Search

A point cloud is a simple and concise 3D representation, but point cloud generation is a long-term challenging task in 3D vision. However, most existing methods only focus on their effectiveness of generation and auto-encoding separately. Furthermore, both generative adversarial networks (GANs) and auto-encoders (AEs) are the most popular generative models. But there is a lack of related research that investigates the implicit connections between them in the field of point cloud generation. Thus, we propose a new bidirectional network (BI-Net) trained with collaborative learning, introducing more priors through the alternate parameter optimizations of a GAN and AE combination, which is different from the way of combining them at the network structure and loss function level. Specifically, BI-Net acts as a GAN and AE in different data processing directions, where their network structures can be reused. If optimizing only the GAN without the AE, there is no direct constraint of ground truth on the generator's parameter optimization. This unique approach enables better network optimization and leads to superior generation results. Moreover, we propose a nearest neighbor mutual exclusion (NNME) loss to further homogenize the spatial distribution of generated points during the reverse direction. Extensive experiments were conducted, and the results show that the BI-Net produces competitive and high-quality results on reasonable structure and uniform distributions compared to existing state-of-the-art methods. We believe that our network structure (BI-Net) with collaborative learning could provide a new promising method for future point cloud generation tasks. [ABSTRACT FROM AUTHOR]

The Qilian Mountains (QLM) are an important ecological barrier in western China. High-precision land cover data products are the basic data for accurately detecting and evaluating the ecological service functions of the QLM. In order to study the land cover in the QLM and performance of different remote sensing classification algorithms for land cover mapping based on the Google Earth Engine (GEE) cloud platform, the higher spatial resolution remote sensing images of Sentinel-1 and Sentinel-2; digital elevation data; and three remote sensing classification algorithms, including the support vector machine (SVM), the classification regression tree (CART), and the random forest (RF) algorithms, were used to perform supervised classification of Sentinel-2 images of the QLM. Furthermore, the results obtained from the classification process were compared and analyzed by using different remote sensing classification algorithms and feature-variable combinations. The results indicated that: (1) the accuracy of the classification results acquired by using different remote sensing classification algorithms were different, and the RF had the highest classification accuracy, followed by the CART and the SVM; (2) the different feature variable combinations had different effects on the overall accuracy (OA) of the classification results and the performance of the identification and classification of the different land cover types; and (3) compared with the existing land cover products for the QLM, the land cover maps obtained in this study had a higher spatial resolution and overall accuracy. [ABSTRACT FROM AUTHOR]

The increasing frequency of global drought events poses a significant threat to the stability of grassland ecosystems' functionality. The Inner Mongolian grasslands stand out as one of the world's most drought-prone regions, facing elevated drought risks compared to other biomes. An in-depth comprehension of the impact of drought on grassland ecosystems is paramount for their long-term sustainability. Using the Standardized Precipitation Evapotranspiration Index (SPEI) from 1982 to 2018, this study identified various drought events within the Inner Mongolian grasslands, encompassing moderate drought, severe drought, and extreme drought. The resistance of the vegetation to the different drought conditions, assessed through net primary productivity (NPP) as a metric (reflecting its capacity to maintain its original level during drought periods), was examined. The research findings indicated that the period from 2001 to 2018 witnessed a substantial increase in both the frequency and the extent of drought events compared to the period from 1982 to 2000, particularly concerning severe and extreme droughts. The areas most severely impacted by extreme drought were the Xilingol League and the Alxa League. From 1982–2000 to 2001–2018, under moderate drought conditions, vegetation resistance exhibited a minor decrease in the central and eastern regions but experienced a slight increase in the western region. In contrast, under severe drought conditions, the western region saw a significant decrease in vegetation resistance. Remarkably, under extreme drought conditions, the western region showed a substantial increase in vegetation resistance, while the central and eastern regions experienced a slight decrease. Across all three drought conditions, as precipitation levels declined, the resistance of the meadow–steppe–desert ecosystems demonstrated a high–low–high distribution pattern. The temperate desert steppe exhibited a minimal vulnerability to drought, boasting resistance levels exceeding 0.9. Notably, extreme drought had the most pronounced impact on the temperate meadow steppe, temperate steppe, and temperate desert steppe, particularly within the temperate meadow steppe category. Given these findings, the authorities responsible for grassland management should prioritize regions characterized by frequent drought occurrences and low drought resistance, such as Ulanqab City, the Xilingol League, and the western part of Hulun Buir City. Safeguarding steppe ecosystems is of paramount importance for stabilizing vegetation productivity and land carbon sinks, especially under the anticipated exacerbation of climate conditions in the future. [ABSTRACT FROM AUTHOR]

With the exploration of outer space, the number of space targets has increased dramatically, while the pressures of space situational awareness have also increased. Among them, spacecraft recognition is the foundation and a critical step in space situational awareness. However, unlike natural images that can be easily captured using low-cost devices, space targets can suffer from motion blurring, overexposure, and excessive dragging at the time of capture, which greatly affects the quality of the images and reduces the number of effective images. To this end, specialized or sufficiently versatile techniques are required, with dataset diversity playing a key role in enabling algorithms to categorize previously unseen spacecraft and perform multiple tasks. In this paper, we propose a joint dataset formulation to increase diversity. Our approach involves reformulating two local processes to condition the Conditional Neural Adaptive Processes, which results in global feature resampling schemes to adapt a pre-trained embedding function to be task-specific. Specifically, we employ variational resampling to category-wise auxiliary features, adding a generative constraint to amortize task-specific parameters. We also develop a neural process variational inference to encode representation, using grid density for conditioning. Our evaluation of the BUAA dataset shows promising results, with no-training performance close to a specifically designed learner and an accuracy rate of 98.2% on unseen categories during the joint training session. Further experiments on the Meta-dataset benchmark demonstrate at least a 4.6% out-of-distribution improvement compared to the baseline conditional models. Both dataset evaluations indicate the effectiveness of exploiting dataset diversity in few-shot feature adaptation. Our proposal offers a versatile solution for tasks across domains. [ABSTRACT FROM AUTHOR]

Constructing a surface representation from the sparse point cloud of a satellite is an important task for satellite on-orbit services such as satellite docking and maintenance. In related studies on surface reconstruction from point clouds, implicit neural representations have gained popularity in learning-based 3D object reconstruction. When aiming for a satellite with a more complicated geometry and larger intra-class variance, existing implicit approaches cannot perform well. To solve the above contradictions and make effective use of implicit neural representations, we built a NASA3D dataset containing point clouds, watertight meshes, occupancy values, and corresponding points by using the 3D models on NASA's official website. On the basis of NASA3D, we propose a novel network called GONet for a more detailed reconstruction of satellite grids. By designing an explicit-related implicit neural representation of the Grid Occupancy Field (GOF) and introducing it into GONet, we compensate for the lack of explicit supervision in existing point cloud surface reconstruction approaches. The GOF, together with the occupancy field (OF), serves as the supervised information for neural network learning. Learning the GOF strengthens GONet's attention to the critical points of the surface extraction algorithm Marching Cubes; thus, it helps improve the reconstructed surface's accuracy. In addition, GONet uses the same encoder and decoder as ConvONet but designs a novel Adaptive Feature Aggregation (AFA) module to achieve an adaptive fusion of planar and volume features. The insertion of AFA allows for the obtained implicit features to incorporate more geometric and volumetric information. Both visualization and quantitative experimental results demonstrate that our GONet could handle 3D satellite reconstruction work and outperform existing state-of-the-art methods by a significant margin. With a watertight mesh, our GONet achieves 5.507 CD-L1, 0.8821 F-score, and 68.86% IoU, which is equal to gains of 1.377, 0.0466, and 3.59% over the previous methods using NASA3D, respectively. [ABSTRACT FROM AUTHOR]

Coastal ship tracking is used in many applications, such as autonomous navigation, maritime rescue, and environmental monitoring. Many general object-tracking methods based on deep learning have been explored for ship tracking, but they often fail to accurately track ships in challenging scenarios, such as occlusion, scale variation, and motion blur. We propose a memory-guided perception network (MGPN) to address these issues. MGPN has two main innovative improvements. The dynamic memory mechanism (DMM) in the proposed method stores past features of the tracked target to enhance the model's feature fusion capability in the temporal dimension. Meanwhile, the hierarchical context-aware module (HCAM) enables the interaction of different scales, global and local information, to address the scale discrepancy of targets and improve the feature fusion capability in the spatial dimension. These innovations enhance the robustness of tracking and reduce inaccuracies in the bounding boxes. We conducted an in-depth ablation study to demonstrate the effectiveness of DMM and HCAM. Finally, influenced by the above two points, MGPN has achieved state-of-the-art performance on a large offshore ship tracking dataset, which contains challenging scenarios such as complex backgrounds, ship occlusion, and varying scales. [ABSTRACT FROM AUTHOR]

Grassland aboveground biomass (AGB) is an important indicator for studying the change in grassland ecological quality and carbon cycle. The rapid development of high-resolution remote sensing and unmanned aerial vehicles (UAV) provides a new opportunity for accurate estimation of grassland AGB on the plot scale. In this study, the mountain grassland was taken as the research object. Using UAV Light Detection and Ranging (LiDAR) data and multispectral satellite images, the influence of topographic correction methods on AGB estimation was compared and a series of LiDAR metrics and vegetation indices were extracted. On this basis, a comprehensive indicator, the vegetation index-height-intensity model (VHI), was proposed to estimate AGB quickly. The results show that: (1) Among the four topographic correction methods, the Teillet regression has the best effect, and can effectively improve the accuracy of AGB estimation in mountain grassland. The correlation between corrected ratio vegetation index and AGB was the highest (correlation coefficient: 0.682). (2) Among the height and intensity metrics, median height and max intensity yielded the higher accuracy in estimating AGB, with Root Mean Square Error (RMSE) of 322 g/m2 and 333 g/m2, respectively. (3) The VHI integrated spectrum and LiDAR information, and its accuracy for AGB estimation for mountain grassland, was obviously better than other indicators, with an RMSE of 272 g/m2. We also found that the accuracy of VHI in univariate models was comparable to that of complex multivariate models such as stepwise regression, support vector machine, and random forest. This study provides a new approach for estimating grassland AGB with multi-source data. As a simple and effective indicator, VHI has shown strong application potential for grassland AGB estimating in mountainous areas, and can be further applied to grassland carbon cycle research and fine management. [ABSTRACT FROM AUTHOR]

Southern California, USA, has been suffering severe surface deformation due to its active crustal movement under the north–south compression of the Pacific Plate and North American Plate. Meanwhile, affected by groundwater extraction and recharge, oil exploitation, surface subsidence, uplift, and seasonal deformation occur commonly in this region. In this paper, multi-path SAR datasets were collected to investigate and monitor surface deformation in Southern California. The unified simultaneous least squares (USLS) approach is applied to remove the deformation discontinuity between adjacent SAR image paths. Multiple deformation patterns of structural faults, groundwater withdrawal, and oil exploitation are observed with the interferometric synthetic aperture radar (InSAR) technique. The InSAR-derived results were validated with GPS monitoring data. The correlations between land deformation and groundwater withdrawal, faults, and precipitation were intensively analyzed, finding out and mastering the magnitude and characteristics of ground deformation in Southern California. [ABSTRACT FROM AUTHOR]

Although the existing deep-learning-based hyperspectral image (HSI) denoising methods have achieved tremendous success, recovering high-quality HSIs in complex scenes that contain mixed noise is still challenging. Besides, these methods have not fully explored the local and global spatial–spectral information of HSIs. To address the above issues, a novel HSI mixed noise removal network called subspace projection attention and residual channel attention network (SPARCA-Net) is proposed. Specifically, we propose an orthogonal subspace projection attention (OSPA) module to adaptively learn to generate bases of the signal subspace and project the input into such space to remove noise. By leveraging the local and global spatial relations, OSPA is able to reconstruct the local structure of the feature maps more precisely. We further propose a residual channel attention (RCA) module to emphasize the interdependence between feature maps and exploit the global channel correlation of them, which could enhance the channel-wise adaptive learning. In addition, multiscale joint spatial–spectral input and residual learning strategies are employed to capture multiscale spatial–spectral features and reduce the degradation problem, respectively. Synthetic and real HSI data experiments demonstrated that the proposed HSI denoising network outperforms many of the advanced methods in both quantitative and qualitative assessments. [ABSTRACT FROM AUTHOR]

Temperature and precipitation are considered to be the most important indicators affecting the green-up date. Sensitivity of the green-up date to temperature and precipitation is considered to be one of the key indicators to characterize the response of terrestrial ecosystems to climate change. We selected the main grassland types for analysis, including temperate steppe, temperate meadow steppe, upland meadow, and lowland meadow. This study investigates the variation in key meteorological indicators (daily maximum temperature (Tmax), daily minimum temperature (Tmin), and precipitation) between 2001 and 2018. We then examined the partial correlation and sensitivity of green-up date (GUD) to Tmax, Tmin, and precipitation. Our analysis indicated that the average GUD across the whole area was DOY 113. The mean GUD trend was −3.1 days/decade and the 25% region advanced significantly. Tmax and Tmin mainly showed a decreasing trend in winter (p > 0.05). In spring, Tmax mainly showed an increasing trend (p > 0.05) and Tmin a decreasing trend (p > 0.05). Precipitation showed no significant (p > 0.05) change trend and the trend range was ±10 mm/decade. For temperate steppe, the increase in Tmin in March promotes green-up (27.3%, the proportion of significant pixels), with a sensitivity of −0.17 days/°C. In addition, precipitation in April also promotes green-up (21.7%), with a sensitivity of −0.32 days/mm. The GUDs of temperate meadow steppe (73.9%), lowland meadow (65.9%), and upland meadow (22.1%) were mainly affected by Tmin in March, with sensitivities of −0.15 days/°C, −0.13 days/°C, and −0.14 days/°C, respectively. The results of this study reveal the response of vegetation to climate warming and contribute to improving the prediction of ecological changes as temperatures increase in the future. [ABSTRACT FROM AUTHOR]

The medium resolution spectral imager-2 (MERSI-2) is one of the most important sensors onboard China's latest polar-orbiting meteorological satellite, Fengyun-3D (FY-3D). The National Satellite Meteorological Center of China Meteorological Administration has developed four precipitable water vapor (PWV) datasets using five near-infrared bands of MERSI-2, including the P905 dataset, P936 dataset, P940 dataset and the fusion dataset of the above three datasets. For the convenience of users, we comprehensively evaluate the quality of these PWV datasets with the ground-based PWV data derived from Aerosol Robotic Network. The validation results show that the P905, P936 and fused PWV datasets have relatively large systematic errors (−0.10, −0.11 and −0.07 g/cm2), whereas the systematic error of the P940 dataset (−0.02 g/cm2) is very small. According to the overall accuracy of these four PWV datasets by our assessments, they can be ranked in descending order as P940 dataset, fused dataset, P936 dataset and P905 dataset. The root mean square error (RMSE), relative error (RE) and percentage of retrieval results with error within ± (0.05 + 0.10 ∗ P W V A E R O N E T ) (PER10) of the P940 PWV dataset are 0.24 g/cm2, 0.10 and 76.36%, respectively. The RMSE, RE and PER10 of the P905 PWV dataset are 0.38 g/cm2, 0.15 and 57.72%, respectively. In order to obtain a clearer understanding of the accuracy of these four MERSI-2 PWV datasets, we compare the accuracy of these four MERSI-2 PWV datasets with that of the widely used MODIS PWV dataset and AIRS PWV dataset. The results of the comparison show that the accuracy of the MODIS PWV dataset is not as good as that of all four MERSI-2 PWV datasets, due to the serious overestimation of the MODIS PWV dataset (0.40 g/cm2), and the accuracy of the AIRS PWV dataset is worse than that of the P940 and fused MERSI-2 PWV datasets. In addition, we analyze the error distribution of the four PWV datasets in different locations, seasons and water vapor content. Finally, the reason why the fused PWV dataset is not the one with the highest accuracy among the four PWV datasets is discussed. [ABSTRACT FROM AUTHOR]