18457636. METHOD AND ELECTRONIC DEVICE FOR DETERMINING USER'S HAND IN VIDEO simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

From WikiPatents
Jump to navigation Jump to search

METHOD AND ELECTRONIC DEVICE FOR DETERMINING USER'S HAND IN VIDEO

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Yevhenii Yakishyn of Kyiv (UA)

METHOD AND ELECTRONIC DEVICE FOR DETERMINING USER'S HAND IN VIDEO - A simplified explanation of the abstract

This abstract first appeared for US patent application 18457636 titled 'METHOD AND ELECTRONIC DEVICE FOR DETERMINING USER'S HAND IN VIDEO

Simplified Explanation

The patent application describes a method for recognizing gestures in a video by tracking the movements of a user's field of view (FoV) and objects in the video. Here are the key points:

  • Obtaining a video with multiple frames
  • Estimating the trajectory of the camera's field of view (FoV) by analyzing the frames
  • Detecting feature points of objects in each frame
  • Estimating the movements of the objects (object trajectories) based on the feature points
  • Identifying potential hand candidates of the user from the objects, using the FoV trajectory and object trajectories
  • Analyzing the movement trajectory of the user's head
  • Determining the user's hand based on the head movement trajectory and object trajectories corresponding to the hand candidates
  • Tracking the user's hand in the video
  • Recognizing gestures performed by the user

Potential Applications

This technology has various potential applications, including:

  • Gesture-based user interfaces: It can be used to control devices or applications through hand gestures, eliminating the need for physical input devices.
  • Virtual reality (VR) and augmented reality (AR): The method can enhance user interaction in VR/AR environments by allowing users to perform gestures naturally.
  • Gaming: Gesture recognition can enable more immersive and interactive gaming experiences, where players can control characters or actions through gestures.
  • Accessibility: This technology can assist individuals with physical disabilities by providing alternative methods of interaction with devices or systems.

Problems Solved

The method addresses several problems related to gesture recognition:

  • Accurate hand detection: By considering the FoV trajectory, object trajectories, and head movement trajectory, the method improves the accuracy of hand detection in complex video scenes.
  • Robust gesture recognition: The combination of FoV and object trajectories helps in accurately recognizing gestures even in challenging scenarios with occlusions or background clutter.
  • Natural interaction: By allowing users to control devices or systems through gestures, the method provides a more intuitive and natural way of interaction compared to traditional input methods.

Benefits

This technology offers several benefits:

  • Enhanced user experience: Gesture-based interaction provides a more immersive and engaging user experience, particularly in applications like gaming or VR/AR.
  • Improved accuracy: By considering multiple factors like FoV trajectory and object trajectories, the method improves the accuracy of hand detection and gesture recognition.
  • Accessibility: Gesture recognition can make technology more accessible to individuals with physical disabilities, enabling them to interact with devices or systems more easily.
  • Elimination of physical input devices: The method eliminates the need for physical input devices like keyboards or controllers, allowing users to interact directly through gestures.


Original Abstract Submitted

A method is provided. The method includes obtaining a video including a plurality of frames, estimating a field of view (FoV) trajectory indicating movements of a FoV of the camera, by using the frames of the video, detecting feature points of one or more objects in each of the frames of the video, estimating object trajectories indicating movements of the one or more objects, based on the feature points, determining hand candidates of a user from among the one or more objects, based on the FoV trajectory of the camera and the object trajectories, obtaining a head movement trajectory indicating movements of a head of the user, determining a hand of the user, based on the head movement trajectory and the object trajectories corresponding to the hand candidates of the user, tracking the determined hand of the user in the video, and recognizing a gesture.

Retrieved from "http://wikipatents.org/index.php?title=18457636._METHOD_AND_ELECTRONIC_DEVICE_FOR_DETERMINING_USER%27S_HAND_IN_VIDEO_simplified_abstract_(SAMSUNG_ELECTRONICS_CO.,_LTD.)&oldid=16890"