20240053463. METHODS AND APPARATUSES FOR LATENCY REDUCTION IN GESTURE RECOGNITION USING MMWAVE RADAR simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
METHODS AND APPARATUSES FOR LATENCY REDUCTION IN GESTURE RECOGNITION USING MMWAVE RADAR
Organization Name
Inventor(s)
Saifeng Ni of Santa Clara CA (US)
Priyabrata Parida of Garland TX (US)
Boon Loong Ng of Plano TX (US)
METHODS AND APPARATUSES FOR LATENCY REDUCTION IN GESTURE RECOGNITION USING MMWAVE RADAR - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240053463 titled 'METHODS AND APPARATUSES FOR LATENCY REDUCTION IN GESTURE RECOGNITION USING MMWAVE RADAR
Simplified Explanation
The method described in the patent application involves analyzing radar data to detect gestures by using a sliding input data window and binary predictions.
- Radar data is obtained and organized into a sliding input data window consisting of recent radar frames.
- Each radar frame in the data window includes selected features and time-velocity or time-angle data.
- For each radar frame in the data window, a binary prediction is received to indicate if a gesture end is present.
- If a gesture end is predicted, an early stop (ES) checker is triggered to determine if certain conditions are met.
- The ES checker evaluates noise frames and valid activity conditions to decide if the ES condition is satisfied.
- If the ES condition is met, a gesture classifier is activated to predict the type of gesture.
Potential applications of this technology: - Gesture recognition systems for human-computer interaction - Security systems for detecting suspicious movements or gestures - Automotive safety systems for driver monitoring and control
Problems solved by this technology: - Efficient and accurate detection of gestures in radar data - Real-time analysis of gestures without processing unnecessary data - Improved user interface experiences through gesture recognition
Benefits of this technology: - Enhanced security and surveillance capabilities - Seamless integration of gesture control in various devices - Increased efficiency in human-computer interaction and automation systems
Original Abstract Submitted
a method includes obtaining a stream of radar data into a sliding input data window composed of recent radar frames from the stream. each radar frame within the data window includes features selected from a predefined feature set and at least one of time-velocity data or time angle data. the method includes, for each radar frame within the data window, receiving a binary prediction indicating whether the radar frame includes a gesture end. the method includes in response to the binary prediction indicating that the radar frame includes the gesture end, triggering an early stop (es) checker to determine whether an es condition is satisfied. determining whether the es condition is satisfied comprises determining whether a noise frames condition and a valid activity condition are satisfied. the method includes in response to a determination that the es condition is satisfied, triggering a gesture classifier to predict a gesture type.
