickly access the necessary information, thus reducing the time and effort required to find the desired data.

[0066] Furthermore, the present invention enables the sending of electronic messages, which facilitates communication between individuals and organizations. The ability to display different types of information relating to an entity also allows users to easily access and consult relevant data, such as press articles or product descriptions.

[0067] Overall, the technical advantages of the present invention offer a more complete and user-friendly experience, enabling individuals to access and interact effectively with a wide range of information and services.

[0068] According to one example, the present invention includes at least one information collection phase, said information collection phase including at least the recording in at least one database of a history of the interaction of said user with said tracker.

[0069] Data collection is an advantageous phase of the process, as it allows for the gathering of valuable data on the interaction between the user and the tracker(s), and therefore with the video. This phase makes it possible to detect recurring trends and user behaviors, which can be useful for improving the performance of the computer system or adjusting its parameters.

[0070] For example, by recording the history of the interaction between the user and the tracker in a database, it is possible to identify the times when the user tends to use the tracker more efficiently or less efficiently. This can enable computer system developers to put in place mechanisms to encourage efficient behaviors and reduce errors.

[0071] Furthermore, information gathering can also help detect anomalies in the use of the tracker, which can be important for ensuring data security and confidentiality. By understanding user habits, it is possible to implement more effective anomaly detection mechanisms, thereby reducing the risk of sensitive data being compromised.

[0072] Finally, data collection can also be used to personalize the use of the tracker according to each user's specific needs. By knowing the user's preferences and habits, it is possible to offer configuration options better suited to their needs, thus improving the overall user experience.

[0073] According to one example, said tracker is configured to track several entities.

[0074] Configuring the tracker to follow multiple entities allows for great flexibility in the use of the present invention. Thus, the method can be adapted to various fields of application, such as online commerce from a film, the monitoring of people or animals, etc.

[0075] For example, in the context of online sales, it is possible that the various garments of an outfit worn by a person in a film can be tracked via the same tracker, allowing the purchase of said outfit via an interaction with this single tracker.

[0076] For example, in a security context, it is possible to configure the tracker to follow several individuals simultaneously, which allows for more effective monitoring and better handling of crisis situations.

[0077] Ultimately, configuring the tracker to track multiple entities offers great flexibility and allows for improved efficiency in many areas of application.

[0078] According to one example, said entity is associated with several tracers.

[0079] The technical advantage of associating the entity with several tracers lies in its ability to provide a more precise and complete understanding of the entity's behavior and characteristics.

[0080] The use of multiple tracers allows for a more robust and reliable measurement of the entity's characteristics, such as its speed, direction, and position. Indeed, any error or bias introduced by a single tracer can be compensated for by combining data from multiple sources.

[0081] In addition, for example if the entity is a person, several tracers can be used in order to match one tracer to a piece of clothing, one tracer to a piece of jewelry and another tracer to the person himself, for example, without limitation.

[0082] Overall, the technical advantage of using multiple tracers lies in its ability to provide a more complete, accurate and reliable understanding of the entity's characteristics and behavior, which can have important implications for a wide range of applications.

[0083] According to one example, said tracker is configured to adapt to changes in position and / or size of the entity at each instant T of the video.

[0084] Configuring the tracker to adapt to changes in the entity's position and / or size at each instant T of the video allows for increased accuracy in tracking and interacting with entities. Thanks to this adaptation, the present invention can take into account complex movements and shape transformations of the entity, which is particularly useful for applications requiring high precision, such as video surveillance or online sales.

[0085] Thus, the tracker can accurately follow the entity even if it changes position or size over time, which makes it possible to detect and analyze movements and transformations more precisely.

[0086] In addition, this adaptation also makes it possible to reduce the interaction error and improve the reliability of the present invention.

[0087] Finally, this configuration also improves the robustness of the present invention against disturbances and background noise. Indeed, the plotter can adapt to changes in the entity even if there are disturbances or background noise in the video, thus maintaining high accuracy despite the difficulties.

[0088] According to one example, said entity is taken from at least: a person, an article, an object, a living being, animal or plant.

[0089] According to one example, the determination of the matrix position of said entity in the video according to a predetermined list of times T in the video where said entity is visible in said video is carried out via the use of artificial intelligence.

[0090] The use of artificial intelligence allows for very rapid determination of the matrix position, which is particularly useful when processing real-time video. The algorithm can be trained to take into account different contexts and variations in brightness, thus ensuring high accuracy even under difficult recording conditions.

[0091] Furthermore, determining the matrix position according to a predetermined list of time points T allows for a more precise analysis of the entity's movements in space. This is particularly useful for applications requiring precise and continuous monitoring or tracking, such as tracking people or objects.

[0092] Finally, the use of artificial intelligence also allows for great flexibility in determining the matrix position. The algorithm can be adapted to take into account different types of videos and different recording conditions, which guarantees high accuracy in all cases.

[0093] According to one example, the determination of the matrix position of said entity in the video according to a predetermined list of times T in the video where said entity is visible in said video is carried out manually by at least one operator.

[0094] According to one example, said interactivity mask is partially transparent.

[0095] The examples and conditional language mentioned herein are primarily intended to aid the reader in understanding the principles of the present invention and are not intended to limit its scope to the examples and conditions specifically mentioned. It is considered that persons skilled in the art could devise various arrangements which, although not explicitly described or illustrated herein, nevertheless incorporate the principles of the present invention and are included in its spirit and scope.

[0096] Furthermore, to facilitate understanding, the following description may describe relatively simplified implementations of the present invention. As those skilled in the art will understand, various implementations of the present invention may be of greater complexity.

[0097] In some cases, examples of modifications to the present invention may also be shown. These are merely to aid understanding and, again, do not define the scope or limitations of the present invention. These modifications do not constitute an exhaustive list, and a person skilled in the art may make other modifications while remaining within the scope of the present invention. Furthermore, the absence of any example of a modification should not be inferred that no modification is possible and / or that what is described is the only way to implement that element of the present invention.

[0098] Furthermore, all statements of principles, aspects, and implementations of the present invention, as well as their specific examples, are intended to encompass their structural and functional equivalents, whether currently known or developed in the future. Thus, for example, those skilled in the art will understand that the functional diagrams presented herein represent conceptual views of the present invention and its principles and features. Similarly, it will be appreciated that the flowcharts, diagrams, pseudocodes, and the like represent various processes that can be substantially represented on a computer-readable medium and thus executed by a computer or processor, whether or not that computer or processor is explicitly shown.

[0099] The width of the video refers to the dimension of the images in the video stream along a direction corresponding to the X coordinate, which can typically be represented on one, for example horizontally, of the two directions of a rectangular screen. The height of the video corresponds to the complementary dimension, along a direction corresponding to the Y coordinate, which can typically be a vertical direction of a rectangular screen.

[0100] Having established these fundamental principles, we will now examine some non-limiting examples to illustrate various implementations of certain aspects of the present invention.

[0101] According to one embodiment, the present invention relates to a method 10 and a computer system 20 for interacting with multimedia content comprising at least one video 30. The method 10 is advantageously configured to be executed by said computer system 20. Said computer system 20 comprises at least one tracking module 23 that tracks the position of objects or entities 40, 50, 60 in the video 30, as well as other modules described below. Preferably, the tracking module 23 uses spatiotemporal coordinates, which are defined by (X, Y, T) coordinates in the video 30, to track the movement of the entities over time. It should be noted that an entity 40, 50, 60 can represent a person 50, an object 60, an item of clothing, a vehicle 40, a tool, and more generally any element that may or may not be present in a video 30.The computer system 20 also includes an interface 24 which allows users to interact with the tracked objects or entities, preferably by clicking on them.

[0102] According to one embodiment, the present invention relates to a solution that marks and records the matrix position of one or more entities 40, 50, 60 (objects or individuals) present in a video 30. It advantageously uses tracers 71, 72, 73 visible in the video 30, which have a specific position at each time unit of the video 30. Advantageously, these tracers 71, 72, 73 are configured to be worn and to move within an interactivity mask 70. According to one embodiment, the coordinates of each tracer 71, 72, 73 are defined by positions expressed as percentages of the width X and height Y of the video 30, at a given time T, preferably from the beginning of the video 30. In addition to these spatiotemporal coordinates, a tracer 71, 72, 73 may include other properties 71a, 72a, 73b which allow the user to interact, such as: a. A trade name representative b.A URI (from the English "Uniform Resource Identifier"): Internet resource (URL (for "Universal Resource locator"), email, call-to-action, etc.). c. An illustration: representing the entity's media, for example d. A description e. Other properties specific to the type of product (price, color, SKU (for stock keeping unit), a unique identifier such as a barcode or QR code, a standard identification number, a bank identifier, etc.).

[0103] From a user perspective, and according to one embodiment, when the user pauses video 30, all visible trackers 71, 72, 73 become active (clickable): Preferably, when the user pauses video 30, the interactivity mask 70 to which all visible trackers 71, 72, 73 belong becomes active. These trackers 71, 72, 73 can be represented by a pictogram placed at a given location where the element 40, 50, 60 associated with tracker 71, 72, 73 is present in video 30. Advantageously, if the time coordinate T of a tracker lies between two known points of a given tracker, its position will be extrapolated by weighting the three data points X, Y, and T.

[0104] The present invention makes it possible to place trackers 71, 72, 73 (or hotspots or trackers) which follow in real time the person 50 or the object 40, 60 in a video 30. It is possible to decide at any time to pause a video broadcast and the corresponding tracker(s) 71, 72, 73 will be placed exactly in the right place on the image of the paused video 30.

[0105] The invention can be used for various applications, including but not limited to: a. E-commerce b. Informative content c. Product placement in any sector of activity d. Security

[0106] The present invention can be used in various contexts, including: a. Online learning b. Tourism c. Services to individuals d. Concierge / Hotel Services e. Sports and sports coaching f. Online commerce

[0107] According to one embodiment, the invention relates to a method 10 of interaction with at least one multimedia content comprising at least one video 30. This video 30 comprises at least one visual representation of at least one entity 40, 50, 60.

[0108] According to one embodiment, the process 10 comprises at least two phases: the monitoring phase 100 and the interaction phase 200. Preferably, the process 10 comprises a plurality of steps described below, as illustrated by [Fig. 1].

[0109] The method 10 is advantageously configured to be executed by at least one computer interaction system 20, as illustrated by [Fig.2].

[0110] According to one embodiment, the monitoring phase 100 comprises: a. select 101, by at least one selection module 21, at least one entity 40, 50, 60, said entity 40, 50, 60 being present in at least a plurality of images of a video 30; b. determine 102, by at least one determination module 22, the matrix position of said entity 40, 50, 60 in the video 30 according to a predetermined list of instants T of the video 30 where said entity 40, 50, 60 is visible in said video 30; Preferably, the set of instants T where the entity is visible in the video includes said predetermined list of instants T; Advantageously, this list is predetermined on the basis of a set of rules and / or via the use of a mathematical model, i.e. artificial intelligence, configured to optimize the selection of these key instants so as to reduce the amount of system resources required for determining the matrix positions of said entity 40, 50, 60 in the video 30; c. assign 103, by at least one tracking module 23, at least one tracker 71, 72, 73 to said entity 40, 50, 60, said tracker 71, 72, 73 being configured to track, preferably in real time, the matrix position of said entity 40, 50, 60 at each instant T of the video 30 where said entity 40, 50, 60 is visible in said video 30; d. generate 104, by said tracking module 23, at least one interactivity mask 70, said interactivity mask 70 being configured to be superimposed on said video 30, said interactivity mask 70 comprising said tracker 71, 72, 73; e. calculate 105, by said tracking module 23, the position of said tracer 71, 72, 73 in said interactivity mask 70 at each instant T of the video 30, said position comprising at least three coordinates (X, Y and T), the first coordinate X corresponding to a first spatial coordinate, the second coordinate Y corresponding to a second spatial coordinate, and the third coordinate T corresponding to a temporal coordinate; f. define 106, by said tracking module 23, the first X coordinate of said plotter 71, 72, 73 as a percentage of the width of said video 30; g. define 107, by said tracking module 23, the second Y coordinate of said plotter 71, 72, 73 as a percentage of the height of said video 30; h. record 108, by said tracking module 23, the position of said tracker 71, 72, 73 at each instant T of the video 30 where said entity 40, 50, 60 is visible in said video 30; i. assign 109, by said tracking module 23, at least one functionality to said tracer 71, 72, 73; j. follow 110, by said tracking module 23, said entity 40, 50, 60 by said tracker 71, 72, 73 at each instant T of the video 30.

[0111] Indeed, preferably in the tracking phase 100, the computer system 20 is configured to select, by at least said selection module 21, at least one entity 40, 50, 60, which is present in at least a plurality of images of the video 30. The computer system 20 is preferably configured to determine, by at least said determination module 22, the matrix position of the entity 40, 50, 60 in the video 30 according to a predetermined list of instants T of the video 30 where the entity 40, 50, 60 is visible in the video 30.

[0112] Next, the computer system 20 is advantageously configured to assign, by at least said tracking module 23, at least one tracker 71, 72, 73, to the entity, preferably via the use of at least said interactivity mask 70. This tracker 71, 72, 73 is configured to track, preferably in real time, the matrix position of the entity 40, 50, 60 at each instant T of the video 30 where the entity 40, 50, 60 is visible in the video 30.

[0113] The computer system 20 is preferably configured to generate, by at least said tracking module 23, at least said interactive mask 70, which is superimposed on the video 30. This interactive mask 70 advantageously includes the tracker 71, 72, 73. The computer system 20 is preferably configured to calculate, by at least said tracking module 23, the position of the tracker 71, 72, 73 in said interactive mask 70 at each instant T of the video 30.

[0114] The position of the tracer 71, 72, 73 comprises at least three coordinates (X, Y and T), where the first coordinate X corresponds to a first spatial coordinate, the second coordinate Y corresponds to a second spatial coordinate, and the third coordinate T corresponds to a temporal coordinate.

[0115] The computer system 20 is advantageously configured to define, by at least said tracking module 23: a. The first X coordinate of the plotter as a percentage of the video width; and b. The second Y coordinate of the plotter as a percentage of the video height.

[0116] Finally, the computer system is preferably configured to record, by at least said tracking module 23, the position of the tracker 71, 72, 73 at each instant T of the video 30 where the entity 40, 50, 60 is visible in the video 30. The computer system 20 is advantageously configured to assign, by at least said tracking module 23, at least one functionality 71a, 72a, 73a to the tracker 71, 72, 73.

[0117] According to one embodiment, the interaction phase 200 comprises at least: a. selecting 201 said tracer 71, 72, 73 by at least one user using at least one interface 24; b. activate at least one feature 71a, 72a, 73a of said plotter 71, 72, 73 by said user using at least said interface 24.

[0118] According to one embodiment, in the interaction phase 200, the user selects the plotter 71, 72, 73 using at least one user interface 25, as illustrated by Figures 5, 6 and 7. The user can then activate at least one of the functionalities 71a, 72a, 73a of the plotter 71, 72, 73 by said interface 24. Advantageously, this interface 24 may include a keyboard and / or a mouse, or even a touch display screen 25.

[0119] As illustrated in [Fig. 3], the video 30 can include a first entity 40 in the form of a vehicle, a second entity 50 in the form of a person, and a third entity 60 in the form of a smartphone. As illustrated in [Fig. 4], the computer system 20 allows a tracker 71, 72, 73 to be assigned to each entity 40, 50, 60.

[0120] As illustrated in [Fig. 5], the user interacts with the first tracker 71 via the user interface 24, which activates a function 71a of the first tracker 71, such as displaying information. As illustrated in [Fig. 6], the user can interact with the second tracker 72 via the user interface 24, which activates a function 72a of the second tracker 72, such as opening a web page related to the profile of person 50 on a social network. As illustrated in [Fig. 7], the user can also interact with the third tracker 73 via the user interface 25, which activates a function 73a of the third tracker 73, such as adding the product represented by the third entity 60 to a shopping cart for the purpose of purchasing it, for example (this list is not exhaustive).

[0121] In summary, the invention relates to a method 100 of interacting with at least one multimedia content comprising at least one video 30. The computer system 20 is configured to track the matrix position of at least one entity 40, 50, 60 in the video 30 and to assign a tracker 71, 72, 73 to said entity 40, 50, 60. The user interacts with the tracker 71, 72, 73 via the user interface 24, which activates at least one function 71a, 72a, 73a of the tracker 71, 72, 73.

[0122] According to one embodiment, the present invention simplifies user interaction processes by automatically selecting and tracking entities within a video. This functionality eliminates the need to manually search for visual elements in the video, resulting in a more intuitive and efficient user experience.

[0123] The dynamic generation of an interactivity mask 70 that is superimposed on the video 30 makes it possible to create a more immersive and intuitive user interface. This interactivity mask 70 can be designed to adapt to the matrix position of the entity 40, 50, 60 in real time, thus ensuring more precise and efficient interaction.

[0124] The ability of the tracer 71, 72, 73 to track the matrix position of the entity 40, 50, 60 in real time also allows for the creation of more complex and precise interactions. Indeed, it is possible to calculate the X, Y, and T coordinates of the position of the tracer 71, 72, 73 within the interactivity mask 70, which makes it possible to take into account the spatial and temporal position of the entity 40, 50, 60 and of the tracer 71, 72, 73.

[0125] Advantageously, the position of the tracer 71, 72, 73 can also be extrapolated from two known positions.

[0126] The ability to assign functionalities 71a, 72a, 73a to the plotter 71, 72, 73 allows for customization and extension of the user interface functionalities, according to the user's needs and preferences.

[0127] According to one embodiment, the present invention is configured to dynamically generate a tracer 71, 72, 73 for each desired entity 40, 50, 60. According to one embodiment, this tracer 71, 72, 73 is designed to be linked to the position and / or size of the entity 40, 50, 60.

[0128] According to one embodiment, the present invention makes it possible to create customized tracers 71, 72, 73 for each entity 40, 50, 60, which offers great flexibility in the implementation of the present invention. Preferably, the tracers 71, 72, 73 are generated according to the position and / or size of the entity 40, 50, 60, which allows for better integration with the context.

[0129] By way of example, [Fig. 4] illustrates how the present invention can be implemented to create customized tracers 71, 72, 73 for each entity. The elements of [Fig. 3] are repeated, and [Fig. 4] thus illustrates a tracer 71, 72, 73 for each entity 40, 50, 60, i.e., a first tracer 71 for the first entity 40, a second tracer 72 for the second entity 50, and a third tracer 73 for the third entity 60.

[0130] Fig. 5 shows a feature 71a of the first plotter 71 which includes a display of information relating to the first entity 40 when the user interacts with the first plotter 71 via the user interface 24.

[0131] Figure 6 illustrates a feature 72a of the second tracker 72 which includes opening a web page relating to the profile of person 50 on a social network when the user interacts with the second tracker 72 via the user interface 24. In one embodiment, this feature allows the user to discover additional information about the people present in the video 30.

[0132] Finally, [Fig. 7] presents a feature 73a of the third tracker 73 which includes adding the product represented by the third entity 60 to a shopping cart for the purpose of purchase when the user interacts with the first tracker 73 via the user interface. According to one embodiment, this feature allows the user to purchase products online simply and efficiently from a video 30.

[0133] According to one embodiment, the interactivity mask 70 is generated according to the dimensions of the video 30 and / or the entity 40, 50, 60.

[0134] Preferably, the present invention makes it possible to create an adaptive interactivity mask 70 that meets the specific needs of each entity and / or each user.

[0135] Preferably, the dimensions of the video 30 and / or the entity 40, 50, 60 are taken into account to determine the elements to be included in the interactivity mask 70. According to one embodiment, the present invention makes it possible to create an interactivity mask 70 that is in line with user needs and meets their expectations.

[0136] In [Fig.4], it is illustrated how the process 10 dynamically generates the interactivity mask 70 as a function of the dimensions of the video 30 and / or the entity 40, 50, 60. The elements of the interactivity mask 70 can be adapted to meet the specific needs of each entity 40, 50, 60.

[0137] The present invention offers a competitive advantage by providing a personalized and intuitive user experience. For example, the present invention allows companies to create stronger relationships with their customers and improve their market visibility.

[0138] According to one embodiment, the present invention is designed to allow a tracer 71, 72, 73 to be visible to the user, preferably at least when the user pauses the video 30.

[0139] Preferably, this tracker 71, 72, 73 is visible at every instant T of the video. According to one embodiment, this visibility of the tracker 71, 72, 73 allows the user to interact with the entities 40, 50, 60 present in the video 30.

[0140] According to one embodiment, the present invention also makes it possible to provide additional information to the user depending on their interaction with the tracker 71, 72, 73. For example, according to [Fig. 5], when the user interacts with the first plotter 71 via user interface 24, a display 71a of information is provided.

[0141] According to one embodiment, interactions with trackers 71, 72, 73 can also lead to additional actions. For example, according to [Fig. 6], when the user interacts with the second tracker 72 via the user interface 24, a web page 72a relating to the profile of person 50 on a social network is opened.

[0142] According to one embodiment, interactions with trackers 71, 72, 73 can also lead to purchase actions. For example, according to [Fig. 7], when the user interacts with the third tracker 73 via the user interface 24, the product represented by the third entity 60 is added 73a to a shopping cart for purchase.

[0143] According to one embodiment, a tracker 71, 72, 73 may include one or more functionalities 71a, 72a, 73a. These functionalities 71a, 72a, 73a may be taken from at least: Opening an Internet page, Adding an item to a basket; calling a telephone number, sending an email, displaying a name, displaying information, displaying information related to said entity, etc.

[0144] According to one embodiment, said functionality 71a, 72a, 73a can provide additional information to the user, such as purchase advice or product recommendations, which can improve the user experience and increase the chances of a sale.

[0145] According to one embodiment, the present invention may include at least one information collection phase. Preferably, this information collection phase includes recording in at least one database a history of the interaction of said user with said tracker.

[0146] Advantageously, this information collection phase makes it possible to gather information on the interactions between the user and the tracker.

[0147] According to one embodiment, the present invention is designed to allow a tracker to follow several entities. Preferably, the present invention allows the tracking parameters to be defined for each distinct entity.

[0148] According to one embodiment, the tracker can be configured to track several entities, such as vehicles, people or objects, for example.

[0149] According to one embodiment, the present invention is configured to allow an entity to be associated with several tracers.

[0150] Preferably, the present invention allows each entity to be linked to one or more trackers, thus offering great flexibility. For example, a person can be tracked by one tracker and their clothing by another.

[0151] According to one embodiment, the present invention is configured to adapt to changes in position and / or size of the entity at each instant T of the video.

[0152] According to one embodiment, the tracker is configured to adapt to changes in the position and / or size of the entity at each instant T of the video. Advantageously, this improves the accuracy of entity tracking and reduces detection errors.

[0153] In one embodiment, the present invention comprises determining the matrix position of an entity in a video according to a predetermined list of instants T in the video where said entity is visible in said video. In one embodiment, this determination can be performed using artificial intelligence. Preferably, this artificial intelligence is trained to recognize the different forms that these entities can take, such as a vehicle, a person or an object, or even clothing, for example, but not limited to.

[0154] According to one embodiment, the video can contain several entities, as illustrated in [Fig. 3]. This figure shows a video 30 comprising a first entity in the form of a vehicle 40, a second entity in the form of a person 50 and a third entity in the form of a smart phone, also called a smartphone 60.

[0155] According to one embodiment, for each entity visible in the video, a tracer 71, 72, 73 can be generated, as illustrated in [Fig.4].

[0156] According to one embodiment, the present invention comprises a partially transparent interactivity mask 70. Preferably, this interactivity mask 70 is designed to allow effective interaction between the user and the video 30 via the trackers 71, 72, 73. Preferably, said interactivity mask 70 is partially transparent, meaning that some parts of the mask are transparent, while others may be opaque or semi-opaque. Advantageously, this transparency makes it possible to reduce the visibility of elements of the video 30 that are not relevant to the user and / or to draw the user's attention to a specific area of ​​the video 30.

[0157] According to one embodiment, the present invention relates to a computer program product. This computer program product is designed to execute the present invention. This computer program product is stored on a non-transient memory medium, such as hard drives, memory cards, or other storage media.

[0158] The computer program product includes instructions which, when executed by at least one of a processor and a computer, performs at least some of the steps of the present invention.

[0159] According to one embodiment, the present invention relates to the computer interaction system 20 described above and configured to allow at least one user to interact with at least one multimedia content comprising at least one video 30. This video 30 includes at least one visual representation of at least one entity 40, 50, 60, as illustrated by [Fig.3].

[0160] The computer interaction system 20 may include several modules, including a selection module 21, a determination module 22 and a monitoring module 23.

[0161] According to one embodiment, and as illustrated by [Fig.2], the computer interaction system 20 comprises at least: a. a selection module 21, said selection module 21 being configured to select 101 at least one entity 40, 50, 60, said entity 40, 50, 60 being present in at least a plurality of images of a video 30; b. a determination module 22, said determination module 22 being configured to determine 102 the matrix position of said entity 40, 50, 60 in the video 30 according to a predetermined list of instants T of the video 30 where said entity 40, 50, 60 is visible in said video 30; c. a tracking module 23, said tracking module 23 being configured to: i. assign 103 at least one tracker 71, 72, 73 to said entity 40, 50, 60, said tracker 71, 72, 73 being configured to track, preferably in real time, the matrix position of said entity 40, 50, 60 at each instant T of the video 30 where said entity 40, 50, 60 is visible in said video 30; ii. generate at least one 70 interactivity mask, said 70 interactivity mask being configured to overlay said video 30, said 70 interactivity mask comprising said tracer 71, 72, 73; iii. calculate 105 the position of said tracer 71, 72, 73 in said interactivity mask 70 at each instant T of the video 30, said position comprising at least three coordinates (X, Y and T), the first coordinate X corresponding to a first spatial coordinate, the second coordinate Y corresponding to a second spatial coordinate, and the third coordinate T corresponding to a temporal coordinate; iv. define 106 the first X coordinate of said plotter 71, 72, 73 as a percentage of the width of said video 30; v. define 107 the second Y coordinate of said plotter 71, 72, 73 as a percentage of the height of said video 30; vi. record 108 the position of said tracer 71, 72, 73 at each instant T of the video 30 where said entity 40, 50, 60 is visible in said video 30; vü. assign at least one functionality 71a, 72a, 73a to audit tracer 71, 72, 73; viii. follow 110 of said entity 40, 50, 60 by said tracer 71, 72, 73 at each instant T of video 30; d. an interface 24, said interface 24 being configured to allow: i. the selection 201 of said plotter 71, 72, 73 by at least one user using said interface 24; ii. the activation 202 of at least one functionality 71a, 72a, 73a of said tracer 71, 72, 73 by said user using at least said interface 24.

[0162] Advantageously, the tracking module 23 is configured to record the position of said tracker 71, 72, 73 at each instant T of the video 30 where said entity 40, 50, 60 is visible in said video 30. It is also configured to assign at least one functionality 71a, 72a, 73a to said tracker 71, 72, 73.

[0163] Advantageously, the computer interaction system 20 allows the user to select and activate the functionalities 71a, 72a, 73a of the plotters 71, 72, 73 via the user interface 24, as illustrated by Figures 5, 6 and 7.

[0164] According to one embodiment, the invention relates to a computer system for tracking and storing the matrix position of one or more entities (objects or people) at any time in a video. The present invention makes it possible to track the position of an entity in real time and allows the user to stop playback at any time to interact with the video, which has become an interactive video.

[0165] The computer system uses one or more plotters visible on the video, which have a specific position at each instant of the video. The coordinates of each plotter are preferably defined by positions expressed as a percentage of the width X and height Y of the video, at a time T from the beginning of the video.

[0166] The trackers also have other properties, as discussed previously, that allow the user to interact with them, such as the trade name, URI, illustration, description, and other properties specific to the entity type. When the user pauses the video, all visible trackers become active, i.e., clickable, for example.

[0167] In this description, certain specific details are included to facilitate understanding of the various implementations described. However, those skilled in the art will recognize that the implementations can be performed without one or more of these specific details, steps in a method, components, modules, etc. In some cases, well-known steps or implementations of steps associated with artificial intelligence, machine learning, and / or neural networks have not been shown or described in detail to avoid unnecessarily obscuring the descriptions of disclosed implementations.

[0168] The computer system may include one or more processors and one or more data storage spaces, these elements being configured to respectively execute and store instructions enabling the implementation of the steps and modules presented herein.

[0169] In this description and the attached claims, the terms "a," "an," or "another" applied to an "embody," "example," or "implementation" are used to mean that a particular feature, structure, or element described in relation to the embodiment, example, or implementation is included in at least one embodiment, example, or implementation. Thus, expressions such as "according to one embodiment," "according to another embodiment," or "according to an example" do not necessarily all refer to the same embodiment. Furthermore, particular features, structures, or traits can be combined in any way in one or more embodiments, examples, or implementations.

[0170] Unless the context otherwise indicates, in this description and the attached claims, the word "include" and its variants, such as "comprise" and "comprising", should be interpreted in an open and inclusive sense, i.e., as "including, but not limited to".

[0171] Modifications and improvements to the applications of the present invention described above may be apparent to those skilled in the art. The preceding description is intended to be exemplary and not limiting. References

[0172] 10 Process

[0173] 20 Computer system

[0174] 21 Selection Module

[0175] 22 Determination Module

[0176] 23 Tracking Module

[0177] 24 Interface

[0178] 25 Display screen

[0179] 30 Video

[0180] 40 Interactivity Mask

[0181] 50 First entity

[0182] 60 Second entity

[0183] 70 Third entity

[0184] 71 First tracer

[0185] 71a Information

[0186] 72 Second tracer

[0187] 72a Internet page

[0188] 73 Third tracer

[0189] 73a Shopping Cart

[0190] 100 Follow-up Phase

[0191] 101 Select an entity

[0192] 102 Determine the matrix position of the entity

[0193] 103 Assign a tracer to the entity

[0194] 104 Generate an interactivity mask

[0195] 105 Calculate the position of the tracer

[0196] 106 Define the X coordinate

[0197] 107 Define the Y coordinate

[0198] 108 Record the position of said tracer at each time T

[0199] 109 Assign at least one functionality

[0200] 110 Follow 1 ' entity [0201 ] 200 Interaction phase

[0202] 201 Select the plotter

[0203] 202 Activate the feature

Claims

1. Demands Method (10) for interaction of at least one user with at least one multimedia content comprising at least one video (30), said video (30) comprising at least one visual representation of at least one entity (40, 50, 60), said method (10) being configured to be executed by at least one computer interaction system (20), said method (10) comprising: • a follow-up phase (100) including: i. select (101), by at least one selection module (21), at least said entity (40, 50, 60), said entity (40, 50, 60) being present in at least a plurality of images of said video (30); ii. determine (102), by at least one determination module (22), the matrix position of said entity (40, 50, 60) in the video (30) according to a predetermined list of instants T of the video (30) where said entity (40, 50, 60) is visible in said video (30); iii. assign (103), by at least one tracking module (23), at least one tracker (71, 72, 73) to said entity (40, 50, 60), said tracker (71, 72, 73) being configured to track, preferably in real time, the matrix position of said entity (40, 50, 60) at each instant T of the video (30) where said entity (40, 50, 60) is visible in said video (30); iv. generate (104), by said tracking module (23), at least one interactivity mask (70), said interactivity mask (70) being configured to overlay said video (30), said interactivity mask (70) comprising said tracker (71, 72, 73); v. calculate (105), by said tracking module (23), the position of said tracker (71, 72, 73) in said interactive mask (70) at each instant T of the video (30), said position comprising at least three coordinates (X, Y and T), the first coordinate X corresponding to a the first spatial coordinate, the second Y coordinate corresponding to a second spatial coordinate, and the third T coordinate corresponding to a temporal coordinate; vi. define (106), by said tracking module (23), the first X coordinate of said plotter (71, 72, 73) as a percentage of the width of said video (30); vii. define (107), by said tracking module, the second Y coordinate of said plotter (71, 72, 73) as a percentage of the height of said video (30); viii. record (108), by said tracking module (23), the position of said tracker (71, 72, 73) at each instant T of the video (30) where said entity (40, 50, 60) is visible in said video (30); ix. assign (109), by said tracking module (23), at least one functionality (71a, 72a, 73a) to said tracker (71, 72, 73); x. follow (110), by said tracking module (23), said entity (40, 50, 60) by said tracker (71, 72, 73) at each instant T of the video (30); • an interaction phase (200) comprising at least: i. select (201) said plotter (71, 72, 73) by at least one user using at least one interface (24); ii. activate (202) at least one feature (71a, 72a, 73a) of said plotter (71, 72, 73) by said user using at least said interface (24).

2. Method (10) according to claim 1 wherein the tracer (71, 72, 73) is generated dynamically, preferably according to the position and / or size of the entity (40, 50, 60).

3. Method (10) according to any one of the preceding claims wherein the interactivity mask (70) is generated dynamically, preferably according to the dimensions of the video (30) and / or the entity (40, 50, 60).

4. Method (10) according to any one of the preceding claims wherein the tracker (71, 72, 73) is visible to the user, preferably at each instant T of the video (30).

5. A method (10) according to any one of the preceding claims in which said functionality (71a, 72a, 73a) comprises at least one of the following functionalities: opening an Internet page, adding an item to a shopping cart, calling a telephone number, sending an email, displaying a name, displaying information related to said entity (40, 50, 60), etc.

6. Method (10) according to any one of the preceding claims comprising at least one information collection phase, said information collection phase comprising at least the recording in at least one database of a history of the interaction of said user with said tracker (71, 72, 73).

7. Method (10) according to any one of the preceding claims wherein said tracer (71, 72, 73) is configured to track several entities (40, 50, 60).

8. Method (10) according to any one of the preceding claims wherein said entity (40, 50, 60) is associated with several tracers (71, 72, 73).

9. Method (10) according to any one of the preceding claims wherein said tracker (71, 72, 73) is configured to adapt to changes in position and / or size of the entity at each instant T of the video (30).

10. A method (10) according to any one of the preceding claims in which said entity (40, 50, 60) is taken from at least: a person, an object, a living being, animal or vegetable.

11. A method (10) according to any one of the preceding claims in which the determination of the matrix position of said entity (40, 50, 60) in the video, according to a predetermined list of instants T of the video where said entity is visible in said video, is carried out via the use of artificial intelligence.

12. A method according to any one of claims 1 to 10 wherein the determination (102) of the matrix position of said entity (40, 50, 60) in the video (30), according to a predetermined list of instants T of the video (30) where said entity (40, 50, 60) is visible in said video (30), is carried out manually by at least one operator.

13. Method (10) according to any one of the preceding claims wherein said interactivity mask (70) is partially transparent.

14. Product computer program, preferably stored on a non-transient memory medium, comprising instructions which, when executed by at least one of a processor and a computer, carries out the method (10) according to any one of the preceding claims.

15. Non-transient memory carrier comprising at least one computer program product according to the preceding claim.

16. Computer system (20) for interaction of at least one user with at least one multimedia content comprising at least one video (30), said video (30) comprising at least one visual representation of at least one entity (40, 50, 60) said computer system (20) comprising at least: • a selection module (21), said selection module (21) being configured to select (101) at least said entity (40, 50, 60), said entity (40, 50, 60) being present in at least a plurality of images of said video (30); • a determination module (22), said determination module (22) being configured to determine (102) the matrix position of said entity (40, 50, 60) in the video (30) according to a predetermined list of times T in the video (30) where said entity (40, 50, 60) is visible in said video (30); • a tracking module (23), said tracking module (23) being configured to: i.assign (103) at least one tracker (71, 72, 73) to said entity (40, 50, 60), said tracker (71, 72, 73) being configured to track, preferably in real time, the matrix position of said entity (40, 50, 60) at each instant T of the video (30) where said entity (40, 50, 60) is visible in said video (30); ii. generate (104) at least one interactivity mask (70), said interactivity mask (70) being configured to be superimposed on said video. (30), said interactivity mask (70) comprising said tracer (71, 72, 73); iii. calculate (105) the position of said tracer (71, 72, 73) in said interactivity mask (70) at each instant T of the video, said position comprising at least three coordinates (X, Y and T), the first coordinate X corresponding to a first spatial coordinate, the second coordinate Y corresponding to a second spatial coordinate, and the third coordinate T corresponding to a temporal coordinate; iv. define (106) the first X coordinate of said plotter (71, 72, 73) as a percentage of the width of said video (30); v. define (107) the second Y coordinate of said plotter (71, 72, 73) as a percentage of the height of said video (30); vi. record (108) the position of said tracer (71, 72, 73) at each instant T of the video (30) where said entity (40, 50, 60) is visible in said video (30); vii. assign (109) at least one functionality (71a, 72a, 73a) to said tracer (71, 72, 73); viii. follow (110) of said entity (40, 50, 60) by said tracer (71, 72, 73) at each instant T of the video (30); an interface (24), said interface (24) being configured to allow: i. the selection (201) of said plotter (71, 72, 73) by at least one user using at least said interface (24); ii. the activation (202) of at least one feature (71a, 72a, 73a) of said tracker (71, 72, 73) by said user using at least said interface (24).

Images