Method and apparatus for controlling surveillance system with gesture and/or audio commands
A computer-implemented method controls aspects of a surveillance system using gestures and/or voice commands, and comprises: receiving one or both of an operator's skeleton input data and voice input data from a gesture detection camera and a microphone; using a processor, matching one or both of the received skeleton input data with a gesture stored in a database and the received voice input data with a text string stored in the database; matching one or both of the gesture and text string to a corresponding video management program command stored on the database; and transmitting the one or more video management program commands to a video management program of the surveillance system.
1. A non-transitory computer readable medium having stored thereon computer program code that is executable by a processor and that, when executed by the processor, causes the processor to perform a method for controlling a surveillance system, the method comprising:
receiving human body tracking data of an operator;
matching the human body tracking data with a respective gesture stored in a database;
based on the gesture, determining at least one corresponding video management program command stored in the database, wherein the at least one video management program command comprises video panning and zooming; and
causing the at least one video management program command to be transmitted to a video management program of the surveillance system, and wherein the human body tracking data comprises frames of data and determining the at least one corresponding video management program command comprises, for each of the frames that is used:
determining a horizontal distance between a horizontal position of a hand on one side of the operator to a shoulder on an identical side of the operator; and
determining a vertical distance between a vertical position of the hand on one side of the operator to the shoulder on the identical side of the operator, and the corresponding video management program command comprises a command to pan up and down in proportion to the horizontal distance and vertical distance, respectively.
2. The medium of claim 1 , wherein the at least one video management program command comprises commands in the form of three-dimensional Cartesian coordinate values for the panning and zooming.
3. The medium of claim 1 , wherein the at least one video management program command comprises javascript or HTML values.
4. The medium of claim 1 , wherein matching the human body tracking data with a gesture comprises using only one of every n frames of the human body tracking data, wherein n is two or more.
5. A method for controlling a surveillance system comprising:
receiving human body tracking data of an operator;
matching the human body tracking data with a respective gesture stored in a database;
based on the gesture, determining at least one corresponding video management program command stored in the database and including video panning and zooming, the determining the at least one corresponding video management program command including, for each of the frames that is used:
determining a horizontal distance between a horizontal position of a hand on one side of the operator to a shoulder on an identical side of the operator; and
determining a vertical distance between a vertical position of the hand on one side of the operator to the shoulder on the identical side of the operator; and
causing the at least one video management program command to be transmitted to a video management program of the surveillance system, and
wherein the human body tracking data includes frames of data, and the video panning includes panning up and down in proportion to the horizontal distance and vertical distance, respectively.
6. The method of claim 5 , wherein the at least one video management program command includes commands in the form of three-dimensional Cartesian coordinate values for the panning and zooming.
7. The method of claim 5 , wherein the at least one video management program command includes javascript or HTML, values.
8. The method of claim 5 , wherein matching the human body tracking data with a gesture includes using only one of every n frames of the human body tracking data, wherein n is two or more.