Aiming at the problem that he gray level of different spectral images varies greatly and the traditional feature extraction algorithm is difficult to maintain the local precision and edge detail of the image, a multi-channel multi-spectral image registration method based on A-KAZE algorithm. In the registration process, the Fast Explicit Diffusion (FED) numerical analysis framework is used to solve the nonlinear diffusion filter equation, and the nonlinear scale space is constructed. The feature points are obtained by calculating the Hessian matrix of each pixel; The invariant image feature vectors are constructed by the Modified-Local Difference Binary (M-LDB) descriptor. Then, the feature vectors are matched by KNN using Hamming distance, and the mismatched points are eliminated by M-estimator Sample Consensus (MSAC). Finally, the transformation matrix is calculated based on projection transformation model. For multi-channel multi-spectral images, the optimal registration route is calculated by level-by-level registration method, and the image registration is realized by registration strategy and transformation matrix. Multispectral phenological observation data were selected to verify the image registration effect of the algorithm, and compared with SIFT, SURF, KAZE algorithm. Experimental results show that this method can achieve sub-pixel registration accuracy on any two images, and has strong robustness and faster speed.
With digital cameras coming into wide-spread use and the intelligence in application system increasingly growing, 3D reconstruction has become an essential part of the vision system. For the sake of achieving it, geometric camera calibration in the context of three-dimensional machine vision must be performed firstly to determine a set of parameters that describe the mapping between 3-D reference coordinates and 2-D image coordinates. In the typical classic method with high calculation accuracy and strong robustness, however, little attention has been paid to initial values of distortion coefficients, and model constraints that make results global optimal. In this paper, we present an improved algorithm based on the traditional calibration method. First, determine exact homography matrices by RANSAC algorithm to reject more error points, solve the initial values of distortion with distortion model, and then constrain the image coordinates of feature points in line by straight lines. Finally, the whole optimized parameters, the suppression of re-projection errors, and the calibration parameters with higher precision are obtained. It becomes a prerequisite for the realization of image fusion and the wide application of computer vision in the field of 3D reconstruction.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.