Controlling a camera using a voice command and image recognition

Patent metadata

Field	Value
Publication number	US-10178293-B2
Application number	US-201615189469-A
Country	US
Kind code	B2
Filing date	Jun 22, 2016
Priority date	Jun 22, 2016
Publication date	Jan 8, 2019
Grant date	Jan 8, 2019

Abstract

A method, a computer program product, and a computer system for controlling a camera using a voice command and image recognition. One or more processors on the camera captures the voice command that is from a user of the camera and declares a subject of interest. The one or more processors processes the voice command and sets the subject of interest. The one or more processors receives a camera image from an imaging system of the camera. The one or more processors identifies the subject of interest in the camera image. The one or more processors sets camera one or more parameters that are appropriate to the subject of interest.

First claim

What is claimed is:

1. A method for controlling a camera using a voice command and image recognition, the method comprising:
capturing, by one or more processors on the camera, the voice command from a user of the camera, the voice command declaring a subject of interest, wherein the voice command uses a comparative statement stating at least one of a color, a location, and a stature of the subject of interest;
processing, by the one or more processors, the voice command declaring the subject of interest;
setting, by the one or more processors, the subject of interest in a frame of the camera, according to the voice command declaring the subject of interest;
highlighting the subject of interest when the subject of interest is in the frame;
making an audible alert when the subject of interest is in the frame;
receiving, by the one or more processors, a camera image from an imaging system of the camera;
identifying in the camera image, by the one or more processors, the subject of interest defined by the voice command declaring the subject of interest;
capturing, by the one or more processors, a second voice command from the user of the camera, the second voice command locking in the subject of interest, the locking in the subject of interest identifies a second object as the subject of interest when a first object that has been identified as the subject of interest leaves the frame of the camera; and
setting, by the one or more processors, at least one of camera parameters of focus, exposure, pan, and tilt such that the at least one of the camera parameters are appropriate to the subject of interest defined by the voice command declaring the subject of interest.

2. The method of claim 1 , wherein the voice command declaring the subject of interest uses a feature of the subject of interest to differentiate the subject of interest defined by the voice command declaring the subject of interest from other subjects in the camera image.

3. The method of claim 1 , wherein the subject of interest defined by the voice command declaring the subject of interest is set for multiple camera images.

4. The method of claim 1 , wherein the voice command declaring the subject of interest pre-primes the camera before the subject of interest defined by the voice command declaring the subject of interest appears in the camera image.

5. The method of claim 1 , wherein the voice command declaring the subject of interest declares multiple subjects of interest, wherein the at least one of camera parameters of focus, exposure, pan, and tilt are set to be appropriate to the multiple subjects of interest.

Assignees

• IBM

Inventors

• Butts Deborah J
• Kyte Adrian P
• Moran Timothy A
• Taylor John D

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• H04N23/62

  Control of parameters via user interfaces · CPC title

• H04N23/60 Primary

  Control of cameras or camera modules · CPC title

• H04N5/232 Primary

  Electricity · mapped topic