Atmospheric Image Research Articles

Interplay Between Atmospheric Correction and Fusion Techniques Enhances the Quality of Remote Sensing Image Fusion

Remote sensing image fusion technology integrates observational data from multiple satellite platforms to leverage the complementary advantages of the different types of remote sensing images. High-quality fused remote sensing images provide detailed information on surface radiation, climate, and environmental conditions, thereby supporting governmental policies on environmental changes. Improving the quality and quantitative accuracy of fused images is a crucial trend in remote sensing image fusion research. This study investigates the impact of atmospheric correction and five widely applied fusion techniques on remote sensing image fusion. By constructing four fusion frameworks, it evaluates how the choice of fusion method, the implementation of atmospheric correction, the synchronization of atmospheric parameters, and the timing of atmospheric correction influence the outcomes of remote sensing image fusion. Aerial flights using remote sensors were conducted to acquire atmospheric parameter distribution images that are strictly synchronous with the remote sensing images. Comprehensive and systematic evaluations of the fused remote sensing images were performed. Experiments show that for the remote sensing images used, selecting the appropriate fusion method can improve the spatial detail evaluation metrics of the fused images by up to 2.739 times, with the smallest deviation from true reflectance reaching 35.02%. Incorporating synchronous atmospheric parameter distribution images can enhance the spatial detail evaluation metrics by up to 2.03 times, with the smallest deviation from true reflectance reaching 5.4%. This indicates that choosing an appropriate fusion method and performing imaging-based synchronous atmospheric correction before fusion can maximize the enhancement of spatial details and spectral quantification in fused images.

LUIE: Learnable physical model-guided underwater image enhancement with bi-directional unsupervised domain adaptation

Recently, learning-based underwater enhancement (UIE) methods have made considerable progress, significantly benefiting downstream tasks such as underwater semantic segmentation and underwater depth estimation. Most existing unsupervised UIE methods utilize the atmospheric image formation model to decompose underwater images into background color, transmission map, and scene radiance. However, they rely on simplified physical models for estimating the transmission map, over-simplifying its complex formation, which results in imprecise modeling of underwater scattering effects. Additionally, supervised UIE methods heavily depend on synthetic data or ground truth, leading to limited generalization capabilities due to the substantial domain gap presented in different underwater scenarios. To tackle these challenges, we propose a Learnable physical model-guided unsupervised domain adaptation framework for Underwater Image Enhancement, dubbed LUIE. LUIE learns to predict background light, depth, and scene radiance from an underwater image. We incorporate a learnable network to estimate the transmission map based on the predicted depth map. To minimize the inter-domain gap between synthetic and real underwater images, we introduce a bi-directional domain adaptation method that alternates the background light from each domain. Experimental results demonstrate the effectiveness of our proposed method compared to existing approaches, and high-level experiment results validate that our enhanced underwater results. Experiments in real-world settings on underwater ROVs platform with NVIDIA Jetson AGX Xavier further confirm the effectiveness and efficiency of our work.

Remote sensing image registration method based on synchronous atmospheric correction.

Image registration is a crucial preprocessing step in remote sensing applications, integrating information from multiple images to achieve synergistic advantages. Nevertheless, aerosols characterized by spatiotemporal heterogeneity can result in the blurring of remote-sensing images, thereby compromising the accuracy of image registration. This paper begins by analyzing the basic principles of atmospheric correction and image registration. The variations in atmospheric radiative contribution caused by aerosol changes in real-world scenarios were simulated, along with an examination of the relationship between atmospheric effects and the quantity of image features. Subsequently, addressing the challenge posed by insufficient synchronicity in aerosol parameters and the influence of atmospheric effects on remote sensing image registration, we propose a registration method based on synchronous atmospheric correction. This approach utilizes the Airborne Synchronous Monitoring Atmospheric Corrector (ASMAC) to obtain aerosol optical depth and column water vapor images for synchronous atmospheric correction of remote sensing images, along with the assessment of the registration transformation matrix. Finally, airborne experiments involving ASMAC and high-resolution cameras are conducted to validate the proposed method's improvement in remote sensing image registration accuracy. Experimental results demonstrate the effectiveness of the proposed method, showcasing an increase in the number of features and improvements in quantitative evaluation metrics. Specifically, the normalized correlation coefficient improved by up to 2.408%, while the normalized mutual information increased by a maximum of 1.395%, a maximum feature count and successfully matched features improvement of 21.1% and 38.5.

Atmospheric Cloud Image Detection with Convolutional Neural Network (CNN

Atmospheric Cloud Image Detection with Convolutional Neural Network (CNN

Performance test of clean-coastal-water composite sentinel 2A image for shallow water bathymetry mapping

The “clean-coastal-water time-series composite” image preprocessing algorithm is one of the alternatives for obtaining minimal atmospheric disturbance satellite images for data inputs in Satellite-Derived Bathymetry (SDB). However, the performance of time-series composite images for shallow water bathymetric mapping needs to be assessed, considering the presence of pixel and band dispersion during the composite image construction process. This research aims to study the result of a clean-coastal-water time-series composite Sentinel-2 by using cloud computing preprocessing as input data for SDB in shallow waters, compare the results of SDB from a Sentinel-2 single date image and from the clean-coastal-water time-series composite image using a random forest regressor (RFR) algorithm in terms of accuracy and spatial distribution of the bathymetry, and evaluate the performance and quality of bathymetric maps obtained from a single date image and clean-coastal-water time-series composite Sentinel-2 images based on International Hydrographic Organization standards (IHO). The results show that not all time-series composite processes can produce clean images of interference from clouds, sunglints, bad waters, and pixel wave breaks. The acquisition time range affects the quality of the time-series composite image. The SDB RFR model can handle the complex relationship between the in situ water depth variable and the surface reflectance value of a clean-coastal-water time-series composite image that has pixel and band dispersion. Overall, the SDB RFR model was successfully used to predict bathymetry in shallow waters with accuracy that meets the IHO standard CATZOC requirements, with RMSE and MAE values of less than 0.5 m as well as TVU confidence level values of more than 95% at a depth of 0–5 m resulting from each - respectively clean-coastal-water time-series composite images in shallow waters around Morotai Island.

Social media for brand image manipulation: an automotive industry applied approach

The paper illustrates how social media marketing and analytics can assist businesses in achieving branding objectives by increasing their social media impact through advertising, getting social, using appropriate keywords, and creating effective and interactive communication channels with their intended audience. The multifaceted influence of social media postings is demonstrated by leveraging the Toyota Motor Corporation example. An explanation of how defamatory incidents have impacted the company’s social media atmospheric image is also included. Evidence of how negative intervals of social media presence could have been intelligently reversed through efficient content infusions is presented. Among numerous instruments allowing for analysis of marketing strategy results, “Social Mention”, “Talkwalker” and “Mentiolytics” were selected in order to demonstrate the efficiency and utility of social media monitoring methods using freely available tools. In this study, Toyota’s social media marketing strategy is highlighted by presenting measurements of variables such as the reach, strength, passion and sentiment of the brand over randomly selected time windows, demonstrating the dynamically evolving field of social media monitoring techniques.

Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network

The prevalence and mobility of smartphones make these a widely used tool for environmental health research. However, their potential for determining aggregated air quality index (AQI) based on PM2.5 concentration in specific locations remains largely unexplored in the existing literature. In this paper, we thoroughly examine the challenges associated with predicting location-specific PM2.5 concentration using images taken with smartphone cameras. The focus of our study is on Dhaka, the capital of Bangladesh, due to its significant air pollution levels and the large population exposed to it. Our research involves the development of a Deep Convolutional Neural Network (DCNN), which we train using over a thousand outdoor images taken and annotated. These photos are captured at various locations in Dhaka, and their labels are based on PM2.5 concentration data obtained from the local US consulate, calculated using the NowCast algorithm. Through supervised learning, our model establishes a correlation index during training, enhancing its ability to function as a Picture-based Predictor of PM2.5 Concentration (PPPC). This enables the algorithm to calculate an equivalent daily averaged AQI index from a smartphone image. Unlike, popular overly parameterized models, our model shows resource efficiency since it uses fewer parameters. Furthermore, test results indicate that our model outperforms popular models like ViT and INN, as well as popular CNN-based models such as VGG19, ResNet50, and MobileNetV2, in predicting location-specific PM2.5 concentration. Our dataset is the first publicly available collection that includes atmospheric images and corresponding PM2.5 measurements from Dhaka. Our codes and dataset are available at https://github.com/lepotatoguy/aqi.

Atmospheric Turbulence Degradation Image Restoration Based on Grid Network

Atmospheric Turbulence Degradation Image Restoration Based on Grid Network

The Elusive Nature of “Seeing”

Atmospheric image blur, “seeing”, is one of the key parameters that influences the selection of observatory sites and the performance of ground-based telescopes. In this review, the common definition of seeing based on the Kolmogorov turbulence model is recalled. The ability of this model to represent real, non-stationary fluctuations of the air refractive index is discussed. Even in principle, seeing (a model parameter) cannot be measured with arbitrary accuracy; consequently, describing atmospheric blur by a single number, seeing, is a crude approximation. The operating principles of current seeing monitors are outlined. They measure optical effects caused by turbulence, sampling certain regions of spatial and temporal spectrum of atmosphreic optical disturbances, and interpret their statistics in the framework of the standard model. Biases of seeing monitors (measurement noise, propagation, finite exposure time, optical defects, wind shake, etc.) should be quantified and corrected using simulations, while instrument comparison campaigns serve as a check. The elusive nature of seeing follows from its uniqueness (a given measurement cannot be repeated or checked later), its non-stationarity (dependence on time, location, and viewing direction), a substantial role of the highly variable surface layer, and a potential bias caused by the air flow in the immediate vicinity of the seeing monitors. The results of seeing measurements are outside the scope of this review.

Restoration of Binocular Images Degraded by Optical Scattering through Estimation of Atmospheric Coefficients.

A binocular vision-based approach for the restoration of images captured in a scattering medium is presented. The scene depth is computed by triangulation using stereo matching. Next, the atmospheric parameters of the medium are determined with an introduced estimator based on the Monte Carlo method. Finally, image restoration is performed using an atmospheric optics model. The proposed approach effectively suppresses optical scattering effects without introducing noticeable artifacts in processed images. The accuracy of the proposed approach in the estimation of atmospheric parameters and image restoration is evaluated using synthetic hazy images constructed from a well-known database. The practical viability of our approach is also confirmed through a real experiment for depth estimation, atmospheric parameter estimation, and image restoration in a scattering medium. The results highlight the applicability of our approach in computer vision applications in challenging atmospheric conditions.

Integrated digital image processing techniques and deep learning approaches for wheat stripe rust disease detection and grading

This study proposes integrated image processing and deep learning approaches for wheat rust disease detection and grading. Wheat stripe rust is one of the diseases affecting the crop in nearly all wheat-growing countries, where humidity and high temperatures characterize the growing season. The early and prompt detection of this disease is essential for establishing timely remedial measures to contain its spread. We present several image-processing and deep-learning approaches for detecting wheat stripe rust. The image processing techniques used in this research include single-band and dual-band processing, computing the Visual Atmospheric Resistance Index (VARI), image segmentation, and image cropping. These techniques are evaluated with different deep learning approaches like transfer learning and other Convolutional Neural Networks (CNNs) architectures. The results obtained on the dataset show that processing the images to eliminate the background as much as possible before training a suitable deep learning model with a low number of epochs optimally classifies the wheat stripe rust into the target classes (i.e., healthy, resistant, and susceptible) with an overall accuracy of 84.1% on the holdout test set. Besides the comparative analysis of various image processing approaches with different deep learning models, this study suggests multiple future research directions.

Blind Restoration of a Single Real Turbulence-Degraded Image Based on Self-Supervised Learning

Turbulence-degraded image frames are distorted by both turbulent deformations and space–time varying blurs. Restoration of the atmospheric turbulence-degraded image is of great importance in the state of affairs, such as remoting sensing, surveillance, traffic control, and astronomy. While traditional supervised learning uses lots of simulated distorted images for training, it has poor generalization ability for real degraded images. To address this problem, a novel blind restoration network that only inputs a single turbulence-degraded image is presented, which is mainly used to reconstruct the real atmospheric turbulence distorted images. In addition, the proposed method does not require pre-training, and only needs to input a single real turbulent degradation image to output a high-quality result. Meanwhile, to improve the self-supervised restoration effect, Regularization by Denoising (RED) is introduced to the network, and the final output is obtained by averaging the prediction of multiple iterations in the trained model. Experiments are carried out with real-world turbulence-degraded data by implementing the proposed method and four reported methods, and we use four non-reference indicators for evaluation, among which Average Gradient, NIQE, and BRISQUE have achieved state-of-the-art effects compared with other methods. As a result, our method is effective in alleviating distortions and blur, restoring image details, and enhancing visual quality. Furthermore, the proposed approach has a certain degree of generalization, and has an excellent restoration effect for motion-blurred images.

Robust Orientation Method Based on Atmospheric Polarization Model for Complex Weather

Accurate and reliable navigation data is a key component in Internet of Things (IoT). High-precision and stable autonomous orientation has attracted considerable attention regarding environments in which the global navigation satellite system signal is unreliable. This study proposed a robust orientation method based on the atmospheric polarization mode called weather weighting sparse coding that includes weather classification, sparse coding, and fitting. In comparison with previous studies, the proposed method is effective in restoring the angle-of-polarization image and achieving accurate orientation under complex weather. Specifically, to achieve high-precision orientation in complex weather, a polarization compass was designed, which used the characteristics of the different levels of destruction of atmospheric polarization images under different weather conditions for classification and denoising. The proposed strategy was used to process atmospheric polarization images obtained in complex weather. Experimental results showed that the orientation accuracy was better than 0.31° (root-mean-square error) under conditions of overcast, sandstorms, clear with overexposed areas, and smog with tree-obscured and overexposed areas.

Effects of Atmospheric Correction and Image Enhancement on Effective Plastic Greenhouse Segments Based on a Semi-Automatic Extraction Method

To improve the multi-resolution segmentation (MRS) quality of plastic greenhouses (PGs) in GaoFen-2 (GF-2) images, the effects of atmospheric correction and image enhancement on effective PG segments (EPGSs) were evaluated. A new semi-automatic method was also proposed to extract EPGSs in an accurate and efficient way. Firstly, GF-2 images were preprocessed via atmospheric correction, orthographical correction, registration, fusion, linear compression, or spatial filtering, and, then, boundary-removed point samples with adjustable density were made based on reference polygons by taking advantage of the characteristics of chessboard segmentation. Subsequently, the point samples were used to quickly and accurately extract segments containing 70% or greater of PG pixels in each MRS result. Finally, the extracted EPGSs were compared and analyzed via intersection over union (IoU), over-segmentation index (OSI), under-segmentation index (USI), error index of total area (ETA), and composite error index (CEI). The experimental results show that, along with the change in control variables, the optimal scale parameter, time of segmentation, IoU, OSI, USI, and CEI all showed strong changing trends, with the values of ETA all close to 0. Furthermore, compared with the control group, all the CEIs of the EPGSs extracted from those corrected and enhanced images resulted in lower values, and an optimal CEI involved linearly compressing the DN value of the atmospheric-corrected fusion image to 0–255, and then using Fast Fourier Transform and a circular low-pass filter with a radius of 800 pixels to filter from the spatial frequency domain; in this case, the CEI had a minimum value of 0.159. The results of this study indicate that the 70% design in the experiment is a reasonable pixel ratio to determine the EPGSs, and the OSI-USI-ETA-CEI pattern can be more effective than IoU when it is needed to evaluate the quality of EPGSs. Moreover, taking into consideration heterogeneity and target characteristics, atmospheric correction and image enhancement prior to MRS can improve the quality of EPGSs.

Super-resolution Inversion and Reconstruction for Remote Sensing Images of Bands of Interest

The super-resolution inversion and reconstruction algorithm of remote sensing image of band of interest is proposed in this paper. Based on the existing multi-resolution hyperspectral images, a spectral reflectance dictionary is constructed, according to which the objects in radiation calibrated and atmospheric corrected scene spectral reflectance images are sorted and classified using the end element extraction algorithm and the correlation distance method. Based on the classification results, a dictionary of scene feature spectral reflectance is constructed. Based on this, the sparse representation method and the secondary optimization algorithm based on image similarity are used to solve and optimize the feature distribution of the scene image. According to the feature distribution of the scene image, using the remote sensing link imaging model, super-resolution inversion reconstruction is performed to obtain a high-resolution remote sensing image of a band of interest. Experimental results show that the proposed algorithm can reconstruct low-resolution remote-sensing images of different bands into high-resolution remote-sensing images. Thus, the proposed algorithm can effectively boost image resolution, enrich image details and improve the target detection capability by the image.

Segmentation on remote sensing imagery for atmospheric air pollution using divergent differential evolution algorithm.

Air pollution is a global issue causing major health hazards. By proper monitoring of air quality, actions can be taken to control air pollution. Satellite remote sensing is an effective way to monitor global atmosphere. Various sensors and instruments fitted to satellites and airplanes are used to obtain the radar images. These images are quite complex with various wavelength differentiated by very close color differences. Clustering of such images based on its wavelengths can provide the much-needed relief in better understanding of these complex images. Such task related to image segmentation is a universal optimization issue that can be resolved with evolutionary techniques. Differential Evolution (DE) is a fairly fast and operative parallel search algorithm. Though classical DE algorithm is popular, there is a need for varying the mutation strategy for enhancing the performance for varied applications. Several alternatives of classical DE are considered by altering the trial vector and control parameter. In this work, a new alteration of DE technique labeled as DiDE (Divergent Differential Evolution Algorithm) is anticipated. The outcomes of this algorithm were tested and verified with the traditional DE techniques using fifteen benchmark functions. The new variant DiDE exhibited much superior outcomes compared to traditional approaches. The novel approach was then applied on remote sensing imagery collected form TEMIS, a web based service for atmospheric satellite images and the image was segmented. Fuzzy Tsallis entropy method of multi-level thresholding technique is applied over DiDE to develop image segmentation. The outcomes obtained were related with the segmented results using traditional DE and the outcome attained was found to be improved profoundly. Experimental results illustrate that by acquainting DiDE in multilevel thresholding, the computational delay was greatly condensed and the image quality was significantly improved.

Blind Restoration of Atmospheric Turbulence-Degraded Images Based on Curriculum Learning

Atmospheric turbulence-degraded images in typical practical application scenarios are always disturbed by severe additive noise. Severe additive noise corrupts the prior assumptions of most baseline deconvolution methods. Existing methods either ignore the additive noise term during optimization or perform denoising and deblurring completely independently. However, their performances are not high because they do not conform to the prior that multiple degradation factors are tightly coupled. This paper proposes a Noise Suppression-based Restoration Network (NSRN) for turbulence-degraded images, in which the noise suppression module is designed to learn low-rank subspaces from turbulence-degraded images, the attention-based asymmetric U-NET module is designed for blurred-image deconvolution, and the Fine Deep Back-Projection (FDBP) module is used for multi-level feature fusion to reconstruct a sharp image. Furthermore, an improved curriculum learning strategy is proposed, which trains the network gradually to achieve superior performance through a local-to-global, easy-to-difficult learning method. Based on NSRN, we achieve state-of-the-art performance with PSNR of 30.1 dB and SSIM of 0.9 on the simulated dataset and better visual results on the real images.

Effect of Image-Processing Routines on Geographic Object-Based Image Analysis for Mapping Glacier Surface Facies from Svalbard and the Himalayas

Advancements in remote sensing have led to the development of Geographic Object-Based Image Analysis (GEOBIA). This method of information extraction focuses on segregating correlated pixels into groups for easier classification. This is of excellent use in analyzing very-high-resolution (VHR) data. The application of GEOBIA for glacier surface mapping, however, necessitates multiple scales of segmentation and input of supportive ancillary data. The mapping of glacier surface facies presents a unique problem to GEOBIA on account of its separable but closely matching spectral characteristics and often disheveled surface. Debris cover can induce challenges and requires additions of slope, temperature, and short-wave infrared data as supplements to enable efficient mapping. Moreover, as the influence of atmospheric corrections and image sharpening can derive variations in the apparent surface reflectance, a robust analysis of the effects of these processing routines in a GEOBIA environment is lacking. The current study aims to investigate the impact of three atmospheric corrections, Dark Object Subtraction (DOS), Quick Atmospheric Correction (QUAC), and Fast Line-of-Sight Atmospheric Analysis of Hypercubes (FLAASH), and two pansharpening methods, viz., Gram–Schmidt (GS) and Hyperspherical Color Sharpening (HCS), on the classification of surface facies using GEOBIA. This analysis is performed on VHR WorldView-2 imagery of selected glaciers in Ny-Ålesund, Svalbard, and Chandra–Bhaga basin, Himalaya. The image subsets are segmented using multiresolution segmentation with constant parameters. Three rule sets are defined: rule set 1 utilizes only spectral information, rule set 2 contains only spatial and contextual features, and rule set 3 combines both spatial and spectral attributes. Rule set 3 performs the best across all processing schemes with the highest overall accuracy, followed by rule set 1 and lastly rule set 2. This trend is observed for every image subset. Among the atmospheric corrections, DOS displays consistent performance and is the most reliable, followed by QUAC and FLAASH. Pansharpening improved overall accuracy and GS performed better than HCS. The study reports robust segmentation parameters that may be transferable to other VHR-based glacier surface facies mapping applications. The rule sets are adjusted across the processing schemes to adjust to the change in spectral characteristics introduced by the varying routines. The results indicate that GEOBIA for glacier surface facies mapping may be less prone to the differences in spectral signatures introduced by different atmospheric corrections but may respond well to increasing spatial resolution. The study highlighted the role of spatial attributes for mapping fine features, and in combination with appropriate spectral features may enhance thematic classification.

Coregistration of projections and extended unsharp masking filtering for improving the reconstruction of targets hidden in turbid media

We experimentally demonstrate an integrated approach for improving reconstruction quality of targets embedded within a turbid media by integrating multiple viewpoints (projections) together with an extended unsharp masking (eUSM) algorithm recently demonstrated in atmospheric solar images. In the setup, objects with differing geometrical shapes and sizes were embedded within media with a range of turbidity and varying attenuation and viscosity values. The medium was illuminated with a laser beam after which multiview images, obtained by lens array, were captured with a camera. In offline processing, each sub-image (viewpoint) was digitally cropped, extracted from the array, eUSM filtered, and qualitatively evaluated by contrast metrics. After sub-images were sorted and ranked based on metric values, the selected ‘best’ sub-images were shifted to a common center and co-added with others using a shift-and-add (SAA) method to form a single average image revealing the shape of the object. Linear polarization was also introduced into the setup to give higher contrast image quality. Moreover, by optimizing eUSM parameters, further improvement was achieved in the reconstruction. Experimental results illustrate the improvement of the proposed approach as compared to the previously described SAA method alone.

VIRTUALLY THROWING BENCHMARKS INTO THE OCEAN FOR DEEP SEA PHOTOGRAMMETRY AND IMAGE PROCESSING EVALUATION

Abstract. Vision in the deep sea is acquiring increasing interest from many fields as the deep seafloor represents the largest surface portion on Earth. Unlike common shallow underwater imaging, deep sea imaging requires artificial lighting to illuminate the scene in perpetual darkness. Deep sea images suffer from degradation caused by scattering, attenuation and effects of artificial light sources and have a very different appearance to images in shallow water or on land. This impairs transferring current vision methods to deep sea applications. Development of adequate algorithms requires some data with ground truth in order to evaluate the methods. However, it is practically impossible to capture a deep sea scene also without water or artificial lighting effects. This situation impairs progress in deep sea vision research, where already synthesized images with ground truth could be a good solution. Most current methods either render a virtual 3D model, or use atmospheric image formation models to convert real world scenes to appear as in shallow water appearance illuminated by sunlight. Currently, there is a lack of image datasets dedicated to deep sea vision evaluation. This paper introduces a pipeline to synthesize deep sea images using existing real world RGB-D benchmarks, and exemplarily generates the deep sea twin datasets for the well known Middlebury stereo benchmarks. They can be used both for testing underwater stereo matching methods and for training and evaluating underwater image processing algorithms. This work aims towards establishing an image benchmark, which is intended particularly for deep sea vision developments.