17584682. METHOD AND APPARATUS WITH POSE ESTIMATION simplified abstract (Samsung Electronics Co., Ltd.)
Contents
METHOD AND APPARATUS WITH POSE ESTIMATION
Organization Name
Inventor(s)
Donghoon Sagong of Suwon-si (KR)
METHOD AND APPARATUS WITH POSE ESTIMATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17584682 titled 'METHOD AND APPARATUS WITH POSE ESTIMATION
Simplified Explanation
The abstract describes a method for pose estimation using image and motion sensor data. Here are the key points:
- The method tracks the position of a feature point extracted from a series of image frames captured by an image sensor.
- It predicts the current state variable of an estimation model for determining the pose of an electronic device based on motion information from a motion sensor.
- The method determines the noise in the estimation model by comparing the actual position of the feature point with the predicted position based on the current state variable.
- It updates the current state variable using the tracked position of the feature point and the noise.
- Finally, the method determines the pose of the electronic device based on the updated current state variable.
Potential Applications
- Augmented reality: This method can be used to accurately determine the pose of an electronic device, such as a smartphone or a head-mounted display, which is crucial for overlaying virtual objects onto the real world.
- Robotics: The pose estimation technique can be applied to robots to help them navigate and interact with their environment more effectively.
- Virtual reality: By accurately determining the pose of a user's head-mounted display, this method can enhance the immersive experience in virtual reality applications.
Problems Solved
- Uncertainty in pose estimation: The method addresses the challenge of accurately estimating the pose of an electronic device by incorporating both image and motion sensor data.
- Noise reduction: By considering the noise due to the uncertainty of the estimation model, the method improves the accuracy of the pose estimation.
Benefits
- Improved accuracy: By combining image and motion sensor data, the method provides more accurate pose estimation results.
- Real-time tracking: The method can track the pose of an electronic device in real-time, allowing for responsive and interactive applications.
- Robustness: By accounting for the uncertainty and noise in the estimation model, the method is more robust to variations and disturbances in the environment.
Original Abstract Submitted
A processor-implemented method with pose estimation includes: tracking a position of a feature point extracted from image information comprising a plurality of image frames, the image information being received from an image sensor; predicting a current state variable of an estimation model for determining a pose of an electronic device, based on motion information received from a motion sensor; determining noise due to an uncertainty of the estimation model based on a residual between a first position of the feature point extracted from the image frames and a second position of the feature point predicted based on the current state variable; updating the current state variable based on the current state variable, the tracked position of the feature point, and the noise; and determining the pose of the electronic device based on the updated current state variable.