Pixel-based Methods Research Articles

Abstract 4123639: Tumor Endothelial Marker 1 is Upregulated in Atrial Cardiac Fibroblasts in Atrial Fibrillation and Correlates With Atrial Fibrosis

Background: Tumor endothelial marker 1 (TEM1 or CD248) is a transmembrane protein found in activated mesenchymal cells during embryo development. Its expression level becomes very low or undetectable in adult tissue. Re-expression of TEM1 in fibroblasts has been reported in hepatic, renal, and pulmonary fibrosis. We evaluated atrial TEM1 expression in atrial fibrillation (AF) and its relation with atrial fibrosis. Methods and Results: All data were presented as mean±standard error. Left atrial (LA) tissues were collected from 30 patients (pts) (mean age 64.0±1.6 yrs, male 76.7%) with AF underwent cardiac surgery (mitral and/or tricuspid valve surgery 96.7%) and maze procedure with LA appendage excision. Immunofluorescence (IF) staining showed TEM1 expressed in atrial cardiac fibroblasts (CFs) in the LA tissue of AF pts, but not in normal LA tissue (US Biomax). Primary human CFs were directly isolated from the LA tissue. IF staining showed TEM1 expression in the isolated CFs from AF pts but not in normal human CFs (ScienCell). Western blot could detect TEM1 expression in the LA tissues of all 30 AF pts. Sirius Red staining was used to visualize collagen and atrial fibrosis was quantified using a pixel-based method (Adobe Photoshop) by calculating the total numbers of red pixels and the percentage (%) of red pixels to total pixels. Atrial fibrosis was increased in AF pts compared with normal control (total number of red pixels: 160740±13066 vs. 50863±6357, % of red pixels to total pixels: 11.4±0.8 vs. 3.8±0.2%, all p<0.001). There was a positive correlation between the expression level of TEM1 (ratio of TEM1/actin band density in western blot) with the severity of atrial fibrosis, including the total numbers of red pixels (r = 0.47, p = 0.01) and the % of red pixels to total pixels (r = 0.48, p = 0.01). TEM1 and galectin expression levels had positive correlation (r = 0.60, p < 0.01). There were no correlations of atrial TEM1 expression with the LA diameter and CHA2DS2-VASc score. In vitro study showed TEM1 knockdown in cultured CFs with siRNA reduced cell proliferation (scrambled- vs TEM1-siRNA, BrdU absorbance: 1.84±0.05 vs 1.50±0.07, p<0.05), increased starvation-induced cell apoptosis (cell death ELISA absorbance: 0.69±0.11 vs 2.88±0.05, p<0.05) and decreased cell migration. Conclusions: There is increased TEM1 expression in atrial CFs in AF and its expression level is associated with atrial fibrosis. TEM1 expression changes the cell behaviors of CFs.

Diagnostic Performance for Detection of Glaucomatous Structural Damage Using Pixelwise Analysis of Retinal Thickness Measurements.

To compare the diagnostic accuracy of thickness measurements of individual and combined macular retinal layers to discriminate 188 glaucomatous and 148 glaucoma suspect eyes from 362 healthy control (HC) eyes on a pixel-by-pixel basis. For this retrospective study, we manually corrected the segmentations of posterior pole optical coherence tomography (OCT) scans to determine the thickness of the nerve fiber layer (NFL), ganglion cell layer (GCL), inner plexiform layer (IPL), the ganglion cell complex (GCC), and the total neural retina (TR). For each eye, the total number of pixels with thickness values less than the fifth percentile of the HC distribution was used to create a receiver operating characteristic (ROC) curve for each layer and for layer combinations. Using total abnormal pixel count criteria to discriminate glaucoma from HC eyes, the individual layers with the highest area under the ROC curve (AUC) were the NFL and GCL; IPL performance was significantly lower (P < 0.05). GCC had a significant higher AUC (94.3%) than individual the AUC of the NFL (92.3%) (P = 0.0231) but not higher than AUC of the GCL (93.4%) (P = 0.3487). The highest AUC (95.4%) and sensitivity (85.1%) at 95% specificity was found for the Boolean combination of NFL or GCL. The highest AUC is not significantly higher (P = 0.0882) than the AUC of the GCC but the highest sensitivity is significantly higher than the sensitivity of the GCC. This pattern was similar for discriminating between suspect and HC eyes (P = 0.0356). Using pixel-based methods, the diagnostic accuracy of NFL and GCL exceeded that of IPL and TR. GCC had equivalent performance as NFL and GCL. The specific spatial locations within the posterior pole that exhibit best performance vary depending on which layer is being assessed. Recognizing this dependency highlights the importance of considering multiple layers independently, as they offer complementary information for effective and comprehensive diagnosis.

Remote Sensing Detection of Growing Season Freeze-Induced Defoliation of Montane Quaking Aspen (Populus tremuloides) in Southern Utah, USA

Growing season freeze events pose a threat to quaking aspen (Populus tremuloides Michx.), leading to canopy defoliation, reduced vigor, and increased mortality, especially for declining montane populations western North America. Detecting the spatial distribution and progression of this damage is challenging due to limited in situ observations in this region. This study represents the first attempt to comprehensively resolve the spatial extent of freeze-induced aspen canopy damage in southern Utah using multispectral remote sensing data. We developed an approach to detect the spatial and temporal dynamics of freeze-damaged aspen stands, focusing on a freeze event from 8–9 June 2020 in southern Utah. By integrating medium- (~250 to 500 m) and high-resolution (~10 m) satellite data, we employed the Normalized Difference Vegetation Index (NDVI) to compare post-freeze conditions with historical norms and pre-freeze conditions. Our analysis revealed NDVI reductions of 0.10 to 0.40 from pre-freeze values and a second flush recovery. We introduced a pixel-based method to evaluate freeze vulnerability, establishing a strong correlation (R values 0.78 to 0.82) between the onset of the first flush (NDVI &gt; 0.50) and the accumulation of 100 growing degree days (GDD). These methods support the potential for retrospective assessments, proactive forest monitoring, and forecasting future risks.

Far-focused pixel-based imaging of internal defects in multi-layered media based on attenuation compensation and circular coherence factor

ABSTRACT The multi-layered media composed of layers with different sound velocities exhibit anisotropy, strong attenuation, and interface reflection in terms of sound propagation, posing challenges for conventional ultrasound imaging methods, especially in detecting deep-seated and near-interface defects. In this study, an improved far-focused pixel-based (FPB) imaging method for detecting internal defects in multi-layered media is proposed. First, the time delay calculation in the FPB method is corrected using the shortest path searching method to determine the acoustic time-of-flight. Then, phase information is extracted from the echo signal to construct a circular coherence factor (CCF) that dynamically weights the time-corrected FPB images, addressing the issue of ineffective detection of near-interface defects caused by interface reflection. Finally, considering the sound attenuation in multi-layered media, the directivity coefficient, transmission coefficient, and divergence coefficient are determined through theoretical derivation to compensate for the echo amplitude. Experimental results demonstrate that the improved FPB method significantly enhances the reflection echo from deep-seated defects, reduces the maximum relative localisation error to 0.9%, and the quantisation error to 6.4%. The proposed method also greatly improves the lateral resolution and signal-to-noise ratio (SNR) of internal defect imaging compared to the total focusing method (TFM) and traditional FPB method.

Semisupervised Change Detection Based on Bihierarchical Feature Aggregation and Extraction Network.

With the rapid development of remote sensing (RS) technology, high-resolution RS image change detection (CD) has been widely used in many applications. Pixel-based CD techniques are maneuverable and widely used, but vulnerable to noise interference. Object-based CD techniques can effectively utilize the abundant spectrum, texture, shape, and spatial information but easy-to-ignore details of RS images. How to combine the advantages of pixel-based methods and object-based methods remains a challenging problem. Besides, although supervised methods have the capability to learn from data, the true labels representing changed information of RS images are often hard to obtain. To address these issues, this article proposes a novel semisupervised CD framework for high-resolution RS images, which employs small amounts of true labeled data and a lot of unlabeled data to train the CD network. A bihierarchical feature aggregation and extraction network (BFAEN) is designed to achieve the pixelwise together with objectwise feature concatenation feature representation for the comprehensive utilization of the two-level features. In order to alleviate the coarseness and insufficiency of labeled samples, a confident learning algorithm is used to eliminate noisy labels and a novel loss function is designed for training the model using true- and pseudo-labels in a semisupervised fashion. Experimental results on real datasets demonstrate the effectiveness and superiority of the proposed method.

Detection of Na in the atmosphere of the hot Jupiter HAT-P-55b

The spectral signatures of optical absorbers, when combined with those of infrared molecules, play a critical role in constraining the cloud properties of exoplanet atmospheres. We aim to use optical transmission spectroscopy to confirm the tentative color signature previously observed by multiband photometry in the atmosphere of hot Jupiter HAT-P-55b. We observed a transit of the HAT-P-55b with the OSIRIS spectrograph on the Gran Telescopio Canarias (GTC). We created two sets of spectroscopic light curves, using the conventional band-integrated method and the newly proposed pixel-based method, to derive the transmission spectrum. We performed Bayesian spectral retrieval analyses on the transmission spectrum to interpret the observed atmospheric properties. The transmission spectra derived from the two methods are consistent, both spectrally resolving the tentative color signature observed by MuSCAT2. The retrievals on the combined OSIRIS and MuSCAT2 transmission spectrum yield a detection of Na at 5.5σ and a tentative detection of MgH at 3.4σ. The current optical-only wavelength coverage cannot constrain the absolute abundances of the atmospheric species. Space-based observations covering the molecular infrared bands or ground-based high-resolution spectroscopy are needed to further constrain the atmospheric properties of HAT-P-55b.

A rapid evaluation method of the seismic damage to buildings based on UAV images

With the widespread application of UAVs in post-disaster damage evaluation, feature extraction and analysis based on drone images has become the main trend in seismic assessment. In this research, a fast assessment method that integrates object-oriented 2D classification and 3D assessment is proposed in the paper. Firstly, to segment the regional orthoimage, a multi-scale feature segmentation method is developed to segment the orthoimage of the region and the features are selected based on the attributes of ground objects. Meanwhile, a two-stage object-oriented hierarchical classification method is put forward to establish partition rules at different levels. The classification method takes the overall attributes of the object into account which reduces the amount of data correspondingly resulting in much higher efficiency and accuracy of feature extraction than the pixel-based method. In addition, the integrity of building’s top texture after classification is used as the first criterion to assess building seismic damage. Besides, a 3D elevation analysis method based on regional normalized digital surface model (nDSM) is developed by comparing digital surface model with digital elevation model to serve as the second criterion for determining the vertical changes in building. The proposed method is validated by a field test at the Beichuan earthquake site with an accuracy rate of 86.95 %. The experimental results show that the proposed method can meet the accuracy requirement of seismic assessment and has a high application value in the field of regional disaster evaluation.

Pixel-MPS: Stochastic Embedding and Density-Based Clustering of Image Patterns for Pixel-Based Multiple-Point Geostatistical Simulation

Multiple-point geostatistics (MPS) is an established tool for the uncertainty quantification of Earth systems modeling, particularly when dealing with the complexity and heterogeneity of geological data. This study presents a novel pixel-based MPS method for modeling spatial data using advanced machine-learning algorithms. Pixel-based multiple-point simulation implies the sequential modeling of individual points on the simulation grid, one at a time, by borrowing spatial information from the training image and honoring the conditioning data points. The developed methodology is based on the mapping of the training image patterns database using the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm for dimensionality reduction, and the clustering of patterns by applying the Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, as an efficient unsupervised classification technique. For the automation, optimization, and input parameter tuning, multiple stages are implemented, including entropy-based determination of the template size and a k-nearest neighbors search for clustering parameter selection, to ensure the proposed method does not require the user’s interference. The proposed model is validated using synthetic two- and three-dimensional datasets, both for conditional and unconditional simulations, and runtime information is provided. Finally, the method is applied to a case study gold mine for stochastic orebody modeling. To demonstrate the computational efficiency and accuracy of the proposed method, a two-dimensional training image with 101 by 101 pixels is simulated for 100 conditional realizations in 453 s (~4.5 s per realization) using only 361 hard data points (~3.5% of the simulation grid), and the resulting average simulation has a good visual match and only an 11.8% pixel-wise mismatch with the training image.

Pixel-based small-window parametric ultrasound imaging for liver tumor characterization.

Characterizing liver tumors remains a challenge in clinical practice. Ultrasound parametric imaging based on statistical distribution can enhance image contrast compared with B-mode imaging, requiring scatterers following specific distributions. This study proposes a pixel-based small-window parametric ultrasound imaging method using weighted horizontally normalized Shannon entropy (WhNSE) and fuzzy entropy (FE) to improve detectability liver tumor. Pixel-based parametric imaging requires a sliding window to traverse across the B-mode image with the step of one pixel, while calculating the entropy by the pixel values in the window. The entropy is assigned to the center pixel of the sliding window. The entropy image is obtained after getting the entropy values of all pixels. FE and WhNSE are two novel entropies first applied to parametric imaging. The detection abilities of regions of interest (ROI) and the contrast-to-noise ratio (CNR) were evaluated through simulations and clinical explorations. In simulations, FE imaging showed the highest improvement in detecting hyperechoic ROIs, with a CNR gain up to 457.31% (p < 0.01) in simulations. WhNSE imaging demonstrated the best performance in hyperechoic ROI detection, with a CNR of 1.607 ± 0.816 (p = 0.05), significantly higher than B-mode images. The proposed pixel-based parametric imaging method based on fuzzy entropy and weighted horizontally normalized Shannon entropy both effectively enhance the contrast and detectability of ultrasound images. The imaging enhancement method of the pixel-based fuzzy entropy imaging with proper parameters got better detection performance, due to the consideration of the relationship of neighboring pixels.

A review of Explainable Artificial Intelligence in healthcare

Explainable Artificial Intelligence (XAI) encompasses the strategies and methodologies used in constructing AI systems that enable end-users to comprehend and interpret the outputs and predictions made by AI models. The increasing deployment of opaque AI applications in high-stakes fields, particularly healthcare, has amplified the need for clarity and explainability. This stems from the potential high-impact consequences of erroneous AI predictions in such critical sectors. The effective integration of AI models in healthcare hinges on the capacity of these models to be both explainable and interpretable. Gaining the trust of healthcare professionals necessitates AI applications to be transparent about their decision-making processes and underlying logic. Our paper conducts a systematic review of the various facets and challenges of XAI within the healthcare realm. It aims to dissect a range of XAI methodologies and their applications in healthcare, categorizing them into six distinct groups: feature-oriented methods, global methods, concept models, surrogate models, local pixel-based methods, and human-centric approaches. Specifically, this study focuses on the significance of XAI in addressing healthcare-related challenges, underscoring its vital role in safety-critical scenarios. Our objective is to provide an exhaustive exploration of XAI's applications in healthcare, alongside an analysis of relevant experimental outcomes, thereby fostering a holistic understanding of XAI's role and potential in this critical domain.

Advance Image Forgery Detection

Abstract :- In the digital era, the proliferation of sophisticated image editing tools has made image forgery a prevalent issue, posing significant challenges in various fields, including legal proceedings, journalism, and digital security. Advanced image forgery detection techniques are crucial to ensuring the authenticity and integrity of digital images. This paper explores the state-of-the-art methods and technologies employed in the detection of image forgeries. We focus on both traditional and deep learning-based approaches, highlighting their respective strengths and weaknesses. Traditional methods, such as pixel-based, format-based, and geometry-based techniques, rely on the intrinsic properties of images to identify inconsistencies and manipulations. These methods are effective in detecting simple forgeries but often fall short against more sophisticated alterations. On the other hand, deep learning-based approaches, leveraging convolutional neural networks (CNNs) and generative adversarial networks (GANs), have shown significant promise in identifying subtle and complex forgeries by learning high-level features from large datasets. In conclusion, while significant advancements have been made in image forgery detection, continuous research and development are necessary to stay ahead of emerging forgery techniques. The integration of multidisciplinary approaches and the collaboration between academia and industry will be pivotal in advancing the efficacy of forgery detection systems. Keywords : Image Forgery Detection, Deep Learning, Digital Image Authentication, Pixel-based Methods, Image Manipulation. Image Manipulation.

High-resolution feature pyramid attention network for high spatial resolution images land-cover classification in arid oasis zones

ABSTRACT Land-cover classification based on remote sensing technology has been adopted for decision-making concerning agricultural development, urban planning, and ecosystem protection in arid oasis zones. The semantic segmentation method based on deep learning, as a new paradigm, can effectively overcome the limitations of traditional pixel-based and object-based methods and obtain good classification results from high spatial resolution (HSR) remote sensing images. However, how to extract the exact category boundary and realize the high precision mapping is still a problem. This paper proposes a novel high-resolution feature pyramid attention network (HRFPANet) for land-cover classification. It effectively integrates the advantages of multi-scale feature extraction, attention mechanism, and feature fusion and alleviates boundary inconsistency, roughness, and category fragmentation associated with previous semantic segmentation models. The experimental results show that the mIoU score of HRFPANet is 79.5%, which is 11.5% and 2.6% higher than that of PSPNet and UPerNet, respectively. It proves the proposed model can be used for qualified land-cover mapping in arid oasis zones. Our source code is available at https://github.com/HPU-CPD/HRFPANet.git.

Multi-Scale Fusion Siamese Network Based on Three-Branch Attention Mechanism for High-Resolution Remote Sensing Image Change Detection

Remote sensing image change detection (CD) is an important means in remote sensing data analysis tasks, which can help us understand the surface changes in high-resolution (HR) remote sensing images. Traditional pixel-based and object-based methods are only suitable for low- and medium-resolution images, and are still challenging for complex texture features and detailed image detail processing in HR images. At present, the method based on deep learning has problems such as inconsistent fusion and difficult model training in the combination of the difference feature information of the deep and shallow layers and the attention mechanism, which leads to errors in the distinction between the changing region and the invariant region, edge detection and small target detection. In order to solve the above problems of inconsistent fusions of feature information aggregation and attention mechanisms, and indistinguishable change areas, we propose a multi-scale feature fusion Siamese network based on attention mechanism (ABMFNet). To tackle the issues of inconsistent fusion and alignment difficulties when integrating multi-scale fusion and attention mechanisms, we introduce the attention-based multi-scale feature fusion module (AMFFM). This module not only addresses insufficient feature fusion and connection between different-scale feature layers, but also enables the model to automatically learn and prioritize important features or regions in the image. Additionally, we design the cross-scale fusion module (CFM) and the difference feature enhancement pyramid structure (DEFPN) to assist the AMFFM module in integrating differential information effectively. These modules bridge the spatial disparity between low-level and high-level features, ensuring efficient connection and fusion of spatial difference information. Furthermore, we enhance the representation and inference speed of the feature pyramid by incorporating a feature enhancement module (FEM) into DEFPN. Finally, the BICD dataset proposed by the laboratory and public datasets LEVIR-CD and BCDD are compared and tested. We use F1 score and MIoU values as evaluation metrics. For AMBMFNet, the F1 scores on the three datasets are 77.69%, 81.57%, and 77.91%, respectively, while the MIoU values are 84.65%, 85.84%, and 84.54%, respectively. The experimental results show that ABMFNet has better effectiveness and robustness.

Remote sensing approaches to identify trees to species-level in the urban forest: A review

Most urban tree inventories depend on resource-intensive, field-based assessments, which are unevenly distributed in space and time. Recently, these inventories have been conducted using field inventories combined with airborne multispectral, hyperspectral, LiDAR, and spaceborne multispectral remote sensing. Significant advances have been made in urban tree GIS databases and remote sensing methods, which include delineating individual tree crowns, extracting tree species metrics, and employing classification techniques. Generally, remote sensing methods distinguish individual urban trees using either pixel-based or object-based methods, while image classification procedures are typically divided into parametric (e.g., regression-based classification, Bayesian, and principal component analysis) and non-parametric approaches such as machine learning (e.g., random forests support vector machines) and deep learning (e.g., convolutional neural networks). Our synthesis of the current state of science suggests sensors with the highest spatial (m), spectral (bands), and temporal (repeat time) resolutions result in the most accurate tree species identification. Combining airborne LiDAR/hyperspectral or airborne LiDAR/spaceborne high-resolution multispectral sensors yields the highest accuracy for the most diverse urban forests. An object-based non-parametric approach, like a fully convolutional neural network, scores higher in accuracy assessments than pixel-based parametric approaches. Future studies can leverage global/regional GIS field inventory databases to expand the scope of studies within and across multiple cities, utilizing LiDAR and spaceborne sensors.

Winter Wheat Mapping in Shandong Province of China with Multi-Temporal Sentinel-2 Images

Wheat plays an important role in China’s and the world’s food supply, and it is closely related to economy, culture and life. The spatial distribution of wheat is of great significance to the rational planning of wheat cultivation areas and the improvement of wheat yield and quality. The current rapid development of remote sensing technology has greatly improved the efficiency of traditional agricultural surveys. The extraction of crop planting structure based on remote sensing images and technology is a popular topic in many researches. In response to the shortcomings of traditional methods, this research proposed a method based on the fusion of the pixel-based and object-oriented methods to map the spatial distribution of winter wheat. This method was experimented and achieved good results within Shandong Province. The resulting spatial distribution map of winter wheat has an overall accuracy of 92.2% with a kappa coefficient of 0.84. The comparison with the actual situation shows that the accuracy of the actual recognition of winter wheat is higher and better than the traditional pixel-based classification method. On this basis, the spatial pattern of winter wheat in Shandong was analyzed, and it was found that the topographic undulations had a great influence on the spatial distribution of wheat. This study vividly demonstrates the advantages and possibilities of combining pixel-based and object-oriented approaches through experiments, and also provides a reference for the next related research. Moreover, the winter wheat map of Shandong produced in this research is important for yield assessment, crop planting structure adjustment and the rational use of land resources.

Aboveground Biomass Inversion Based on Object-Oriented Classification and Pearson–mRMR–Machine Learning Model

Cities play a crucial role in the carbon cycle. Measuring urban aboveground biomass (AGB) is essential for evaluating carbon sequestration. Satellite remote sensing enables large-scale AGB inversion. However, the apparent differences between forest and grassland biomass pose a significant challenge to the accurate estimation of urban AGB using satellite-based data. To address this limitation, this study proposed a novel AGB estimation method using the eastern part of the Zhahe mining area in Huaibei City as the study area, which integrates land cover classification, feature selection, and machine learning modelling to generate high quality biomass maps of different vegetation types in an urban area with complex feature distribution. Utilizing the GEE platform and Sentinel-2 image, we developed an object-oriented machine learning classification algorithm, combining SNIC and GLCM to extract vegetation information. Optimal feature variables for forest and crop-grass AGB inversion were selected using the Pearson–mRMR algorithm. Finally, we constructed nine machine learning models for AGB inversion and selected the model with the highest accuracy to generate the AGB map of the study area. The results of the study are as follows: (1) Compared with the pixel-based classification method, the object-oriented classification method can extract the boundaries of different vegetation types more accurately. (2) Forest AGB is strongly correlated with vegetation indices and physiological parameters, while agri-grass AGB is primarily associated with vegetation indices and vegetation physiological parameters. (3) For forest AGB modelling, the RF-R model outperforms other machine learning models with an R2 of 0.77. For agri-grass AGB modelling, the XGBoost-R model is more accurate, with an R2 of 0.86. (4) The mean forest AGB in the study area was 4.60 kg/m2, while the mean agri-grass AGB was 0.71 kg/m2. High AGB values were predominantly observed in forested areas, which were mainly distributed along roads, waterways, and mountain ranges. Overall, this study contributes to a better understanding of the health of local urban ecosystems and provides valuable insights for ecosystem protection and the sustainable use of natural resources.

Toward a More Robust Estimation of Forest Biomass Carbon Stock and Carbon Sink in Mountainous Region: A Case Study in Tibet, China

Mountainous forests are pivotal in the global carbon cycle, serving as substantial reservoirs and sinks of carbon. However, generating a reliable estimate remains a considerable challenge, primarily due to the lack of representative in situ measurements and proper methods capable of addressing their complex spatial variation. Here, we proposed a deep learning-based method that combines Residual convolutional neural networks (ResNet) with in situ measurements, microwave (Sentinel-1 and VOD), and optical data (Sentinel-2 and Landsat) to estimate forest biomass and track its change over the mountainous regions. Our approach, integrating in situ measurements across representative elevations with multi-source remote sensing images, significantly improves the accuracy of biomass estimation in Tibet’s complex mountainous forests (R2 = 0.80, root mean squared error = 15.8 MgC ha−1). Moreover, ResNet, which addresses the vanishing gradient problem in deep neural networks by introducing skip connections, enables the extraction of complex spatial patterns from limited datasets, outperforming traditional optical-based or pixel-based methods. The mean value of forest biomass was estimated as 162.8 ± 21.3 MgC ha−1, notably higher than that of forests at comparable latitudes or flat regions in China. Additionally, our findings revealed a substantial forest biomass carbon sink of 3.35 TgC year−1 during 2015–2020, which is largely underestimated by previous estimates, mainly due to the underestimation of mountainous carbon stock. The significant carbon density, combined with the underestimated carbon sink in mountainous regions, emphasizes the urgent need to reassess mountain forests to better approximate the global carbon budget.

Accuracy assessment of land surface temperature retrievals from remote sensing imagery: pixel-based, single and multi-channel methods

Land Surface Temperature (LST) measurements using remote sensing data are conducted using various methods, including the Single Channel Method (SCM) and the Multi-Channel Method (MCM). Emissivity, which significantly affects LST, is determined using methods such as the Correction-Based Emissivity Method (CBEM) and the Non-Linear Based Emissivity Method (NBEM). Given these factors, validating LST measurements is crucial for assessing the accuracy of data processing results. This study aims to compare LST data retrieved using SCM and MCM with various emissivity calculation methods and assess their accuracy compared to single measurements with an infrared thermometer, measurements using a grid plot, and measurements using a thermal camera with the assistance of an Unmanned Aerial Vehicle (UAV). The results show that SCMJM&S and SCMAC did not produce optimal accuracy (>2.5K) when using the emissivity estimates from CBEM and NBEM. In contrast, MCM that adopted MCMSko, MCMQin, and MCMMao generally produced high-accuracy LST with an average difference of <1 K from actual temperatures, specifically in shrub pixels. MCM with the NDVI threshold method (NDVITHM) showed excellent results in distinguishing between vegetation and non-vegetation objects. In conclusion, MCM provides more accurate LST than SCM. Nevertheless, selecting the appropriate method should consider heterogeneity, homogeneity, and regional physiography.

A flexible multi-temporal orthoimage mosaicking method based on dynamic variable patches

Orthoimage mosaicking plays an important role in remote sensing applications, such as environment monitoring and protection. However, the cloud coverage in remote sensing images often results in substantial loss of information and degradation of data quality, bringing lots of challenges to orthoimage mosaicking. Therefore, this paper proposes a flexible multi-temporal orthoimage mosaicking method based on dynamic variable patches. Different from most existing pixel-based mosaicking methods, the proposed method defines patch as the minimal processing unit for orthoimage mosaicking, and the size and position of each patch are dynamic variable. Patches from different images are rearranged under the image texture consistency constraint to generate the mosaic image. In the proposed method, the initial positions of available patches of all images are determined first, then the initial size of each patch is determined by the cloud coverage and the effective area of image. Subsequently, considering the inevitable misalignments between different orthoimages, the texture similarity between patches is utilized to select the most suitable patch, and the size of the patch is also dynamically adjusted to make the misalignments within each patch controllable. Finally, considering the color inconsistency in the overlapping areas of neighboring images, an area-weighted image blending algorithm is also presented to achieve invisible seams and smooth transitions in the final mosaic. Not only does the proposed method produce mosaic images with minimal cloud coverage areas by excluding cloud pixels as much as possible, but it is also flexible for the mosaicking of images with varying degrees of misalignments, which is achieved by dynamically adjusting the size and position of each patch while maintaining texture consistency constraint. Both simulated experiments and real data experiments are carried out to verify the performance of the proposed method. The experimental results demonstrate that the proposed method can generate the mosaic image with higher spatial continuity and radiometric consistency.

Face De-Identification Using Convolutional Neural Network (CNN) Models for Visual-Copy Detection

The proliferation of media-sharing platforms has led to issues with illegally edited content and the distribution of pornography. To protect personal information, de-identification technologies are being developed to prevent facial identification. Existing de-identification methods directly alter the pixel values in the face region, leading to reduced feature representation and identification accuracy. This study aims to develop a method that minimizes the possibility of personal identification while effectively preserving important features for image- and video-copy-detection tasks, proposing a new deep-learning-based de-identification approach that surpasses traditional pixel-based alteration methods. We introduce two de-identification models using different approaches: one emphasizing the contours of the original face through feature inversion and the other generating a blurred version of the face using D2GAN (Dual Discriminator Generative Adversarial Network). Both models were evaluated on their performance in image- and video-copy-detection tasks before and after de-identification, demonstrating effective feature preservation. This research presents new possibilities for personal-information protection and digital-content security, contributing to digital-rights management and law enforcement.