CNN-based fusion and classification of SAR and Optical data

Shakya, Achala; Biswas, Mantosh; Pal, Mahesh

doi:10.1080/01431161.2020.1783713

Cited by 35 publications

(16 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, when we consider NDVI components, the model seems to generalise well when recovering S1 features as depicted in Figures 5 and 6. The key role of feature-adapted solutions based on CNN is also underlined in recent studies [33], [34], [35] when there is no available (fully cloudy condition) training data at a certain time for dynamic monitoring of agricultural fields.…”

Section: A Image Translation Between Sentinel-1/2mentioning

confidence: 94%

Soil Moisture Estimation Using Sentinel-1/-2 Imagery Coupled With CycleGAN for Time-Series Gap Filing

Efremova

Seddik

Erten

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Fast soil moisture content (SMC) mapping is necessary to support water resource management and to understand crops' growth, quality and yield. Thereby, Earth Observation (EO) plays a key role due to its ability of almost real-time monitoring of large areas at a low cost. This study aimed to explore the possibility of taking advantage of freely available Sentinel-1 (S1) and Sentinel-2 (S2) EO data for the simultaneous prediction of SMC with cycle-consistent adversarial network (cycleGAN) for time-series gap filling. The proposed methodology, first, learns latent low-dimensional representation of the satellite images, then learns a simple machine learning model on top of these representations. To evaluate the methodology, a series of vineyards, located in South Australia's Eden valley are chosen. Specifically, we presented an efficient framework for extracting latent features from S1 and S2 imagery. We showed how one could use S1 to S2 feature translation based on Cycle-GAN using S1&S2 time series when there are missing images acquired over an area of interest. The resulting data in our study is then used to fill gaps in time series data. We used the resulting latent representations to predict SMC with various ML tools. In the experiments, cycleGAN and the autoencoders were trained with data randomly chosen around the site of interest, so we could augment the existing dataset. The best performance was demonstrated with random forest algorithm, whereas linear regression model demonstrated significant overfitting. The experiments demonstrate that the proposed methodology outperforms the compared state-of-the-art methods if there are missing optical and synthetic-aperture radar (SAR) images.

show abstract

Section: A Image Translation Between Sentinel-1/2mentioning

confidence: 94%

Soil Moisture Estimation Using Sentinel-1/-2 Imagery Coupled With CycleGAN for Time-Series Gap Filing

Efremova

Seddik

Erten

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Second, the percentage difference was calculated by considering images of 2019 as a reference image to determine the extent of changes in two different periods. Later on, the P-SNR values were also computed, which shows the peak signal-to-noise ratio, in decibels, between two images [30]. This ratio was further used as a quality measurement between the original and a compressed image.…”

Section: Satellite Data Derived Urban Natural Environment Variablesmentioning

confidence: 99%

“…This ratio was further used as a quality measurement between the original and a compressed image. The higher the PSNR, the better the quality of the compressed or reconstructed image [30,31].…”

Section: Satellite Data Derived Urban Natural Environment Variablesmentioning

confidence: 99%

Did Covid-19 lockdown positively affect the urban environment and UN- Sustainable Development Goals?

et al. 2022

Self Cite

View full text Add to dashboard Cite

This work quantifies the impact of pre-, during- and post-lockdown periods of 2020 and 2019 imposed due to COVID-19, with regards to a set of satellite-based environmental parameters (greenness using Normalized Difference Vegetation and water indices, land surface temperature, night-time light, and energy consumption) in five alpha cities (Kuala Lumpur, Mexico, greater Mumbai, Sao Paulo, Toronto). We have inferenced our results with an extensive questionnaire-based survey of expert opinions about the environment-related UN Sustainable Development Goals (SDGs). Results showed considerable variation due to the lockdown on environment-related SDGs. The growth in the urban environmental variables during lockdown phase 2020 relative to a similar period in 2019 varied from 13.92% for Toronto to 13.76% for greater Mumbai to 21.55% for Kuala Lumpur; it dropped to −10.56% for Mexico and −1.23% for Sao Paulo city. The total lockdown was more effective in revitalizing the urban environment than partial lockdown. Our results also indicated that Greater Mumbai and Toronto, which were under a total lockdown, had observed positive influence on cumulative urban environment. While in other cities (Mexico City, Sao Paulo) where partial lockdown was implemented, cumulative lockdown effects were found to be in deficit for a similar period in 2019, mainly due to partial restrictions on transportation and shopping activities. The only exception was Kuala Lumpur which observed surplus growth while having partial lockdown because the restrictions were only partial during the festival of Ramadan. Cumulatively, COVID-19 lockdown has contributed significantly towards actions to reduce degradation of natural habitat (fulfilling SDG-15, target 15.5), increment in available water content in Sao Paulo urban area(SDG-6, target 6.6), reduction in NTL resulting in reducied per capita energy consumption (SDG–13, target 13.3).

show abstract

“…Considering the complementarity between different types of sensor data, researchers have started to fuse multi-type sensor data to solve traditional remote sensing problems, such as land cover analysis [10][11][12][13], change detection [14][15][16], image classification [17], and image fusion [18,19]. As a critical problem in the field of photogrammetry and remote sensing, topographic mapping is mainly completed using optical satellite images [20].…”

Section: Introductionmentioning

confidence: 99%

Exploiting High Geopositioning Accuracy of SAR Data to Obtain Accurate Geometric Orientation of Optical Satellite Images

et al. 2021

View full text Add to dashboard Cite

Accurate geopositioning of optical satellite imagery is a fundamental step for many photogrammetric applications. Considering the imaging principle and data processing manner, SAR satellites can achieve high geopositioning accuracy. Therefore, SAR data can be a reliable source for providing control information in the orientation of optical satellite images. This paper proposes a practical solution for an accurate orientation of optical satellite images using SAR reference images to take advantage of the merits of SAR data. Firstly, we propose an accurate and robust multimodal image matching method to match the SAR and optical satellite images. This approach includes the development of a new structural-based multimodal applicable feature descriptor that employs angle-weighted oriented gradients (AWOGs) and the utilization of a three-dimensional phase correlation similarity measure. Secondly, we put forward a general optical satellite imagery orientation framework based on multiple SAR reference images, which uses the matches of the SAR and optical satellite images as virtual control points. A large number of experiments not only demonstrate the superiority of the proposed matching method compared to the state-of-the-art methods but also prove the effectiveness of the proposed orientation framework. In particular, the matching performance is improved by about 17% compared with the latest multimodal image matching method, namely, CFOG, and the geopositioning accuracy of optical satellite images is improved, from more than 200 to around 8 m.

show abstract

CNN-based fusion and classification of SAR and Optical data

Cited by 35 publications

References 61 publications

Soil Moisture Estimation Using Sentinel-1/-2 Imagery Coupled With CycleGAN for Time-Series Gap Filing

Soil Moisture Estimation Using Sentinel-1/-2 Imagery Coupled With CycleGAN for Time-Series Gap Filing

Did Covid-19 lockdown positively affect the urban environment and UN- Sustainable Development Goals?

Exploiting High Geopositioning Accuracy of SAR Data to Obtain Accurate Geometric Orientation of Optical Satellite Images

Contact Info

Product

Resources

About