Search Results (24)

Automatic ship monitoring models leveraging image recognition have become integral to regulatory applications within maritime management, with multi-source image co-monitoring serving as the primary method for achieving comprehensive, round-the-clock surveillance. Despite their widespread use, the existing models predominantly train each data source independently or simultaneously train multiple sources without fully optimizing the integration of similar information. This approach, while capable of all-weather detection, results in the underutilization of data features from related sources and unnecessary repetition in model training, leading to excessive time consumption. To address these inefficiencies, this paper introduces a novel multi-task learning framework designed to enhance the utilization of data features from diverse information sources, thereby reducing training time, lowering costs, and improving recognition accuracy. The proposed model, VIOS-Net, integrates the advantages of both visible and infrared data sources to meet the challenges of all-weather, all-day ship monitoring under complex environmental conditions. VIOS-Net employs a Shared Bottom network architecture, utilizing both shared and specific feature extraction modules at the model’s lower and upper layers, respectively, to optimize the system’s recognition capabilities and maximize data utilization efficiency. The experimental results demonstrate that VIOS-Net achieves an accuracy of 96.20% across both visible and infrared spectral datasets, significantly outperforming the baseline ResNet-34 model, which attained accuracies of only 4.86% and 9.04% in visible and infrared data, respectively. Moreover, VIOS-Net reduces the number of parameters by 48.82% compared to the baseline, achieving optimal performance in multi-spectral ship monitoring. Extensive ablation studies further validate the effectiveness of the individual modules within the proposed framework. Full article

Accurate, real-time, and dynamic monitoring of crop planting distributions in hilly areas with complex terrain and frequent meteorological changes is highly important for agricultural production. Dual-polarization SAR has high application value in the fields of feature classification and crop distribution extraction because of its all-day all-weather operation, large mapping bandwidth, and easy data acquisition. To explore the feasibility and applicability of dual-polarization synthetic-aperture radar (SAR) data in crop monitoring, this study draws on two basic methods of dual-polarization decomposition (eigenvalue decomposition and three-component polarization decomposition) to construct time series of crop dual-polarization radar vegetation indices (RVIs), and it performs a full coverage analysis of crop distribution extraction in dryland mountainous areas of southeastern China. On the basis of the Sentinel-1 dual-polarization RVIs, the time-series classification and rapeseed distribution extraction impacts were compared using southern Hunan Province’s principal rapeseed (Brassica napus L.) production area as the study area. From the comparison results, $RV{I}_{3-c}$ performed better in terms of single-point recognition capability and area extraction accuracy than the other indices did, as verified by sampling points and samples, and the OA and F-1 score of rapeseed extraction based on $RV{I}_{3-c}$ were 74.13% and 81.02%, respectively. Therefore, three-component polarization decomposition is more suitable than other methods for crop information extraction and remote sensing classification applications involving dual-polarized SAR data. Full article

Synthetic Aperture Radar (SAR) is a remote sensing technology that can realize all-weather and all-day monitoring, and it is widely used in ocean ship monitoring tasks. Recently, many oriented detectors were used for ship detection in SAR images. However, these methods often found it difficult to balance the detection accuracy and speed, and the noise around the target in the inshore scene of SAR images led to a poor detection network performance. In addition, the rotation representation still has the problem of boundary discontinuity. To address these issues, we propose S4Det, a Sinusoidal Single-Stage SAR image detection method that enables real-time oriented ship target detection. Two key mechanisms were designed to address inshore scene processing and angle regression challenges. Specifically, a Breadth Search Compensation Module (BSCM) resolved the limited detection capability issue observed within inshore scenarios. Neural Discrete Codebook Learning was strategically integrated with Multi-scale Large Kernel Attention, capturing context information around the target and mitigating the information loss inherent in dilated convolutions. To tackle boundary discontinuity arising from the periodic nature of the target regression angle, we developed a Sine Fourier Transform Coding (SFTC) technique. The angle is represented using diverse sine components, and the discrete Fourier transform is applied to convert these periodic components to the frequency domain for processing. Finally, the experimental results of our S4Det on the RSSDD dataset achieved 92.2% mAP and 31+ FPS on an RTXA5000 GPU, which outperformed the prevalent mainstream of the oriented detection network. The robustness of the proposed S4Det was also verified on another public RSDD dataset. Full article

Combining multiple data sources, Digital Earth is an integrated observation platform based on air–space–ground–sea monitoring systems. Among these data sources, the Inverse Synthetic Aperture Radar (ISAR) is a crucial observation method. ISAR is typically utilized to monitor both military and civilian ships due to its all-day and all-weather superiority. However, in complex scenarios, multiple targets may exist within the same radar antenna beam, resulting in severe defocusing due to different motion conditions. Therefore, this paper proposes a multiple-target ISAR imaging method with the removal of micro-motion connections based on the integration of joint constraints. The fully motion-compensated targets exhibit low rank and local similarity in the high-resolution range profile (HRRP) domain, while the micro-motion components possess sparsity. Additionally, targets display sparsity in the image domain. Inspired by this, we formulate a novel optimization by promoting the low-rank, the Laplacian, and the sparsity constraints of targets and the sparsity constraints of the micro-motion components. This optimization problem is solved by the linearized alternative direction method with adaptive penalty (LADMAP). Furthermore, the different motions of various targets degrade their inherent characteristics. Therefore, we integrate motion compensation transformation into the optimization, accordingly achieving the separation of rigid bodies and the micro-motion components of different targets. Experiments based on simulated data demonstrate the effectiveness of the proposed method. Full article

Hail poses a significant meteorological hazard in China, leading to substantial economic and agricultural damage. To enhance the detection of hail and mitigate these impacts, this study presents an ensemble machine learning model (BPNN+Dtree) that combines a backpropagation neural network (BPNN) and a decision tree (Dtree). Using FY-4A satellite and ERA5 reanalysis data, the model is trained on geostationary satellite infrared data and environmental parameters, offering comprehensive, all-day, and large-area hail monitoring over China. The ReliefF method is employed to select 13 key features from 29 physical quantities, emphasizing cloud-top and thermodynamic properties over dynamic ones as input features for the model to enhance its hail differentiation capability. The BPNN+Dtree ensemble model harnesses the strengths of both algorithms, improving the probability of detection (POD) to 0.69 while maintaining a reasonable false alarm ratio (FAR) on the test set. Moreover, the model’s spatial distribution of hail probability more closely matches the observational data, outperforming the individual BPNN and Dtree models. Furthermore, it demonstrates improved regional applicability over overshooting top (OT)-based methods in the China region. The identified high-frequency hail areas correspond to the north-south movement of the monsoon rain belt and are consistent with the northeast-southwest belt distribution observed using microwave-based methods. Full article

Atmospheric aerosols affect climate change, air quality, and human health. The aerosol optical depth (AOD) is a widely utilized parameter for estimating the concentration of atmospheric aerosols. Consequently, continuous AOD monitoring is crucial for environmental studies. However, a method to continuously monitor the AOD throughout the day or night remains a challenge. This study introduces a method for estimating the All-Day AOD using ground air quality and meteorological data. This method allows for the hourly estimation of the AOD throughout the day in the Beijing–Tianjin–Hebei (BTH) region and addresses the lack of high temporal resolution monitoring of the AOD during the nighttime. The results of the proposed All-Day AOD estimation method were validated against AOD measurements from Advanced Himawari Imager (AHI) and Aerosol Robotic Network (AERONET). The R² between the estimated AOD and AHI was 0.855, with a root mean square error of 0.134. Two AERONET sites in BTH were selected for analysis. The results indicated that the absolute error between the estimated AOD and AERONET was within acceptable limits. The estimated AOD showed spatial and temporal trends comparable to those of AERONET and AHI. In addition, the hourly mean AOD was analyzed for each city in BTH. The hourly mean AOD in each city exhibits a smooth change at night. In conclusion, the proposed AOD estimation method offers valuable data for investigating the impact of aerosol radiative forcing and assessing its influence on climate change. Full article

Crop classification is indispensable for agricultural monitoring and food security, but early-season mapping has remained challenging. Synthetic aperture radar (SAR), such as RADARSAT Constellation Mission (RCM) and Sentinel-1, can meet higher requirements on the reliability of satellite data acquisition with all-weather and all-day imaging capability to supply dense observations in the early crop season. This study applied the local window attention transformer (LWAT) to time-series SAR data, including RCM and Sentinel-1, for early-season crop classification. The performance of this integration was evaluated over crop-dominated regions (corn, soybean and wheat) in southwest Ontario, Canada. Comparative analyses against several machine learning and deep learning methods revealed the superiority of the LWAT, achieving an impressive F1-score of 97.96% and a Kappa coefficient of 97.08% for the northern crop region and F1-scores of 98.07% and 97.02% for the southern crop region when leveraging time-series data from RCM and Sentinel-1, respectively. Additionally, by the incremental procedure, the evolution of accuracy determined by RCM and Sentinel-1 was analyzed, which demonstrated that RCM performed better at the beginning of the season and could achieve comparable accuracy to that achieved by utilizing both datasets. Moreover, the beginning of stem elongation of corn was identified as a crucial phenological stage to acquire acceptable crop maps in the early season. This study explores the potential of RCM to provide reliable prior information early enough to assist with in-season production forecasting and decision making. Full article

As urban economies flourish and populations become increasingly concentrated, urban surface deformation has emerged as a critical factor in city planning that cannot be overlooked. Surface deformation in urban areas can lead to deformations in structural supports of infrastructure such as road bases and bridges, thereby posing a serious threat to public safety and creating significant safety hazards. Consequently, research focusing on the monitoring of urban surface deformation holds paramount importance. Interferometric synthetic aperture radar (InSAR), as an important means of earth observation, has all-day, wide-range, high-precision, etc., characteristics and is widely used in the field of surface deformation monitoring. However, traditional solitary InSAR techniques are limited in their application scenarios and computational characteristics. Additionally, the manual selection of ground control points (GCPs) is fraught with errors and uncertainties. Permanent scatterers (PS) can maintain high interferometric coherence in man-made building areas, and distributed scatterers (DS) usually show moderate coherence in areas with short vegetation; the combination of DS and PS solves the problem of manually selecting GCPs during track re-flattening and regrading, which affects the monitoring results. In this paper, 45 Sentinel-1B data from 16 February 2019 to 14 December 2021 are used as the data source in the urban area of Horqin District, Tongliao City, Inner Mongolia Autonomous Region, for example. A four-threshold (coherence coefficient threshold, FaSHPS adaptive threshold, amplitude divergence index threshold, and deformation velocity interval) GCPs point screening method for PS-DS, as well as a Small Baseline Subset-Permanent Scatterers-Distributed Scatterers-Interferometric Synthetic Aperture Radar (SBAS-PS-DS-InSAR) method for selecting PS and DS points as ground control points for orbit refinement and re-flattening, are proposed. The surface deformation results obtained using the Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) and the SBAS-PS-DS-InSAR proposed in this paper were comparatively analysed and verified. The maximum cumulative line-of-sight settlements were −90.78 mm and −83.68 mm, and the maximum cumulative uplifts are 74.94 mm and 97.56 mm, respectively; the maximum annual average line-of-sight settlements are −35.38 mm/y and −30.38 mm/y, and the maximum annual average uplifts are 25.27 mm/y and 27.92 mm/y. The results were evaluated and analysed in terms of correlation, mean absolute error (MAE), and root mean square error (RMSE). The deformation results of the two InSAR methods were evaluated and analysed in terms of correlation, MAE, and RMSE. The errors show that the Pearson correlation coefficients between the vertical settlement results obtained using the SBAS-PS-DS-InSAR method and the GPS monitoring results were closer to 1. The maximum MAE and RMSE were 13.7625 mm and 14.8004 mm, respectively, which are within the acceptable range; this confirms that the monitoring results of the SBAS-PS-DS-InSAR method were better than those of the original SBAS-InSAR method. SBAS-InSAR method, which is valid and reliable. The results show that the surface deformation results obtained using the SBAS-InSAR, SBAS-PS-DS-InSAR, and GPS methods have basically the same settlement locations, extents, distributions, and temporal and spatial settlement patterns. The deformation results obtained using these two InSAR methods correlate well with the GPS monitoring results, and the MAE and RMSE are within acceptable limits. By comparing the deformation information obtained using multiple methods, the surface deformation in urban areas can be better monitored and analysed, and it can also provide scientific references for urban municipal planning and disaster warning. Full article

Clouds are diverse and complex, making accurate cloud type identification vital in improving the accuracy of weather forecasting and the effectiveness of climate monitoring. However, current cloud classification research has largely focused on daytime data. The lack of visible light data at night presents challenges in characterizing nocturnal cloud attributes, leading to difficulties in achieving continuous all-day cloud classification results. This study proposed an all-day infrared cloud classification model (AInfraredCCM) based on XGBoost. Initially, the latitude/longitude, 10 infrared channels, and 5 brightness temperature differences of the Himawari-8 satellite were selected as input features. Then, 1,314,275 samples were collected from the Himawari-8 full-disk data and cloud classification was conducted using the CPR/CALIOP merged cloud type product as training data. The key cloud types included cirrus, deep convective, altostratus, altocumulus, nimbostratus, stratocumulus, stratus, and cumulus. The cloud classification model achieved an overall accuracy of 86.22%, along with precision, recall, and F1-score values of 0.88, 0.84, and 0.86, respectively. The practicality of this model was validated across all-day temporal, daytime/nighttime, and seasonal scenarios. The results showed that the AInfraredCCM consistently performed well across various time periods and seasons, confirming its temporal applicability. In conclusion, this study presents an all-day cloud classification approach to obtain comprehensive cloud information for continuous weather monitoring, ultimately enhancing weather prediction accuracy and climate monitoring. Full article

Millimeter wave radar has the advantage of all-day and all-weather capability for detection, speed measurement. It plays an important role in urban traffic flow monitoring and traffic safety monitoring. The conventional 2-dimensional Fast Fourier Transform (2DFFT) algorithm is performed target detection in the range-Doppler domain. However, the target motion will induce the range walk phenomenon, which leads to a decrease in the target energy and the performance of the target detection and speed measurement. To solve the above problems, this paper proposes a moving vehicle detection algorithm based on Keystone-2DFFT for a traffic scene. Firstly, this paper constructs and analyzes the Frequency Modulated ContinuousWave (FMCW) moving target signal model under traffic monitoring scenario’s radar observation geometry. The traditional 2DFFT moving target detection algorithm is briefly introduced. Then, based on mentioned signal model, an improved moving vehicle detection algorithm based on Keystone-2DFFT transform is proposed. The method first input the echo, then the range walk is removed by keystone transformation. the keystone transformation is achieved via Sinc interpolation. Next is transform data into range-Doppler domain to perform detection and speed estimation. The algorithm is verified by simulation data and real data. Full article

InSAR (Interferometric Synthetic Aperture Radar) is widely recognized as a crucial remote sensing tool for monitoring various geological disasters because it provides all-day and all-weather monitoring. Nevertheless, the current interpretation methods for InSAR heavily depend on the interpreter’s experience, which hinders efficiency and fails to meet the requirements for the timely detection of geologic hazards. Furthermore, the results obtained through current InSAR processing carry inherent noise interference, further complicating the interpretation process. To address those issues, this paper proposes an approach that enables automatic and rapid identification of deformation zones. The proposed method leverages IPTA (Interferometric Point Target Analysis) technology for SAR data processing. It combines the power of HNSW (Hierarchical Navigable Small Word) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithms to cluster deformation results. Compared with traditional methods, the computational efficiency of the proposed method is improved by 11.26 times, and spatial noise is suppressed. Additionally, the clustering results are fused with slope units determined using DEM (Digital Elevation Model), which facilitates the automatic identification of slopes experiencing deformation. The experimental verification in the western mountainous area of Beijing has identified 716 hidden danger areas, and this method is superior to the traditional technology in speed and automation. Full article

Reliable and timely rice distribution information is of great value for real-time, quantitative, and localized control of rice production information. Synthetic aperture radar (SAR) has all-weather and all-day observation capability to monitor rice distribution in tropical and subtropical areas. To improve the physical interpretability and spatial interpretability of the deep learning model for SAR rice field extraction, a new SHapley Additive exPlanation (SHAP) value-guided explanation model (SGEM) for polarimetric SAR (PolSAR) data was proposed. First, a rice sample set was produced based on field survey and optical data, and the physical characteristics were extracted using decomposition of polarimetric scattering. Then a SHAP-based Physical Feature Interpretable Module (SPFIM) combing the long short-term memory (LSTM) model and SHAP values was designed to analyze the importance of physical characteristics, a credible physical interpretation associated with rice phenology was provided, and the weight of physical interpretation was combined with the weight of original PolSAR data. Moreover, a SHAP-guided spatial interpretation network (SSEN) was constructed to internalize the spatial interpretation values into the network layer to optimize the spatial refinement of the extraction results. Shanwei City, Guangdong Province, China, was chosen as the study area. The experimental results showed that the physical explanation provided by the proposed method had a high correlation with the rice phenology, and spatial self-interpretation for finer extraction results. The overall accuracy of the rice mapping results was 95.73%, and the kappa coefficient reached 0.9143. The proposed method has a high interpretability and practical value compared with other methods. Full article

Entomological radar is a specially designed instrument that can measure the behavioral and biological characteristics of high-altitude migrating insects. Its application is of great significance for the monitoring, early warning, and control of agricultural pests. As an important component of the local migratory biomass, insects fly in the air during the day and night. The fully polarimetric entomological radar was carefully designed with all-day, all-weather, and multi-function measurement capabilities. The fully polarimetric entomological radar measures the mass of a single insect based on the radar cross-sectional (RCS) measurement and then calculates the biomass of migrating insects. Therefore, the measurement accuracy of the insect RCS is the key indicator affecting the accuracy of migratory biomass statistics. Due to the radar’s lack of in-beam angle measurement ability, the insect RCS is usually measured based on the assumption that the insect is on the beam center. Therefore, the measured RCS will be smaller than true value if the insect deviates from the beam center due to the gain curve of the antenna. This leads to measurement errors in regard to the insect mass and migratory biomass. In order to solve this problem, a biomass estimation method, reported in this paper, was designed under the assumption of a uniform distribution of migrating insects in the radar monitoring airspace. This method can estimate the individual RCS expectation of migrating insects through a statistical method without measuring the position of the insects in the beam and then obtain the migratory biomass. The effectiveness of the model and algorithm is verified by simulations and entomological radar field measurements. Full article

Timely and accurate information on rice cultivation makes important contributions to the profound reform of the global food and agricultural system, and promotes the development of global sustainable agriculture. With all-day and all-weather observing ability, synthetic aperture radar (SAR) can monitor the distribution of rice in tropical and subtropical areas. To solve the problem of misclassification of rice with no marked signal during the flooding period in subtropical hilly areas, this paper proposes a new feature combination and dual branch bi-directional long short-term memory (DB-BiLSTM) model to achieve high-precision rice mapping using Sentinel-1 time series data. Based on field investigation data, the backscatter time series curves of the rice area were analyzed, and a characteristic index (VV − VH)/(VV + VH) (VV: vertical emission and vertical receipt of polarization, VH: vertical emission and horizontal receipt of polarization) for small areas of hilly land was proposed to effectively distinguish rice and non-rice crops with no marked flooding period. The DB-BiLSTM model was designed, ensuring the independent learning of multiple features and effectively combining the time series information of both (VV − VH)/(VV + VH) and VH features. The city of Shanwei, Guangdong Province, China, was selected as the study area. Experimental results showed that the overall accuracy of the rice mapping results was 97.29%, and the kappa coefficient reached 0.9424. Compared to other methods, the rice mapping results obtained by the proposed method maintained good integrity and had less misclassification, which demonstrated the proposed method’s practical value in accurate and effective rice mapping tasks. Full article

A low-cost and power-efficient video surveillance system, named XDMOM, is developed for real-time moving object detection outdoors or in the wild. The novel system comprises four parts: imaging subsystem, video processing unit, power supply, and alarm device. The imaging subsystem, which consists of a dual-spectrum camera and rotary platform, can realize 360-degree and all-day monitoring. The video processing unit uses a power-efficient NVIDIA GeForce GT1030 chip as the processor, which ensures the power consumption of the whole system maintains a low level of 60~70 W during work. A portable lithium battery is employed to supply power so that the novel system can be used anywhere. The work principle is also studied in detail. Once videos are recorded, the single-stage neural network YOLOv4-tiny is employed to detect objects in a single frame, and an adaptive weighted moving pipeline filter is developed to remove pseudo-targets in the time domain, thereby reducing false alarms. Experimental results show that the overall correct alarm rate of the novel system could reach 85.17% in the daytime and 81.79% at night when humans are monitored in real outdoor environments. The good performance of the novel system is demonstrated by comparison with state-of-the-art video surveillance systems. Full article