Sound image integration positioning long distance voice acquisition device

Abstract

For solving difficulty in acquiring voice under the long distance noise background, a video camera and a microphone array are integrated to determine a target speaker in a sound image integration mode, and problems of difficulty in determining the target speaker and requirement of a mechanic rotating device caused by simply employing a camera, a high directivity microphone or a microphone array in the prior art are solved. The voice acquisition device integrated with the monitoring camera and the microphone array wave beam shaping technology is advantaged in that target speaker positioning is carried out through sound and image integration, and outdoor long distance voice acquisition performance is enhanced on the condition that a noise environment is improved.

Description

Technical field [0001] The invention relates to a voice collection device, in particular to a long-distance voice collection device for joint audio and image positioning. Background technique [0002] In the fields of security, security, etc., various video surveillance systems have been widely used. Relying on various video surveillance systems, it is possible to confirm and screen relevant personnel in remote videos. When using the video surveillance system to confirm and identify remote suspects, if the language and dialogue information can be used through remote voice collection, it will greatly affect work efficiency. However, it is still extremely difficult to carry out long-distance voice collection under actual environmental background noise conditions. [0003] Due to the presence of environmental noise, the high directivity of the collection device must be used to ensure the quality of the collected long-distance voice during long-distance voice collection. Current lon...

AI Technical Summary

Problems solved by technology

[0010] Aiming at the difficulty of voice collection under long-distance and noisy backgrounds, combined with video cameras and microphone arrays, the audio-visual joint determination of the target speaker is carried out, thereby solving the difficulty of determining the target speaker and the need for mechanical Rotating device and other problems, the present invention proposes a voice acquisition device combined with monitoring camera and microphone array beamforming technology to jointly determine the location of the target speaker with sound and image, thereby improving the performance of outdoor long-distance voice enhancement acquisition under environmental noise conditions

Images