Image stabilizing apparatus and method based on a predicted movement position
AssigneeHanwha Techwin Co., Ltd.
InventorsYeongeol Ryu, Sangji Park, Hwalsuk Lee
Life of this patent
Estimating the term…
Abstract
Provided are an image stabilizing apparatus and method thereof. The image stabilizing apparatus performs image stabilization by using both an image sensor and a motion sensor. Image distortion and movement are stably corrected by using both the position of a feature point, which is extracted by the image sensor and image processing, and the movement position of the feature point, which is predicted by the motion sensor.
Claims19
A vibration correcting method in a moving camera, the vibration correcting method comprising:
- extracting a feature point in an input image of the moving camera;
- predicting a position, to which a feature point extracted in a first image is to move due to vibration of the moving camera, by using a motion sensor;
- generating a motion vector between the feature point extracted in the first image, the predicted position to which the feature point extracted in the first image is to move, and a feature point extracted in a second image captured by the moving camera after occurrence of the vibration;
- and
- correcting vibration of the second image based on the motion vector,
- wherein the feature point extracted in the first image is detected based on a physical movement amount of the moving camera measured by using the motion sensor, and the feature point extracted in the second image is detected based on an image sensor of the moving camera.
A vibration correcting method in a moving camera, the vibration correcting method comprising:
- extracting a feature point in an input image of the moving camera;
- predicting a position, to which a feature point extracted in a first image is to move due to vibration of the moving camera, by using a motion sensor;
- generating a motion vector between the feature point extracted in the first image, the predicted position to which the feature point extracted in the first image is to move, and a feature point extracted in a second image captured by the moving camera after occurrence of the vibration;
- and
- correcting vibration of the second image based on the motion vector,
- wherein the correcting the vibration of the second image comprises determining that a position of the feature point extracted in the second image is accurate, when a distance between the predicted position to which the feature point extracted in the first image is to move and the feature point extracted in the second image captured by the moving camera after the occurrence of the vibration is within a predetermined range, and correcting the vibration of the second image by using position information of the feature point extracted in the second image.
A vibration correcting method in a moving camera, the vibration correcting method comprising:
- extracting a feature point in an input image of the moving camera;
- predicting a position, to which a feature point extracted in a first image is to move due to vibration of the moving camera, by using a motion sensor;
- generating a motion vector between the predicted position to which the feature point extracted in the first image is to move and a feature point extracted in a second image captured by the moving camera after occurrence of the vibration;
- and
- correcting vibration of the second image based on the motion vector,
- wherein the feature point extracted in the first image is detected based on a physical movement amount of the moving camera measured by using the motion sensor, and the feature point extracted in the second image is detected based on an image sensor of the moving camera.
A vibration correcting method in a moving camera, the vibration correcting method comprising:
- extracting a feature point in an input image of the moving camera;
- predicting a position, to which a feature point extracted in a first image is to move due to vibration of the moving camera, by using a motion sensor;
- generating a motion vector between the predicted position to which the feature point extracted in the first image is to move and a feature point extracted in a second image captured by the moving camera after occurrence of the vibration;
- and
- correcting vibration of the second image based on the motion vector,
- wherein the correcting the vibration the second image comprises determining that a position of the feature point extracted in the second image is accurate, when a distance between the predicted position to which the feature point extracted in the first image is to move and the feature point extracted in the second image captured by the moving camera after the occurrence of the vibration is within a predetermined range, and correcting the vibration of the second image by using position information of the feature point extracted in the second image.
Dependencies are inferred from the claim text.