Video processing apparatus for designating an object on a predetermined video and control method of the same, and storage medium
A video processing apparatus accepts, from a user, designation of an object on a predetermined video captured by a first real image capturing apparatus, specifies, from a plurality of second real image capturing apparatuses, an image capturing apparatus that captured a video including the designated object in an image capturing range based on three dimensional shape information corresponding to the designated object. The designated object exists in an image capturing area captured by the plurality of second real image capturing apparatuses. The video processing apparatus outputs display information including presentation of the specified image capturing apparatus.
1 . A video processing apparatus comprising:
one or more memories storing instructions; and
one or more processors for executing the instructions to:
distribute, to a user terminal, a virtual viewpoint video generated by using videos captured by a plurality of second real image capturing apparatuses;
receive, from the user terminal, information of designation of an object on a video for designation of the object by a user, wherein the video for designation of the object is not the virtual viewpoint video, the video for designation of the object is displayed on the user terminal, and the video for designation of the object is captured by a first real image capturing apparatus that is directly connected to the user terminal;
specify, from the plurality of second real image capturing apparatuses that are used for generation of the virtual viewpoint video and are connected to the video processing apparatus, a plurality of image capturing apparatuses that captured a video including the designated object in an image capturing range based on three dimensional shape information corresponding to the designated object, the designated object existing in an image capturing area captured by the plurality of second real image capturing apparatuses;
output, to the user terminal, display information including presentation of a plurality of videos, each of which is captured by the specified plurality of image capturing apparatuses;
receive selection of one of the plurality of videos captured by a respective one of the specified plurality of image capturing apparatuses; and
change a video to be distributed to the user terminal from the virtual viewpoint video to the one of the plurality of videos captured by the respective one of the specified plurality of image capturing apparatuses.
2 . The video processing apparatus according to claim 1 , wherein the display information including the presentation of the video for designation of the object in addition to the video captured by the specified image capturing apparatus is output.
3 . The video processing apparatus according to claim 1 , wherein each of the specified plurality of image capturing apparatuses is an image capturing apparatus whose image capturing range includes at least a part of a bounding box surrounding an object represented by the three dimensional shape information.
4 . The video processing apparatus according to claim 1 , wherein an image capturing range of each of the plurality of second real image capturing apparatuses is obtained based on a position and an orientation of each of the plurality of second real image capturing apparatuses.
5 . The video processing apparatus according to claim 1 , wherein the presentation further includes presentation of information for identifying the specified plurality of image capturing apparatuses.
6 . The video processing apparatus according to claim 1 , wherein the one or more processors further execute the instructions to
set an order of the specified plurality of image capturing apparatuses or a video of the respective one of the specified plurality of image capturing apparatuses based on the video of the respective one of the specified plurality of image capturing apparatuses; and
in the display information, the presentation is arranged based on the set order.
7 . The video processing apparatus according to claim 6 , wherein the order is set for the respective one of the specified plurality of image capturing apparatuses based on any one of the conditions of setting a higher order as the size of the object appearing in the video becomes larger; setting a higher order to a video in which the object appearing in the video is facing front; and setting a higher order as the position of the object appearing in the video becomes closer to the center of the video.
8 . The video processing apparatus according to claim 1 , wherein the one or more processors further execute the instructions to
classify the specified plurality of image capturing apparatuses into groups of image capturing apparatuses that have captured similar videos by quantifying size or position of an object in the image, and determine one image capturing apparatus for each group; and
the display information includes presentation of the determined one image capturing apparatus.
9 . The video processing apparatus according to claim 1 , wherein the one or more processors further execute the instructions to
specify, from preset virtual viewpoints, a virtual viewpoint from which a virtual viewpoint video including the object designated by the user is generated; and
the display information includes presentation of the specified image capturing apparatus and presentation of the specified virtual viewpoint.
10 . The video processing apparatus according to claim 9 , wherein the presentation of the image capturing apparatus and the virtual viewpoint according to the display information enables a user to distinguish whether the presentation is the image capturing apparatus or the virtual viewpoint.
11 . The video processing apparatus according to claim 9 , wherein the one or more processors further execute the instructions to
switch a video to be distributed to a video of an image capturing apparatus or a virtual viewpoint selected by a user from the image capturing apparatuses and the virtual viewpoints presented according to the display information.
12 . A control method of a video processing apparatus, the method comprising:
distributing, to a user terminal, a virtual viewpoint video generated by using videos captured by a plurality of second real image capturing apparatuses;
receiving, from the user terminal, information of designation of an object on a video for designation of the object by a user, wherein the video for designation of the object is not the virtual viewpoint video, the video for designation of the object is displayed on the user terminal, and the video for designation of the object is captured by a first real image capturing apparatus that is directly connected to the user terminal;
specifying, from the plurality of second real image capturing apparatuses that are used for generation of the virtual viewpoint video and are connected to the video processing apparatus, a plurality of image capturing apparatuses that captured a video including the designated object in an image capturing range based on three dimensional shape information corresponding to the designated object, the designated object existing in an image capturing area captured by the plurality of second real image capturing apparatuses;
outputting, to the user terminal, display information including presentation of a plurality of videos, each of which is captured by the specified plurality of image capturing apparatuses;
receiving selection of one of the plurality of videos captured by a respective one of the specified plurality of image capturing apparatuses; and
changing a video to be distributed to the user terminal from the virtual viewpoint video to the one of the plurality of videos captured by the respective one of the specified plurality of image capturing apparatuses.
13 . A non-transitory computer-readable storage medium storing a program for causing a computer to execute a method for controlling a video processing apparatus, the control method comprising:
distributing, to a user terminal, a virtual viewpoint video generated by using videos captured by a plurality of second real image capturing apparatuses;
receiving, from the user terminal, information of designation of an object on a video for designation of the object by a user, wherein the video for designation of the object is not the virtual viewpoint video, the video for designation of the object is displayed on the user terminal, and the video for designation of the object is captured by a first real image capturing apparatus that is directly connected to the user terminal;
specifying, from the plurality of second real image capturing apparatuses that are used for generation of the virtual viewpoint video and are connected to the video processing apparatus, a plurality of image capturing apparatuses that captured a video including the designated object in an image capturing range based on three dimensional shape information corresponding to the designated object, the designated object existing in an image capturing area captured by the plurality of second real image capturing apparatuses;
outputting, to the user terminal, display information including presentation of a plurality of videos, each of which is captured by the specified plurality of image capturing apparatuses;
receiving selection of one of the plurality of videos captured by a respective one of the specified plurality of image capturing apparatuses; and
changing a video to be distributed to the user terminal from the virtual viewpoint video to the one of the plurality of videos captured by the respective one of the specified plurality of image capturing apparatuses.