18492234. SYSTEMS AND METHODS FOR ENCODING TEMPORAL INFORMATION FOR VIDEO INSTANCE SEGMENTATION AND OBJECT DETECTION simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
- 1 SYSTEMS AND METHODS FOR ENCODING TEMPORAL INFORMATION FOR VIDEO INSTANCE SEGMENTATION AND OBJECT DETECTION
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 SYSTEMS AND METHODS FOR ENCODING TEMPORAL INFORMATION FOR VIDEO INSTANCE SEGMENTATION AND OBJECT DETECTION - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
SYSTEMS AND METHODS FOR ENCODING TEMPORAL INFORMATION FOR VIDEO INSTANCE SEGMENTATION AND OBJECT DETECTION
Organization Name
Inventor(s)
Biplab Ch Das of Bengaluru (IN)
Kiran Nanjunda Iyer of Bengaluru (IN)
Himadri Sekhar Bandyopadhyay of Bengaluru (IN)
SYSTEMS AND METHODS FOR ENCODING TEMPORAL INFORMATION FOR VIDEO INSTANCE SEGMENTATION AND OBJECT DETECTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18492234 titled 'SYSTEMS AND METHODS FOR ENCODING TEMPORAL INFORMATION FOR VIDEO INSTANCE SEGMENTATION AND OBJECT DETECTION
Simplified Explanation
The abstract describes a method of encoding temporal information for stable video instance segmentation and video object detection using a neural network.
- Neural network analyzes input frame of a video to output a prediction template.
- Prediction template includes segmentation masks or bounding boxes of objects in the input frame.
- Prediction template is color coded by a template generator.
- Color coded template, along with a subsequent frame, is supplied to a template encoder to encode temporal information.
Potential Applications
- Video surveillance systems
- Autonomous vehicles
- Augmented reality applications
Problems Solved
- Stable video instance segmentation
- Accurate video object detection
Benefits
- Improved accuracy in identifying objects in videos
- Enhanced stability in segmenting objects
- Efficient encoding of temporal information for better analysis of video data
Original Abstract Submitted
In a method of encoding of temporal information for stable video instance segmentation and video object detection, a neural network analyzes an input frame of a video to output a prediction template. The prediction template includes either segmentation masks of objects in the input frame or bounding boxes surrounding objects in the input frame. The prediction template is then colour coded by a template generator. The colour coded template, along with a frame subsequent to the input frame, is supplied to a template encoder such that temporal information from the input frame is encoded into the output of the temporal encoder.