FR3131675A1 - video capture method and device, video composition method and device and video analysis method. - Google Patents

Abstract

A video capture method and device, video composition method and device, and video analysis method are provided. More particularly, the method of video composition in a server comprises: - receiving from at least a first video capture device a first video representative of a first part of a scene and metadata associated with at least one fixed image of said first part of said scene, said metadata being representative of a geographical position of the first capture device at the time of capturing the image,- the reception of at least one second video capture device from a second video representing at least a second part of said scene and metadata associated with at least one fixed image of said second part of said scene, said metadata being representative of the geographical position of the second capture device at the time of capture of the image, said first and second videos being synchronized, - determining fixed points of interest in each of said videos, - said composition of a composite video representative of said scene from said first and at least one second videos by matching of said points of interest, - provision of said video representative of said scene, the detection of a movement of at least one of the two capture devices on the basis of the received metadata triggering a new determination of the fixed points of interest in said video captured by the moving device then said composition of a new composite video . Figure for abstract: Fig. 2.

Description

method and device for video capture, method and device for composing a video and method for video analysis.

The invention concerns the processing of a video of a scene from several videos representative of a part of the scene.

The broadcasting and recording of events, such as, but not limited to, concerts and sporting events often requires the deployment of expensive and complex means to implement. Indeed, it is often necessary to position numerous cameras to capture the event, the cameras generally being positioned all around the scene to be filmed. Not only is the capture of the scene made complex by the positioning of the numerous cameras, but also the composition and restitution of the scene by the broadcasters.

The complexity of such systems can lead spectators to use devices that are simpler to handle, such as cell phones for recording. However, the recomposition of a video from phones positioned around the scene remains complex, particularly due to the mobility of such phones and therefore the respective positions of the phones with respect to the scene.

The present invention aims to remedy all or part of the drawbacks of the prior art, in particular those set out above, by proposing a solution which allows, in comparison with the solutions of the state of the art, to recompose a single video from several videos of the same scene while avoiding complex mobility management solutions for capture terminals and user intervention.

To this end, according to a first aspect, the invention proposes a video capture method comprising

- video capture of a scene,

- obtaining at least one metadata from data associated with a still image of said scene, said metadata being representative of a geographical position of the capture device at the time of capturing the image,

- the transmission of the video and at least said metadata.

Thus, the metadata makes it possible to detect if one of the capture devices has moved during the capture and thus to recalculate the points of interest when this is the case. This advantageously avoids a user having to regularly monitor the position of the points of interest and furthermore having to reposition the points of interest on a regular basis. Thus, the points of interest make it possible to obtain a composition of a single video of a scene from one or more videos of the same scene without user intervention and in a very reliable manner producing a quality video and capturing the entire scene.

In particular modes of implementation, the metadata also includes one or more elements chosen from:

- an inclination of the capture device,

- a plate of the capture device,

- the compass (the inclination of the capture means relative to North) of the capture device,

These data advantageously make it possible to obtain information on the orientation of the video capture device.

Tilting the capture means has the effect, for example, of raising the horizon (dive mode) or lowering the horizon (dipped).

The attitude of the device makes it possible to detect the inclination relative to the horizon.

The compass, also called pan or pano or panoramic, makes it possible to detect the inclination of the capture means relative to the North.

A movement of the capture means induces a change in the value of one or more of these metadata, depending on whether the movement is horizontal, vertical, oblique, etc.

According to a second aspect, the invention relates to a method of composing a video comprising:

- receiving from at least one first video capture device a first video representative of a first part of a scene and metadata associated with at least one still image of the first part of said scene, the metadata being representative of a geographical position of the first capture device at the time of image capture,

- receiving from at least one second video capture device a second video representative of at least a second part of said scene and metadata associated with at least one still image of the second part of the scene, the metadata being representative of the geographical position of the second capture device at the time of capturing the image, the first and second videos being synchronized,

- the determination of fixed points of interest in each of the videos,

- the composition of a composite video representative of said scene from the first and at least one second videos by matching said points of interest,

- the provision of the representative video of the scene,

detecting a movement of at least one of the two capture devices on the basis of the received metadata triggering a new determination of the fixed points of interest in the video captured by the moving device then the composition of a new composite video .

Thus, the method can advantageously detect that the capture devices have moved, or at least one of them, and automatically recalculate the points of interest. In this way, compositing the two videos produces a consistent quality video from both videos. No human intervention is necessary either to reposition the capture devices or to request a new calculation of the points of interest as long as the method can calculate or recalculate the points of interest or as long as the variation of the metadata remains below a threshold .

In particular modes of implementation, the determination of fixed points of interest in each of the videos includes:

- transmission to at least one video display device, of the first and at least second videos,

- reception of at least one video display device, points of interest relating to each part of the scene.

In particular modes of implementation, the provision includes one or the other or more of:

- recording the composite video,

- display of the composite video,

- transmitting the composite video to at least one analysis device.

Advantageously, the recomposed video is intended to be broadcast, for example to a broadcast group. It can be broadcast live, the process being rapid and causing only a very slight delay with the event. The video can also be recorded and broadcast on time, on demand.

In particular modes of implementation, when said video is transmitted to at least one analysis device, it further comprises

- reception, following the transmission of scene enrichment data,

- synchronization of enrichment data with the composite video;

- the provision of the composite video enriched with enrichment data.

Thus, in addition to the automatic recomposition of the video from the two videos, the method can advantageously offer an end user content enriched with additional data relating to the captured content.

According to a third aspect, the invention relates to a video analysis method comprising

- The reception of a composite video representative of a scene obtained by a method of composing a video according to the invention,

- Adding enrichment data to said composite video to annotate said composite video,

- Provision of annotated composite video and enrichment data.

Preferably, the enrichment data is obtained by positioning the enrichment data by a user through a graphical interface.

According to another embodiment, the composition method analyzes the composite video (for example using artificial intelligence) and compares the enrichment data received with the analyzed data and in the event of inconsistency, subjects said inconsistencies to the user through the graphical interface for final validation.

The invention also relates to a video capture device comprising video capture means, a communication interface with at least one server and at least one processor capable of implementing a video capture method according to the invention.

The invention also relates to a server comprising

- at least a first communication interface with a video capture device,

- at least a second communication interface with a video display device,

- at least one processor capable of implementing a method for composing a video according to the invention.

The invention also relates to a system comprising at least a first and a second video capture device according to the invention, at least one server according to the invention and at least one analysis device capable of implementing an analysis method according to the invention.

The invention also relates to a computer program comprising instructions for implementing one of the methods according to the invention when the program is executed by a computer.

The invention also relates to a computer-readable recording medium on which a computer program according to the invention is recorded.

There represents a video capture method according to a particular embodiment of the invention.

There represents a method of composing a video according to a particular embodiment of the invention.

There represents the position of the points of interest according to a particular embodiment of the invention.

There represents a video analysis method according to a particular embodiment of the invention.

There represents a video capture device according to a particular embodiment of the invention.

There represents a server for composing a video according to a particular embodiment of the invention.

There represents a video analysis device according to a particular embodiment of the invention.

There represents a system according to a first particular embodiment of the invention.

There represents the position of two cameras around a scene to be captured according to a particular embodiment of the invention.

There the position of three cameras around a scene to be captured according to a particular embodiment of the invention.

There represents a system according to a second particular embodiment of the invention.

In the embodiments described below, the captured scene is a scene representative of a football match and therefore more precisely of the events taking place on a football field during a match. Thus, when reference is made to a first part of the scene and to a second part of the scene, particular reference is made to a first part of the football field, for example a little more than half a field for a first part and a little more than half a field for a second part. Of course, this is an example of a captured scene and in no way constitutes a limitation of the invention to the capture of a football match. Likewise, other sports can be considered but also other events such as concerts or other scenes of life.

Furthermore, the description of Figures 1 to 9 refers mainly to embodiments based on the capture of two parts of the same scene. It should be noted that speaking of two parts of the scene is not limited to two and that the invention is not limited to two captures but to at least two. There illustrates for example the possible positioning of three capture means.

There represents in flowchart form the main steps of a video capture method according to a preferred embodiment of the invention. Said method comprises steps E1a and E1b during which two videos are captured. More precisely, during step E1a, a video of a part of said scene is captured and during step E1b, a video of at least one other part of said scene is captured. The two steps E1a and E1b are carried out simultaneously. The two captured parts contain at least one common portion of the scene, this common portion comprising at least two common fixed points of interest.

The two videos are captured synchronously or can be synchronized using time tags. To do this, before starting the capture process, a synchronization process (not shown in the figures) is launched so as to associate a time label (“timecode” in English) with each captured video. This is for example advantageously achieved by using the NTP protocol (“network Time Protocol” in English). Each of the captured images having its time label, it is possible to synchronize the two videos when they are received by a remote device, regardless of the transmission delays of each of the videos which could be caused by network disturbances or different transmission speeds. depending on the network used by each of the capture devices.

In other embodiments, the synchronization of the two streams can be done using the audio tracks of the streams. The sound sampling frequency being much higher than the image frequency, and the sound tracks being practically identical on all the streams because the microphones are very close, setting the sound tracks also makes it possible to set the time labels, therefore the streams. . This system is used for synchronization and editing of multi-camera recordings while avoiding echo effects.

Then, during a step E2a, E2b, metadata are obtained, preferably from data from the GPS sensor (for “Global Positioning System” in English or global positioning system in French) and/or data from an accelerometer and/or a gyroscope and/or a magnetometer. Each video of a part of the scene is captured by capture means and these means can for example be associated or collaborate with a GPS, an accelerometer, a gyroscope or a magnetometer.

According to another embodiment, a processor associated with the capture means can also, using a software program, obtain said metadata.

Thus, when capturing each part of the scene, it is possible to associate the metadata with each captured image. Each image is therefore associated with a temporal label and metadata. Of course, certain metadata vary little, such as latitude and longitude, whereas in the event of bad weather, certain metadata will vary more, such as attitude, compass or inclination. Thus, longitude and latitude can be associated with the video and transmitted less frequently than others which might vary more during capture.

The metadata mainly relate to the geographical position, which may also include the orientation, of a capture device implementing the method and for example described in . Thus, a change in the metadata makes it possible to identify a shift or movement of the camera. Such a displacement/movement is not necessarily, but can be, a displacement carried out, voluntarily or involuntarily, by a person. Such a shift/movement can also be linked to meteorology for example. If there is a lot of wind, it is possible that the capture device implementing the method deviates from its initial position. This is especially true if the capture device is attached high up (to have a better view of the scene to be captured). Preferably, to avoid significant modifications of the metadata, the capture means are rigidly fixed and anchored to the ground. For example, they can be fixed on one or more tripods, removable or fixed to the ground.

During a step E3a, E3b, each video stream (including the time labels) and the metadata associated with the capture are transmitted to a server, represented in .

According to a preferred embodiment, the metadata is transmitted periodically to the server. Periodically means at regularly spaced times in time or at irregularly spaced times in time. For example, it can be envisaged that the metadata be transmitted every 60 s. The frequency of sending metadata can also be programmed and vary depending on weather conditions, for example if the capture devices are located outdoors. When there is a lot of wind for example, the capture means may possibly move, depending on their location or their attachment to the ground and thus it may be chosen to transmit the metadata with a greater frequency than when the weather is calm. Each of the capture devices may also transmit the metadata at a different frequency since each of the capture devices may be subject to different variations depending on its location or the conditions specific to its location.

Transmission can be done using the wireless communication network, such as the 2G, 3G, 4G, 5G and more cellular network or using a WIFI connection. Each of the capture devices may also use a different network to transmit video and metadata.

The images of the video streams are preferably transmitted at a rate of 30 images per second. In other embodiments, they may be transmitted at a rate of 60, 120 or 240 frames per second. The evolution of communication networks and video standards may allow the transmission of larger videos, for example Full HD, 4K, 8K using transmission networks such as 5G and later versions, or WIFI networks of future standards.

Of course, the video can be transmitted in an encoded (compressed) manner before transmission using coding algorithms such as MPEG-4, H.264 or X.264 or other formats...

There represents a method of composing a composite video according to a particular embodiment of the invention. The method is advantageously implemented in a server as represented in .

During a step T1, the video (including the time labels) and the metadata representative of a first part of the scene, and at least a second part of the scene, are received. The videos were captured with the same time tag, so they can be synchronized using those time tags. Likewise, the metadata being associated with an image, each image being associated with a temporal label, the metadata is therefore associated with the same label as the image with which it is associated.

During a step T2, fixed points of interest in the scene are determined in each of the two videos. The composition of the composite video representative of said scene is produced from the first and at least one second videos by matching the points of interest.

During this step, the determination of points of interest is linked to the nature of the captured scene. For example, when the captured scene is a football match, 4 points of interest are determined on each part of the scene.

According to a first embodiment, as illustrated in , the 4 points of interest are defined as being the points of intersection between

- The center line and the two sidelines:

- the Rlu and Rld points for the first part of the video representing the right part of the scene in right and the points Lru and Lrd for the second part of the video in left representing the left part of the scene

- The goal line and the two touchlines:

the points Rru and Rrd for the first part of the video representing the right part of the scene in right and the points Llu and Lld for the second part of the video in left representing the left part of the scene

The composition process and particularly the detection of points of interest are linked to the type of scene filmed. Thus, the composition process can be configured in advance with the type of event captured.

According to a preferred embodiment, the points of interest are determined using different functions and algorithms from the open-cv library. First of all, the color masks (green for the terrain and white for the lines). Contour detection can be carried out by the Canny filter (Canny algorithm), by the gradient or Laplacian method. In order to eliminate the remaining false positives, the process implements the open-cv, numpy, and skimage.morphology libraries in python (or equivalent in C++ language) or the watershed algorithm. The morpho function is calibrated to keep only the longest straight line elements (thus eliminating goals including the posts and the crossbar, the central circle or the penalty area for the example of football).

According to a particular embodiment, the determination, in step T2, of fixed points of interest in each of said videos may include:

- the transmission to at least one video analysis device of the at least two videos received, each representative of at least one part of the scene,

- Receiving from at least one video analysis device, points of interest relating to each of the parts of said scene.

The video analysis device is represented in

This can possibly allow the points of interest to be determined by another device and possibly allow the points of interest to be adjusted if necessary in the event that automatic detection cannot take place, for example through the intervention of a user. .

For example, if only three points of interest can be determined during step T2 by the method, then the user may be required to position a fourth point of interest to improve the composition process, more reliable with four points of interest than with three points of interest.

According to a particular embodiment, the determination, in step T2, of fixed points of interest in each of said videos may include:

- the transmission to at least one video analysis device of the at least two videos received, each representative of at least one part of the scene, and of the points of interest,

- Receiving from at least one video analysis device, new points of interest relating to each of the parts of said scene.

Thus, this can advantageously adjust one or more points of interest when the automatic detection does not work correctly or sufficiently precisely.

According to another particular embodiment, the determination, in step T2, of fixed points of interest in each of said videos may include:

- the transmission to at least one video analysis device of the at least two videos received, each representative of at least one part of the scene, and of the points of interest,

- Receipt from at least one video analysis device of a message validating the position of at least one of the points of interest.

This can advantageously allow a user or an operator to confirm or not the automatic detection of the position of points of interest.

According to another embodiment, during transmission to at least one video analysis device, of the at least two received videos each representative of at least one part of the scene, the two videos are transmitted at the same resolution (definition ) and more particularly at the lower resolution of that of the two videos when the two videos are not captured according to the same definition.

According to another preferred embodiment, in addition to the position of the points of interest, data such as the detection of the boundaries of the terrain can be transmitted and validated or corrected by the video analysis device. More generally, geometry data relating to said scene can be transmitted to the video analysis device and repositioned by it or validated by it. Thus, according to this embodiment, step T2 can include:

- the transmission to at least one video analysis device of the at least two videos received, each representative of at least one part of the scene, points of interest or data relating to the geometry of the part of the scene,

- Receipt from at least one video analysis device of a message validating the position of at least one of the points of interest or the geometry of the scene.

During a step T3, the metadata received with each video are analyzed to study their variation. As described in the , the metadata are representative of a geographical position of the capture means, the attitude, the inclination or the compass (the inclination of the capture means relative to North). Metadata is transmitted periodically, at regular or irregular time intervals, and analyzed upon receipt by comparing it to reference metadata. Reference metadata including metadata transmitted by the capture means during their initialization or implementation (during locking). If this comparison detects that the geographic position (e.g. latitude or longitude), or inclination, or attitude or compass has varied and the variation is greater than a given threshold, then the points of interest are recalculated. As indicated, these variations are due to a movement of the capture means. Advantageously, when the metadata does not vary, for example because the capture means are not easily accessible and therefore cannot be moved inadvertently or when the weather conditions are good (absence of wind for example), then the comparison can be done more spaced out over time and not systematically each time new metadata is received.

If the result of the comparison, step T4, is greater than a threshold, each threshold being defined for each type of metadata, then the points of interest are redefined. Otherwise the points of interest are not redefined. Of course, the points of interest being used during step T5, they are always defined at the launch of the process when receiving the first metadata, the analysis and comparison steps T3 and T4 then occurring during the capture to check the geographic stability of capture devices.

According to another embodiment, the metadata are not compared to a threshold but must be included in a tolerance range centered around the value of the first corresponding metadata received called reference metadata.

It is possible that only one of the capture devices has moved and that the variation in the associated metadata is significant enough to require a recalculation of the points of interest. In this case, the points of interest are recalculated only for this part of the video during step T2.

According to another embodiment, several thresholds can be defined.

The first threshold S1 is defined as being a threshold below which the variation of the metadata does not involve recalculation of the position of the points of interest.

The second threshold S2 is defined as being a threshold above which the at least two capture devices no longer capture a common area allowing the determination of a sufficient number of fixed points of interest for the composition of the composite video.

If the variation of the metadata is below the first threshold S1, then there is no recalculation of the points of interest because this low variation does not imply deformation of the symmetries or parallelisms of the composite image to be constructed.

If the variation of the metadata is between this first threshold S1 and the second threshold S2, then a recalculation of the points of interest is necessary as indicated above.

If the variation of the metadata is greater than this second threshold S2, then the repositioning of the means or at least one of the capture means is necessary before recalculating the points of interest.

During a step T5, a composite video representing the scene is composed from the two videos each representing at least part of the scene and points of interest.

During this step, with reference to the , this involves creating a single video, called a composite video, in which a single scene is created. The scene recomposed from the two half-scenes of the left videos and right videos is shown below.

Thus, during this step, the two videos are matched, by matching the points Lru and Rlu and the points Lrd and Rld. This is illustrated in low, the points of interest Lru and Rlu are combined as are the points of interest Lrd and Rld.

The composition is carried out using graphic stitching and cropping algorithms. In the case of a scene representing a sports field, the following constraints are taken into account for the composition of the composite video:

- The composite image must have the top and bottom key lines parallel,

- The composite image must have the center line perpendicular to the key lines,

- The lines along the goals on the composite image are chiral,

- The length of the bottom touchline must be twice the definition of the lowest resolution stream, in number of pixels,

- the height of the center line is chosen by comparing the heights of the two points of common interest and keeping the largest, the second will have to stretch to match it.

- In the case of 3 capture devices, the height of the center line on the central capture device will be the referent,

- The length of each half of the high key lines is the same

- The width of the composite image is 2 times the width of the flow (if 2 flows), its height is reduced to eliminate empty areas (holes) created by stiching.

According to a particular embodiment, the cutting and pasting algorithms use Python libraries such as open-cv and functions cv2.getPerspectiveTransform and cv2.getWarpPerspective. Encoding is then carried out in X.264 format with the cv2.videoWriter function, specifying the size of the image (size) and the number of images per second (fps). Other equivalent functions can be used when the coding language used is C++.

According to a particular embodiment, this step may include a validation sub-step. This validation sub-step includes the transmission to a video analysis device of a version, for example low definition, of the composite video.

The subscriber terminal can receive instructions, from a user, to adjust certain geometric points of the recomposed scene obtained during composition. For example, in the context of a sports field, it may involve the adjustment of the 4 corners of the sports field. More precisely, according to a preferred mode, only the two points of interest defined by the intersection of the upper touchline (top of the image) and the goal lines are modifiable. The instructions may also include an adjustment, such as decreasing the height of the image, for example by eliminating unnecessary elements. The instructions may also include replacing these unnecessary areas with advertising banners.

By unnecessary area, we can mean, for example, areas outside the boundaries of the land.

During this composition step T5, according to a variant, the differences between the color and brightness parameters, such as for example contrast, brightness, saturation, exposure between the two videos are also taken into account in order to generate composite video. Thus, these differences can be smoothed out, filters can also be applied to homogenize, or even transform, one or the other stream to have a homogeneous composite video on the two parts thus brought together.

Once the video has been recomposed from the points of interest and the two videos, it is made available, step T6.

According to a first variant, the provision consists of recording the composite video so as, for example, to broadcast it subsequently.

According to another variant, the provision consists of display.

According to another variant, the provision consists of transmitting the composite video to one or more devices for its display or for its recording for later viewing or use. The video can be recorded at different resolutions depending on the capacity of the communication networks and terminals for which it is intended.

The three variants can of course be combined. Likewise, different definitions of composite video may be made available depending on bandwidth, the end use of the video, and the capabilities of the end device using the video.

When the provision consists of the display of the composite video (which may also be preceded by recording), according to a particular embodiment, the composite video can be enriched by a user, or automatically by a program.

In one embodiment, when it is a program which enriches the composite video, the enrichment can be carried out using image analysis software and detection of preferential actions linked to the broadcast event. . For example, during a match, it is possible to detect goals, corners, and compile statistics, it is also possible to add for example the names of the players, the number of ball possessions, the number of balls touched, lost, recovered, the time of ball possession by player or team, the number of shots on target or not, the distance covered by each player, by match, by position and thus to see the evolution of the statistics during a full season.

When it is a user who enriches the composite video, it is transmitted to at least one analysis device, for example a device 3 as illustrated in and used by the user who will enrich the composite video. In this case, the video composition process includes

- the reception, following transmission, of enrichment data from said scene,

- synchronization of enrichment data with the composite video;

- the provision of the composite video enriched with enrichment data.

When the video is transmitted for enrichment, it can advantageously be transmitted with a high compression ratio so as to make the latency very low. The compression rate is adapted to the available flow. Thus, the enrichment is done almost directly or “live” in English.

One embodiment, when the user enriches the video, is described later in .

There , briefly described above illustrates the two parts of the scene and their composition by the composition process.

The video on the left represents the video capture of a first means of capture which captures the right part of a sports field, more particularly a football field. On this video are positioned 4 points of interest Llu, Lru, Lrd and Lld. These four points of interest are fixed and represent, as described above, for example, intersections of lines on a piece of land.

The hatched area on the two videos on the right and left represents a common or overlapping area of the scene, that is to say a part of the scene captured by the two video capture devices. Thus the points Lru, Rlu represent identical points of the scene and the points Lrd and Rld also represent the same point of the scene.

The video composition process will generate the composite video, seen from below the , as described previously with regard to the .

On the , the points Lld and Rrd do not coincide with the edges of the image. This represents a non-limiting version of the composite image. In other embodiments, it is envisaged that the points of interest Lld and Lrd coincide with the edges of the composite image, the latter then representing in length the length of the terrain. So the represents one of several composite images, depending on the desired zoom. We can thus envisage having a composite image including only the pitch or also the or part of the stands, or for example a buffer zone around the pitch or around certain edges of the pitch.

There represents an analysis method according to a particular embodiment of the invention in which the composite video made available during step T5 with reference to the , is transmitted to a user device. This user device can be, without limitation, a mobile phone, a computer, a tablet, a television, etc. The composite video is received on the user device during step U1. It is also decoded if it has been transmitted in an encoded manner to then be displayed on a screen of the user's device. During a step U2, the user positions information, called enrichment information, on the composite video or associates enrichment information with the composite video. The enrichment information, in the example of a football match, can for example correspond to information allowing the match to be annotated in the form of words such as "goal", "corner", "touch". They can also identify players, add personal comments from the user, add statistics on the number of successful passes, score, etc. This information as well as the composite video can then be displayed on the user's terminal , transmitted to the server for broadcast to other display terminals or recorded or both.

To do this, the user uses a user interface in an advantageous but non-limiting manner. This graphical interface can for example allow it to select predefined events corresponding to the type of scene captured. For example, when the scene is a football match, the predefined events can be "goal", "corner", "touch". The user can also associate names with players, request the compilation of statistics, etc.

If the event is a concert then it can add the title of the song, it can also position the name of the musicians, the year of the song, the title of the album, etc.

Thus, recording information is obtained or positioned based on an analysis of the scene content.

Once the enrichment data is positioned, during a step U3, the composite video and the enrichment data are synchronized if necessary.

Finally, during a step U4, the composite video enriched with enrichment information is made available.

According to a first variant, the provision consists of recording the enriched composite video so as to broadcast it subsequently, for example.

According to another variant, the provision consists of displaying the enriched composite video on the user's terminal.

According to another variant, the provision consists of transmitting the enriched composite video to a server or to one or more devices for its display or for its recording for later viewing or use.

When the server receives the enriched video, it may also compile or have analyzed the video and compare its analysis to the enrichment data to verify the latter. In the event of a conflict during verification, a validation request can be transmitted to the video analysis device and therefore to the user via the graphical interface for example.

The three variants can, of course, be combined.

The method is implemented in an analysis device and for example an analysis device as described in .

There represents a capture device configured to implement a method as described in .

The device 1 comprises capture means 11. The capture means 11 are preferably a camera such as can be found in a mobile telephone. Thus, preferably, the device 1 is a mobile telephone but can also be a computer or more generally a device equipped with capture means. The capture means capture at least part of a video scene according to a preferred embodiment.

The device 1 also includes display means 16. These display means are optional but can advantageously make it possible to view the scene captured by the capture means 11. The device 1 also includes a communication interface 14 adapted to communicate with remote devices, such as for example but not limited to a server 4. This communication interface can be cellular (3G, 4G, 5G, etc.) or WIFI or both, or even other protocols. The device 1 also includes a memory 15 containing data and program instructions and a memory 12 making it possible to record data, such as for example video data. The memory 12 can for example record temporarily or in the longer term the data captured by the capture means 11, before transmission to the communication interface 14. The device 1 comprises a processor 13 capable of cooperating with the aforementioned means of the device 1 and mainly configured to implement the method described in . The device 1 also includes an accelerometer 18, a GPS sensor 17, a magnetometer 19 and an (electronic) gyroscope 20. The GPS sensor 17 makes it possible to determine the geographical position of the capture device and the accelerometer 18 makes it possible to determine the movements of the device (the speed of movement). The gyroscope 20 makes it possible to measure the rotation of the capture device and the magnetometer 19 functions like a digital compass. Thus, the inclination, the compass, and the attitude of the capture device are measured. In addition, a log of the positions of the capture device can be kept up to date.

Before any launch of capture according to a preferred embodiment of the invention, the capture device is locked, that is to say it is positioned in a position considered as a reference position. It is therefore a physical locking which can be followed by a digital locking, making it possible to have a constant rendering, i.e. for example obtaining a video which does not have an overexposed area. During physical locking, the capture device transmits metadata obtained by the GPS sensor 17 and the accelerometer 18 which constitute the reference metadata used by the method according to the for comparison with the metadata subsequently transmitted periodically.

There describes a video composition device 4 and preferably a server type device. Thus this server can for example be located remotely or in the “computing cloud” well known in English under the term “cloud”. Furthermore, according to certain embodiments, the functions of this device can be distributed across several servers. For example, the analysis device 3 can receive the data (composite video and points of interest) from a first server and transmit the enriched video and/or the enrichment data to another server, physically different from the server which serves it. transmitted the composite video and possibly the points of interest. Likewise a third server can communicate/cooperate with either server to transmit the video at one or more additional resolutions.

The video communication device 4 comprises a processor 47 configured to implement a video composition method as described in . The processor 47 collaborates with a recording memory 43 and a program memory 44. The recording memory 43 can for example record temporarily or in the longer term the data received or transmitted by the communication interfaces 41a, 41b, 41c . The communication interfaces 41a, 41b, 41c are preferably adapted to communicate respectively with several capture devices 1, one or more analysis devices 3. The number of communication interfaces is given for illustration purposes. Such communication interfaces are preferably cellular type interfaces (3 G, 4G, 5G and future, etc.) or WIFI standard 5, 6 and future or both.

There represents a video analysis device 3 according to a preferred embodiment.

The device 3 comprises a processor 33 configured to implement a video analysis method as described in . The memory 35 includes data and program instructions of the processor 33 and the memory 32 is used to record in particular temporarily or permanently the video received through the communication interface 34 and enrichment data entered by the user by via the graphical interface 37. The communication interface 34 is preferably a cellular type interface (3 G, 4G, 5G, etc.) or WIFI or both.

There represents a system according to a preferred embodiment of the invention. Two capture devices 1a and 1b are arranged around a scene 2, here a football match. The two devices are arranged so as to each film at least part of the football field, with an overlapping zone, that is to say that each of the devices can capture more than half a field. The two devices 1a and 1b are configured to implement a capture method according to the invention and described with regard to the . The two devices 1a and 1b each transmit through their respective communication interfaces, the captured video (including in a preferred embodiment the time labels) and the metadata to the server 4. The server 4 can be composed of one or more devices distinct. The server 4 is configured to implement a video composition method according to the invention and more precisely described in . The server 4 transmits the video obtained according to the video composition method to a video analysis device 3 which enriches the video according to the analysis method described in and retransmits the enriched video and/or enrichment data and/or point of interest validation or enrichment data validation to server 4. Server 4 then records the recording data and/or annotated video or transmits them to the device 5 for display or recording or to the device 3. The device 5 is an electronic device such as for example a mobile telephone, a computer, a television.

According to a preferred embodiment, such a system can be used according to the following scenario.

The analysis device 3 receives instructions from a user to launch an application. Preferably the analysis device 3 is a mobile telephone. The application receives application settings from the user. Such a setting may for example be an indication of the type of event captured, for example a sports match, for example football. The application also receives information relating to the number of capture devices 1a, 1b used for capturing the event. Likewise, these capture devices are preferably mobile phones. The application creates a QR code for each capture device 1a, 1b.

Each of the capture devices 1a, 1b scans one of the QR codes present on the analysis device 3. This makes it possible to link each capture device to one of the flows. This allows you to launch an application on the capture devices or download the application if it was not present and then start clock synchronization using the NTP protocol. According to advantageous embodiments, the capture devices can also carry out flow tests to check the appropriate bandwidth depending on the network parameters, the type of network available (2G, 4G, 5G, WIFI standard 5, 6, etc.). .), of the environment.

The capture devices also identify themselves with the server 4 so as to allow the server 4 to detect which stream is associated with which capture device and possibly modify this.

An operator then locks the position of the capture devices around the scene by verifying that each part of the scene captured by each of the capture devices includes at least one overlapping area in which two fixed points of interest can be determined. This determination can be visual by the operator but this determination can also be made at the server level. For example, the server can transmit notifications to the capture devices to orient/move the capture devices, as long as it has not succeeded in determining common points of interest for the first time. Once common points of interest are detected, the operator locks the physical position of the capture devices. Then, as described previously, the points of interest are automatically recalculated based on the variation in the metadata. Only a significant variation in metadata no longer allowing the detection of points of interest will make it necessary to physically reposition the capture devices.

During locking, the metadata is also recorded and thus constitutes position reference metadata of the capture devices 1a, 1b. This reference metadata is used when comparing with metadata received periodically (regularly or irregularly) to determine the need for recalculation of the position of points of interest as indicated in reference to the .

There illustrates the positioning of two video capture devices 1a and 1b around a football scene. Devices 1a and 1b are similar to device 1 described in . They are positioned geographically close to the center line of the field. The device 1a is oriented towards the left part of the field and the device 1b is oriented towards the right part of the field, so that their respective capture means capture more than half of the scene, i.e. more than half a field . The capture device 1a has a capture angle α and the capture device 1b has a capture angle β. The hatched area of the shows the area of overlap of the two video captures taken by device 1a and device 1b.

There illustrates the positioning of three video capture devices 1c, 1d and 1e around a football scene. Devices 1c, 1d and 1e are similar to devices 1a and 1b described with reference to but the capture means have different capture angles. The third capture device 1e can be placed in such a way that its capture means are parallel to the touchline.

It may be necessary to use a larger number of capture devices. Particularly when two capture devices are not sufficient to fully capture an entire scene, for example because their capture angle is insufficient or because they cannot be positioned so as to cover the entire scene. Certain technical or geographical limitations may also lead to the addition of new means of capture, for example. Here, the respective capture angles γ and ε of the devices 1c and 1d being lower than the capture angles of the devices 1a and 1b, a third device 1e is added whose capture angle is µ. Thus the positioning of the three capture devices and their angles make it possible to cover the entire terrain.

There represents a system according to a second embodiment of the invention. Such a system is particularly advantageous when the capture devices 1a and 1b as well as 3 are not connected to a network such as a cellular network (3G, 4G, 5G, 6G) or WIFI. In this case, in fact, they cannot communicate with a server as illustrated in and therefore transmit the captured videos for recomposition to a server.

Such a configuration is also advantageous when the bandwidth between the capture devices 1a and 1b and the server 4 is low and does not allow the transmission of video streams and metadata to server 3 at sufficient quality.

In this embodiment, the capture devices 1a, 1b and the analysis device 3 communicate via a local network established between them. This is particularly possible through new generation WIFI networks or 5G, 6G and 6E cellular networks.

In this embodiment, the analysis device 3 synchronizes the two capture devices 1a and 1b by creating a provisional time clock which it transmits to them. The video streams from the two devices 1a and 1b can then be synchronized by the device 3.

The device 3 receives the two video streams and constructs the composite video from the two received videos and the received metadata. To do this, the device 3 implements the method according to the . Once recomposed, the video is then enriched by the device 3 according to steps U2 to U4 of the method described in .

The thus enriched video is transmitted to the server 4 when the device 3 is again connected to a cellular or WIFI network or allowing it to benefit from sufficient bandwidth for transmission. The device 3 and the server 4 can thus enrich and analyze the composite video. In the same way as previously, the server 4 can request validations of the enrichment information transmitted by the device 3 and compile statistics.

Of course, by video stream or by video, we also mean throughout the preceding description, the audio associated with this video.

Claims (13)

Video capture method comprising:
- video capture (E1a, E1b) of a scene (2),
- obtaining (E2a, E2b) at least one metadata from data associated with a fixed image of said scene (2), said metadata being representative of a geographical position of the capture device (1) at the time of 'a capture of the image,
- the transmission (E3a, E3b) of the video (2) and at least said metadata. Video capture method according to claim 1 characterized in that said metadata further comprises one or more elements chosen from:
- an inclination of the video capture device (1),
- a plate of the video capture device (1),
- a compass for the video capture device (1). Method for composing a video comprising:
- receiving (T1) from at least one first video capture device (1a) of a first video representative of a first part of a scene (2) and metadata associated with at least one still image of said first part of said scene, said metadata being representative of a geographical position of the first capture device (1a) at the time of capturing the image,
- receiving (T1) from at least one second video capture device (1b) of a second video representative of at least a second part of said scene (2) and of metadata associated with at least one still image of said second part of said scene, said metadata being representative of the geographical position of the second capture device (1b) at the time of capturing the image, said first and second videos being synchronized,
- the determination (T2) of fixed points of interest in each of said videos,
- said composition (T5) of a composite video representative of said scene from said first and at least one second videos by matching said points of interest,
- the provision (T6) of said video representative of said scene,
detecting (T3, T4) a movement of at least one of the two capture devices on the basis of the metadata received triggering a new determination (T2) of the fixed points of interest in said video captured by the moving device then said composition (T5) of a new composite video. Method according to claim 3 characterized in that the determination (T2) of fixed points of interest in each of said videos comprises:
- transmitting said first and at least second videos to at least one video analysis device (3),
- receiving from said at least one video analysis device (3), said points of interest relating to each of said parts of said scene (2). Method according to one of claims 3 to 4 characterized in that the provision (T6) comprises one or the other or more of:
- recording of said composite video,
- displaying said composite video,
- transmitting said composite video to at least one analysis device (3). Method according to claim 5 characterized in that when said composite video is transmitted to at least one analysis device (3), it further comprises
- the reception, following said transmission, of enrichment data from said scene,
- synchronization of the enrichment data with said composite video;
- making said composite video enriched with enrichment data available. Video analysis method comprising
- The reception (U1) of a composite video representative of a scene (2) obtained by a method according to one of claims 3 to 6,
- Adding (U2) enrichment data to said composite video to annotate said composite video,
- The provision (U4) of the annotated composite video and enrichment data. Analysis method according to claim 7 characterized in that obtaining the enrichment data is obtained by positioning the enrichment data by a user through a graphical interface (37). Video capture device comprising video capture means (10), a communication interface (14) with at least one server (4) and at least one processor (13) capable of implementing a method according to one of the claims 1 to 2. Server including:
- at least a first communication interface (41a) with a video capture device,
- at least a second communication interface (41b) with a video display device,
- at least one processor (47) capable of implementing a method according to one of claims 3 to 6. System comprising at least a first (1a) and a second (1b) video capture device according to claim 9, at least one server (4) according to claim 10 and at least one analysis device (3, 5) capable of implement a method according to claim 7 or 8. Computer program comprising instructions for executing the steps of the capture method according to one of claims 1 or 2 or of the method of composing a video according to one of claims 3 to 6 or of the analysis method video according to any one of claims 7 or 8 when said program is executed by a computer. Computer-readable recording medium on which is recorded a computer program comprising instructions for executing the steps of the capture method according to one of claims 1 or 2 or of the method of composing a video according to one of claims 3 to 6 or the video analysis method according to any one of claims 7 or 8.