Matching Accuracy Research Articles

Multi-scale transformer network for super-resolution of visible and thermal air images

Reference image-based Super-Resolution (RefSR) is introduced to improve the quality of a Low-resolution (LR) input image by leveraging the additional information provided by a High-Resolution (HR) reference image (Ref). While existing RefSR methods focus on thermal or visible flows separately, they often struggle to enhance the resolution of small objects such as Mini/Micro UAVs (Unmanned Aerial Vehicle) due to the resolution disparities between the input and reference images. To cope with these challenges when dealing with UAV early detection in context of video surveillance, we propose ThermoVisSR, a multiscale texture transformer for enhancing the Super-Resolution (SR) of visible and thermal images of Mini/Micro UAVs. Our approach tries to reconstruct the fine details of these objects while preserving their approximation (the body form and color of the different scene objects) already contained in the LR image. Hence, our model is divided up into two streams dealing separately with approximation and detail reconstruction. In the first one, we introduce a Convolution Neural Network (CNN) fusion backbone to extract the Low-Frequency (LF) approximation from the original LR image pairs. In the second one and to extract the details from the Ref image, our approach involves blending features from both visible and thermal sources to make the most of what each offer. Subsequently, we introduce the High-Frequency Texture Transformer (HFTT) across various resolutions of the merged features to ensure an accurate correspondence matching and significant transfer of High-Frequency (HF) patches from Ref to LR images. Moreover, to adapt the injection to the different bands well, we incorporate the separable software decoder (SSD) into the HFTT allowing to capture channel-specific details during the reconstruction phase. We validated our approach using a newly created dataset of Air images of Mini/Micro UAVs. Experimental results demonstrate that the proposed model consistently outperforms the state-of-the-art approaches on both qualitative and quantitative assessments.

VLR-BPP: An intelligent virtual location replacement based bilateral privacy-preserving architecture for edge cloud systems

Mobile Crowdsourcing (MCS) has emerged as a significant edge-cloud computing paradigm in which workers perceive data at the network edge and report it to cloud-based computing services for processing, enabling the construction of various applications. Consequently, it is imperative to achieve Bilateral Location Privacy-Preserving (BLPP) to protect the privacy of both Data Requester (DR) and workers, as disclosing location information entails many sensitive details that can result in losses for DR and workers alike. The Local Differential Privacy (LDP) approach is widely employed in Privacy-Preserving (PP) techniques due to its inherent advantages, wherein owners release data with added noise, allowing for proactive customization of privacy strength without relying on any third party. However, the current state of LDP methods presents a dilemma: when privacy protection is strong, introducing excessive location noise can lead to a decrease in the accuracy of task-worker matching, while a high rate of task-worker matching necessitates the compromise of privacy strength. In this paper, an intelligent Virtual Location Replacement based enhanced Bilateral Privacy-Preserving (VLR-BPP) architecture is proposed to improve privacy protection strength and matching accuracy in MCS simultaneously. Within the VLR-BPP architecture, a Bipartite-Graph-based Matrix Completion (BGMC) model is employed to establish the spatiotemporal correlations among data. Then, a Virtual Location Replacement (VLR) strategy is proposed to obfuscate the locations of tasks or workers to their highly correlated virtual location before publishing. Based on VLR, three preemptive location virtualization approaches are introduced: Only Task Location Virtual (OTLV), Only Workers Location Virtual (OWLV), and Both Task and Workers Location Virtual (BTWLV). For workers and DR, Randomized Response (RR) techniques and Random Matrix Multiplication Mechanism (RMM) are used to implement LDP independently. A greedy algorithm is adopted to recruit workers for tasks. In response to the data submitted by workers, BGMC imputation mechanism is utilized to enhance data quality. Finally, simulations based on real-world datasets demonstrate that the performance of our architecture surpasses existing state-of-the-art methods in privacy protection and data collection quality by 18.92∼38.17% and 15.49∼50.77%, respectively.

Study on Nonlinear Parameter Inversion and Numerical Simulation in Condensate Reservoirs

The B6 metamorphic buried hill condensate gas reservoir exhibits a highly compact matrix, leading to a rapid decline in bottom-hole pressure during initial production. The minimal difference between formation and saturation pressures results in severe retrograde condensation, with multiphase flow further increasing resistance. Conventional numerical simulations often overestimate reservoir energy supply due to their failure to account for this additional resistance, leading to inaccuracies in bottom-hole pressure predictions and gas–oil ratio during history matching. To address these challenges, this study conducted research on nonlinear numerical simulation for buried hill condensate gas reservoirs and established a method for calculating a multiphase pressure sweep range based on the well testing theory. By correcting and fitting the pressure propagation boundaries with numerical simulation, the nonlinear flow parameters applicable to the B6 gas field were inversed. This study revealed that conventional Darcy flow is inadequate for predicting pressure propagation boundaries and that it is possible to reasonably characterize the pressure sweep range through nonlinear flow. This approach resulted in an improvement in the accuracy of historical matching for bottom-hole pressure and gas–oil ratio, which improve the historical fitting accuracy to 85%, providing valuable insights for the development of similar reservoirs.

CorMatcher: A corners-guided graph neural network for local feature matching

Local feature matching is crucial for various computer vision tasks like Structure from Motion (SfM) and visual localization. In human visual matching, individuals typically scan image pairs to detect and match prominent corners, then refine matches by leveraging the geometric structure information from these corners. Inspired by this observation, we propose CorMatcher, a corners-guided detector-free network that investigates the guiding role of prominent corners in local feature matching. The concept of CorMatcher is utilizing the corners-images interaction module (CIIM) and deep supervision technique (DST) to replicate the aforementioned human behaviors, thus generating more human-intuitive features for accurate feature matching. CIIM imitates human behavior that first observes corners to guide the matching process, and then extend the matching space from corners to entire images. Technically, In particular, CIIM first integrates global information across all keypoints to ensure overall perception. Then, CIIM extracts reliable corners, performs feature enhancement among them, and propagates the enhanced features of corners to entire images. Finally, CIIM interacts features of all keypoints to ensure that the global information is comprehensively considered to establish final matches. In addition, we apply DST to the corners, rather than all keypoints, to supervise matching results after each feature enhancement process, thus simulating the human behavior that appraises matching results after each observation. Comprehensive experiments demonstrate that CorMatcher exhibits superior performance compared to several benchmarks.

Ontology Merging Using the Weak Unification of Concepts

Knowledge representation and manipulation in knowledge-based systems typically rely on ontologies. The aim of this work is to provide a novel weak unification-based method and an automatic tool for OWL ontology merging to ensure well-coordinated task completion in the context of collaborative agents. We employ a technique based on integrating string and semantic matching with the additional consideration of structural heterogeneity of concepts. The tool is implemented in Prolog and makes use of its inherent unification mechanism. Experiments were run on an OAEI data set with a matching accuracy of 60% across 42 tests. Additionally, we ran the tool on several ontologies from the domain of robotics. producing a small, but generally accurate, set of matched concepts. These results clearly show a good capability of the method and the tool to match semantically similar concepts. The results also highlight the challenges related to the evaluation of ontology-merging algorithms without a definite ground truth.

The surface tension of Martini 3 water mixtures.

The Martini model, a coarse-grained forcefield for biomolecular simulations, has experienced a vast increase in popularity in the past decade. Its building-block approach balances computational efficiency with high chemical specificity, enabling the simulation of organic and inorganic molecules. The modeling of coarse-grained beads as Lennard-Jones particles poses challenges for the accurate reproduction of liquid-vapor interfacial properties, which are crucial in various applications, especially in the case of water. The latest version of the forcefield introduces refined interaction parameters for water beads, tackling the well-known artifact of Martini water freezing at room temperature. In addition, multiple sizes of water beads are available for simulating the solvation of small cavities, including the smallest pockets of proteins. This work focuses on studying the interfacial properties of Martini water, including surface tension and surface thickness. Employing the test-area method, we systematically compute the liquid-vapor surface tension across various combinations of water bead sizes and for temperatures from 300 to 350K. These findings are of interest to the Martini community as they allow users to account for the low interfacial tension of Martini water by properly adjusting observables computed via coarse-grained simulations to allow for accurate matching against all-atom or experimental results. Surface tension data are also interpreted in terms of local enrichment of the various mixture components at the liquid-vapor interface by means of Gibbs' adsorption formalism. Finally, the critical scaling of the Martini surface tension with temperature is reported to be consistent with the critical exponent of the 3D Ising universality class.

FELC-SLAM: feature extraction and loop closure optimized lidar SLAM system

Abstract Simultaneous Localization and Mapping (SLAM) is one of the key technologies in robot navigation and autonomous driving, playing an important role in robot navigation. Due to the sparsity of LiDAR data and the singularity of point cloud features, accuracy loss of LiDAR SLAM can occur during point cloud matching and localization. In response to these issues, this paper proposes a LiDAR Measurement SLAM algorithm that integrates multi type geometric feature extraction and optimized point cloud registration algorithms. This article first adopts advanced ground segmentation methods and feature segmentation strategies, including ground features, edge features, planar features, and spherical features, to improve matching accuracy. In addition, this article improves the previous method for extracting edge and planar features, extracting clearer and more robust line and surface features to address the degradation of geometric features. Finally, by introducing a robust decoupling global registration method for loop closure detection in the backend of the system, the sparsity problem of distant point clouds and the degradation problem caused by the reduction of inner layers in point cloud registration were effectively solved. In the evaluation of the KITTI dataset, our algorithm reduced absolute trajectory error values by 60%, 29%, and 71% compared to LeGO-LOAM in multi loop and feature constrained scenarios (such as sequences 00, 01, and 02), respectively. The evaluation of the M2DGR and Botanic Garden datasets also indicates that the positioning accuracy of our algorithm is superior to other advanced LiDAR SLAM algorithms.

Characteristic reflection wavefield-based wave equation traveltime inversion

Introducing a high-precision deep-depth velocity model is essential for accurately imaging seismic data in complex areas such as deepwater and deep depth in oil and gas exploration. Conventional methods, such as reflection full-waveform inversion (RFWI), face challenges, notably the cycle-skipping issue, especially when the initial velocity model is far away from the true model. To address this, we develop a novel wave equation traveltime inversion (WETI) using the characteristic reflection wavefield (CRW) to update the low-wavenumber components of the velocity model. The CRWs are primary reflections in seismic data that contribute significantly to velocity model updates. We implement a multistep approach, including migration, characteristic reflector structure (CRS) picking, and demigration to extract the CRW. This extraction, constrained by CRS, ensures accurate matching between the observed and the simulated CRWs, even with an inaccurate initial velocity model, thus enabling an accurate traveltime shift estimation during inversion. Unlike conventional methods that use all reflection data simultaneously, CRW-WETI strategically selects fewer CRWs, enhancing inversion convexity and avoiding local minima from the cycle-skipping problem. This selective inversion begins with a limited number of CRWs to ensure stability and progressively incorporates more as the WETI process advances, eventually transitioning into conventional RFWI. Moreover, with the CRS constraint, CRW can be selected based on the target region. The target-oriented velocity inversion can also be implemented easily to update a local anomalous velocity model. Numerical examples of synthetic and field data demonstrate the effectiveness and validity of our method.

Image reconstruction and bladder stimulation using electrical impedance tomography

Impedance tomography (EIT) is an imaging technique that harnesses differences in electrical conductivity to visualize the interior of objects. Despite limitations such as low resolution and nonlinearity of current distribution, its potential in medicine and industry is a source of fascination. The research in this work is a step towards unlocking this potential, focusing on improving the quality of EIT image reconstruction, particularly in bladder modeling. A key element is regularization techniques, including Laplace matrices and the iterative Gauss-Newton algorithm, which balance matching accuracy and image smoothness. In the practical part, simulations were conducted on dense and sparse meshes. Modeling the urinary bladder as a rotational ellipse significantly influences the interpretation of data by algorithms, a crucial factor for the accuracy of reconstruction. Various electrode configurations were also analyzed, revealing the impact of their arrangement on electrical properties and imaging quality. Iterative testing led to identifying optimal electrode placement and grid configuration, underscoring the importance of precise modeling for obtaining high-quality images. The results underscore the critical role of appropriately selecting the regularization parameter in minimizing reconstruction errors.

Map matching on low sampling rate trajectories through deep inverse reinforcement learning and multi-intention modeling

Analyzing freight vehicle movements using GPS trajectory data presents challenges due to environmental conditions and hardware limitations impacting data accuracy. Map matching, the process of aligning GPS signals with road networks, facilitates accurate route reconstruction. However, existing methods have limitations, particularly with low and ultra-low sampling rates. They often assume the shortest path between points, overlook historical data insights and neglect diverse driving behaviors, which may not align with real-world scenarios where shortest paths are not always optimal and different drivers exhibit varied behaviors. These limitations affect existing methods’ reliability, especially when we face low sampling rate trajectories. In this study, we propose multi-intention deep inverse reinforcement learning for map matching (MIDIRL) to address these challenges. MIDIRL integrates deep neural networks and multi-intention capturing mechanisms with inverse reinforcement learning to model complex driving preferences from historical trajectories, improving map matching accuracy, especially in ultra-low-frequency trajectories. Our experiments on real-world datasets demonstrate MIDIRL’s improved accuracy and efficiency of map matching compared to previous methods, even with limited training data.

CSIP: Contrastive learning with Graph Neural Network enables chemical structure to image mapping

The development of advanced AI has been transforming the biomedical field. The emergence of multi-modal biomedical data such as imaging, sequencing, and other omics data further enabled the training of AI models for complex analytical tasks. However, such data analysis remains challenging due to the difficulty of integrating information from different modalities. In this paper, we aim to address this challenge by proposing a methodology to integrate image and molecular structure data. We present the Contrastive Structure-to-Image Pretraining (CSIP) framework, which leverages a self-supervised Graph Neural Network (GNN) to encode molecules and images into a joint feature embedding space. This direct mapping between the two modalities enables a wide variety of applications, including image profiling and clustering of molecules based on their effects on cell morphology. Image profiles generated by CSIP archived an average AUC of 0.708 on various biological activity prediction tasks, rivalling the state-of-the-arts and outperforming some fully supervised methodologies. Further, CSIP improved the accuracy of image-molecule matching by 29-folds from the random baseline after being trained on a small dataset, which demonstrated data efficiency. The code to reproduce our results can be found at https://github.com/LeoL18/CSIP.

Hybrid-feature based spherical quasi-conformal registration for AD-induced hippocampal surface morphological changes

Background and objectiveEstablishing accurate one-to-one morphological correspondence between different hippocampal surfaces is a solid foundation for the analysis of AD-induced hippocampal morphological changes. However, owing to the large variations between hippocampal surfaces, exiting registration work either fails to obtain the accurate matching of local and overall morphological features or does not preserve the bijectivity during parametric mapping. For this reason, this study proposes a hybrid-feature based spherical quasi-conformal registration (HSQR) method that can effectively maintain the diffeomorphic property while meeting the hybrid-feature matching constraints in the spherical parameter domain. MethodsThe HSQR algorithm is primarily achieved through hippocampal surface hybrid feature extraction and spherical quasi-conformal registration. First, hybrid features for a comprehensive morphological description of the hippocampal surface were established, which included essential anatomical features (landmarks) and mean curvature (intensity) features to ensure the accuracy of surface morphology alignment. Second, spherical parameterization was applied to genus-0 closed surfaces, such as the hippocampus, which maximized the preservation of the original local surface morphology through area-preserving properties. Third, a novel spherical quasi-conformal registration algorithm that can handle large deformations is established. It transforms a 3D spherical parameter domain into a 2D plane parameter domain using iterative local stereo projection to improve the efficiency of the registration algorithm. Subsequently, by controlling the Beltramin coefficient, the hybrid morphological features could be aligned while ensuring bijection before and after registration. ResultsUsing a cohort including 161 patients with amyloid-β (Aβ) positive Alzheimer disease (AD), 234 Aβ positive mild cognitive impairment (MCI) and 266 Aβ negative cognitively unimpaired (CU) individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, we set up the experiment which indicated that the HSQR-based whole bilateral hippocampal atrophy features demonstrated the stronger statistical power for group morphological differences of CU vs. MCI with q-value: 0.0453 for left hippocampus and 0.0401 for right hippocampus and group morphological differences of AD vs. MCI with q-value: 0.0282 for left hippocampus and 0.0421 for right hippocampus. ConclusionsOur registration algorithm may provide a solid foundation for the accurate quantification of hippocampal surface morphological changes for the differential diagnosis and tracking of AD.

Research on English Teaching of Solar Energy and Photovoltaic Power Generation Technology

As an emerging energy development industry, solar-photovoltaic power generation technology has the problems of inaccurate translation and translation bias, which affects its long-term development. Therefore, improving the English teaching level of solar-photovoltaic power generation technology majors is an urgent problem to be solved. In order to explore the relationship between solar-photovoltaic power generation technology and the professional practice of English teaching, this paper establishes a vocabulary set of English teaching based on the Clicker calculation model to match the needs of solar-photovoltaic power generation technology majors. Then, combined with teaching theory and intelligent algorithm, the translation constraint feature was used to call and extract data, so as to verify the matching accuracy of solar-photovoltaic power generation technology and English teaching practice. The results show that the matching adjustment coefficients t=-2.822 and df=0.23, and the professional adjustment coefficients t=-3.011 and df=0.85 in the proposed model have significant changes, which are significantly better than those of the manual algorithm. Moreover, the matching accuracy of the Clicker calculation model is more than 95%. The results show that there is a positive correlation between solar-photovoltaic power generation technology and English teaching practice, and the Clicker calculation model can provide support for the matching of solar-photovoltaic power generation technology and English teaching practice.

Temporal subgraph matching method for multi-connected temporal graph

Temporal graph matching is used to find a matching subgraph set that satisfies temporal and topological information on the temporal graph. It is widely used in real scenarios and provides important support for big data mining and analysis. Most existing matching methods take the single-connected graph as the matching graph, which has a high computational cost. Simultaneously, the construction and matching complexity of its index on multi-connected temporal subgraph matching is high. To solve the above problems, we propose a new temporal subgraph matching problem for multi-connected temporal graphs and proposes the corresponding efficient filtering-selecting-matching three-stage multi-connected temporal subgraph matching method. In the filtering stage, a vertex-based filter is proposed to generate a candidate temporal subgraph set. In the select phase, a set of temporal subgraphs satisfying the vertex mapping is found. In the matching stage, the single-filter temporal subgraph matching method and temporal subgraph matching based on the temporal information tree index method are proposed to solve the problems that the edges of multi-connected temporal subgraphs cannot be mapped and the single graph matching efficiency is low, respectively. The experimental results show that the proposed method improves the matching accuracy, and the corresponding index size is reduced.

RTMFusion: An enhanced dual-stream architecture algorithm fusing RGB and depth features for instance segmentation of tomato organs

Accurate and rapid acquisition of semantically annotated point clouds from tomato cultivation regions is crucial for autonomous tomato harvesting robots. This entails the robot’s ability to perceive tomato point clouds from various locations and identify the stems and pedicels connecting the fruits. However, amidst background interference from similar stem and pedicel features, the heterogeneous growth postures of tomato clusters and the slender and short nature of pedicels pose challenges in semantic point cloud segmentation and matching of different tomato fruits, pedicels, and stems. Leveraging the salient feature representation of depth images in fine contours and distance dimensions, this paper introduces RTMFusion, a lightweight dual-stream backbone instance segmentation model that integrates color images and depth images. A Depth Enhanced Feature Fusion module is designed for multi-modal feature fusion. Fruit-bearing organ matching is facilitated by a method based on distance constraints and conditional search. Key characteristics are extracted from semantic point clouds, and an optimal condition search is conducted on candidates meeting constraint conditions. On the test dataset, our model improved the mask mAP by 4.6 % compared to the baseline, achieving 72.1 % with a speed of 17.1 ms. Our matching method achieved 99.2 % pedicel matching accuracy and 97.3 % stem matching accuracy on 150 greenhouse samples. These results demonstrate the effectiveness of accurately identifying and matching tomato organs in real-world scenarios, addressing the challenge from complex greenhouse environments. This integrated visual system enhances the success rate of visual identification and the precision of cutting position localization for tomato harvesting robots.

Power-efficient wideband programmable pseudo differential ring oscillator CP-PLL

A power-efficient, wide-band, programmable pseudo-differential ring-oscillator charge-pump phase-locked loop (CP-PLL) is proposed. The ring-VCO, characterized by its low power consumption and broadband, is achieved based on a feedforward pseudo-differential configuration. The linearity of ring-VCO is improved by using the source negative feedback topology. Through the rail-to-rail operatingamplifier clamping current source, the current matching accuracy is improved to realize a high-performance CP circuit. The results show that the output frequency range of the phase-locked loop is 0.6–6 GHz at a 1.2 V supply voltage, and the power consumption is 1.372 mW at 5 GHz with a lock-up time of 1.72 μs and RMS jitter of 9.3 ps. The power consumption is as low as 0.643 mW at 2.5 GHz and 1.067 mW at 4 GHz, and the final layout area is 0.00716 mm2. The implemented CP-PLL can be used effectively in wireless RF communication system of NB-IoT and intelligent edge computing scenario.

Echoes from Sensory Entrainment in Auditory Working Memory for Pitch.

Ongoing neural oscillations reflect cycles of excitation and inhibition in local neural populations, with individual neurons being more or less likely to fire depending upon the oscillatory phase. As a result, the oscillations could determine whether or not a sound is perceived and/or whether its neural representation enters into later processing stages. While empirical support for this idea has come from sound detection studies, large gaps in knowledge still exist regarding memory for sound events. In the current study, it was investigated how sensory entrainment impacts the fidelity of working memory representations for pitch. In two separate experiments, an 8 Hz amplitude modulated (AM) entraining stimulus was presented prior to a multitone complex having an f0 between 270 and 715 Hz. This "target" sound could be presented at phases from 0 to 2π radians in relation to the previous AM. After a retention interval of 4 s (Experiment 1; n = 26) or 2 s (Experiment 2; n = 28), listeners were tasked to reproduce the target sound's pitch by moving their finger along the horizontal axis of a response pad. It was hypothesized that if entrainment modulates auditory working memory fidelity, reproductions of a target's pitch would be more accurate and precise when targets were presented in phase with the entrainment. Cosine fits of the average data for both experiments showed a significant entrainment "echo" in the accuracy of pitch matches. There was no apparent echo in the matching precision. Fitting of the individual data accuracy showed that the optimal phase was consistent across individuals, aligning near the next AM peak had the AM continued. The results show that sensory entrainment modulates auditory working memory in addition to stimulus detection, consistent with the proposal that ongoing neural oscillatory activity modulates higher-order auditory processes.

Stereo Matching Method with Cost Volume Collaborative Filtering

Aiming at the problem of matching ambiguity and low disparity accuracy at the object boundary in stereo matching, a novel stereo matching algorithm with cost volume collaborative filtering is proposed. Firstly, for each pixel, two support windows are built, namely a local cross- support window as well as a global support window for the whole image. Secondly, a new adaptive weighted guide filter with a cross-support window as a kernel window is derived, and it is used to locally filter the cost volume. In addition, a minimum spanning tree is constructed in the whole image window, and then the minimum spanning tree filter is used to globally filter the cost volume. The collaborative filtering of cost volume is realized by fusing the filtering results of the local filter and global filter, so that each pixel can not only receive the support of the neighboring pixels in the local adaptive window, but can also receive the effective support of other pixels in the whole image, thus effectively eliminating the matching ambiguity in different texture regions while maintaining the disparity edges. The experimental results show that the average matching error rate of our method on the Middlebury stereo images is 3.17%. Compared with the other state-of-the-art methods, our method has higher robustness and matching accuracy, the generated disparity maps are smoother, and the disparity edges are better preserved.

Automatic driving image matching via Random Sample Consensus (RANSAC) and Spectral Clustering (SC) with monocular camera.

In today's big data era, with the development of the Internet of Things (IoT) technology and the trend of autonomous driving prevailing, visual information has shown a blowout increase, but most image matching algorithms have problems such as low accuracy and low inlier rates, resulting in insufficient information. In order to solve the problem of low image matching accuracy and low inlier rate in the field of autonomous driving, this research innovatively applies spectral clustering (SC) in the field of data analysis to image matching in the field of autonomous driving, and a new image matching algorithm "SC-RANSAC" based on SC and Random Sample Consensus (RANSAC) is proposed. The datasets in this research are collected based on the monocular cameras of autonomous driving cars. We use RANSAC to obtain the initial inlier set and the SC algorithm to filter RANSAC's outliers and then use the filtered inliers as the final inlier set. In order to verify the effectiveness of the algorithm, it shows the matching effect from three angles: camera translation, rotation, and rotation and translation. SC-RANSAC is also compared with RANSAC, graph-cut RANSAC, and marginalizing sample consensus by using two different types of datasets. Finally, we select three representative pictures to test the robustness of the SC-RANSAC algorithm. The experimental results show that SC-RANSAC can effectively and reliably eliminate mismatches in the initial matching results; has a high inlier rate, real-time performance, and robustness; and can be effectively applied in the environment of autonomous driving.

A deep learning-based convolutional spatiotemporal network proxy model for reservoir production prediction

Accurate production prediction is crucial in the field of reservoir management and production optimization. Traditional models often struggle with the complexities of nonlinear relationships and high-dimensional data, which hinders their ability to capture the variability of the production process efficiently and results in time-consuming calculations. To overcome these limitations, this paper introduces an innovative proxy modeling technique employing a convolutional spatiotemporal neural network. This method utilizes convolutional neural networks to extract spatial features from high-dimensional data, while the Transformer is used to model and predict complex temporal dynamics in production. To validate the effectiveness of the proposed proxy model, two case studies involving four injection and nine production wells within two-dimensional (2D) and three-dimensional (3D) non-homogeneous reservoirs were conducted, with the R2 coefficient serving as the primary evaluation metric. As the number of training iterations and data volume increase, the proxy model demonstrates rapid convergence. In tests conducted on the 2D and 3D datasets, the average R2 value exceeded 0.96 and 0.94. These results confirm the accuracy and stability of the proxy model. It also shows that the proxy model can accurately describe the geological and fluid seepage characteristics of the reservoir, which in turn can achieve a highly accurate match with the real data. In addition, the computational time is reduced by two orders of magnitude compared to traditional models. Compared with the long short-term memory method, the accuracy of the prediction results is increased by 30%, which greatly enhances efficiency and accuracy. To some extent, the presented proxy model can provide some guidance for the efficient history match of production data.