CN218071620U - Main board capable of automatically locking face of speaker - Google Patents

Main board capable of automatically locking face of speaker Download PDF

Info

Publication number
CN218071620U
CN218071620U CN202220784304.1U CN202220784304U CN218071620U CN 218071620 U CN218071620 U CN 218071620U CN 202220784304 U CN202220784304 U CN 202220784304U CN 218071620 U CN218071620 U CN 218071620U
Authority
CN
China
Prior art keywords
speaker
camera
main control
control board
degree
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202220784304.1U
Other languages
Chinese (zh)
Inventor
郑洪明
金盛明
张国志
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Jiangyuan Technology Group Co ltd
Original Assignee
Shenzhen Jiangyuan Technology Group Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Jiangyuan Technology Group Co ltd filed Critical Shenzhen Jiangyuan Technology Group Co ltd
Priority to CN202220784304.1U priority Critical patent/CN218071620U/en
Application granted granted Critical
Publication of CN218071620U publication Critical patent/CN218071620U/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Studio Devices (AREA)

Abstract

The utility model discloses an automatic locking speaker facial mainboard, including main control board and camera and miaow head subassembly, the beneficial effects of the utility model are that this novel automatic locking speaker facial mainboard, connect camera and miaow head subassembly through the main control board, each position sound of 8 miaow head conveying on the record subassembly, the image of 2 180 degree camera conveying on the record subassembly simultaneously, and merge into 360 degrees panoramic image 2 180 degree images, the current speaker sound characteristic of main control board rapid analysis, through miaow head angle algorithm, calculate each position sound of 8 miaow heads, judge the angle that speaker locates in 360 degrees panoramic image, cut apart from 360 degrees panoramic image, the speaker's image is drawed out to the speech, and output current speaker's image, and through the people's sound after the angle calculation, the algorithm has suppressed background noise, speaker sound is more clear, realize speaker sound and picture synchronization, bring efficient communication effect.

Description

Main board capable of automatically locking face of speaker
Technical Field
The utility model relates to a mainboard, especially an automatic locking speaker facial mainboard.
Background
The conference recording and broadcasting system in the prior art has the advantages that the whole conference is recorded and stored, and the conference recording and broadcasting system has a simple speaker shooting and tracking function. The conference recording and broadcasting system is realized by associating each microphone key with the corresponding position of the camera cloud deck, and fixedly records the output image of the camera with the cloud deck. And when speaking, pressing a microphone speaking key, and controlling the camera holder to move to the associated position through commands to realize conference speaking tracking. However, there is a disadvantage that, first, the image pickup and tracking detects a speaker by turning on a microphone, and after switching speakers, a camera is fixed in relation to the position of the speaker, and a close-up image of the speaker during the movement of the conference platform cannot be tracked when the speaker is on the platform for explanation. And secondly, the cloud deck is controlled through the conference tracking host, and the cloud deck is controlled through the conference tracking host, so that smooth switching of shooting pictures cannot be achieved, and the recorded video has a camera moving process.
To this end, we propose a main board that automatically locks the face of the speaker to solve the above problem.
SUMMERY OF THE UTILITY MODEL
An object of the utility model is to provide an automatic locking speaker face's mainboard to solve the problem that proposes among the above-mentioned background art.
The utility model aims at realizing through the following technical scheme: a main board capable of automatically locking the face of a speaker comprises a main control board, a camera and a microphone assembly, wherein a microphone angle algorithm module and a 360-degree image segmentation algorithm module are integrated in the main control board; the camera and microphone assembly comprises a 180-degree camera 1, a 180-degree camera 2 and 8 microphones; the main control board is electrically connected with the camera and the microphone assembly.
Furthermore, the main control board records each azimuth sound transmitted by 8 microphones on the assembly through the cameras and the microphone assembly, records images transmitted by 2 180-degree cameras on the assembly at the same time, and combines the 2 180-degree images into a 360-degree panoramic image.
Furthermore, the main control board rapidly analyzes the sound characteristics of the current speaker, calculates the sound of each direction of 8 microphones through the microphone angle algorithm module, judges the angle of the speaker in the 360-degree panoramic image, segments the speaker from the 360-degree panoramic image through the 360-degree image segmentation algorithm module, extracts the image of the speaker, and outputs the image of the current speaker.
Furthermore, a power supply can be arranged in the main control board to provide electric energy for the main control board, the camera and the microphone.
Furthermore, the camera in the camera and the microphone assembly has an anti-glare function.
Compared with the prior art, the beneficial effects of the utility model are that this novel facial mainboard of automatic locking speaker, connect camera and miaow head subassembly through the main control board, record each side sound of 8 miaow head conveyances on the subassembly, record the image of 2 180 degrees camera conveyances on the subassembly simultaneously, and merge into 360 degrees panoramic image to 2 180 degrees images, the main control board rapid analysis current speaker sound characteristic, through miaow head angle algorithm, calculate each side sound of 8 miaow heads, judge the angle that the speaker locates in 360 degrees panoramic image, cut apart from 360 degrees panoramic image, draw out speaker's image, and output current speaker's image, and the voice after the angle calculates, the algorithm has suppressed background noise, speaker sound is more clear, realize speaker sound and picture synchronization, bring efficient communication effect.
Drawings
FIG. 1 is the overall effect diagram of the present invention;
in the figure: 1-main control board, 2-camera and microphone subassembly.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative work belong to the protection scope of the present invention based on the embodiments of the present invention.
As shown in fig. 1, the utility model discloses a main board for automatically locking the face of a speaker, which comprises a main control board 1, a camera and a microphone component 2, wherein a microphone angle algorithm module and a 360-degree image segmentation algorithm module are integrated in the main control board 1; the camera and microphone assembly 2 comprises a 180-degree camera 1, a 180-degree camera 2 and 8 microphones; the main control board 1 is electrically connected with the camera and the microphone component 2.
It is worth mentioning that the main control board 1 records each azimuth sound transmitted by 8 microphones on the assembly through the cameras and the microphone assembly 2, records images transmitted by 2 180-degree cameras on the assembly at the same time, and combines the 2 180-degree images into a 360-degree panoramic image, the main control board 1 rapidly analyzes the sound characteristics of the current speaker, calculates each azimuth sound of 8 microphones through the microphone angle algorithm module, judges the angle of the speaker in the 360-degree panoramic image, divides the speaker from the 360-degree panoramic image through the 360-degree image division algorithm module, extracts the image of the speaker, and outputs the image of the current speaker, a power supply can be arranged in the main control board 1 to provide electric energy for the main control board 1, the cameras and the microphone, and the cameras in the microphone assembly 2 have an anti-glare function.
The specific implementation mode is that the main control board 1 is connected with the camera and the microphone component 2, 8 directions of sound transmitted by 8 microphones on the component are recorded, 2 images transmitted by 180-degree cameras on the component are recorded simultaneously, and the 2 images of 180 degrees are combined into a 360-degree panoramic image, the main control board 1 rapidly analyzes the sound characteristics of the current speaker, the directions of sound of 8 microphones are calculated through a microphone angle algorithm, the angle of the speaker in the 360-degree panoramic image is judged, the speaker is divided from the 360-degree panoramic image, the image of the speaker is extracted, the image of the current speaker is output, the voice after the angle calculation is carried out, the algorithm restrains background noise, the voice of the speaker is clearer, the voice and the image of the speaker are synchronized, and an efficient communication effect is brought.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein, and any reference signs in the claims are not intended to be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present specification describes embodiments, not every embodiment includes only a single embodiment, and such description is for clarity purposes only, and it is to be understood that all embodiments may be combined as appropriate by one of ordinary skill in the art to form other embodiments as will be apparent to those of skill in the art from the description herein.

Claims (5)

1. The utility model provides an automatic locking speaker facial mainboard, includes main control board (1) and camera and miaow head subassembly (2), its characterized in that: a microphone angle algorithm module and a 360-degree image segmentation algorithm module are integrated in the main control board (1); the camera and microphone assembly (2) comprises a 180-degree camera 1, a 180-degree camera 2 and 8 microphones; the main control board (1) is electrically connected with the camera and the microphone assembly (2).
2. A main board for automatically locking a speaker's face according to claim 1, wherein: the main control board (1) records each azimuth sound transmitted by 8 microphones on the assembly through the cameras and the microphone assembly (2), records images transmitted by 2 180-degree cameras on the assembly at the same time, and combines the 2 180-degree images into a 360-degree panoramic image.
3. A main board for automatically locking a speaker's face according to claim 1, wherein: the main control board (1) rapidly analyzes the sound characteristics of the current speaker, calculates the sound of each direction of 8 microphones through the microphone angle algorithm module, judges the angle of the speaker in a 360-degree panoramic image, segments the speaker from the 360-degree panoramic image through the 360-degree image segmentation algorithm module, extracts the image of the speaker and outputs the image of the current speaker.
4. A main board for automatically locking a speaker's face according to claim 1, wherein: the main control board (1) can be internally provided with a power supply to provide electric energy for the main control board (1), the camera and the microphone.
5. A main board for automatically locking a speaker's face according to claim 1, wherein: the camera in the camera and the microphone assembly (2) has an anti-dazzle function.
CN202220784304.1U 2022-04-06 2022-04-06 Main board capable of automatically locking face of speaker Active CN218071620U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202220784304.1U CN218071620U (en) 2022-04-06 2022-04-06 Main board capable of automatically locking face of speaker

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202220784304.1U CN218071620U (en) 2022-04-06 2022-04-06 Main board capable of automatically locking face of speaker

Publications (1)

Publication Number Publication Date
CN218071620U true CN218071620U (en) 2022-12-16

Family

ID=84415374

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202220784304.1U Active CN218071620U (en) 2022-04-06 2022-04-06 Main board capable of automatically locking face of speaker

Country Status (1)

Country Link
CN (1) CN218071620U (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119071424A (en) * 2024-09-27 2024-12-03 江门市金丰贝卡音视频科技有限公司 A multi-microphone conference data management system and method based on speech recognition

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119071424A (en) * 2024-09-27 2024-12-03 江门市金丰贝卡音视频科技有限公司 A multi-microphone conference data management system and method based on speech recognition

Similar Documents

Publication Publication Date Title
CN102833476B (en) Camera for terminal equipment and implementation method of camera for terminal equipment
CN109413359B (en) Camera tracking method, device and equipment
CN103595953B (en) A kind of method and apparatus for controlling video capture
JP3115798B2 (en) Audio tracking video system
CN114827517A (en) Projection video conference system and video projection method
WO2010072075A1 (en) Method, device and system of video communication
US20100118112A1 (en) Group table top videoconferencing device
CN107613243A (en) A kind of panoramic video recording arrangement and method for recording based on tone tracking
US20110052139A1 (en) Imaging Device And Playback Device
CN102843540A (en) Automatic camera selection for videoconference
CN218071620U (en) Main board capable of automatically locking face of speaker
US11477393B2 (en) Detecting and tracking a subject of interest in a teleconference
CN114338965A (en) Audio processing method and electronic device
CN102998880A (en) Projector with function of camera and shooting method
CN115134556A (en) A remote video conference system
JPH1042264A (en) Video conference system
CN202798928U (en) Pick-up head for terminal equipment
US12407789B2 (en) Automated video conference system with multi-camera support
US8848927B2 (en) Recorder that creates stereophonic sound
CN117527768A (en) Audio/video selection method and system for tracking and shooting speaker
TWI753741B (en) Sound source tracking system and method
US11496654B2 (en) Projection-type video conference device and system there of
CN115361521A (en) Holographic image video conference system
CN208849876U (en) A kind of sound control camera
KR20100006029A (en) A remote video conference system

Legal Events

Date Code Title Description
GR01 Patent grant
GR01 Patent grant