17931859. SEGMENTATION MASK EXTRAPOLATION simplified abstract (QUALCOMM Incorporated)
Contents
SEGMENTATION MASK EXTRAPOLATION
Organization Name
Inventor(s)
Qureshi Asma of Thornhill (CA)
Darren Gnanapragasam of Aurora (CA)
Alireza Shoa Hassani Lashdan of Burlington (CA)
SEGMENTATION MASK EXTRAPOLATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17931859 titled 'SEGMENTATION MASK EXTRAPOLATION
Simplified Explanation
The patent application describes a technique for processing video data, including estimating motion vectors and extrapolating segmentation masks.
- Receiving a first image after a previous image
- Receiving a first segmentation mask associated with the previous image
- Estimating a first set of forward motion vectors between the previous image and the first image
- Estimating the reliability of the first set of forward motion vectors
- Extrapolating a second segmentation mask associated with the first image using the motion vectors and first segmentation mask based on the estimated reliability
Potential Applications
- Video editing software
- Surveillance systems
- Virtual reality technology
Problems Solved
- Accurate motion estimation in video processing
- Seamless object tracking in video sequences
Benefits
- Improved video quality
- Enhanced object segmentation
- Efficient video data processing
Original Abstract Submitted
Systems and techniques are described herein for processing video data. For instance, a technique can include receiving a first image after a previous image. The process can further include receiving a first segmentation mask associated with the previous image. The process can also include estimating a first set of forward motion vectors between the previous image and the first image. The process can further include estimating a reliability of the first set of forward motion vectors. The process can also include extrapolating a second segmentation mask associated with the first image using the first set of forward motion vectors and first segmentation mask based on the estimated reliability of the first set of forward motion vectors.
