CN116761040A

CN116761040A - VR cloud platform interaction method and interaction system

Info

Publication number: CN116761040A
Application number: CN202311054985.1A
Authority: CN
Inventors: 王磊; 张继洲; 闫京坤
Original assignee: Super Core Jiangsu Intelligent Technology Co ltd
Current assignee: Super Core Jiangsu Intelligent Technology Co ltd
Priority date: 2023-08-22
Filing date: 2023-08-22
Publication date: 2023-09-15
Anticipated expiration: 2043-08-22
Also published as: CN116761040B

Abstract

The invention provides a VR cloud platform interaction method and an interaction system, which are used for obtaining an interaction sub-video and an interaction time period according to interception information of a VR interaction video by a video frame group; responding to the fixed configuration information, and configuring the fixed gesture slot based on the first interactive gesture and the first preset time length to obtain a fixed coherent gesture; responding to the adjustment configuration information, and configuring the adjustment gesture slot position based on the second interaction gesture and a preset adjustment identification tag to obtain a dynamic adjustment gesture; determining lecturer equipment and student equipment according to the classification information, and selecting fixed coherent gestures and/or dynamic adjustment gestures of each interaction sub-video to obtain a lecturer interaction set and a student interaction set; and acquiring gesture images at the lecturer equipment and the student equipment to obtain lecturer instruction gestures and student instruction gestures, determining lecturer control instructions and student control instructions, and controlling VR interactive videos based on the lecturer control instructions and/or the student control instructions.

Description

VR cloud platform interaction method and interaction system

Technical Field

The invention relates to a data processing technology, in particular to a VR cloud platform interaction method and an interaction system.

Background

Virtual reality technology (abbreviated as VR), also known as virtual reality or smart technology, can show 360 degrees panoramic shots for users, makes users personally on the scene, and with the continuous development of social productivity and scientific technology, various industries are more mature in application of VR technology, such as travel, education and the like in service industry, and can provide various VR interactive videos for users.

In the prior art, when a user plays VR interactive video, the user can control the VR interactive video by means of a handle controller, a wearable device and the like, when the video is played to a key point in the video, a lecturer and the user can control the video, when the video is controlled, a control gesture preset by a VR cloud platform is needed, but customization setting cannot be realized for different contents in the VR interactive video, so that user experience is reduced.

Therefore, how to customize gestures according to different video contents in the VR interactive video, so as to improve the experience of the user, is a problem to be solved.

Disclosure of Invention

The embodiment of the invention provides a VR cloud platform interaction method and an interaction system, which can customize gestures according to different video contents in VR interaction videos, so that the experience of a user is improved.

In a first aspect of an embodiment of the present invention, a VR cloud platform interaction method is provided, including:

receiving selected information of a management terminal on VR interactive videos to obtain a plurality of groups of video frame groups comprising prompt frames and cut-off frames, and obtaining a plurality of interactive sub-videos and interaction time periods corresponding to the interactive sub-videos according to interception information of the video frame groups on the VR interactive videos;

responding to the fixed configuration information of the management end on each interactive sub-video, calling a plurality of fixed gesture slots, continuously acquiring a plurality of first interactive gestures of the management end based on an image acquisition device, and configuring the fixed gesture slots based on the first interactive gestures and a first preset duration to obtain fixed coherent gestures corresponding to the interactive sub-video;

responding to adjustment configuration information of the management end on each interactive sub-video, adjusting the adjustment gesture slot position, controlling the image acquisition device to acquire a second interactive gesture of the management end, and configuring the adjustment gesture slot position based on the second interactive gesture and a preset adjustment identification tag to obtain a dynamic adjustment gesture of the corresponding interactive sub-video;

the VR equipment diagram is called and sent to a management end, according to the classification information of the management end, lecturer equipment and student equipment are determined, fixed coherent gestures and/or selection information of dynamic adjustment gestures of each interaction sub-video are received by the management end, a lecturer interaction set and a student interaction set corresponding to each interaction sub-video are obtained, the lecturer interaction set is configured to the lecturer equipment, and the student interaction set is configured to the student equipment;

When the current frame in the VR interactive video is determined to be in the interactive time period, the image acquisition device is controlled to acquire gesture images of the lecturer equipment and the student equipment, a lecturer instruction gesture and a student instruction gesture are obtained, a lecturer control instruction is determined according to comparison of the lecturer instruction gesture and a lecturer interactive set, a student control instruction is determined according to comparison of the student instruction gesture and the student interactive set, and the VR interactive video is controlled based on the lecturer control instruction and/or the student control instruction.

Optionally, in one possible implementation manner of the first aspect, the continuously collecting, based on the image collecting device, the plurality of first interaction gestures of the management end, configuring a fixed gesture slot based on the first interaction gestures and a first preset duration, to obtain a fixed coherent gesture corresponding to the interaction sub-video, including:

and continuously acquiring a plurality of first interaction gestures of the management end based on the image acquisition device, sequentially placing the first interaction gestures in the fixed gesture slots, and configuring a first preset time length to all the fixed gesture slots to obtain fixed coherent gestures corresponding to the interaction sub-video.

Optionally, in a possible implementation manner of the first aspect, the determining the lecturer control instruction according to a comparison between the lecturer instruction gesture and the lecturer interaction set includes:

When the lecturer instruction gesture is detected in real time in the interaction time period, taking a first lecturer instruction gesture after a first preset time interval as a lecturer trigger gesture, and sequentially detecting a next lecturer instruction gesture as a relay lecturer instruction gesture based on the first preset time interval;

screening the fixed coherent gestures and/or the dynamic adjustment gestures in the lecturer interaction set for one time according to the lecturer triggering gestures to obtain a current lecturer interaction set;

if the lecturer trigger gesture is a first interactive gesture, a lecturer gesture set is obtained according to the lecturer trigger gesture and a plurality of relay lecturer instruction gestures, a fixed matching gesture is determined based on the lecturer gesture set and the current lecturer interaction set, and a lecturer control instruction is obtained according to the fixed matching gesture, wherein the fixed coherent gesture corresponds to a preset control instruction one by one;

and if the lecturer trigger gesture is a second interaction gesture, obtaining a lecturer control gesture according to the dynamic adjustment gesture.

Optionally, in one possible implementation manner of the first aspect, if the lecturer trigger gesture is the second interaction gesture, the lecturer control instruction is obtained according to the dynamic adjustment gesture, including:

If the lecturer triggers the gesture to correspond to the second interaction gesture, acquiring a regulating gesture slot position in the corresponding dynamic regulating gesture as a current regulating gesture slot position, and taking a preset regulating identification tag corresponding to the current regulating gesture slot position as a current regulating identification tag;

if the attribute of the current adjustment identification tag is an angle type, invoking an angle control strategy control image acquisition device to acquire a lecturer instruction gesture at a lecturer device in a preset judging time period as a judging gesture, and determining a lecturer control gesture according to the lecturer triggering gesture and the judging gesture;

and if the attribute of the current adjustment identification tag is a duration type, acquiring a plurality of lecturer instruction gestures at the lecturer equipment by the duration control strategy control image acquisition device in real time as judgment gestures, and determining the lecturer control gestures according to the lecturer triggering gestures and the judgment gestures.

Optionally, in one possible implementation manner of the first aspect, the retrieving an instruction gesture of a lecturer at a lecturer device within a preset judgment duration is collected by the angle control policy control image collecting device as a judgment gesture, and the lecturer control instruction is determined according to the lecturer trigger gesture and the judgment gesture, including:

Taking an acquired image corresponding to the lecturer triggering gesture as a first image, extracting a first moment for acquiring the first image, and controlling the image acquisition device to acquire a plurality of acquired images corresponding to the judging gesture in real time as second images according to the first moment and a preset judging duration;

acquiring a first angle value corresponding to the lecturer triggering gesture in the first image and a second angle value corresponding to the judging gesture in the plurality of second images, obtaining a plurality of angle difference values according to the first angle value and the plurality of second angle values, taking the largest angle difference value as a target angle difference value, and taking the judging gesture corresponding to the target angle difference value as a target judging gesture;

determining the relative position of the lecturer trigger gesture and the target judgment gesture, obtaining a backward instruction or a forward instruction according to the relative position, and determining instruction duration based on the target angle difference value;

and determining a lecturer control instruction according to the backward instruction or the forward instruction and the instruction duration.

Optionally, in one possible implementation manner of the first aspect, the acquiring a first angle value corresponding to the lecturer trigger gesture in the first image and a second angle value corresponding to the judgment gesture in the plurality of second images includes:

Carrying out coordinated processing on the first image, extracting a first hand coordinate set of a first hand outline of the lecturer trigger gesture in the first image, and acquiring an intersection point of the lecturer trigger gesture and the lower edge of the first image to obtain a first intersection coordinate set;

acquiring a first center point coordinate of the first hand coordinate set and a first middle point coordinate of the first intersecting coordinate set, obtaining a first slope value according to the first center point coordinate and the first middle point coordinate, and obtaining a first angle value based on the first slope value;

performing coordinated processing on a plurality of second images, extracting a second hand coordinate set of a second hand outline of the judgment gesture in the second images, and acquiring an intersection point of the judgment gesture and the lower edge of the second images to obtain a second intersection coordinate set;

and obtaining a second central point coordinate of the second hand coordinate set and a second middle point coordinate of the second intersecting coordinate set, obtaining a second slope value corresponding to a plurality of second images according to the second central point coordinate and the second middle point coordinate, and obtaining a plurality of second angle values based on a plurality of second slope values.

Optionally, in a possible implementation manner of the first aspect, the acquiring a first center point coordinate of the first hand coordinate set and a first intermediate point coordinate of the first intersecting coordinate set includes:

obtaining a first central point abscissa according to the maximum value and the minimum value of the abscissas in the first hand coordinate set, obtaining a first central point ordinate according to the maximum value and the minimum value of the abscissas in the first hand coordinate set, and obtaining a first central point coordinate according to the first central point abscissa and the first central point ordinate;

and obtaining a first intermediate point abscissa according to the maximum value and the minimum value of the abscissas in the first intersecting coordinate set, obtaining the intersecting ordinate in the first intersecting coordinate set, and obtaining a first intermediate point coordinate according to the intersecting ordinate and the first intermediate point abscissa.

Optionally, in one possible implementation manner of the first aspect, the determining a relative position of the lecturer trigger gesture and the target judgment gesture, obtaining a backward instruction or a forward instruction according to the relative position, and determining an instruction duration based on the target angle difference value includes:

Acquiring a first center point coordinate corresponding to the lecturer triggering gesture and a second center point coordinate corresponding to the target judging gesture;

when the abscissa of the first center point coordinate is determined to be larger than the abscissa of the second center point coordinate, a backward instruction is obtained;

when the abscissa of the first center point coordinate is determined to be smaller than the abscissa of the second center point coordinate, a forward instruction is obtained;

and obtaining a time length adjustment coefficient according to the ratio of the target angle difference value to a preset reference angle, and adjusting the preset reference time length according to the time length adjustment coefficient to obtain the instruction time length.

Optionally, in one possible implementation manner of the first aspect, the retrieving duration control policy control image capturing device captures, in real time, a plurality of lecturer instruction gestures at a lecturer device as judgment gestures, and determines a lecturer control instruction according to the lecturer trigger gesture and the judgment gesture, including:

taking an acquired image corresponding to the lecturer trigger gesture as a first image, carrying out coordinate processing on the first image, extracting a first hand coordinate set of a first hand outline of the lecturer trigger gesture in the first image, and obtaining a first center point coordinate of the first hand coordinate set;

Controlling the image acquisition device to acquire a plurality of acquired images corresponding to the judgment gestures in real time as a second image, carrying out coordinate processing on the second image, extracting a second hand coordinate set of a second hand outline of the lecturer trigger gesture in the second image, and acquiring a second center point coordinate of the second hand coordinate set;

when the abscissa of the first center point coordinate is determined to be larger than the abscissa of the second center point coordinate, a backward instruction is obtained, and when the abscissa of the first center point coordinate is determined to be smaller than the abscissa of the second center point coordinate, a forward instruction is obtained;

acquiring the duration of the judgment gesture which is the same as the duration of the lecturer triggering gesture, obtaining a first duty ratio according to the ratio of the duration to the preset duration, and obtaining a command duration according to the product of the first duty ratio and the preset command duration;

In a second aspect of an embodiment of the present invention, there is provided a VR cloud platform interaction system, including:

the selection module is used for receiving the selected information of the VR interactive video from the management end, obtaining a plurality of groups of video frame groups comprising prompt frames and cut-off frames, and obtaining a plurality of interactive sub-videos and interaction time periods corresponding to the interactive sub-videos according to the intercepted information of the VR interactive video from the video frame groups;

The fixed configuration module is used for responding to the fixed configuration information of the management end on each interactive sub-video, calling a plurality of fixed gesture slots, continuously collecting a plurality of first interactive gestures of the management end based on the image collecting device, and configuring the fixed gesture slots based on the first interactive gestures and a first preset duration to obtain fixed coherent gestures of the corresponding interactive sub-video;

the adjusting configuration module is used for responding to adjusting configuration information of the management end on each interactive sub-video, adjusting the gesture slot position, controlling the image acquisition device to acquire a second interactive gesture of the management end, and configuring the gesture slot position based on the second interactive gesture and a preset adjusting identification tag to obtain a dynamic adjusting gesture of the corresponding interactive sub-video;

the classification module is used for retrieving the VR equipment graph and sending the VR equipment graph to the management end, determining lecturer equipment and student equipment according to classification information of the management end, receiving selection information of fixed coherent gestures and/or dynamic adjustment gestures of the management end on each interactive sub-video, obtaining a lecturer interaction set and a student interaction set corresponding to each interactive sub-video, configuring the lecturer interaction set to the lecturer equipment and configuring the student interaction set to the student equipment;

And the control module is used for determining that when the current frame in the VR interactive video is in the interaction time period, the image acquisition device is controlled to acquire gesture images of the lecturer equipment and the student equipment, obtain lecturer instruction gestures and student instruction gestures, determine lecturer control instructions according to comparison of the lecturer instruction gestures and the lecturer interaction set, determine student control instructions according to comparison of the student instruction gestures and the student interaction set, and control the VR interactive video based on the lecturer control instructions and/or the student control instructions.

The beneficial effects of the invention are as follows:

1. according to the invention, 3-step customization processing is performed on the VR interactive video, so that customization control can be performed according to user requirements and the playing content of the video when the VR interactive video is controlled, and the user experience is improved while the control is facilitated. Selecting corresponding video segments according to VR interactive videos to obtain a plurality of interactive sub-videos and interactive time periods, configuring corresponding 2 types of gestures for each interactive sub-video, namely a fixed coherent gesture and a dynamic adjustment gesture, and customizing and configuring corresponding gestures for the interactive sub-videos according to the requirements of users; the second step, corresponding gesture sets are configured for corresponding lecturer equipment and student equipment according to demands of lectures and students, different gestures are configured for different equipment, so that respective controllable instructions are different, and the third step, when the interaction time period is in, control of VR interaction videos can be achieved, overall play smoothness of the VR interaction videos is guaranteed, the sections requiring explanation and the like are controlled, and customization processing is conducted on the controllable time period. The invention can carry out customization processing of 3 dimensions according to VR interactive video and the requirement of the user, is convenient for the user to control and improves the experience of the user.

2. According to the method and the device for controlling the interactive video, gestures of a lecturer and a student are identified, corresponding control instructions are determined, and when the gestures are judged to be dynamically adjusted, the adjusted time length is automatically identified, so that the operation complexity is reduced, and the user can conveniently control the interactive video. According to the method, the fixed coherent gesture and the dynamic adjustment gesture are identified through the triggering gesture, and when the fixed coherent gesture is judged, the current lecturer interaction set obtained by screening the triggering gesture is compared with the lecturer gesture set, so that corresponding control instructions are determined. When the dynamic adjustment gesture is judged, the corresponding 2 control strategies are called according to the preset adjustment identification tag in the adjustment gesture slot, and the video adjustment direction and the time length are identified through the angle control strategy and the time length control strategy respectively, so that the user can conveniently control the video adjustment direction and the time length. The invention can identify the direction and time length required to be regulated by a user by adopting an angle control strategy, and can determine the corresponding time length by determining the maximum arm rotation angle according to the angle difference value between the angle in the corresponding first graph and the angle in the corresponding second graph according to the connecting line of the arm at the center point of the edge of the picture and the center point of the palm according to the first image and the plurality of acquired second images corresponding to the triggering gesture, and the invention determines the video advance or retreat instruction and the instruction time length of the corresponding instruction by comparing the coordinate values. The method and the device can identify the direction and the duration required to be regulated by the user by adopting a duration control strategy, identify the duration corresponding to the duration continuously maintained by statistics when the duration triggering gesture occurs, so as to obtain the instruction duration, and determine the forward or backward instruction through the comparison of coordinate values.

Drawings

Fig. 1 is a flowchart of a VR cloud platform interaction method provided by the present invention;

FIG. 2 is a schematic diagram of a gesture of a first image according to the present invention;

FIG. 3 is a schematic diagram of a gesture of a second image according to the present invention;

fig. 4 is a schematic structural diagram of a VR cloud platform interaction system provided by the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein.

It should be understood that, in various embodiments of the present invention, the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

It should be understood that in the present invention, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that in the present invention, "plurality" means two or more. "and/or" is merely an association relationship describing an association object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "comprising A, B and C", "comprising A, B, C" means that all three of A, B, C comprise, "comprising A, B or C" means that one of the three comprises A, B, C, and "comprising A, B and/or C" means that any 1 or any 2 or 3 of the three comprises A, B, C.

It should be understood that in the present invention, "B corresponding to a", "a corresponding to B", or "B corresponding to a" means that B is associated with a, from which B can be determined. Determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information. The matching of A and B is that the similarity of A and B is larger than or equal to a preset threshold value.

As used herein, "if" may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to detection" depending on the context.

The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.

The invention provides a VR cloud platform interaction method, as shown in figure 1, comprising the following steps of S1-S5:

s1, receiving selected information of a management end on VR interactive videos, obtaining a plurality of groups of video frame groups comprising prompt frames and cut-off frames, and obtaining a plurality of interactive sub-videos and interaction time periods corresponding to the interactive sub-videos according to interception information of the video frame groups on the VR interactive videos.

It should be noted that, the VR interactive video is composed of a plurality of video content segments, the video playing durations corresponding to different content are different, the pictures displayed by the content are different, and the complexity of the content is different, for example, when the VR interactive video is applied to the tourism industry, the video interactive video needs to be introduced to each scenic spot in the scenic spot, the introduction durations corresponding to different scenic spots are different, the side points of the introduction are different, and the like, so that corresponding different functions can be set according to the actual situation of the video segment corresponding to each scenic spot, and the different functions correspond to different gestures.

For example, a sub-video for a segment a in an interactive video may allow a lecturer to pause, start, allow a student to pause, and a sub-video for a segment B in the corresponding interactive video may allow the lecturer to fast forward, pause, not allow the student to operate.

It can be understood that the management end can sequentially select any video segment in the VR interactive video, take the video frame selected first as a prompt frame, take the video frame selected later as a cut-off frame, thereby obtaining a group of video frames, obtain a plurality of groups of video frames through multiple selections of the management end, and obtain a plurality of interactive sub-videos and interaction time periods corresponding to the interactive sub-videos according to interception information of the VR interactive video by the video frame groups. For example, the video duration is 1 hour and 50 minutes, and the interaction time period for capturing the A sub-video is 15 minutes-17 minutes.

According to the embodiment, the VR interactive video can be divided into the plurality of interactive sub-videos according to the requirements of the user, corresponding gestures are customized for each video according to the actual requirements of the user conveniently, and meanwhile, when the video is played to the prompt frame, corresponding prompt frames can be generated to display corresponding gestures, instructions and operable real-time for the user, and the details are omitted in the prior art.

S2, responding to the fixed configuration information of the management end to each interactive sub-video, calling a plurality of fixed gesture slots, continuously collecting a plurality of first interactive gestures of the management end based on the image collecting device, and configuring the fixed gesture slots based on the first interactive gestures and a first preset duration to obtain fixed coherent gestures corresponding to the interactive sub-video.

The fixed configuration information is configuration information for configuring a fixed operation for the VR interactive video, for example, information for configuring corresponding gestures for the fixed operation such as pause and start. The fixed gesture slot is a slot for configuring a gesture corresponding to the fixed operation. The first preset duration is the duration of the pre-facilities according to the artificial condition.

It can be understood that after the fixed configuration information of each interactive sub-video is responded, a plurality of fixed gesture slots are called, corresponding gestures can be placed in each fixed gesture slot, so that a coherent gesture is formed, a plurality of first interactive gestures of the management end are continuously collected based on the image collecting device, the fixed gesture slots are configured according to the first interactive gestures and a first preset duration, and the fixed coherent gestures corresponding to the interactive sub-video are obtained.

The fixed coherent gestures are coherent gestures corresponding to fixed operations.

Through the embodiment, the fixed coherent gestures corresponding to the corresponding fixed operations of each interactive sub-video configuration are completed, and each fixed coherent gesture corresponds to corresponding instructions, such as pause, start and the like, so that gesture customization processing of the interactive sub-video is performed.

In some embodiments, in step S2 (based on the image capturing device continuously capturing the plurality of first interaction gestures of the management end, configuring a fixed gesture slot based on the first interaction gestures and a first preset duration, and obtaining a fixed coherent gesture corresponding to the interaction sub-video), the method includes:

It can be understood that the image acquisition device continuously acquires the plurality of first interaction gestures of the management end, sequentially places the first interaction gestures in the fixed gesture slots, and configures a first preset time period, such as 10 seconds, 15 seconds, and the like, for each fixed gesture slot, so that gestures exceeding 10 seconds are not recorded, and thus fixed coherent gestures corresponding to the interaction sub-video are obtained.

For example, by sequentially recording a plurality of first interaction gestures of the management end, for example, recording gestures of stones and scissors and sequentially filling the gestures into the slots, the gestures exist in the sequence of the stones and the scissors, and a recognition duration of 10 seconds is configured for each fixed gesture slot, and gestures after 10 seconds are not recorded as a group of gestures.

Through the embodiment, the corresponding fixed coherent gestures for the mutual sub-video configuration are completed, the fixed coherent gestures are composed of a plurality of gestures, and a user can conveniently control the video.

And S3, responding to the adjustment configuration information of the management end to each interactive sub-video, calling the adjustment gesture slot position, controlling the image acquisition device to acquire a second interactive gesture of the management end, and configuring the adjustment gesture slot position based on the second interactive gesture and a preset adjustment identification tag to obtain a dynamic adjustment gesture of the corresponding interactive sub-video.

It will be appreciated that there are adjustable operations such as advancing, reversing, etc. the video in addition to fixed operations such as starting, pausing, etc.

Therefore, the method and the device can respond to the adjustment configuration information of the management end on each interactive sub-video, call the adjustment gesture slot position, control the image acquisition device to acquire the second interactive gesture of the management end, fill the second interactive gesture into the adjustment gesture slot position, and configure the adjustment gesture slot position by the preset adjustment identification tag, so that the dynamic adjustment gesture of the corresponding interactive sub-video is obtained.

The adjusting configuration information is configuration information for VR interactive video configuration adjustment operation, the adjusting gesture slot is a slot of a gesture corresponding to the configuration adjustment operation, and the adjusting gesture slot is one.

It can be understood that a corresponding adjustment gesture can be configured for each interactive sub-video, so that a user can conveniently adjust the video, for example, the user can go forward for 10 seconds, go backward for 10 seconds and the like, when the gesture of the subsequent user is consistent with the second interactive gesture, a preset adjustment identification tag can be called, a corresponding execution code is called according to the preset adjustment identification tag, the user gesture is identified, the video is adjusted, the user can conveniently and accurately adjust the video, and compared with the complexity of the operation of dragging and reducing the video frame in the prior art, the user can more accurately adjust the video according to the requirement of the user. When the dynamic adjustment gesture and the fixed coherent gesture are set, automatic traversal is performed to check whether gesture repetition occurs, and if the repeated gesture occurs, the user is reminded.

And S4, calling a VR equipment diagram, sending the VR equipment diagram to a management end, determining lecturer equipment and student equipment according to classification information of the management end, receiving selection information of fixed coherent gestures and/or dynamic adjustment gestures of the management end on each interactive sub-video, obtaining a lecturer interaction set and a student interaction set corresponding to each interactive sub-video, configuring the lecturer interaction set to the lecturer equipment, and configuring the student interaction set to the student equipment.

It will be appreciated that, for all VR devices, there is a failure to sit full, so that VR device diagrams may be configured according to the actual number of people and the number of people of the corresponding lecturer, so that the devices are classified into lecturer devices and student devices, and corresponding gestures may be selected from the previously customized gestures to be configured to the corresponding lecturer and student, so as to obtain a lecturer interaction set and a student interaction set corresponding to each interaction sub-video, configure the lecturer interaction set to the lecturer devices, and configure the student interaction set to the student devices.

The lecturer interaction set is a gesture set corresponding to the fixed coherent gesture and/or the dynamic adjustment gesture of the management end for each interaction sub-video after selection. The student interaction set is a corresponding gesture set after receiving fixed coherent gestures and/or dynamic adjustment gestures of the management end on each interaction sub-video

S5, when the current frame in the VR interactive video is in the interaction time period, the image acquisition device is controlled to acquire gesture images of the lecturer equipment and the student equipment, a lecturer instruction gesture and a student instruction gesture are obtained, a lecturer control instruction is determined according to comparison of the lecturer instruction gesture and a lecturer interaction set, a student control instruction is determined according to comparison of the student instruction gesture and the student interaction set, and the VR interactive video is controlled based on the lecturer control instruction and/or the student control instruction.

It can be understood that when the current frame in the VR interactive video is in the interactive time period, the image acquisition device is controlled to acquire gesture images at the lecturer device and the student device at the moment, and it is easy to understand that only students and lectures can control the VR interactive video in the interactive time period, so that smoothness of video playing is ensured, and simultaneously the lectures and students can operate the video to discuss, read and the like the played video content.

Specifically, when the current frame in the VR interactive video is in the interactive time period, the image acquisition device is controlled to acquire gesture images of the lecturer equipment and the student equipment, the lecturer instruction gesture is compared with the lecturer interactive set, the lecturer control instruction is determined, the student instruction gesture is compared with the student interactive set, the student control instruction is determined, and the VR interactive video is controlled through the teacher control instruction and/or the student control instruction.

In some embodiments, in step S5 (determining lecturer control instructions based on a comparison of lecturer instruction gestures with lecturer interaction sets), steps S51-S54:

and S51, when the lecturer instruction gesture is detected in real time in the interaction time period, taking the first lecturer instruction gesture after a first preset time interval as a lecturer trigger gesture, and sequentially detecting the next lecturer instruction gesture as a relay lecturer instruction gesture based on the first preset time interval.

It can be understood that when the lecturer instruction gesture is detected in real time in the interaction time period, the first lecturer instruction gesture after a first preset time interval is taken as a lecturer trigger gesture, and the detected first lecturer instruction gesture is taken as a lecturer trigger gesture, and it is easy to understand that the gesture after the first preset time interval does not count into the upper group gesture, and the invalid gesture and the error gesture can be avoided by setting the first preset time interval, so that the user can cancel the corresponding instruction by himself. And the gestures within the first preset time period are recorded in sequence, for example, every time the gestures are recorded, the next gesture is recorded within 10 seconds.

For example, the triggering gesture is a stone gesture, a scissor gesture appears after 10 seconds, and the triggering gesture is not recorded as a group, if the scissor gesture appears within 10 seconds, the stone is a lecturer triggering gesture, the scissors are relay lecturer instruction gestures, wherein the lecturer triggering gesture is the first gesture of the user, and the relay lecturer instruction gestures are subsequent gestures of the lecturer triggering gesture.

Through the embodiment, the real-time gesture action of the lecturer is decomposed into the lecturer triggering gesture and the relay lecturer instruction gesture, so that the corresponding fixed coherent gesture or dynamic adjustment gesture can be conveniently determined according to the lecturer triggering gesture, and it is easy to understand that the first gesture action in the fixed coherent gesture and the dynamic adjustment gesture is inconsistent.

S52, screening the fixed coherent gestures and/or the dynamic adjustment gestures in the lecturer interaction set for one time according to the lecturer trigger gestures to obtain the current lecturer interaction set.

It can be understood that the fixed coherent gesture and/or the dynamic adjustment gesture in the lecturer interaction set is screened once according to the lecturer trigger gesture, so that the current lecturer interaction set is obtained, and it is easy to understand that the first interaction gesture in the fixed coherent gesture is inconsistent with the first interaction gesture in the dynamic adjustment gesture, so that the fixed coherent gesture and/or the dynamic adjustment gesture in the lecturer interaction set can be screened according to the lecturer trigger gesture, and the current lecturer interaction set is obtained.

For example, when the first gesture of the lecturer is a stone, a fixed coherent gesture with the first gesture being a stone and/or a dynamic adjustment gesture, for example, the first gesture of the dynamic adjustment gesture is a cloth, are selected from the lecturer interaction set according to the stone, so that the server can select a plurality of fixed coherent gestures with the first gesture being a stone from a plurality of fixed coherent gestures according to the first gesture of the user as a stone, thereby reducing the data volume of subsequent comparison.

S53, if the lecturer trigger gesture is a first interactive gesture, a lecturer gesture set is obtained according to the lecturer trigger gesture and a plurality of relay lecturer instruction gestures, a fixed matching gesture is determined based on the lecturer gesture set and the current lecturer interaction set, and a lecturer control instruction is obtained according to the fixed matching gesture, wherein the fixed coherent gesture corresponds to a preset control instruction one by one.

It may be appreciated that if the lecturer trigger gesture is the first interactive gesture, it is explained that the lecturer wants to execute a fixed operation, a lecturer gesture set is obtained according to the lecturer trigger gesture and the plurality of relay lecturer instruction gestures, the lecturer gesture set is compared with the current lecturer interactive set, a corresponding fixed coherent gesture is determined to be a fixed matching gesture, and a lecturer control instruction is obtained according to the fixed matching gesture, wherein the fixed coherent gesture corresponds to a preset control instruction one by one.

And S54, if the lecturer trigger gesture is a second interaction gesture, obtaining a lecturer control gesture according to the dynamic adjustment gesture.

It can be understood that if the lecturer triggers the gesture to be the second interaction gesture, the lecturer is instructed to execute the adjustment operation, and the lecturer control instruction is obtained according to the dynamic adjustment gesture.

In some embodiments, in step S54 (if the lecturer trigger gesture is the second interaction gesture, the lecturer control instruction is obtained according to the dynamic adjustment gesture), including S541-S543:

and S541, if the lecturer triggers that the gesture corresponds to the second interactive gesture, acquiring a regulating gesture slot in the corresponding dynamic regulating gesture as a current regulating gesture slot, and taking a preset regulating identification tag corresponding to the current regulating gesture slot as a current regulating identification tag.

It can be appreciated that if the lecturer triggers the gesture to correspond to the second interaction gesture, a corresponding dynamic adjustment gesture is obtained, the adjustment gesture slot in the corresponding dynamic adjustment gesture is used as the current adjustment gesture slot, and a preset adjustment identification tag in the current adjustment gesture slot is obtained as the current adjustment identification tag.

It is easy to understand that after the corresponding dynamic adjustment gesture is determined according to the lecturer trigger gesture, a preset adjustment identification tag in the dynamic adjustment gesture is obtained and used as a current adjustment identification tag, wherein the preset adjustment identification tag is a manually preset tag, and each preset adjustment identification tag corresponds to a corresponding control strategy, so that the subsequent gesture recognition of a user is facilitated, and the adjustment control of the video is performed.

S542, if the attribute of the current adjustment identification tag is an angle type, invoking an angle control strategy to control the image acquisition device to acquire a lecturer instruction gesture at the lecturer equipment within a preset judging time period as a judging gesture, and determining a lecturer control instruction according to the lecturer triggering gesture and the judging gesture.

It can be understood that if the attribute of the pre-adjustment identification tag is an angle type, the angle control strategy is invoked to control the image acquisition device to acquire all instruction gestures of the lecturer at the lecturer device within a preset judgment time period as judgment gestures, and the instruction gestures are processed according to the trigger gestures and the judgment gestures to determine the lecturer control instructions.

In some embodiments, in step S542 (the capturing angle control policy controls the image capturing device to capture a lecturer instruction gesture at the lecturer device within a preset determination period as a determination gesture, and determines a lecturer control instruction according to the lecturer trigger gesture and the determination gesture), including S5421-S5424:

s5421, taking an acquired image corresponding to the lecturer triggering gesture as a first image, extracting a first moment for acquiring the first image, and controlling the image acquisition device to acquire a plurality of acquired images corresponding to the judging gesture in real time as second images according to the first moment and a preset judging duration.

S5422, obtaining a first angle value corresponding to the lecturer trigger gesture in the first image and a second angle value corresponding to the judgment gesture in the second images, obtaining a plurality of angle differences according to the first angle value and the second angle values, taking the maximum angle difference as a target angle difference, and taking the judgment gesture corresponding to the target angle difference as a target judgment gesture.

It can be understood that the lecturer triggers the gesture to process to obtain a corresponding first angle value in the first image, processes the judging gesture to obtain a corresponding second angle value in the second images, obtains a plurality of angle differences according to the first angle value and the second angle values, uses the largest angle difference as a target angle difference, and uses the judging gesture corresponding to the target angle difference as a target judging gesture.

In some embodiments, in step S5422 (obtaining a first angle value corresponding to the lecturer trigger gesture in the first image and a second angle value corresponding to the judgment gesture in the plurality of second images) includes:

and carrying out coordinated processing on the first image, extracting a first hand coordinate set of a first hand outline of the lecturer trigger gesture in the first image, and acquiring an intersection point of the lecturer trigger gesture and the lower edge of the first image to obtain a first intersection coordinate set.

It should be noted that, in the present invention, the first image and the second image are subjected to the coordinate processing, and all subsequent coordinate processing establishes a coordinate system based on the same origin of coordinates, for example, each vertex of the picture is used as the origin of coordinates to establish the coordinate system for the coordinate processing.

It may be understood that, the first image is subjected to coordinated processing based on the first preset vertex, a first hand coordinate set of a first hand outline of a lecturer trigger gesture in the first image is extracted, it is easy to understand that all coordinate points of a hand of the lecturer in the image are extracted to obtain the first hand coordinate set, and an intersection point of the lecturer trigger gesture and the lower edge of the first image is obtained to obtain a first intersecting coordinate set, it is easy to understand that an intersection point of an arm of the lecturer in the first image and the lower edge of the first image is obtained to obtain the first intersecting coordinate set, where the extraction of the hand outline is in the prior art, for example, the extraction of the hand outline may be performed through OpenCV, which is not repeated herein for the prior art.

Acquiring a first center point coordinate of the first hand coordinate set and a first middle point coordinate of the first intersecting coordinate set, obtaining a first slope value according to the first center point coordinate and the first middle point coordinate, and obtaining a first angle value based on the first slope value.

It can be understood that, as shown in fig. 2, a first center point coordinate of the first hand coordinate set and a first intermediate point coordinate of the first intersecting coordinate set are obtained, and a corresponding linear equation can be obtained by performing a line calculation according to the first center point coordinate and the first intermediate point coordinate, so as to obtain an angle value corresponding to a slope of the linear equation, and the angle value is used as a first angle value.

In some embodiments, obtaining a first center point coordinate of the first set of hand coordinates and a first intermediate point coordinate of the first set of intersecting coordinates comprises:

and obtaining a first central point abscissa according to the maximum value and the minimum value of the abscissas in the first hand coordinate set, obtaining a first central point ordinate according to the maximum value and the minimum value of the abscissas in the first hand coordinate set, and obtaining a first central point coordinate according to the first central point abscissa and the first central point ordinate.

It can be understood that the first center point abscissa is obtained according to the average value of the maximum value and the minimum value of the abscissas in the first hand coordinate set, the first center point ordinate is obtained according to the average value of the maximum value and the minimum value of the abscissas in the hand coordinate set, and the first center point coordinate is obtained according to the first center point abscissa and the first center point ordinate.

It is easy to understand that the first intersecting coordinate set is an edge point of the arm in the picture, a first intermediate point abscissa is obtained according to a maximum value and a minimum value of abscissas in the first intersecting coordinate set, an intersecting ordinate in the first intersecting coordinate set is obtained, and a first intermediate point coordinate is obtained according to the intersecting ordinate and the first intermediate point abscissa.

And carrying out coordinated processing on the plurality of second images, extracting a second hand coordinate set of a second hand outline of the judgment gesture in the second images, and acquiring an intersection point of the judgment gesture and the lower edge of the second images to obtain a second intersection coordinate set.

It can be understood that, consistent with the principle of extracting the corresponding hand coordinate set and the intersecting coordinate set in the first image, the present invention performs the first preset vertex coordinate processing on the plurality of second images, extracts the second hand coordinate set of the second hand outline of the judgment gesture in the second images, and obtains the intersecting point of the judgment gesture and the lower edge of the second images to obtain the second intersecting coordinate set.

It will be appreciated that, as shown in fig. 3, consistent with the principle of determining the first slope value of the first image, a second slope value corresponding to a plurality of second images is obtained according to the second center point coordinates and the second intermediate point coordinates, and a corresponding second angle value is determined according to the slope of the straight line.

S5423, determining the relative position of the lecturer trigger gesture and the target judgment gesture, obtaining a backward instruction or a forward instruction according to the relative position, and determining instruction duration based on the target angle difference value.

It is understood that, the relative positions of the lecturer trigger gesture and the target judgment gesture are determined, and the backward instruction or the forward instruction is determined, it is easy to understand that when the lecturer rotates forward to be the forward instruction, rotates backward to be the backward instruction, and determines the corresponding instruction duration according to the rotating angle, that is, the target angle difference value.

In some embodiments, in step S5423 (determining the relative position of the lecturer trigger gesture and the target judgment gesture, obtaining a backward instruction or a forward instruction according to the relative position, and determining an instruction duration based on the target angle difference value) includes:

and acquiring a first center point coordinate corresponding to the lecturer trigger gesture and a second center point coordinate corresponding to the target judgment gesture.

It can be understood that the first center point coordinates corresponding to the lecturer trigger gesture and the second center point coordinates corresponding to the target judgment gesture are obtained.

And when the abscissa of the first center point coordinate is determined to be larger than the abscissa of the second center point coordinate, a backward instruction is obtained.

It will be appreciated that when the abscissa of the first center point coordinate is greater than the abscissa of the second center point coordinate, indicating that the user gesture is rotated backward at this time, a backward instruction is obtained.

And when the abscissa of the first center point coordinate is determined to be smaller than the abscissa of the second center point coordinate, obtaining a forward instruction.

It will be appreciated that when the abscissa of the first center point coordinate is less than the abscissa of the second center point coordinate, indicating that the user gesture is rotating forward at this time, a forward command is obtained.

It can be understood that when the larger the angle of the lecturer is, the longer the corresponding adjustment time length is, so that the user can conveniently control, and the larger the angle of the lecturer is, the longer the corresponding instruction time length is.

Therefore, a time length adjustment coefficient is obtained according to the ratio of the target angle difference value to a preset reference angle, and the instruction time length is obtained according to the product of the time length adjustment coefficient and the preset reference time length, and it can be understood that the proportional relation is obtained, wherein the preset reference angle corresponds to the preset reference time length.

S5424, determining a lecturer control instruction according to the backward instruction or the forward instruction and the instruction duration.

It will be appreciated that the corresponding lecturer control instruction is determined based on the back instruction and the instruction duration, or the lecturer control instruction is determined based on the forward instruction and the instruction duration.

Besides the above-mentioned rotation angle of the user gesture obtained by the slope, the corresponding rotation angle can also be calculated by a triangle determined by the connection line between the central point of the palm of the user and two preset vertexes in the image, and the specific mode is as follows:

In other embodiments, the step (capturing the instruction gesture of the lecturer at the lecturer device in the preset judging period by using the angle control policy control image capturing device as the judging gesture, and determining the lecturer control instruction according to the lecturer trigger gesture and the judging gesture) includes A1-A7:

a1, taking an acquired image corresponding to the lecturer triggering gesture as a first image, extracting a first moment for acquiring the first image, and controlling the image acquisition device to acquire a plurality of acquired images corresponding to the judging gesture in real time as second images according to the first moment and a preset judging duration.

A2, carrying out coordinate processing based on the first image and the second image to obtain a first coordinate of a first preset vertex and a second coordinate of a second preset vertex.

It can be understood that the vertex of the upper left corner on the first image and the second image is used as a second preset vertex, the vertex of the lower left corner is used as a second preset vertex, and the first coordinate of the first preset vertex and the second coordinate of the second preset vertex of the first image and the second image are obtained after the coordinate processing.

A3, acquiring initial center coordinates of a first hand coordinate set of the lecturer triggering gesture in the first image, and calculating according to the initial center coordinates, the first coordinates and the second coordinates to obtain initial included angles between connecting lines of the first coordinates in the corresponding first image and the second coordinates and the initial center coordinates respectively.

It can be understood that, consistent with the principle of determining the first center point coordinate of the first hand coordinate set, the initial center coordinate of the first hand coordinate set of the lecturer triggering gesture in the first image is determined, the initial center coordinate is also the center point coordinate of the hand, the calculation is performed according to the initial center coordinate, the first coordinate and the second coordinate, 3 coordinate connecting lines can determine 3 sides of the triangle, and an initial included angle between the corresponding first coordinate and connecting lines of the second coordinate and the initial center coordinate can be obtained according to the cosine theorem, namely, the included angle between the top left corner vertex of the picture and the connecting line of the top left corner vertex and the hand center point is the initial included angle.

And A4, acquiring a rotation center coordinate of the hand part for judging the gesture in the second image, calculating according to the rotation center coordinate, the first coordinate and the second coordinate, obtaining a rotation included angle between the connecting lines of the first coordinate and the second coordinate and the rotation center coordinate in the corresponding second image, and selecting the largest rotation included angle as a termination included angle.

It can be understood that, consistent with the principle of step A3, the rotation angles of the judgment gestures in the plurality of second images are obtained, and the largest rotation angle is selected as the termination angle.

And A5, when the abscissa of the initial center coordinate is smaller than the abscissa of the rotation center coordinate, calling an advancing instruction, obtaining a hand rotation angle according to the termination included angle and the initial included angle, determining a first adjusting coefficient based on the ratio of the hand rotation angle to a preset angle, and shifting the preset time length according to the first adjusting coefficient to obtain the advancing time length.

It can be understood that, according to the termination included angle and the initial clamping difference value, a hand rotation angle can be obtained, and it is easy to understand that the hand rotation angle obtained by the termination included angle and the initial clamping difference value is in direct proportion to the hand rotation amplitude, the larger the rotation amplitude is, the larger the corresponding part rotation angle is, the first adjustment coefficient is determined according to the ratio of the hand rotation angle to the preset angle, the fast-forward time length is obtained according to the product of the first adjustment coefficient and the preset time length, and the forward instruction is fetched according to the abscissa of the initial center coordinate being greater than the abscissa of the rotation center coordinate.

A6, when the abscissa of the initial center coordinate is determined to be larger than the abscissa of the rotation center coordinate, a backward instruction is called, a hand rotation angle is obtained according to the termination included angle and the initial included angle, a second adjustment coefficient is determined based on the ratio of the hand rotation angle to a preset angle, and the preset time length is offset according to the second adjustment coefficient, so that the backward time length is obtained.

It is to be understood that, according to the termination included angle and the initial clamping difference value, a hand rotation angle can be obtained, and it is to be understood that, the hand rotation angle obtained by the termination included angle and the initial clamping difference value is proportional to the hand rotation amplitude, the larger the rotation amplitude is, the larger the corresponding part rotation angle is, the first adjustment coefficient is determined according to the ratio of the hand rotation angle to the preset angle, the backward time length is obtained according to the product of the first adjustment coefficient and the preset time length, and the backward instruction is fetched according to the abscissa of the initial center coordinate being greater than the abscissa of the rotation center coordinate.

And A7, determining a lecturer control instruction according to the backward instruction or the forward instruction and the instruction duration.

It will be appreciated that the instructor control instruction is determined based on the back instruction or the forward instruction and the instruction duration.

And S543, if the attribute of the current adjustment identification tag is a duration type, acquiring a plurality of lecturer instruction gestures at the lecturer equipment by using a duration control strategy control image acquisition device in real time as judgment gestures, and determining lecturer control instructions according to the lecturer triggering gestures and the judgment gestures.

It can be understood that if the attribute of the current adjustment identification tag is a duration type, the duration control strategy is invoked to control the image acquisition device to acquire a plurality of lecturer instruction gestures at the lecturer equipment in real time as judgment gestures, and the lecturer control instructions are determined according to the lecturer triggering gestures and the judgment gestures.

In some embodiments, in step S543 (the capturing duration control policy control image capturing device captures, in real time, a plurality of lecturer instruction gestures at the lecturer device as judgment gestures, and determines the lecturer control instruction according to the lecturer trigger gesture and the judgment gesture), including S5431-S5435:

and S5431, taking an acquired image corresponding to the lecturer trigger gesture as a first image, carrying out coordinated processing on the first image, extracting a first hand coordinate set of a first hand outline of the lecturer trigger gesture in the first image, and obtaining a first center point coordinate of the first hand coordinate set.

It can be appreciated that, consistent with the principle of determining the first center point coordinates corresponding to the lecturer trigger gesture, the first center point coordinates of the first hand coordinate set may be directly obtained.

S5432, controlling the image acquisition device to acquire a plurality of acquired images corresponding to the judgment gestures in real time as a second image, carrying out coordinated processing on the second image, extracting a second hand coordinate set of a second hand outline of the lecturer trigger gesture in the second image, and acquiring a second center point coordinate of the second hand coordinate set.

It can be understood that, consistent with the principle of determining the second center point coordinates corresponding to the judgment gesture, the second center point coordinates of the second hand coordinate set may be directly obtained.

S5433, when the abscissa of the first center point coordinate is determined to be larger than the abscissa of the second center point coordinate, a backward instruction is obtained, and when the abscissa of the first center point coordinate is determined to be smaller than the abscissa of the second center point coordinate, a forward instruction is obtained.

It will be appreciated that when the user gesture rotates, the backward instruction is obtained when the abscissa of the first center point coordinate is greater than the abscissa of the second center point coordinate, and the forward instruction is obtained when the abscissa of the first center point coordinate is less than the abscissa of the second center point coordinate.

S5434, obtaining duration of the judgment gesture and the lecturer trigger gesture which are the same, obtaining a first duty ratio according to a ratio of the duration to the preset duration, and obtaining a command duration according to a product of the first duty ratio and the preset command duration.

It can be understood that the duration of the judgment gesture and the duration of the lecturer trigger gesture which are the same are obtained, a first duty ratio is obtained according to the ratio of the duration to the preset duration, and the instruction duration is obtained according to the product of the first duty ratio and the preset instruction duration.

It is to be understood that when the judging gesture of the lecturer is the same as the gesture triggered by the lecturer continuously, the corresponding duration is recorded, the first duty ratio is obtained according to the ratio of the duration to the preset duration, the instruction duration is obtained according to the product of the first duty ratio and the preset instruction duration, the preset duration and the preset instruction duration are set correspondingly, and are all set in advance, for example, the duration is 2 seconds, the preset duration is 1 second, the preset instruction duration is 10 seconds, and the instruction duration is 20 seconds.

For example, if the gesture for adjustment is determined to be a cloth, the user counts the time for holding the cloth when the user holds the cloth continuously, and the time is stopped once the user gesture becomes another gesture.

S5435, determining a lecturer control instruction according to the backward instruction or the forward instruction and the instruction duration.

Through the embodiment, the gesture of the user can be identified, the video is controlled, the operation is simple and convenient, and the user experience is improved.

In order to better implement the VR cloud platform interaction method provided by the present invention, the present invention further provides a VR cloud platform interaction system, as shown in fig. 4, including:

The present invention also provides a readable storage medium having stored therein a computer program for implementing the methods provided by the various embodiments described above when executed by a processor.

The readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. In the alternative, the readable storage medium may be integral to the processor. The processor and the readable storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). In addition, the ASIC may reside in a user device. The processor and the readable storage medium may reside as discrete components in a communication device. The readable storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tape, floppy disk, optical data storage device, etc.

The present invention also provides a program product comprising execution instructions stored in a readable storage medium. The at least one processor of the device may read the execution instructions from the readable storage medium, the execution instructions being executed by the at least one processor to cause the device to implement the methods provided by the various embodiments described above.

In the above embodiment of the apparatus, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims

1. The VR cloud platform interaction method is characterized by comprising the following steps of:

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

the image acquisition device is used for continuously acquiring a plurality of first interaction gestures of the management end, and the fixed gesture slot is configured based on the first interaction gestures and a first preset duration to obtain fixed coherent gestures corresponding to the interaction sub-video, and the method comprises the following steps:

3. The method of claim 2, wherein the step of determining the position of the substrate comprises,

According to the contrast of lecturer instruction gesture and lecturer interactive collection, confirm lecturer control command, include:

4. The method of claim 3, wherein the step of,

If the lecturer trigger gesture is a second interaction gesture, obtaining a lecturer control instruction according to the dynamic adjustment gesture, including:

5. The method of claim 4, wherein the step of determining the position of the first electrode is performed,

the angle control strategy is invoked to control the image acquisition device to acquire a lecturer instruction gesture at a lecturer device within a preset judging time as a judging gesture, and the lecturer control instruction is determined according to the lecturer triggering gesture and the judging gesture, and the method comprises the following steps:

6. The method of claim 5, wherein the step of determining the position of the probe is performed,

the obtaining a first angle value corresponding to the lecturer trigger gesture in the first image and a second angle value corresponding to the judgment gesture in the plurality of second images includes:

7. The method of claim 6, wherein the step of providing the first layer comprises,

the obtaining the first center point coordinate of the first hand coordinate set and the first middle point coordinate of the first intersecting coordinate set includes:

8. The method of claim 7, wherein the step of determining the position of the probe is performed,

the determining the relative position of the lecturer trigger gesture and the target judgment gesture, obtaining a backward instruction or a forward instruction according to the relative position, and determining instruction duration based on the target angle difference value comprises the following steps:

9. The method of claim 4, wherein the step of determining the position of the first electrode is performed,

the time length control strategy is called up and a plurality of lecturer instruction gestures at lecturer equipment are collected in real time by the image collecting device and used as judging gestures, and according to the lecturer triggering gestures and the judging gestures, lecturer control instructions are determined, and the method comprises the following steps:

10. A VR cloud platform interaction system, comprising: