Systems and methods for controlling video wall content using air gestures
AssigneeVerizon Patent and Licensing Inc.
InventorsIndraneel Sen, Yuk Lun Li
Life of this patent
Estimating the term…
Abstract
A device may include a memory storing instructions and processor configured to execute the instructions to receive a video image stream of a scene. The device may be further configured to perform person detection on the received video image stream to identify a plurality of persons; perform gesture detection on the received video image stream to identify a gesture; select a person from the plurality of persons to associate with the identified gesture; and use the identified gesture to enable the selected person to control an object or area displayed on a video screen associated with the scene.
Claims20
A method comprising:
- receiving, by a device, a video image stream of a scene;
- performing, by the device and on the received video image stream, person detection to identify a plurality of persons;
- performing, by the device and on the received video image stream, gesture detection to identify a gesture, wherein performing gesture detection to identify the gesture in the received video image stream includes:
- activating a gesture tracking instance, wherein the gesture tracking instance includes a computer vision machine learning model;
- selecting, by the device, a person from the identified plurality of persons in the received video image stream;
- associate, by the device, the selected person with the activated gesture tracking instance;
- and
- using, by the device, the activated gesture tracking instance to enable the selected person to control an object or area displayed on a video screen associated with the scene.
A device comprising:
- a processor configured to:
- receive a video image stream of a scene;
- perform person detection on the received video image stream to identify a plurality of persons;
- perform gesture detection on the received video image stream to identify a gesture, wherein, when performing gesture detection to identify the gesture in the received video image stream, the processor is further configured to:
- activate a gesture tracking instance, wherein the gesture tracking instance includes a computer vision machine learning model;
- select a person from the identified plurality of persons to associate with the activated gesture tracking instance;
- and
- use the activated gesture tracking instance to enable the selected person to control an object or area displayed on a video screen associated with the scene.
A system comprising:
- a camera configured to:
- capture video images of a scene;
- and
- transmit a video image stream based on the captured video images via a Fifth Generation (5G) wireless connection;
- and
- a Multi-Access Edge Computing (MEC) device configured to:
- receive the video image stream from the camera;
- perform person detection to identify a plurality of persons in the video image stream;
- perform gesture detection to identify a gesture in the received video image stream, wherein, when performing gesture detection to identify the gesture in the received video image stream, the MEC device is further configured to:
- activate a gesture tracking instance, wherein the gesture tracking instance includes a computer vision machine learning model;
- select a person from the plurality of persons to associate with the identified gesture;
- and
- use the identified gesture to enable the selected person to control an object or area displayed on a video screen associated with the scene.
Dependencies are inferred from the claim text.