Researchers have explored various methods to fully exploit the all-weather characteristics of Synthetic aperture radar (SAR) images to achieve high-precision, real-time, computationally efficient, and easily deployable ship target detection models. These methods include Constant False Alarm Rate (CFAR) algorithms and deep learning approaches such as RCNN, YOLO, and SSD, among others. While these methods outperform traditional algorithms in SAR ship detection, challenges still exist in handling the arbitrary ship distributions and small target features in SAR remote sensing images. Existing models are complex, with a large number of parameters, hindering effective deployment. This paper introduces a YOLOv7 oriented bounding box SAR ship detection model (YOLOv7oSAR). The model employs a rotation box detection mechanism, uses the KLD loss function to enhance accuracy, and introduces a Bi-former attention mechanism to improve small target detection. By redesigning the network’s width and depth and incorporating a lightweight P-ELAN structure, the model effectively reduces its size and computational requirements. The proposed model achieves high-precision detection results on the public RSDD dataset (94.8% offshore, 66.6% nearshore), and its generalization ability is validated on a custom dataset (94.2% overall detection accuracy).

The constant need for decarbonization has led to the replacement of artificial light at night (ALAN) with light-emitting diodes (LEDs), inducing blue light pollution and its consequent adverse effects. As a result, there is an urgent need for the development of a technique for the rapid, accurate, and large-scale discrimination of the various illumination sources. The newly launched Sustainable Development Science Satellite-1 (SDGSAT-1) can play this role by supplementing the existing nighttime light data with multispectral and high-resolution features. Along these lines, in this work, a novel approach to identify various types of illumination sources using machine learning in SDGSAT-1 images was proposed, taking Beijing as a worked example. The results indicate that: (1) The method can effectively distinguish the various types of light sources with an overall accuracy of 0.92 for ALAN and 0.95 for streetlights. (2) The illumination patterns can be clearly depicted, indicating distinct spatial heterogeneity in ALAN along Beijing's 5th Ring Road. (3) Statistically significant disparities between road classes and streetlight types were detected, with a notable increase in LED streetlight usage as the road class diminishes. This work emphasizes the crucial role of SDGSAT-1 in analysing ALAN, providing valuable insights in urban lighting management.

During the past decade, implementing reconstruction algorithms on hardware has been at the center of much attention in the field of real-time reconstruction in Compressed Sensing (CS). Orthogonal Matching Pursuit (OMP) is the most widely used reconstruction algorithm on hardware implementation because OMP obtains good quality reconstruction results under a proper time cost. OMP includes Dot Product (DP) and Least Square Problem (LSP). These two parts have numerous division calculations and considerable vector-based multiplications, which limit the implementation of real-time reconstruction on hardware. In the theory of CS, besides the reconstruction algorithm, the choice of sensing matrix affects the quality of reconstruction. It also influences the reconstruction efficiency by affecting the hardware architecture. Thus, designing a real-time hardware architecture of OMP needs to take three factors into consideration. The choice of sensing matrix, the implementation of DP and LSP. In this paper, a sensing matrix, which is sparsity and contains zero vectors mainly, is adopted to optimize the OMP reconstruction to break the bottleneck of reconstruction efficiency. Based on the features of the chosen matrix, the DP and LSP are implemented by simple shift, add and comparing procedures. This work is implemented on the Xilinx Virtex UltraScale+ FPGA device. To reconstruct a digital signal with 1024 length under 0.25 sampling rate, the proposal method costs 0.818us while the state-of-the-art costs 238us. Thus, this work speedups the state-of-the-art method 290 times. This work costs 0.026s to reconstruct an 8K gray image, which achieves 30FPS real-time reconstruction.

To reduce the huge off-chip dynamic random-access memory bandwidth which occupies a significant portion of the system power, reference frame recompression (RFRC) becomes one of the most vital components in the application-specified integrated circuit implementation of video codecs. RFRC challenges to increase the compression ratio with low-complexity and support random access of the compressed data. This article presents an adaptive detachable partition-based RFRC scheme which is capable of compressing a variable-size to a fixed bit of access unit. Compared with the conventional schemes which compress fixed-size partition to variable bits, this work can increase the compression ratio by greatly reducing the redundancy of the partitions' boundaries. Moreover, a high-speed coding algorithm is applied to reduce the complexity and increase the parallelism of compressing and decompressing. Finally, a new memory mapping strategy is utilized to support random access. As a result, the reference frame can be compressed by 68% with no quality degradation.

In the field of SAR-to-optical image synthesis, current methods based on conditional generative adversarial networks (CGANs) have satisfying performance under simple scenarios, but the performance drops severely under complicated scenarios. Considering that SAR images can form a robust time series due to SAR’s all-weather imaging ability, we take advantage of this and extract a temporal correlation from bi-temporal SAR images to guide the translation. To achieve this, we introduce a co-attention mechanism into the CGAN that learns the correlation between optically-available and optically-absent time points, selectively enhances the features of the former time point, and eventually guides the model to a better optical image synthesis on the latter time point. Additionally, we adopt a strategy to balance the weight of optical and SAR features to extract better features from the SAR input. With these strategies, the quality of synthesized images is notably improved in complicated scenarios. The synthesized images can increase the spatial and temporal resolution of optical imagery, greatly improving the availability of data for the applications of crop monitoring, change detection, and visual interpretation.

Recently, specifically designed video codecs have been preferred due to the expansion of video data in Internet of Things (IoT) devices. Context Adaptive Binary Arithmetic Coding (CABAC) is the entropy coding module widely used in recent video coding standards such as HEVC/H.265 and VVC/H.266. CABAC is a well known throughput bottleneck due to its strong data dependencies. Because the required context model of the current bin often depends on the results of the previous bin, the context model cannot be prefetched early enough and then results in pipeline stalls. To solve this problem, we propose a prediction-based context model prefetching strategy, effectively eliminating the clock consumption of the contextual model for accessing data in memory. Moreover, we offer multi-result context model update (MCMU) to reduce the critical path delay of context model updates in multi-bin/clock architecture. Furthermore, we apply pre-range update and pre-renormalize techniques to reduce the multiplex BAE's route delay due to the incomplete reliance on the encoding process. Moreover, to further speed up the processing, we propose to process four regular and several bypass bins in parallel with a variable bypass bin incorporation (VBBI) technique. Finally, a quad-loop cache is developed to improve the compatibility of data interactions between the entropy encoder and other video encoder modules. As a result, the pipeline architecture based on the context model prefetching strategy can remove up to 45.66% of the coding time due to stalls of the regular bin, and the parallel architecture can also save 29.25% of the coding time due to model update on average under the condition that the Quantization Parameter (QP) is equal to 22. At the same time, the throughput of our proposed parallel architecture can reach 2191 Mbin/s, which is sufficient to meet the requirements of 8 K Ultra High Definition Television (UHDTV). Additionally, the hardware efficiency (Mbins/s per k gates) of the proposed architecture is higher than that of existing advanced pipeline and parallel architectures.

High-resolution (HR) remote sensing images have important applications in many scenarios, and improving the resolution of remote sensing images via algorithms is one of the key research fields. However, current super-resolution (SR) algorithms, which are trained on synthetic datasets, tend to have poor performance in real-world low-resolution (LR) images. Moreover, due to the inherent complexity of real-world remote sensing images, current models are prone to color distortion, blurred edges, and unrealistic artifacts. To address these issues, real-SR datasets using the Gao Fen (GF) satellite images at different spatial resolutions have been established to simulate real degradation situations; moreover, a second-order attention generator adversarial attention network (SA-GAN) model based on real-world remote sensing images is proposed to implement the SR task. In the generator network, a second-order channel attention mechanism and a region-level non-local module are used to fully utilize the a priori information in low-resolution (LR) images, as well as adopting region-aware loss to suppress artifact generation. Experiments on test data demonstrate that the model delivers good performance for quantitative metrics, and the visual quality outperforms that of previous approaches. The Frechet inception distance score (FID) and the learned perceptual image patch similarity (LPIPS) value using the proposed method are improved by 17.67% and 6.61%, respectively. Migration experiments in real scenarios also demonstrate the effectiveness and robustness of the method.

High-accuracy sea ice monitoring is of great significance in responding to global climate change and guiding safe navigation. The moderate resolution imaging spectroradiometer (MODIS) sensors carried by Aqua and Terra satellites have great potential in high-resolution monitoring of sea ice in polar regions. This study developed an automatic high-accuracy sea ice concentration (SIC) detection algorithm for the MODIS data. We used a machine learning algorithm that combines spectral and texture features to obtain high-precision sea ice recognition results. Then, according to the cloud characteristics in MODIS images and the full coverage of Advanced Microwave Scanning Radiometer 2 (AMSR2) SICs, outlier removal and cloud area filling are carried out. Finally, the SIC result was calculated according to the distribution of ice types. We assessed the accuracy of our high-accuracy SIC product by comparing with the MOD29/MYD29 products and validating with the Landsat 8/9 images. We found that the deviation increased with the decrease in SIC value. The deviation is larger in the ice melting area and the ice edges area, but smaller in the area completely covered by ice. Compared with MOD29/MYD29 SICs, the SICs obtained in this study have higher accuracy, with an average root-mean-square deviation (RMSD) of 7.64%. It can detect the details of relatively small leads, ice edges, and fragmented ice areas. The high-accuracy SIC product we obtained is expected to provide long-term SIC records of high quality.

The Sustainable Development Goals Science Satellite-1 (SDGSAT-1) Glimmer Imager for Urbanization (GIU) data is very sensitive to low radiation and capable of detecting weak light sources from vessels at night while significantly improving the spatial resolution compared to similar products. Most existing methods fail to use the relevant characteristics of vessels effectively, and it is difficult to deal with the complex shape of vessels in high-resolution Nighttime Light (NTL) data, resulting in unsatisfactory detection results. Considering the overall sparse distribution of vessels and the light source diffusion phenomenon, a novel vessel detection method is proposed in this paper, utilizing the high spatial resolution of the SDGSAT-1. More specifically, noise separation is completed based on a local contrast-weighted RPCA. Then, artificial light sources are detected based on a density clustering algorithm, and an inter-cluster merging method is utilized to realize vessel detection further. We selected three research areas, namely, the Bohai Sea, the East China Sea, and the Gulf of Mexico, to establish a vessel dataset and applied the algorithm to the dataset. The results show that the total detection accuracy and the recall rate of the detection algorithm in our dataset are 96.84% and 96.67%, which is significantly better performance than other methods used for comparison in the experiment. The algorithm overcomes the dataset’s complex target shapes and noise conditions and achieves good results, which proves the applicability of the algorithm.

Over the years, the objective of image and video compression has been to preserve perceived quality according to the Human Visual System (HVS) with minimal rate. Traditional encoders achieve this with the use of Rate-Distortion Optimization (RDO) techniques along with Image Quality Assessment (IQA) metrics that are correlated with human perception. Nowadays, a fast-growing number of applications fall within the realm of Video Coding for Machines (VCM), where the final recipient of compressed data is not a human but a machine performing a vision task. Recently, the lack of correlation between existing distortion measures and machine perception has been revealed, especially for RDO algorithms where distortion measures are computed on a local scale. In this paper, we propose a machine perception-aware metric designed to be incorporated into a standard-compliant Versatile Video Coding (VVC) encoder. Our proposed metric relies on a supervised training procedure as well as additional information available on the encoder side. In terms of correlation with machine perception, our metric significantly outperforms existing distortion measures in the literature.

As clean, renewable energy, photovoltaic (PV) energy can reduce the ozone-layer loss and climate deterioration caused by the use of traditional types of energy to generate electricity. At present, most PV energy products involve the influence of cloud cover on solar radiation. However, the resolution and precision of most cloud cover data are not fine enough to reflect the actual cloud distribution in local areas. This leads to incorrect distribution results of PV energy in areas with high-spatial-variability clouds. Using high-resolution and high-precision cloud cover data obtained by satellite remote sensing to estimate the distribution of PV energy can solve this problem. In this study, the Global Land High-Resolution Cloud Climatology (GLHCC), a 10-day cloud frequency product with a resolution of 1 km and located in China, was used to construct a cloud-based solar radiation estimation model. Using the inverse relationship between cloud cover and solar radiation, the GLHCC was converted into sunshine percentage data. Using meteorological station data in China, a Least Squares Fit (LSF) and error check were carried out on the A-P, Lqbal, Bahel and Sen Models to determine the optimal solar radiation estimation model (Sen Model). Based on the sunshine percentage data, the Sen Model and terrain shielding factors, the distribution of PV energy in China was estimated. Finally, comparing to the Global Horizontal Irradiance (GHI) of the World Bank and the yearly average global irradiance of the Photovoltaic Geographic Information System (PVGIS), PV energy data in this paper more accurately reflected the distribution of PV energy in China, especially in areas with high-spatial-variability clouds.

The reconstruction of Compressed Sensing is iteration-based and contains numerous divisions, thereby costing tremendous processing time. In order to eliminate divisions, we adopt a sparse sensing matrix consisting mainly of zero-vectors. After deleting these zero-vectors, an invertible full-rank matrix is obtained. Then the iteration-based reconstruction procedure can be replaced by a matrix multiplication operated in one iteration. Moreover, because the inverse matrix is sparse and deterministic, the multiplication can be simply processed by the shift and add operators. The proposed architecture is verified on the Xilinx Artix-7 FPGA. The result shows that our work accelerates the state-of-the-art method by 65 × and achieves 81.92Gpixels/s reconstruction.

Text-guided image manipulation aims to use the given text description to modify the semantic content of the corresponding part in the input image. Although researchers have been obtained satisfactory performance in this field, they only 1) utilize the global sentence information at the initial modification stage and 2) exploit the fixed word information for regional adjustment in the subsequent modification process, hindering the improvement of image manipulation quality. Motivated by the mentioned issues, this paper proposes a novel approach to improve the performance of text-guided image manipulation by using sentence-aware and word-aware network. Concretely, we utilize global sentence information throughout the image manipulation process to improve the semantic consistency with the input text. On the other hand, we employ the dynamic selection method to dynamically adjust the word information corresponding to the regional image content to further improve the manipulation quality. As a result, our work surpasses the existing state-of-the-art methods on CUB and Oxford-102 flower datasets, demonstrating our effectiveness and superiority. In terms of Inception Score, our proposed method performs the most excellent performance. In terms of NIMA, the score of our method is closest to the score of the original dataset images, proving that our manipulated results are the most authentic.

Context Adaptive Binary Arithmetic Coding (CABAC) is the entropy coding module widely used in recent video coding standards such as HEVC/H.265 and VVC/H.266. CABAC is a well-known throughput bottleneck due to its strong data dependencies. Because the required context model of the current bin often depends on the results of the previous bin, the context model cannot be prefetched early enough, and then costs pipeline stalls. To solve this problem, we propose a prediction-based context model prefetching strategy. If the prediction is correct, pipeline stalls can be eliminated, and the stalling cycles won't get worse with the wrong prediction. Moreover, the data interaction process between CABAC modules and the multi-stage pipeline structure are optimized to maximize the working frequency. The proposed pipeline architecture can reduce pipeline stalls and save up to 45.66% encoding time, the improved results show that it provides more significant gains in All Intra (AI) under low QP test conditions, which is better than the Random Access (RA) and Low Delay (LD) configuration. The highest hardware efficiency (Mbins/s Per k gates) is higher than the existing advanced pipeline architecture.

Due to the high flexibility and conformity to people's usage habits, text description has been widely used in image synthesis research recently and has achieved many encouraging results. However, the text can only determine the basic content of the generated image and cannot determine the specific shape of the synthesized object, which leads to poor practicability. More importantly, the current text-to-image synthesis research cannot use new text descriptions to further modify the synthesis result. To solve these problems, this paper proposes a text-guided customizable image synthesis and manipulation method. The proposed method synthesizes the corresponding image based on the text and contour information at first. It then modifies the synthesized content based on the new text to obtain a satisfactory result. The text and contour information in the proposed method determine the specific content and object shape of the desired composite image, respectively. Aside from that, the input text, contour, and subsequent new text for content modification can be manually input, which significantly improves the artificial controllability in the image synthesis process, making the entire method superior to other methods in flexibility and practicability. Experimental results on the Caltech-UCSD Birds-200-2011 (CUB) and Microsoft Common Objects in Context (MS COCO) datasets demonstrate our proposed method's feasibility and versatility.

To improve the classification performance of existing adaptive boosting (AdaBoost) based algorithms effectively, an improved AdaBoost algorithm based on misclassified samples oriented feature selection and weighted non-negative matrix factorization (WNMF) is proposed in this paper. Firstly, in order to consider the effects of sample weights, a misclassified samples oriented feature selection (called MOFS) is proposed to select the most discriminative features which occur in the samples with high weights. Secondly, the explicit features and the part-based features of the training samples are both considered, and the WNMF algorithm is introduced and combined with MOFS to reduce the dimension of the training sample set. Finally, the concept of misclassification degree is introduced and a fine grained sample weight updating method is proposed to distinguish the samples with different misclassification degrees. Numerical experiments show that the proposed MOFS method achieves higher accuracy compared to traditional feature selection methods, and the proposed MOFS and WNMF based AdaBoost method obtains significant improvement on classification accuracy when comparing with typical existing AdaBoost based algorithms using different classifiers.

Heterogeneous systems” collaboration strategy is important for natural disaster observation. In this paper, we discuss the collaborative architecture of integrated observation system using satellite remote sensing, $V$ nmanned swarm system, Internet of Things (IoT), and Geographic Information System (GIS) technologies. We concern three issues: inter-domain and intra-domain systems' collaboration mechanisms, heterogeneous communication network, and system function modularization. On the base of the proposed architecture, we perform a series of satellite and UAV remote sensing and modeling experiments, then we develop a data visualization system based on GIS and observed data. We propose an unmanned swarm observation algorithm and perform a series of simulation experiments, also we develop an initial end-edge-cloud system for unmanned swarm observation. The proposed architecture provides better system scalability in complex emergency environment.

Natural disaster observation technology has significant progress with the development of advanced satellite remote sensing (RS), Unmanned Aerial Vehicles (UAVs), and Internet of Things (IOT) technologies. In this paper, we discuss the architecture of an integrated natural disaster observation system using RS, UAVs, and IOT technologies. We concern three aspects: heterogeneous communication, air-ground cooperation mechanism, and data visualization using Geographic Information System (GIS). A Real-world system has been developed, and a series of simulation and experiments have been performed, and the proposed architecture provides better system scalability in complex environment.

In this paper, we propose a multi-perspective fusion method to improve the performance of text-to-image synthesis. From the perspective of the generator, we introduce a dynamic selection method to make the text feature match the corresponding image feature better, while the multi-class discriminant method with mask segmentation image as the extra type is introduced from the perspective of the discriminator to improve its discrimination ability. Through the effective integration of these two aspects of improvement, more excellent results by our method are obtained. Experiments on the Caltech-UCSD Birds 200 (CUB) and Microsoft Common Objects in Context (MS COCO) datasets demonstrate our method's effectiveness and superiority. The qualitative and quantitative experiments validate that our method is superior to the existing state-of-the-art methods.

After the iconic outburst of Zonag Lake in Hoh Xil of Tibetan Plateau (TP) in 2011, the causes of the collapse and its impact on the volume of water contained by the downstream lakes have highly been concerned, but the overall changes of the hydrological ecosystem and its impacts on the basin are yet not clear. This paper analyzes the hydrological system (lake area and hydrological connection) and ecosystem (sandstorm activity and vegetation growth status) changes and their impacts on the regional ecological environment after the outburst event, based on remotely sensed images from 2000 to 2020, meteorological observations, and field surveys. The results show that the outburst of Zonag Lake has not only changed the regional hydrology and ecosystem pattern but also caused a trend of degradation in the ecological environment of Zonag Lake Basin. Some lambing areas and active areas of Tibetan antelope in the area are being buried and eroded by the sandstorm. The downstream Yanhu Lake has risen to the highest level and overflowed through the emergency diversion engineering. These impacts are continuously threatening the health of the ecological environment of the world natural heritage site in Hoh Xil, the safety of Qinghai-Tibet highway, Qinghai-Tibet railway, and other engineering facilities, as well as the stability of fluvial geomorphology in the northern most sources of Yangtze River.