Intel corporation (20240161494). METHODS AND DEVICES FOR GESTURE RECOGNITION simplified abstract

From WikiPatents
Jump to navigation Jump to search

METHODS AND DEVICES FOR GESTURE RECOGNITION

Organization Name

intel corporation

Inventor(s)

Ping Guo of Beijing (CN)

Sangeeta Manepalli of Chandler AZ (US)

Lidan Zhang of Beijing (CN)

Peng Wang of Beijing (CN)

Yimin Zhang of Beijing (CN)

METHODS AND DEVICES FOR GESTURE RECOGNITION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240161494 titled 'METHODS AND DEVICES FOR GESTURE RECOGNITION

Simplified Explanation

The patent application describes a gesture recognition device that processes a sequence of images showing body parts performing gestures to estimate the gesture being performed.

  • Input interface receives sequence of images showing body parts performing gestures
  • Device generates motion-compensated images by compensating for camera movement
  • Gesture is estimated from sequence of motion-compensated images

Potential Applications

This technology can be used in:

  • Virtual reality systems for more accurate gesture recognition
  • Sign language translation applications for improved accuracy

Problems Solved

  • Improved accuracy in gesture recognition
  • Reduction of errors caused by camera movement

Benefits

  • Enhanced user experience in virtual reality applications
  • Improved communication for individuals using sign language

Potential Commercial Applications

  • Gaming industry for more immersive gameplay experiences
  • Healthcare industry for communication assistance tools

Possible Prior Art

One possible prior art could be the use of motion capture technology in the entertainment industry for creating realistic animations.

Unanswered Questions

How does the device handle variations in lighting conditions that may affect image quality?

The patent application does not provide details on how the device compensates for changes in lighting conditions that could impact gesture recognition accuracy.

What is the processing speed of the device and how does it impact real-time applications?

The patent application does not mention the processing speed of the device or how it may affect real-time applications such as virtual reality systems.


Original Abstract Submitted

disclosed herein is a gesture recognition device that includes an input interface configured to receive a sequence of images, each image showing a body part with which a gesture is performed from a viewpoint of a camera. the gesture recognition device also generates a sequence of motion-compensated images from the sequence comprising generating a motion-compensated image for an image of the sequence by compensating the movement of the camera viewpoint from a reference camera viewpoint to the viewpoint from which the image shows the body part based on the image and a motion-compensated image of the sequence generated for a preceding image of the sequence which precedes the image in the sequence and estimate the gesture from the sequence of motion-compensated images.