Feature based remote sensing image registration techniques: a comprehensive and comparative review

Misra, Indranil; Rohil, Mukesh Kumar; Moorthi, S. Manthira; Dhar, Debajyoti

doi:10.1080/01431161.2022.2114112

Cited by 22 publications

(11 citation statements)

References 128 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This basic script aims to provide a straightforward yet effective tool for visualizing two essential water quality indicators (Chlorophyll-a and Turbidity). The empirical models in the script were developed from the fit of in-situ data and specific Sentinel-2 spectral band combinations for studying inland waters, such as lakes and rivers [15]. The equations for each model (one per parameter) are mapped to a color scale with parameters defined in the script.…”

Section: Analysis Of the Imagesmentioning

confidence: 99%

Integrating satellite remote sensing into the standard operating procedure of a water utility

Lioumbas,

Christodoulou,

Katsiapi

et al. 2023

Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023)

View full text Add to dashboard Cite

This study explores the feasibility and benefits of incorporating Satellite Remote Sensing Techniques (SRST) into drinking water supply companies' processes for monitoring large reservoirs' surface water quality. Focusing on Thessaloniki Water Supply & Sewerage Co S.A. (EYATH SA), the study examines an unexpected event in the Polyphytos reservoir detected by satellite-based instruments. Images from Sentinel-2 and Landsat 8-9 were analyzed using algorithms such as Se2WaQ and Oil-index to estimate water quality parameters. The potential of the under-development Water Quality Emergency Monitoring Service (WQeMS) for real-time monitoring and early warning was also assessed. A strategic plan for integrating satellite tools in surface water quality monitoring processes is presented, demonstrating several advantages, such as detecting unexpected events, continuous monitoring, and cost-effectiveness. This study emphasizes the potential benefits of integrating SRST into water utilities' processes for large reservoirs' surface water quality monitoring and suggests a useful workflow for similar applications.

show abstract

Section: Analysis Of the Imagesmentioning

confidence: 99%

Integrating satellite remote sensing into the standard operating procedure of a water utility

Lioumbas,

Christodoulou,

Katsiapi

et al. 2023

Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023)

View full text Add to dashboard Cite

show abstract

“…However, region-based matching methods are sensitive to nonlinear grayscale distortions, making them less suitable for multi-modal image matching. Feature-based matching methods [7] extract common features from reference and target images and establish correspondences to determine the transformation model parameters for matching. These features include region features, line features (extracted from edges and texture information) and point features.…”

Section: Introductionmentioning

confidence: 99%

Structure similarity virtual map generation network for optical and SAR image matching

Chen,

Mei

2024

Front. Phys.

View full text Add to dashboard Cite

Introduction: Optical and SAR image matching is one of the fields within multi-sensor imaging and fusion. It is crucial for various applications such as disaster response, environmental monitoring, and urban planning, as it enables comprehensive and accurate analysis by combining the visual information of optical images with the penetrating capability of SAR images. However, the differences in imaging mechanisms between optical and SAR images result in significant nonlinear radiation distortion. Especially for SAR images, which are affected by speckle noises, resulting in low resolution and blurry edge structures, making optical and SAR image matching difficult and challenging. The key to successful matching lies in reducing modal differences and extracting similarity information from the images.Method: In light of this, we propose a structure similarity virtual map generation network (SVGNet) to address the task of optical and SAR image matching. The core innovation of this paper is that we take inspiration from the concept of image generation, to handle the predicament of image matching between different modalities. Firstly, we introduce the Attention U-Net as a generator to decouple and characterize optical images. And then, SAR images are consistently converted into optical images with similar textures and structures. At the same time, using the structural similarity (SSIM) to constrain structural spatial information to improve the quality of generated images. Secondly, a conditional generative adversarial network is employed to further guide the image generation process. By combining synthesized SAR images and their corresponding optical images in a dual channel, we can enhance prior information. This combined data is then fed into the discriminator to determine whether the images are true or false, guiding the generator to optimize feature learning. Finally, we employ least squares loss (LSGAN) to stabilize the training of the generative adversarial network.Results and Discussion: Experiments have demonstrated that the SVGNet proposed in this paper is capable of effectively reducing modal differences, and it increases the matching success rate. Compared to direct image matching, using image generation ideas results in a matching accuracy improvement of more than twice.

show abstract

“…Then, a descriptor vector is generated for each candidate based on the distributions of grey values around the detected feature that is used for similarity measurement between candidates. Generally, differences in the way of detecting candidates, generating descriptors, and measuring the similarity between the descriptors differentiate the feature-based image matching methods from each other [16,18].…”

Section: Introductionmentioning

confidence: 99%

“…In the feature‐based image matching methods, candidate features (e.g. corners, blobs, or semantic objects) are first detected independently in the images [18]. Then, a descriptor vector is generated for each candidate based on the distributions of grey values around the detected feature that is used for similarity measurement between candidates.…”

Section: Introductionmentioning

confidence: 99%

Automatic refinement of ephemeris‐derived range‐Doppler model through the least‐squares matching of Sentinel‐1 Single‐Look Complex images and DEM in mountainous areas

Saeedi Amale,

Safdarinezhad

2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Range‐Doppler model is a transformation that relates ground and Single‐Look Complex SAR image spaces by knowing the instantaneous position and velocity of the sensor in its trajectory. Its instantaneous position and velocities are determined with the help of vectorial functions, which their precisions directly influence the accuracy of the range‐Doppler model. Ephemeris data is one of the sources used for the estimation of temporal functions. Some reasons can cause uncertainty in the temporal function directly derived from the satellite navigation data. Ground control points are other alternatives for calibration of the range‐Doppler model whose visual measurements are difficult in the mountainous areas of Sentinel‐1 Single‐Look Complex images due to their resolutions and distortions. The temporal functions of the range‐Doppler model are refined through numerous control points extracted from the automatic matching between Single‐Look Complex images and Digital Elevation Model. For this purpose, the radiometric and geometric similarities of the Single‐Look Complex images and Digital Elevation Model in mountainous areas are first increased based on the initial range‐Doppler model, and then their geometric discrepancies are compensated with the least‐squares image matching method. The results indicated that the proposed method in mountainous areas could automatically compensate for up to 30 pixels errors and reach sub‐pixel accuracies.

show abstract

Feature based remote sensing image registration techniques: a comprehensive and comparative review

Cited by 22 publications

References 128 publications

Integrating satellite remote sensing into the standard operating procedure of a water utility

Integrating satellite remote sensing into the standard operating procedure of a water utility

Structure similarity virtual map generation network for optical and SAR image matching

Automatic refinement of ephemeris‐derived range‐Doppler model through the least‐squares matching of Sentinel‐1 Single‐Look Complex images and DEM in mountainous areas

Contact Info

Product

Resources

About