Method for panorama image processing
An image processing method for obtaining a panoramic image includes obtaining a first image and a second image by a camera unit, and obtaining location information between the viewpoints of the first image and the second image by a gyro. First features of the first image and second features of the second image are obtained according to a feature-capturing algorithm when pixel brightness differences exceed a threshold. Predicted features in the second image are obtained by the location information, and predicted features that exceed a predetermined distance from the second features are discarded. A panorama image is obtained by combining the first image and the second image according to the first features and the selected second features.
1. An image processing method, for a panorama image, comprising:
capturing a first image and a second image by a camera unit;
obtaining a location information between the first image and the second image by a gyro;
obtaining a plurality of first features of the first image and a plurality of second features of the second image according to a feature-capturing algorithm when brightness difference between the first features and the second features exceed a threshold;
obtaining predicted features in the second image by the location information;
obtaining selected second features by discarding the predicted features exceeding a predetermined distance from the second features; and
producing the panorama image by combining the first image and the second image according to the first features and the selected second features;
splitting the first image as a plurality of first sub-images and the second image as a plurality second sub-images; and
updating the threshold of the feature-capturing algorithm on each of first sub-images according to numbers of the first features, raises the threshold when the number of the first features on the first sub-image is less than an average of the numbers of the first features on each of sub-images, reduces the threshold when the number of the first features on the first sub-image is more than the average of the numbers of the first features on each of sub-images.
2. The image processing method as claimed in claim 1 , further comprising obtaining the distance between the second features and the corresponding predicted features according to Euclidean distance.
3. The image processing method as claimed in claim 1 , further comprising obtaining a rotation matrix between the first features and the corresponding second features according to Euler angles, and produces the panorama images according to the rotation matrix to combine the first image and the second image.