Grid Segmentation Research Articles

A heat grid-driven method for generation of satellite observation tasks

Managing numerous observation requirements on a large-scale satellite constellation is arduous for satellite control departments. Concurrently, achieving fast and effective task scheduling necessitates autonomous observation task generation. To address this issue, we proposed a novel method combined with Observation Requirements Heat Grid Model (ORHGM) and a Grid Aggregation Algorithm Based on Field of View Exploration (GAAFVE). Firstly, we define a uniform description of the observation requirements for various target types by devising a heat grid model predicated on geographic grid segmentation. Experimental outcomes reveal that our uniform model saves up to 31.93% of the observation tasks for fulfilling identical requirements by independent task generation for various target types. Secondly, based on this model, an autonomous task generation is completed by GAAFVE. Under the constraints regarding satellite imaging width, our algorithm facilitates heat grid search for non-connected regions and demonstrates superiority in computing time compared to other clustering-based task algorithms. The proposed method can allow managing large-scale observation requirements to be completed relatively quickly for satellite control departments. This method can also be extended to task generation in other multi-agent systems beyond satellites, such as the automatic generation of multi-UAV disaster reconnaissance tasks.

Progressive Optimal Fault-Tolerant Control Combining Active and Passive Control Manners

This study develops a progressive optimal fault-tolerant control method based on insufficient fault information. By combining passive and active fault-tolerant control manners during the process of fault diagnosis, insufficient fault information is fully used, and optimal fault-tolerant control effect is achieved. In addition, the fault-tolerant control method based on guaranteed robust cost control is introduced. The proposed progressive optimal fault-tolerant control method considers two aspects. First, as the amount of fault information continually increases, the performance index of the progressive optimal fault-tolerant controller improves. Second, at each moment, based on the corresponding insufficient fault information and prior knowledge, optimal fault-tolerant control is achieved according to current fault information. The process of progressive optimal fault-tolerant control converges to active fault-tolerant control when the fault is completely identified, and the optimal fault-tolerant controller is no longer reconfigured until no more useful fault information can be provided. Furthermore, a progressive optimal fault-tolerant control algorithm based on the grid segmentation in the parameter uncertainty domain and the selection of different auxiliary center points is introduced. Simulation results verified the feasibility of the proposed algorithm and the validity of the proposed theory.

A Comprehensive Review and New Taxonomy on Superpixel Segmentation

Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications, since it allows for reducing the workload, removing redundant information, and preserving regions with meaningful features. Due to the rapid progress in this area, the literature fails to catch up on more recent works among the compared ones and to categorize the methods according to all existing strategies. This work fills this gap by presenting a comprehensive review with a new taxonomy for superpixel segmentation, in which methods are classified according to their processing steps and processing levels of image features. We revisit the recent and popular literature according to our taxonomy and evaluate 23 strategies and a grid segmentation baseline based on nine criteria: connectivity, compactness, delineation, control over the number of superpixels, color homogeneity, robustness, running time, stability, and visual quality. Our experiments show the trends of each approach in superpixel segmentation and discuss individual trade-offs. Finally, we provide a new benchmark for superpixel assessment, available at https://github.com/IMScience-PPGINF-PucMinas/superpixel-benchmark .

A comparison of Eulerian and semi-Lagrangian approaches for modeling stream water quality

ABSTRACT This paper describes and compares some of the advantages and limitations of Eulerian and Lagrangian approaches to water quality modeling and introduces a mixed Eulerian-Lagrangian (or semi-Lagrangian) methodology that captures the strengths of both approaches. The semi-Lagrangian modeling approach is applied to advection-dominated rivers, and flexibly ensures unconditional stability for all time step durations and grid segmentations. The semi-Lagrangian modeling approach is demonstrated by applying it to estimate the dissolved oxygen concentrations in the Sava River in Slovenia, focusing on aspects of the methodology and findings that would be of broad interest to managers of water quality in fluvial water bodies. Results of comparisons of the semi-Lagrangian model with the Eulerian-based QUAL2K model in steady and non-steady scenarios demonstrate that while both models are fully capable of producing satisfactory results when optimally configured, the semi-Lagrangian approach offers accuracy and stability without sensitivity to the interaction of time step size and computational grid segmentation scheme.

The target selection and quantitative evaluation for deep geothermal resource zoning of typical geothermal fields in central Hebei of North China plain

With the rapid economic development in North China, the demand for geothermal energy is increasing. It is urgent to find favorable deep geothermal resource targets in North China. Although geothermal resources in the North China Plain are widely distributed, in order to develop deep geothermal resources in North China safely, stably and efficiently, it is essential to carry out the target selection and evaluation of geothermal resource zoning. This article takes the typical geothermal fields in the central Hebei region as the research object, and through the comprehensive collation of regional geothermal geological data, constructs an optimization evaluation indicator system for geothermal resource target areas from three aspects: resource conditions, mining potential, and heating demand. On this basis, it establishes a linear relationship between the attribute values and scores of each indicator, and uses the analytic hierarchy process to assign weights to each indicator and calculate the comprehensive weight. Then, the comprehensive evaluation value is obtained by weighted calculation of the scores and comprehensive weights of each block in the grid segmentation of the evaluation area. Finally, through the spatial analysis function of GIS, the comprehensive evaluation values of all blocks in the evaluation area were analyzed using kriging difference analysis, and a comprehensive evaluation map, the geothermal resource prospective target area map, was finally obtained. Using quantitative zoning evaluation methods, the target areas for exploration and development of deep geothermal resources in central Hebei Province have been delineated within a large region. The evaluation results indicate that the Cambrian-Ordovician reservoir target area is relatively large, and there are many favorable target areas with good reservoir conditions in the Middle-Upper Proterozoic. The excellent prospective target area of the Mesoproterozoic geothermal reservoir accounts for 56%, mainly located in the Xingji uplift and Gaoyang low uplift. Xiong’an New Area, Cangzhou, and the eastern part of Hengshui are excellent prospective target areas for the evaluation of the Mesoproterozoic geothermal reservoir in a single area. This evaluation method can provide a reference for the optimization of resource exploration and development target areas in key regions.

NAVIBox: Real-Time Vehicle–Pedestrian Risk Prediction System in an Edge Vision Environment

This study introduces a novel system, termed NAVIBox, designed to proactively identify vehicle–pedestrian risks using vision sensors deployed within edge computing devices in the field. NAVIBox consolidates all operational components into a single unit, resembling an intelligent CCTV system, and is built upon four core pipelines: motioned-video capture, object detection and tracking, trajectory refinement, and predictive risk recognition and warning decision. The operation begins with the capture of motioned video through a frame difference approach. Road users are subsequently detected, and their trajectories are determined using a deep learning-based lightweight object detection model, in conjunction with the Centroid tracker. In the trajectory refinement stage, the system converts the perspective of the original image into a top view and conducts grid segmentation to capture road users’ behaviors precisely. Lastly, vehicle–pedestrian risks are predicted by analyzing these extracted behaviors, and alert signals are promptly dispatched to drivers and pedestrians when risks are anticipated. The feasibility and practicality of the proposed system have been verified through implementation and testing in real-world test sites within Sejong City, South Korea. This systematic approach presents a comprehensive solution to proactively identify and address vehicle–pedestrian risks, enhancing safety and efficiency in urban environments.

Grid and homogeneity-based ground segmentation using light detection and ranging three-dimensional point cloud

Grid and homogeneity-based ground segmentation using light detection and ranging three-dimensional point cloud

Fast and Accurate Generation Method of Geometric Digital Twin Model of RC Bridge with Box Chambers Based on Terrestrial Laser Scanning

Digital Twin (DT) plays a crucial role in intelligent bridge management, and the geometric DT (gDT) serves as its foundation. Notably, the fast and high-precision generation of bridge gDT models has gained increasing attention. This research presents a method for generating high-precision and fast RC bridges with chambers for gDT using terrestrial laser scanning. The method begins with a proposed fast point cloud data collection technique designed specifically for bridges with internal chambers. Subsequently, Euclidean clustering and grid segmentation algorithms are developed to automatically extract contour features from the sliced point clouds. Finally, a framework based on the Dynamo–Revit reverse modelling method is introduced, enabling the automatic generation of gDT models from the identified point cloud features. To validate the feasibility and accuracy of the proposed method, a concrete variable section bridge is used. A comparison is made between the generated gDT model and the point cloud model in terms of 3D deviation, revealing a maximum deviation of 6.6 mm and an average deviation of 3 mm. These results affirm the feasibility of the proposed method.

Real-Time Interactive Parallel Visualization of Large-Scale Flow-Field Data

With the increasing demand for high precision in numerical simulations using computational fluid dynamics (CFD), the use of large-scale grids for discretized solutions has become a trend, resulting in an explosive growth of flow-field data size. To address the challenges posed by large-scale flow-field data for real-time interactive visualization, this paper proposes novel strategies for data partitioning and communication management. Firstly, we propose a data-partitioning strategy based on grid segmentation. This approach constructs metadata to create file viewports for each process and performs grid partitioning. Subsequently, it reconstructs sub-grids within each process and utilizes a coordinate-mapping algorithm to map global coordinates to local process coordinates, facilitating access to attribute variables through a lookup table. Secondly, we introduce a real-time interactive method for large-scale flow fields. This method leverages the system architecture of high-speed interconnection among compute nodes in a cluster environment and low-speed interconnection between service nodes and rendering nodes. It enables coordinated management of parallel rendering and synchronized rendering methods. The experimental results on typical flow-field data demonstrate that the proposed data-partitioning strategy improves the loading speed of millions of grid-level data by a factor of 7, surpassing ParaView’s performance by 1.5 times. Furthermore, it achieves system load balancing. Real-time interaction experiments with datasets containing 500 million and 800 million grid cells exhibit millisecond-level latencies, demonstrating the effectiveness of the proposed communication management method in meeting the real-time interactive visualization demands of large-scale flow-field data.

Spatiotemporal Evolution and Risk Analysis of Land Use in the Coastal Zone of the Yangtze River Delta Region of China

The extensive accumulation of big data, along with the development of a high-performance platform, bridge the gap between the previous inability to provide long-term time series and broad-scale coastal zone monitoring and risk warnings with remote sensing techniques. Based on 20 years of Landsat images from the Google Earth Engine platform, the time series land cover in the coastal zone of the Yangtze River Delta in China was classified. Then, a spatiotemporal clustering method based on grid segmentation was proposed to analyze the spatiotemporal evolution details of artificial surface expansion and the risks of cropland loss and ecological degradation caused by this. The results showed that significant changes have taken place in the quantitative structure and spatial morphology of coastal land use in the past 20 years. The artificial surface maintained a growth trend, increasing by 229%, while cropland decreased by 19%. Natural land showed a fluctuation pattern of “up→down→up”. The spatiotemporal details of land use obtained through 1km grid segmentation and clustering analysis were more significant. The artificial surface mainly underwent a progressive spatial expansion along the central urban area and important transportation axes (types III and IV), with the most dramatic changes occurring from 2010 to 2013. Type III cropland loss was the most significant, falling from 75.02% in 2000 to 38.23% in 2020. At the same time, the change in type III water body corresponds to the newly increased area of reclamation, which has decreased by 17% in the past 20 years, indicating that the degradation of coastal natural wetlands was significant. This paper provided a comprehensive diagnosis of coastal land use change, which could help policy makers and implementers to propose more targeted and differentiated coastal development and protection policies.

A comparative analysis of grid-based and object-based modeling approaches for poplar forest growing stock volume estimation in plain regions using airborne LIDAR data

ABSTRACT Poplar (PopulusL.) is one of the most widely distributed tree species planted in the plains of China and plays an important role in wood products and ecological services. Accurate estimation of poplar Growing Stock Volume (GSV) is crucial for better understanding the ecological functions and economic values in plain regions. However, the striped distribution feature of poplar forests in plain regions makes traditional grid-based GSV modeling methods highly uncertain. This research took Lixin County and Yongqiao District as case studies to examine the advantages of using object-based GSV modeling approach over the traditional grid-based approaches for poplar GSV estimation. The canopy height variables and density variables were extracted from airborne LIDAR-derived Canopy Height Model (CHM) data through different grid sizes and segmentation unit for constructing the poplar GSV estimation models using the linear regression. The results indicate that (1) Significantly linear relationships exist between GSV and height percentile variables; (2) The estimation accuracy in Lixin can be effectively improved by incorporating the CHM density variables into height variables, with the coefficient of determination (R 2 ) increasing from 0.46 to 0.71 and Root Mean Square Error (RMSE) decreasing from 20.23 to 14.94 m3/ha when a grid-based approach was implemented at grid size of 26 m by 26 m (plot size). However, CHM density variables have no effect on estimation modeling in Yongqiao district. The patch sizes and shapes considerably affect the selection of modeling variables and accuracy of modeling prediction; (3) The object-based mapping approach outperforms the grid-based approach in solving the mixed plot problem. This is especially valuable in the study areas with striped forest distribution. This study shows that differences in poplar stand structure affect the selection of modeling variables and GSV modeling performance, and an object-based modeling approach is recommended for GSV estimation in the plain areas.

LED Chip Defect Detection Method Based on a Hybrid Algorithm

LED is an extremely important energy-saving lighting products, which has greatly facilitated human life. Meanwhile, it also makes a positive contribution to global carbon neutrality and carbon peaking. Defect detection is a vital part of the production process to control the quality of LED chips. The traditional methods use a microscope for manual visual inspection, which is time-consuming and has inconsistent testing standards, low efficiency, and other deficiencies. To solve these problems, a hybrid algorithm based on geometric computation and a convolutional neural network is proposed for LED chip defect detection. The method takes advantage of the dimensionality reduction of geometric computation to perform coarse detection of defects on preprocessed chip lithography graphs in the form of grid segmentation, which realizes fast coarse screening of large-scale chip samples and reduces postcomputational costs. The convolutional neural network model is used for the secondary fine detection of “suspected defective” chips after geometric coarse screening, and the SPP (spatial pyramid pooling) network model is improved by directly introducing the original feature map into the SPP pooling layer for summation to enhance the global and local feature information of the output feature map. Furthermore, we construct an LED chip image acquisition platform using a high-frequency multimagnification zoom lens, collect training samples of defective chips, and increase the number of samples through image processing techniques. The research introduces the R-CNN, SDD, and YOLO methods to evaluate the superiority of our method in a number of experiments. The experimental results show that our algorithm proposed in this paper has an average precision (AP) of 96.7% for large-scale chip detection with a low defect rate. Compared with other methods, the testing mean average precision (mAP) is 10.39% higher than traditional YOLO v2. The testing mIoU is also 3.63% higher than traditional YOLO v5, the detection speed is also significantly improved, and it has good robustness.

A Pareto Front grid guided multi-objective evolutionary algorithm

For multi-objective optimization problems with irregular Pareto Fronts, most widely used decomposition methods in MOEA/D (multi-objective evolutionary algorithms based on decomposition) have shown to be lack of the ability to balance the diversity and the convergence to track the true Pareto Fronts during the search. This research investigates the recently proposed grid-based decomposition methods, which reflect the inherent characteristics of the neighborhood structure in the solution to address the issues of diversity and convergence. The performance of the grid-based decomposition method, however, depends on the size of its grid segmentation, and its time complexity increases with the number of grids. In order to improve the computational efficiency, we propose a new concept of Pareto Front grid to guide the search in MOEA. In order to reduce the computing time, a new nadir point estimation strategy based on statistical analysis has been proposed to estimate the whole population. In addition, based on the idea of knee point, a novel grid-based knee point selection method is proposed in the environmental selection of the next generation. Finally, a grid-based decomposition multi-objective evolutionary algorithm with Pareto Front Grid (PFG-MOEA) is proposed. Extensive experimental analysis demonstrates the effectiveness of the proposed PFG-MOEA against state-of-the-art multi-objective evolution algorithms. As the extension of the CDG-MOEA (Constrained Decomposition approach with Grids MOEA) algorithm in the literature, PFG-MOEA can obtain better performance by consuming much less computing time.

DGFlow-SLAM: A Novel Dynamic Environment RGB-D SLAM without Prior Semantic Knowledge Based on Grid Segmentation of Scene Flow.

Currently, using semantic segmentation networks to distinguish dynamic and static key points has become a mainstream designing method for semantic SLAM systems. However, the semantic SLAM systems must have prior semantic knowledge of relevant dynamic objects, and their processing speed is inversely proportional to the recognition accuracy. To simultaneously enhance the speed and accuracy for recognizing dynamic objects in different environments, a novel SLAM system without prior semantics called DGFlow-SLAM is proposed in this paper. A novel grid segmentation method is used in the system to segment the scene flow, and then an adaptive threshold method is used to roughly detect the dynamic objects. Based on this, a deep mean clustering segmentation method is applied to find potential dynamic targets. Finally, the results of grid segmentation and depth mean clustering segmentation are jointly used to find moving objects accurately, and all the feature points of the moving objects are removed on the premise of retaining the static part of the moving object. The experimental results show that on the dynamic sequence dataset of TUM RGB-D, compared with the DynaSLAM system with the highest accuracy for detecting moderate and violent motion and the DS-SLAM with the highest accuracy for detecting slight motion, DGflow-SLAM obtains similar accuracy results and improves the accuracy by 7.5%. In addition, DGflow-SLAM is 10 times and 1.27 times faster than DynaSLAM and DS-SLAM, respectively.

A Pseudolite Indoor Wide-Area Networking Technology Based on Signal Multilevel Features

At present, pseudosatellite navigation and positioning technology is the only positioning technology compatible with GNSS navigation signals and applied to indoors. This technology can realize continuous indoor and outdoor positioning services for mobile terminals and dedicated terminals. At the same time, the indoor application of pseudolite technology also faces some problems. Aiming at the large-area networking problem of pseudolites in indoor space, this paper uses the existing indoor array pseudolite technology to propose a technique for constructing a network using the characteristics of pseudolite signals in indoor space. By making full use of the signal’s multiple access classification characteristics and the signal’s Doppler, interstation delay, and other characteristics, a multilevel grid segmentation and networking scheme for indoor space based on pseudolites is realized. This method combines the existing experimental foundation and experience accumulation, has the feasibility of realizing large-area networking indoors, can solve the problems faced in the current indoor pseudolite networking process, and provides guarantee for the application of pseudolite networking in indoor environments.

Smart Waste Management and Classification Systems Using Cutting Edge Approach

With a rapid increase in population, many problems arise in relation to waste dumps. These emits hazardous gases, which have negative effects on human health. The main issue is the domestic solid waste collection, management, and classification. According to studies, in America, nearly 75% of waste can be recycled, but there is a lack of a proper real-time waste-segregating mechanism, due to which only 30% of waste is being recycled at present. To maintain a clean and green environment, we need a smart waste management and classification system. To tackle the above-highlighted issue, we propose a real-time smart waste management and classification mechanism using a cutting-edge approach (SWMACM-CA). It uses the Internet of Things (IoT), deep learning (DL), and cutting-edge techniques to classify and segregate waste items in a dump area. Moreover, we propose a waste grid segmentation mechanism, which maps the pile at the waste yard into grid-like segments. A camera captures the waste yard image and sends it to an edge node to create a waste grid. The grid cell image segments act as a test image for trained deep learning, which can make a particular waste item prediction. The deep-learning algorithm used for this specific project is Visual Geometry Group with 16 layers (VGG16). The model is trained on a cloud server deployed at the edge node to minimize overall latency. By adopting hybrid and decentralized computing models, we can reduce the delay factor and efficiently use computational resources. The overall accuracy of the trained algorithm is over 90%, which is quite effective. Therefore, our proposed (SWMACM-CA) system provides more accurate results than existing state-of-the-art solutions, which is the core objective of this work.

Location and Extraction of Telegraph Poles from Image Matching-Based Point Clouds

The monitoring of telegraph poles as essential features supporting overhead distribution network lines is the primary subject of this work. This paper proposes a method for locating and extracting telegraph poles from an image matching-based point cloud. Firstly, the point cloud of the poles is extracted using the planar grid segmentation clustering algorithm and the connected component analysis algorithm of the region grows according to the isolated features of the poles perpendicular to the ground. Secondly, the candidate telegraph poles are located based on the suspension point of the buffer, considering that the top of the pole is connected to the power suspension line. Thirdly, the horizontal projection method of the backbone area is utilized to eliminate the interference of vegetation in the buffer area. Finally, the point cloud of the telegraph pole is extracted through the density-based spatial clustering of applications with noise (DBSCAN) algorithm. The experimental results demonstrate that the average values of Recall, Precision, and F1-score in telegraph pole detection can reach 91.09%, 90.82%, and 90.90%, respectively. The average RMSE value of location deviation is 0.51m. The average value of the F1-score in the telegraph pole extraction is 91.83%, and the average extraction time of a single pole is 0.27s. Accordingly, this method has strong adaptability to areas with lush vegetation and can automatically locate and extract the telegraph pole point cloud with high accuracy, and it can still achieve very high accuracy even under the holes in the data.

A Semi-Supervised Transfer Learning with Grid Segmentation for Outdoor Localization over LoRaWans.

During the training phase of the supervised learning, it is not feasible to collect all the datasets of labelled data in an outdoor environment for the localization problem. The semi-supervised transfer learning is consequently used to pre-train a small number of labelled data from the source domain to generate a kernel knowledge for the target domain. The kernel knowledge is transferred to a target domain to transfer some unlabelled data into the virtual labelled data. In this paper, we have proposed a new outdoor localization scheme using a semi-supervised transfer learning for LoRaWANs. In the proposed localization algorithm, a grid segmentation concept is proposed so as to generate a number of virtual labelled data through learning by constructing the relationship of labelled and unlabelled data. The labelled-unlabelled data relationship is repeatedly fine-tuned by correctly adding some more virtual labelled data. Basically, the more the virtual labelled data are added, the higher the location accuracy will be obtained. In the real implementation, three types of signal features, RSSI, SNR, and timestamps, are used for training to improve the location accuracy. The experimental results illustrate that the proposed scheme can improve the location accuracy and reduce the localization error as opposed to the existing outdoor localization schemes.

Study on SDE Distribution of Forest Vegetation in China Based on Trapezoidal Grid Segmentation

The trapezoidal grid segmentation of China was carried out at a scale of 1:10000 to form a grid system covering the Chinese mainland. Based on the standard deviation ellipse (SDE) distribution theory, seven major categories and 53 sub-categories of Chinese forest vegetation were studied respectively. The SDE distribution was obtained and the average area distribution rate of 51.75% major-category vegetation was also obtained. Broad-leaved forests and sparse forests accounted for the largest proportion in China, with a proportion of 68.11%, the deviation rate of the average was 31.61%, and the dispersion was 0.097; the average distribution rate of sub-category vegetation was 9.38%, and the temperate subalpine evergreen coniferous forests accounted for the largest proportion in China, with a distribution rate of 30.23% and a dispersion of 0.032. The spatial distribution pattern of vegetation is mostly "southwest-northeast", but the elliptical center of the major-category vegetation moves more; while in terms of the direction of sub-category vegetation, there were nine categories of vegetation with three long-axis azimuths [<45 degrees], 27 categories of vegetation with long-axis azimuth [>45°∪≤90°], and 27 categories of vegetation with long-axis azimuth [> 90°].

Big Earth Observation Data Integration in Remote Sensing Based on a Distributed Spatial Framework

The arrival of the era of big data for Earth observation (EO) indicates that traditional data management models have been unable to meet the needs of remote sensing data in big data environments. With the launch of the first remote sensing satellite, the volume of remote sensing data has also been increasing, and traditional data storage methods have been unable to ensure the efficient management of large amounts of remote sensing data. Therefore, a professional remote sensing big data integration method is sorely needed. In recent years, the emergence of some new technical methods has provided effective solutions for multi-source remote sensing data integration. This paper proposes a multi-source remote sensing data integration framework based on a distributed management model. In this framework, the multi-source remote sensing data are partitioned by the proposed spatial segmentation indexing (SSI) model through spatial grid segmentation. The designed complete information description system, based on International Organization for Standardization (ISO) 19115, can explain multi-source remote sensing data in detail. Then, the distributed storage method of data based on MongoDB is used to store multi-source remote sensing data. The distributed storage method is physically based on the sharding mechanism of the MongoDB database, and it can provide advantages for the security and performance of the preservation of remote sensing data. Finally, several experiments have been designed to test the performance of this framework in integrating multi-source remote sensing data. The results show that the storage and retrieval performance of the distributed remote sensing data integration framework proposed in this paper is superior. At the same time, the grid level of the SSI model proposed in this paper also has an important impact on the storage efficiency of remote sensing data. Therefore, the remote storage data integration framework, based on distributed storage, can provide new technical support and development prospects for big EO data.