18187634. METHODS AND APPARATUS FOR ENABLING DYNAMIC GESTURE INPUT FOR MICRO-GESTURE RECOGNITION simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
METHODS AND APPARATUS FOR ENABLING DYNAMIC GESTURE INPUT FOR MICRO-GESTURE RECOGNITION
Organization Name
Inventor(s)
Priyabrata Parida of Garland TX (US)
Saifeng Ni of Santa Clara CA (US)
Boon Loong Ng of Plano TX (US)
METHODS AND APPARATUS FOR ENABLING DYNAMIC GESTURE INPUT FOR MICRO-GESTURE RECOGNITION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18187634 titled 'METHODS AND APPARATUS FOR ENABLING DYNAMIC GESTURE INPUT FOR MICRO-GESTURE RECOGNITION
Simplified Explanation
The method described in the patent application involves analyzing radar frames within a sliding input data window to detect and segment gesture frames from non-gesture frames. The method includes obtaining the target distance and velocity for each radar frame, as well as determining a dynamic threshold distance for valid gesture performance. It then determines whether the target distance satisfies a proximity condition based on the threshold distance. If the proximity condition is not satisfied, it detects the start of activity based on the extracted features. In response to either the proximity condition being satisfied or the current radar frame including an end of the activity, the method segments the gesture frames from the non-gesture frames in the data window and discards the non-gesture frames to modify the data window.
- The method analyzes radar frames within a sliding input data window.
- It obtains the target distance and velocity for each radar frame.
- It determines a dynamic threshold distance for valid gesture performance.
- It checks if the target distance satisfies a proximity condition based on the threshold distance.
- If the proximity condition is not satisfied, it detects the start of activity based on the extracted features.
- It segments gesture frames from non-gesture frames in the data window based on the proximity condition or the end of activity.
- It discards the non-gesture frames to modify the data window.
Potential Applications
- Gesture recognition systems
- Human-computer interaction
- Virtual reality and augmented reality applications
- Automotive safety systems
Problems Solved
- Accurate detection and segmentation of gesture frames from non-gesture frames in radar data
- Efficient analysis of radar frames for gesture recognition
- Reliable start and end detection of gesture activities
Benefits
- Improved accuracy in gesture recognition
- Real-time detection and segmentation of gestures
- Enhanced user experience in human-computer interaction
- Increased safety in automotive applications
Original Abstract Submitted
A method includes obtaining a target distance and target velocity for each radar frame within a sliding input data window. Each radar frame within the data window includes extracted features. The method includes determining a dynamic threshold distance (d) for a range of distances wherein performance of a gesture is valid. The method includes determining whether the target distance corresponding to a current radar frame satisfies a proximity condition based on the d. The method includes in response to a determination the proximity condition is not satisfied, detecting a start of activity based on the extracted features. The method includes segmenting gesture frames from non-gesture frames in the data window, in response to at least one of: a determination the first proximity condition is satisfied, or a determination the current radar frame includes an end of the activity. The method includes discarding the non-gesture frames to modify the data window.
