Infrared and visible image fusion aims to leverage the complementary information from both modalities to generate fused images that are rich in information and visually appealing. Infrared images can capture thermal information and remain stable under low-light conditions, but they often lack detail. In contrast, visible light images provide rich texture and spatial details but are highly sensitive to lighting changes. This paper presents a novel multi-stage image fusion model, MS-Fusion, which integrates infrared and visible light features through an attention-guided fusion module. Unlike traditional methods, MS-Fusion begins the fusion process at the shallow feature extraction layers, retaining more low-level information that is crucial for preserving complementary details. Furthermore, the model incorporates saliency weights into the loss function to adaptively balance the differences between the two modalities under varying lighting and environmental conditions. Comprehensive experiments conducted on three public datasets (M3FD, LLVIP, and RoadScene) demonstrate the outstanding performance of MS-Fusion in detail preservation, contrast enhancement, and denoising. The experimental results show that MS-Fusion achieves state-of-the-art performance in both qualitative and quantitative evaluations, making it an ideal solution for tasks such as object detection, segmentation, and surveillance in challenging scenarios.

The growing dependence of autonomous vehicles on infrared thermal imaging for adverse-condition perception has heightened the security importance of infrared vehicle detectors. This work proposes the Infrared Vehicle Adversarial Patch (InfVAP), a physically realizable attack framework targeting these detectors. Addressing the dual challenges of limited prior research and complex vehicle geometry, our solution introduces: (1) Pixel-level attack localization using DeepLab-v3+ segmentation to ensure precise patch placement; (2) An improved Particle Swarm Optimization (PSO) algorithm with dynamic parameter adaptation and shape optimization to enhance attack effectiveness; (3) Expectation Over Transformation (EOT)-based robustness enhancement against real-world perturbations; and (4) A top-K confidence suppression loss (K=1000) for maximum attack potency. Extensive evaluations on the FLIR ADAS V2 dataset demonstrate that InfVAP achieves state-of-the-art performance: 93.93% digital Attack Success Rate (ASR) and 80.2% physical ASR at distances of 12 meters. Comprehensive ablation studies prove all components are statistically significant, with PSO optimization contributing most to attack potency.

The L-band differential interferometric SAR satellite, also named as LuTan-1, is the first bistatic spaceborne L-band SAR constellation for multiple applications in China. The Datong, Yulin and Liupanshui coalfields are the main coal production base in China which produce over 100 million tons coal each year and play a significant role for the development of national economy. However, a series of issues such as ground subsidence, landslides and damage of structures are induced by extensive coal mining. Therefore, the preliminary assessment of LuTan-1 SAR data for mining deformation monitoring, including Datong, Yulin and Liupanshui coalmines in China, were implemented in this research. Owing to the high revisit ability and long wavelength of LuTan-1 satellites, obvious subsidence was detected for different coalmines using LuTan-1 SAR data. In comparison with the simultaneous leveling measurements, deformation monitoring with cm accuracy were achieved over the study area.

Due to the limited color information and low hierarchy present in infrared images, traditional CNN-based pose estimation networks designed for visible light often exhibit weak performance when applied to infrared images for human pose estimation. In order to overcome the inherent shortcomings of infrared images and improve the accuracy of human pose estimation in this domain, we propose a novel model called FEPose. Our model incorporates the Transformer Encoder architecture to establish correlation dependencies in the infrared image space, enhancing the network's ability to sense spatial distance and mitigating the impact of low hierarchy on detection accuracy. Additionally, we introduce a specially-designed FELayer layer for infrared images, which enhances the network's response to human grayscale values while reducing the impact of background interference factors. To evaluate the effectiveness of our model, we conduct experiments on a self-built IR multi-person pose estimation dataset comprising 7621 training instances and 1082 test instances. Our most complex model achieves a PCKm of 77.5, while the simplified model achieves 75.1 PCKm.

Human keypoints detection require the capture of long-range spatial constraints and the fusion of channels information. Many studies adopt attention mechanisms to generate feature weights, thereby enhancing the information interaction capability and improving the accuracy of keypoints detection. However, most attention mechanisms currently in use redun-dantly fuse information across all channel levels, which not only increases the computational cost of the network but also weakens the feature differences between different keypoints, affecting the prediction of heatmaps. In this study, we propose a plug-and play attention module based on separate convolution, called DWA module, which avoids the redundant use of information from different channels and improves the network's ability to capture long-range spatial relationships. Additionally, we adopt a novel feature compression method to reduce errors in single-dimensional compression. Experimental results indicate that our DWA model performs well on COCO and MPII datasets, achieving good accuracy improvements with relatively small computational costs

Lutan-l (LT-1) is the first Chinese SAR satellite constellation that provide continuous deformation images covering the whole China. Three deformation products are designed to conduct the geohazard monitoring tasks. The first is DInSAR deformation field product which can be used for general geohazards investigation. The second is stacking deformation velocity field that can be used for geohazards screening. The third is deformation time-series obtained from multi-temporal InSAR and is specially designed for the continuous deformation regions to discover the deformation rules in temporal domain. In this paper, the LT-1 key features for deformation monitoring are provided. Product examples are shown with the Setninel-1A SAR images covering Datong City, Shanxi province. The three deformation products are expected to be used for geohazard monitoring in China.

OpenStreetMap (OSM) is a collaborative good quality crowd-sourced geospatial database (GDB). The quality of OSM is generally very good, it lacks good coverage in many parts of the world. A natural approach for extending its coverage is to conflate missing spatial features from other GDBs into OSM, but this is laborious and time-consuming. We propose a system MAYUR solving road network conflation between two vector GDBs, representing the GDBs as a graph of road intersections (vertices) and road segments (edges). MAYUR is based on a novel map matching framework that adapts the classic Rank Join in databases, where each edge of the reference GDB is modeled as a relation. Our algorithm finds the best matching between a reference and target GDB, respecting the connectivity of the road network. While classic Rank Join in databases gets quickly inefficient on instances with more than 10 relations, MAYUR's enhanced Rank Join incorporates three optimizations that boost the algorithm's efficiency, making it scale to our problem setting featuring hundreds to thousands of relations. Our manual evaluation of MAYUR conflation results on sidewalks in OSM and Boston Open Data shows an impressive 98.65% precision and 99.55% recall.

Within the cloud computing scenario, each server usually carries multiple service processes, which intensifies the concurrency pressure of the system. As a result, the process of memory management during page allocation and deallocation becomes a significant bottleneck. Although several methods such as Buddy System and Inverse Buddy System (iBuddy) have been proposed to improve the performance of memory management, they cannot adapt to the highly concurrent environment of cloud computing, because they either force the memory allocation/deallocation requests to be serialized or bring extra fragmentation. To address the above problem, we propose Spring Buddy, which improves the concurrency of both memory allocation and deallocation and avoids unnecessary fragmentation. It can detect the changes of system- and process-level memory request patterns and dynamically adjust the organization of page frames. Inventively, Spring Buddy uses the spring core layer to provide both concurrent response and resource aggregation capability which is adapted to the system's concurrency pressure, and also uses the spring lazy layer to further mitigate the system resource contention through process behavior prediction. To demonstrate the effectiveness of Spring Buddy, we implement it in the Linux kernel. The results demonstrate that Spring Buddy can reduce memory allocation latency by 71.47 % and deallocation latency by 93.20% on average compared to the existing methods.

Demand for enterprise data warehouse solutions to support real-time Online Transaction Processing (OLTP) queries as well as long-running Online Analytical Processing (OLAP) workloads is growing. Greenplum database is traditionally known as an OLAP data warehouse system with limited ability to process OLTP workloads. In this paper, we augment Greenplum into a hybrid system to serve both OLTP and OLAP workloads. The challenge we address here is to achieve this goal while maintaining the ACID properties with minimal performance overhead. In this effort, we identify the engineering and performance bottlenecks such as the under-performing restrictive locking and the two-phase commit protocol. Next we solve the resource contention issues between transactional and analytical queries. We propose a global deadlock detector to increase the concurrency of query processing. When transactions that update data are guaranteed to reside on exactly one segment we introduce one-phase commit to speed up query processing. Our resource group model introduces the capability to separate OLAP and OLTP workloads into more suitable query processing mode. Our experimental evaluation on the TPC-B and CH-benCHmark benchmarks demonstrates the effectiveness of our approach in boosting the OLTP performance without sacrificing the OLAP performance.

An AIEM based soil moisture retrieval strategy for bare agricultural area was developed in this study. In order to solve the ill-posed problem for soil moisture retrieval, multi-sensor SAR observations were integrated to estimate soil moisture based on the AIEM simulation. Soil surface parameters were derived using the least square method. The influence of surface roughness for soil moisture estimation was removed. Based on the in situ measurement and multi-sensor SAR images acquired on October 2015 over agricultural area, quantitative evaluation of the developed method was implemented. The results indicate that accurate soil moisture was obtained over the study area. The root mean square error of the estimated result is less than 0.05 cm3/cm3.

The automatic extraction of small objects such as roadside milestones, small traffic signs, and other urban furniture remains a technical challenge. This study focuses on methods of deep learning to detect small urban elements in mobile mapping system (MMS) images. Based on images obtained by an MMS in urban areas, we create an urban element detection (UED) data set containing several kinds of small objects found in a city. A simple feature extraction convolution neural network (CNN) called SlimNet is proposed and combined with an optimized faster R-CNN framework. The resulting deep learning method can automatically extract small objects commonly found in cities, including manhole covers, milestones, and license plates. Experiments on the UED data set show that SlimNet has the highest accuracy compared with other popular networks, including VGG, MobileNet, ResNet, and YOLOv3. The SlimNet model can achieve a mean average precision (AP) that is up to 12.3% higher than that of the lowest ResNet-152 network and can accelerate both training and detection owing to its relative simplicity. Moreover,$k$-means clustering is used to choose the dimensions of the anchor box for detection. We ran$k$-means clustering for different numbers of clusters, and the results show that at least four clusters are needed for detection using a small data set such as the UED. We also propose a method to use templates of different scales for anchors to further improve small object detection; this approach improved the AP by 3%–4% in our experiments.

Gaofen-3 (GF-3) is the only in-orbit civilian SAR satellite of China. The satellite is specially designed for ocean observation. The coherence is not exclusively considered during satellite designing phase. In this paper, we conduct the preliminary coherence assessment of GF-3 SAR data. Decoherence sources of GF-3 consists of seven components. Baseline decoherence, signal-to-noise decoherence as well as the volume decoherence affects the coherence severely. While the last four components, i.e., volume decoherence, ambiguity decoherence, Doppler spectral decoherence and processing decoherence contributes to the coherence values slightly. We select 13 pairs of GF-3 SAR data and analyze the coherence. Results of the selected data show that the coherence values after multi-looking, flattening, elevation phase removal and filtering exceed 0.4 even at the dessert regions, making it potential in InSAR related applications such as DEM generation and deformation monitoring.

Investigating the characteristics of dynamic changes of land use in the water source area of South-to-North Water Transfer Project (SNWTP) is of great significance to ameliorate the environmental quality to guarantee adequate, high quality water diverted into Beijing and Tianjin. The spatial and temporal characteristics of land use in the water source core area of middle route of South-to-North Water Transfer Project from 2009 to 2015 were analyzed by RS and GIS technologies based on national geoinformation survey data and basic surveying and mapping data, the results as follow: (1) the land was mainly covered with forest, which was accounting for about 80% of the total area. The area of cropland was reduced obviously, contrarily, the area of grassland increased prominently during the period from 2009 to 2015. The total coverage of wood and grass land rose lightly. (2) the land use transforming mainly occurred among cropland, woodland and grassland. Cropland was mainly changed to woodland and grassland, distributed in the altitude below 1000m and the slope above 15°. (3) the ecological engineering construction and reservoir resettlement policy had provided an effective backdrop for above changes. 53.47% of slope cropland was changed to woodland and grassland. However, there was still a considerable area of woodland, grassland transformation into slope cropland. The government should strengthen the protection of ecological environment, especially in the altitude bellow 1000m and the slope between 15° to 25°, in order to reduce the man-made environment destruction to the water supplying area.

We generated DSM of all China using over 37 thousand stereo and tri-stereo ZY3 images. The original RPCs were modified though bundle adjustment oriented by SRTM. DSMs were generated through dense tri-stereo matching based on a tri-epipolar method. Modified Belief Propagation was used as global method which was more robust than standard SGM. All original DSMs were multi degree overlapping. For every 0.0001 degree horizontal grid geographic coordinate, a middle height was calculated from all DSMs containing this coordinate. All other heights whose distance from this middle height bigger than a threshold were discarded and the rest heights were averaged as result. Over 330 thousand check points were used to estimate the height accuracy of all DSMs. The RMSE is about 4 meters.

Block adjustment can improve the accuracy of airborne InSAR data which covers large areas under the conditions of sparse control points, and it can improve the planar and vertical accuracy using a few of gound control points (GCPs). In this paper, we research the orthogonal decomposition of look vector model, three dimensional reconstruction model for airborne InSAR and the sensitivity equations at first. Secondly, we analyze the error sources and adjustment parameters for the Chinese airborne InSAR system of Chinese Academy of Surveying and Mapping SAR (CASMSAR). Finally, InSAR block adjustment method has been proposed for the airborne CASMSAR system, and the DEM is directly extracted. Experiments are carried out with X-band interferometric data acquired by CASMSAR system, and the effectiveness and practicability of the process method are verified. It can be seen from this article the results met the requirements of topographic mapping for the scale of 1∶10000 in China.

We introduce Cloud DIKW (Data, Information, Knowledge, Wisdom) as an analysis environment supporting scientific discovery through integrated parallel batch and streaming processing, and apply it to one representative domain application: social media data stream clustering. In this context, recent work demonstrated that high-quality clusters can be generated by representing the data points using high-dimensional vectors that reflect textual content and social network information. However, due to the high cost of similarity computation, sequential implementations of even single-pass algorithms cannot keep up with the speed of real-world streams. This paper presents our efforts in meeting the constraints of realtimesocial media stream clustering through parallelization in Cloud DIKW. Specifically, we focus on two system-level issues. Firstly, most stream processing engines such as Apache Storm organize distributed workers in the form of a directed acyclic graph (DAG), which makes it difficult to dynamically synchronize the state of parallel clustering workers. We tackle this challenge by creating a separate synchronization channel using a pub-sub messaging system (ActiveMQ in our case). Secondly, due to the sparsity of the high-dimensional vectors, the size of cancroids grows quickly as new data points are assigned tithe clusters. As a result, traditional synchronization that directly broadcasts cluster cancroids becomes too expensive and limits the scalability of the parallel algorithm. We address this problem by communicating only dynamic changes of the clusters rather than the whole centred vectors. Our algorithm under Cloud DIKWcan process the Twitter 10% data stream ("gardenhose") in realtimewith 96-way parallelism. By natural improvements to CloudDIKW, including advanced collective communication techniques developed in our Harp project, we will be able to process the full Twitter data stream in real-time with 1000-way parallelism. Our use of powerful general software subsystems will enable many other applications that need integration of streaming and batch data analytics.

Social media data analysis demonstrates two special characteristics in Big Data processing. First, most analyses focus on data subsets related to specific social events or activities instead of the whole dataset. Second, analysis workflows consist of multiple stages, and algorithms applied in each stage may use different computation and communication patterns depending on processing frameworks. This paper presents our efforts in supporting the data storage and processing requirements for such characteristics. To achieve efficient queries about target data subsets, we propose a general customizable and scalable indexing framework that can be built over distributed NoSQL databases. This framework allows users to define suitable customized index structures for their query patterns against social media data, and supports scalable indexing of both historical and streaming data. We implement this framework on HBase, and name it IndexedHBase. Starting from IndexedHBase, we build a distributed analysis stack based on YARN to support analysis algorithms using different processing frameworks, such as Hadoop MapReduce, Harp, and Giraph. This analysis stack is used to host the Truthy social media data observatory, and we have applied the customized index structures in supporting both query evaluation and sophisticated analysis algorithms. Performance tests show that our solutions outperform implementations using both direct raw data scans and current indexing mechanisms in existing NoSQL databases.

The development of cloud infrastructures has stimulated interest in virtualized block storage systems, exemplified by Amazon Elastic Block Store (EBS), Eucalyptus’ EBS implementation, and the Virtual Block Store (VBS) system. Compared with other solutions, VBS is designed for flexibility, and can be extended to support various Virtual Machine Managers and Cloud platforms. However, due to its single-volume-server architecture, VBS has the problem of single point of failure and low scalability. This paper presents our latest improvements to VBS for solving these problems, including a new distributed architecture based on the Lustre file system, new workflows, better reliability and scalability, and read-only volume sharing. We call this improved implementation VBS-Lustre. Preliminary tests show that VBS-Lustre can provide both better throughput and higher scalability in multiple attachment scenarios than VBS. VBS-Lustre could potentially be applied to solve some challenges for current cluster file systems, such as metadata management and small file access.

Abstract Traditional techniques in building science portals and gateways are being challenged by new techniques such as Web 2.0 and Cloud Computing. This paper discusses some of our efforts to evaluate these techniques as we evolve the QuakeSim architecture. We believe that architecturally both traditional and newer approaches for Gateways are very similar; thus, giving us a path for moving to hybrid approaches. In this paper, we specifically evaluate techniques for building interactive user interfaces that rely on remote services; architectural approaches for managing massive job submissions that can include both parallel and serial jobs; and an architectural prototype for building component‐based containers compatible with emerging standards. Copyright © 2009 John Wiley & Sons, Ltd.

The fast development of cloud computing systems stimulates the needs for a standalone block storage system to provide persistent block storage services to virtual machines maintained by clouds. This paper presents the Virtual Block Store (VBS) System, a standalone block storage system built on the basis of LVM, iSCSI, and Xen hypervisor, which can provide basic block storage services such as volume creation and attachment. The concept and functional interface of VBS are based on Amazon Elastic Block Store (EBS) service; moreover, VBS works independently with an existing LVM volume server and Xen nodes, and thus can be easily extended to support other types of volume servers and virtual machine managers, or integrated with various cloud computing systems. Preliminary I/O benchmark results are presented and analyzed, indicating that a VBS volume can provide throughput that is similar to an ATA over Ethernet virtual device.

Abstract Web 2.0 approaches are revolutionizing the Internet, blurring lines between developers and users and enabling collaboration and social networks that scale into the millions of users. As discussed in our previous work, the core technologies of Web 2.0 effectively define a comprehensive distributed computing environment that parallels many of the more complicated service‐oriented systems such as Web service and Grid service architectures. In this paper we build upon this previous work to discuss the applications of Web 2.0 approaches to four different scenarios: client‐side JavaScript libraries for building and composing Grid services; integrating server‐side portlets with ‘rich client’ AJAX tools and Web services for analyzing Global Positioning System data; building and analyzing folksonomies of scientific user communities through social bookmarking; and applying microformats and GeoRSS to problems in scientific metadata description and delivery. Copyright © 2009 John Wiley & Sons, Ltd.

We report on a unified on-the-fly, Web services-based observation/analysis/modeling environment for crustal deformation and natural hazards research, intended as a plug-in service for early warning systems, transfer of rapid information to civilian decision makers and the media, and educational purposes. We demonstrate an early warning system for a large earthquake in southern California using the components developed under several NASA-funded projects, including real-time GPS network infrastructure, Geophysical Resources Web Services, and GPS Explorer data portal with its on-the-fly earthquake modeling software. We generate an on-the-fly earthquake fault model based on simulated real-time (dynamic and coseismic) displacements computed by the GPS network, and viewable through GPS Explorer. Our objective is to demonstrate an operational service that could be transitioned to appropriate civilian agencies in southern California.