Surveillance camera system for extracting sound of specific area from visualized object and operating method thereof
A camera system for extracting a sound of a specific area includes: a camera device configured to receive video signals and audio signals from an area; at least one memory configured to store information about the area including data corresponding to the video signals and the audio signals from the area; and a processor configured to change an audio zooming point of the camera device from a first point, in an image of the area captured by the camera device, to a second point based on the information about the area, and perform a beam-forming on an audio signal corresponding to the second point.
1. A camera system for extracting sounds of a specific area, comprising:
a camera device configured to receive video signals and audio signals from an area;
at least one memory configured to store information about the area including data corresponding to the video signals and the audio signals from the area; and
a processor configured to change an audio zooming point of the camera device from a first point, in an image of the area captured by the camera device, to a second point based on the information about the area, and perform a beam-forming on an audio signal corresponding to the second point,
wherein the processor is configured to implement:
a data collector configured to generate a sound-based heatmap for the area based on the information about the area;
a user area selector configured to select a user-designated area to perform the beam-forming thereon, and select the first point in the user-designated area as the audio zooming point;
a calculator configured to select the second point as the audio zooming point in the user-designated area, based on the first point and the sound-based heatmap; and
a corrector configured to perform the beam-forming in a direction corresponding to the second point.
2. The system of claim 1 , wherein the audio signal on which the beam-forming is performed is limited to a human voice signal.
3. The system of claim 2 , wherein the processor is further configured to determine the audio signal as the human voice signal based on determining that the audio signal includes a vowel among language components.
4. The system of claim 1 , wherein the sound-based heatmap displays positions of a pitch range corresponding to human voice signals by a sound source localization based on the video signals and the audio signals received by the camera device.
5. The system of claim 1 , wherein the area is split into a plurality of areas, and the user area selector is configured to select at least one of the plurality of areas as the user-designated area.
6. The system of claim 5 , wherein the user area selector is configured to specify an object corresponding to a target of the beam-forming based on a motion detection algorithm and/or a face recognition algorithm.
7. The system of claim 1 , wherein both the first and second points are displayed on the image of the area.
8. The system of claim 7 , wherein the second point is selected from a plurality of second points displayed by the camera device.
9. The system of claim 1 , wherein the camera device comprises:
a camera configured to collect the video signals having a specific viewing angle; and
a microphone array comprising a plurality of microphones spaced apart from one another, and configured to collect the audio signals.
10. The system of claim 9 , wherein the camera and the microphone array are disposed on different surfaces of the camera device.
11. The system of claim 1 , wherein the memory is further configured to manage data output from the calculator, and store a measurement time and a date corresponding the video signals and the audio signals received by the camera device together with the data output from the calculator.
12. A method for operating a camera system for extracting sounds of a specific area, the method comprising:
receiving video signals and audio signals from an area;
storing information about the area including the video signals and the audio signals;
generating a sound-based heatmap for the area based on the information about the area;
selecting a user-designated area to perform beam-forming thereon and selecting a first point in the user-designated area as an audio zooming point;
changing the audio zooming point to a second point in the user-designated area based on the first point and the sound-based heatmap; and
performing the beam-forming in a direction corresponding to the second point.
13. The method of claim 12 , wherein an audio signal on which the beam-forming is performed is limited to a human voice signal.
14. The method of claim 13 , further comprising:
determining the audio signal as the human voice signal based on determining that the audio signal includes a vowel among language components.
15. The method of claim 12 , wherein the sound-based heatmap displays positions of a pitch range corresponding to human voice signals by a sound source localization based on the video signals and the audio signals.
16. The method of claim 12 , wherein the area is split into a plurality of areas, and the selecting the user-designated area comprises selecting at least one of the plurality of split areas as the user-designated area.
17. The method of claim 16 , wherein the selecting the user-designated area further comprises:
specifying an object corresponding to a target of the beam-forming based on a motion detection algorithm and/or a face recognition algorithm.
18. The method of claim 12 , wherein both the first and second audio zooming points are displayed on an image of the area.
19. The method of claim 18 , wherein the second point is selected from a plurality of second points displayed by a camera device.