A Pixel Shift Estimation Approach Using Spectral Information
Open Access
- 8 February 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (4) , 664
Abstract
This research paper presents a robust image registration algorithm tailored for the accurate estimation of image displacements. Image registration is a fundamental task in computer vision and image processing, with applications ranging from medical imaging to motion tracking in surveillance systems. The algorithm’s efficacy is explored through a series of experiments conducted on image pairs, both in scenarios without noise and those affected by additive noise. The algorithm’s core methodology involves a combination of techniques, including Fourier transforms, phase correlation, and subpixel estimation. By leveraging these techniques, the algorithm can simultaneously compute both the integer and subpixel components of image displacement. This capability is particularly valuable in scenarios demanding precise alignment and motion analysis. In the experiments, the algorithm’s performance is assessed using the Mean Estimation Error (MEE), which quantifies the accuracy of displacement estimation. The results reveal that the algorithm consistently achieves high precision and accuracy, even in the presence of uniform white noise with a mean of 25 and standard deviation of 15. This robustness to noise underscores its suitability for real-world applications where images are often affected by various sources of interference. The comparative analysis between noise-free and noisy scenarios demonstrates the algorithm’s resilience to adverse conditions, making it a versatile tool for image registration tasks in practical environments. Its potential applications encompass computer vision, medical imaging, security and surveillance, and high-precision image processing. The robustness of the algorithm to noise and sub-pixel accuracy makes it an asset for a wide range of applications, promising enhanced capabilities in image alignment and motion analysis.Keywords
This publication has 53 references indexed in Scilit:
- Sub‐Pixel Displacement Estimation With Deep Learning: Application to Optical Satellite Images Containing Sharp DisplacementsJournal of Geophysical Research: Machine Learning and Computation, 2024
- Improved compressed sensing and super‐resolution of cardiac diffusion MRI with structure‐guided total variationMagnetic Resonance in Medicine, 2020
- CNN-based superresolution reconstruction of 3D MR images using thick-slice scansBiocybernetics and Biomedical Engineering, 2020
- Deep convolution network for surveillance records super-resolutionMultimedia Tools and Applications, 2018
- Exploring sex differences in the adult zebra finch brain: In vivo diffusion tensor imaging and ex vivo super-resolution track density imagingNeuroImage, 2017
- A super-resolution reconstruction algorithm for surveillance imagesSignal Processing, 2010
- Fluorescent probes for super-resolution imaging in living cellsNature Reviews Molecular Cell Biology, 2008
- Integrated recurrent neural network for image resolution enhancement from multiple image framesIEE Proceedings - Vision, Image, and Signal Processing, 2003
- Spatial resolution improvement of remotely sensed images by a fully interconnected neural network approachIEEE Transactions on Geoscience and Remote Sensing, 2000
- Image interpolation with adaptive receptive field-based Gaussian radial basis functionsMicrowave and Optical Technology Letters, 1996