Abstract
Image registration is an important basis of image processing, which is of great significance in image mosaicking, target recognition, and change detection. Aiming at the automatic registration problem of multi-angle optical images for ground scenes, a registration method combining point features and line features to register images is proposed. Firstly, the LSD (Line Segment Detector) algorithm is used to extract line features of images. The obtained line segments whose length are less than a given threshold are eliminated by a visual significant algorithm. Then, an affine transform model obtained by estimating a Gaussian mixture model (GMM) is applied to the image to be matched. Lastly, Harris point features are utilized in fine matching to overcome shortages of methods based on line features. In experiments, the proposed algorithm is compared with popular feature-based registration algorithms. The results indicate that the proposed algorithm in this work has obvious advantages in terms of registration accuracy and reliability for optical images acquired at different angles.
Highlights
Academic Editor: Loris NanniThe specific task of image registration technology is to determine point-by-point mapping relationships among images acquired from same scenes in different shooting conditions, such as angles, time, and sensors
Focused on multi-angle optical images of ground scenes, this work combines line features with point features to improve the quality of image registration
An iteration method is designed based on Gaussian mixture model (GMM) to match extracted linear segments and optimize parameters of affine transform models
Summary
The specific task of image registration technology is to determine point-by-point mapping relationships among images acquired from same scenes in different shooting conditions, such as angles, time, and sensors. There are various divergences in images caused by differences of view procedure of our algorithm, in which rough matching by using LSD and GMMs a angles, such as displacement, scale, and rotation. The proposed registration method is verified and compared with other algorithms by using multi-angle optical images. For ordinary optical images with certain differences of view angles, point a features are combined in order to deal with the limitations of popular regis. For ordinary optical images with certain differences of view angles, point and line methods based on point features in this work.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have