A multi-resolution area-based technique for automatic multi-modal image registration

Abstract:The science of satellite observation is called remote sensing. In optical remote sensing, the multispectral (MS) image which contains color information is produced by three sensors covering the red, green and blue spectral wavelengths. Because of the trade-off imposed by the physical constraint between spatial and spectral resolutions, the MS image has poor spatial resolution. On the contrast, the panchromatic (PAN) images has high spatial resolution but without color information. Image fusion can combine the geometric detail of the PAN image and the color information of the MS image to produce a high-resolution MS image. -Image fusion is powerful tool to include the detail information into single image from many images taken from different sensors at different instants This study is carried out using Cartosat-2 Panchromatic image with 1m spatial resolution and Resource sat-1 Liss-IV sensor of 3 bands b 2 , b 3 and b 4 with 5.8 m spectral resolution. The images are to be pre-processed to accommodate the fusion algorithm requirements. This pre-processing may include registration and resampling of the MS and PAN images. Image Resampling is the mathematical technique used to alter the scale of an image. Popularly known basic interpolation techniques are nearest neighbor, bilinear and bicubic. These resampled MS and PAN images are fused by using Discrete Wavelet Transformations (DWT) technique. Fusion results are evaluated numerically; and quality metrix are calculated between the fused image and MS image.

show abstract

“…PAN image size [8] is 1000×1000 and MS image size is 200×200. These are taken from National Remote Sensing Centre (NRSC).…”

Section: Resultsmentioning

confidence: 99%

Evaluation of DWT based image Fusion with three Different Resampling Methods

Mamatha¹,

Lakshmaiah²,

Sumalatha³

2015

International Advanced Research Journal in Science, Engineering

View full text Add to dashboard Cite

show abstract

“…Moreover, the matching results cannot be obtained through the use of an ordinary computer because the needed memory exceeds that of the computer hardware. The other approach only uses ABM and performs a progressive image matching based on an image pyramid, thereby reducing the time consumed for searching corresponding points [4,15]. However, constructing a multi-level image pyramid based on complex subsampling method (e.g., wavelet pyramid) for very large images reduces efficiency.…”

Section: About the Coarse-to-fine Registrationmentioning

confidence: 99%

“…In the field of RS, automatic image registration (AIR) has been a widely studied problem for decades. AIR has been achieved in many different datasets, including multi-platform [1,2], multi-modal [3][4][5][6], multi-scale [7,8], and multi-angle [2,9] RS images. Considerable accuracy and efficiency have been obtained.…”

Section: Introductionmentioning

confidence: 99%

“…The most commonly used algorithms are methods based on mutual information [10][11][12], frequency-domain correlation [13,14], and cross correlation [4,8,9,15,16]. The main disadvantage of ABM lies in the excessive computing time spent on searching for the corresponding point; a matching strategy based on the image pyramid is usually helpful in accelerating the processing speed [4,15]. In FBM algorithms, salient features are extracted from different images, and then corresponding features are determined by comparing the similarities of their descriptions.…”

Section: Introductionmentioning

confidence: 99%

“…However, under certain situations, such as when the image size is extremely large or when complex image distortion exists, the aforementioned two models can make only a rough estimation of the transformation, but the fitting precision is insufficient and usually uneven on the image. To implement high-precision registration of images with significant distortions, some local fitting methods, such as B-spline functions [11], thin-plate splines [9,21,30], and local affine transformation based on triangulated irregular network (TIN) [4,8,15,29] have been applied. The experiment results of Arévalo et al [31] demonstrate that local methods outperform global methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Registration Method for Fusion of ZY-1-02C Satellite Images

Chen

Wang

et al. 2013

Remote Sensing

View full text Add to dashboard Cite

Automatic image registration (AIR) has been widely studied in the fields of medical imaging, computer vision, and remote sensing. In various cases, such as image fusion, high registration accuracy should be achieved to meet application requirements. For satellite images, the large image size and unstable positioning accuracy resulting from the limited manufacturing technology of charge-coupled device, focal plane distortion, and unrecorded spacecraft jitter lead to difficulty in obtaining agreeable corresponding points for registration using only area-based matching or feature-based matching. In this situation, a coarse-to-fine matching strategy integrating two types of algorithms is proven feasible and effective. In this paper, an AIR method for application to the fusion of ZY-1-02C satellite imagery is proposed. First, the images are geometrically corrected. Coarse matching, based on scale invariant feature transform, is performed for the subsampled corrected images, and a rough global estimation is made with the matching results. Harris feature points are then extracted, and the coordinates of the corresponding points are calculated according to the global estimation results. Precise matching is conducted, based on normalized cross correlation and least squares matching. As complex image distortion cannot be precisely estimated, a local estimation using the structure of triangulated irregular network is applied to eliminate the false matches. Finally, image resampling is conducted, based on local affine transformation, to achieve high-precision registration. Experiments with ZY-1-02C datasets demonstrate that the accuracy of the proposed method meets the requirements of fusion application, and its efficiency is also suitable for the commercial operation of the automatic satellite data process system. OPEN ACCESSRemote Sens. 2014, 6 158

show abstract

Application of Deep Learning for Registration Between SAR and Optical Images

Zhang¹,

Zhao²

2023

Smart Innovation, Systems and Technologies

View full text Add to dashboard Cite

A multi-resolution area-based technique for automatic multi-modal image registration

Cited by 36 publications

References 38 publications

Evaluation of DWT based image Fusion with three Different Resampling Methods

Evaluation of DWT based image Fusion with three Different Resampling Methods

Automatic Registration Method for Fusion of ZY-1-02C Satellite Images

Application of Deep Learning for Registration Between SAR and Optical Images

Contact Info

Product

Resources

About