Matching Accuracy Research Articles

Assessing the shade matching accuracy among dental students through visual and instrumental methods.

To evaluate the shade selection accuracy of male dental students according to the three dimensions of color: value, hue, and chroma, using visual and instrumental shade selection methods under different lighting conditions. This comparative cross-sectional study was instigated amongst 70 male 4th, 5th, and 6th years BDS students of the Dental Clinics Complex at King Faisal University, Saudi Arabia for a duration of two months. First, the principal investigator determined the shade of tooth 11 and 46 on patient utilizing the spectrophotometer after calibration. In the next step, students were asked to select the shade of same tooth 11 and 46 using VITA 3D-Master shade guide under clinic lightening condition and corrected light. The characteristics of the color such as hue, chroma and value were recorded. The Kruskal-Wallis test was applied to find the significant difference in shade selection between visual and instrumental methods with respect to academic years. The mean of the value of instrumental shade selection of tooth # 46 was slightly higher among 4th year students (4.41±0.73), than that of 5th year (3.72±1.02), and 6th year students (3.83±0.83), with a statistically significant difference among them (p= 0.024), indicating 6th year students selected darker shades. Additionally, a statistically significant relationship was noticed among 4th, 5th, and 6th year students with respect to the means of the chroma of 2.18 ±1.29, 2.92±1.11, and 3.13±1.10, respectively (p= 0.025). The selection of posterior teeth shades was notably influenced by academic years, employing both instrumental and visual methods, while considering color parameters.

Study on solidified material from dredged sediment, fly ash, and blended Portland cement using the response surface method

Treating dredged sediment is a complex processing and ongoing challenge. To utilize dredged sediment for the landfill or construction purposes, a material fabricated from a mixture of dredged sediment, Portland cement, and fly ash, was cured under room temperature and hydrothermal condition at 180 °C and 0.9 MPa pressure for 16 hours. The response surface methodology was used to evaluate the compressive strength of the material, with the range of factors investigated being the dredged sediments/solid ratio (0.3-0.9), cement/fly ash ratio (2-4), and water/solid ratio (0.45-0.55). The fitting models offered an accurate and reliable match to the actual data. The optimum mix proportions of two curing conditions were obtained using total desirability function, meet multi-objective criteria. This result finger out hydrothermal curing significantly enhances treatment capacity of dredged sediment, with a lower CO2 emission in the mixture compared to ambient curing. Scanning electron microscopy (SEM), X-ray diffraction (XRD), and Fourier transform infrared spectroscopy (FTIR) were used to figure out the difference between the minerals formed in the material under two curing conditions, such as tobermorite.

Three-Dimensional Deformation Estimation from Multi-Temporal Real-Scene Models for Landslide Monitoring

This study proposes a three-dimensional (3D) deformation estimation framework based on the integration of shape and texture information for real-scene 3D model matching, effectively addressing the issue of deformation assessment in large-scale geological landslide areas. By extracting and merging the texture and shape features of matched points, correspondences between points in multi-temporal real-scene 3D models are established, resolving the difficulties faced by existing methods in achieving robust and high-precision 3D point matching over landslide areas. To ensure the complete coverage of the geological disaster area while enhancing computational efficiency during deformation estimation, a voxel-based thinning method to generate interest points is proposed. The effectiveness of the proposed method is validated through tests on a dataset from the Lijie north hill geological landslide area in Gansu Province, China. Experimental results demonstrate that the proposed method significantly outperforms existing classic and advanced methods in terms of matching accuracy metrics, and the accuracy of our deformation estimates is close to the actual measurements obtained from GNSS stations, with an average error of only 2.2 cm.

Unpaired Image-text Matching via Multimodal Aligned Conceptual Knowledge.

Recently, the accuracy of image-text matching has been greatly improved by multimodal pretrained models, all of which use millions or billions of paired images and texts for supervised model learning. Different from them, human brains can well match images with texts using their stored multimodal knowledge. Inspired by that, this paper studies a new scenario as unpaired image-text matching, in which paired images and texts are assumed to be unavailable during model learning. To deal with it, we accordingly propose a simple yet effective method namely Multimodal Aligned Conceptual Knowledge (MACK). First, we collect a set of words and their related image regions from publicly available datasets, and compute prototypical region representations to obtain pretrained general knowledge. To make the obtained knowledge better suit for certain datasets, we refine it using unpaired images and texts in a self-supervised learning manner to obtain fine-tuned domain knowledge. Then, to match given images with texts based on the knowledge, we represent parsed words in the texts by prototypical region representations, and compute region-word similarity scores. At last, the scores are aggregated based on bidirectional similarity pooling into an image-text similarity score, which can be directly used for unpaired image-text matching. The proposed MACK is complementary with existing models, which can be easily extended as a re-ranking method to substantially improve their performance of zero-shot and cross-dataset image-text matching.

Construction of a Multi-Label Classifier for Extracting Multiple Incident Factors From Medication Incident Reports in Residential Care Facilities: Natural Language Processing Approach.

Medication safety in residential care facilities is a critical concern, particularly when nonmedical staff provide medication assistance. The complex nature of medication-related incidents in these settings, coupled with the psychological impact on health care providers, underscores the need for effective incident analysis and preventive strategies. A thorough understanding of the root causes, typically through incident-report analysis, is essential for mitigating medication-related incidents. We aimed to develop and evaluate a multilabel classifier using natural language processing to identify factors contributing to medication-related incidents using incident report descriptions from residential care facilities, with a focus on incidents involving nonmedical staff. We analyzed 2143 incident reports, comprising 7121 sentences, from residential care facilities in Japan between April 1, 2015, and March 31, 2016. The incident factors were annotated using sentences based on an established organizational factor model and previous research findings. The following 9 factors were defined: procedure adherence, medicine, resident, resident family, nonmedical staff, medical staff, team, environment, and organizational management. To assess the label criteria, 2 researchers with relevant medical knowledge annotated a subset of 50 reports; the interannotator agreement was measured using Cohen κ. The entire data set was subsequently annotated by 1 researcher. Multiple labels were assigned to each sentence. A multilabel classifier was developed using deep learning models, including 2 Bidirectional Encoder Representations From Transformers (BERT)-type models (Tohoku-BERT and a University of Tokyo Hospital BERT pretrained with Japanese clinical text: UTH-BERT) and an Efficiently Learning Encoder That Classifies Token Replacements Accurately (ELECTRA), pretrained on Japanese text. Both sentence- and report-level training were performed; the performance was evaluated by the F1-score and exact match accuracy through 5-fold cross-validation. Among all 7121 sentences, 1167, 694, 2455, 23, 1905, 46, 195, 1104, and 195 included "procedure adherence," "medicine," "resident," "resident family," "nonmedical staff," "medical staff," "team," "environment," and "organizational management," respectively. Owing to limited labels, "resident family" and "medical staff" were omitted from the model development process. The interannotator agreement values were higher than 0.6 for each label. A total of 10, 278, and 1855 reports contained no, 1, and multiple labels, respectively. The models trained using the report data outperformed those trained using sentences, with macro F1-scores of 0.744, 0.675, and 0.735 for Tohoku-BERT, UTH-BERT, and ELECTRA, respectively. The report-trained models also demonstrated better exact match accuracy, with 0.411, 0.389, and 0.399 for Tohoku-BERT, UTH-BERT, and ELECTRA, respectively. Notably, the accuracy was consistent even when the analysis was confined to reports containing multiple labels. The multilabel classifier developed in our study demonstrated potential for identifying various factors associated with medication-related incidents using incident reports from residential care facilities. Thus, this classifier can facilitate prompt analysis of incident factors, thereby contributing to risk management and the development of preventive strategies.

Improved mirror-assisted multi-view digital image correlation for accuracy-enhanced dual-surface profile and deformation measurement

Accurate measurement of dual-surface kinematic fields is essential for characterizing the mechanical behavior and anisotropic parameters of sheet specimens. To this end, a cost-efficient and simple-to-implement mirror-assisted multi-view digital image correlation (MV-DIC) was recently proposed and has been proven to be effective. Nevertheless, this method conventionally relies on reflection transformation calibration to map the measured virtual surfaces to their actual positions. The positional transformation for each surface is mutually independent and lacks constraint relationships. This work proposes an improved mirror-assisted MV-DIC method for accuracy-enhanced dual-surface deformation measurement by utilizing the overlapped region of the virtual surfaces instead of reflection transformation calibration. Through preliminary feature matching and precise matching of subsets for corresponding points in the overlapped regions, the relative positional transformations between the measured surfaces of the specimen can be accurately determined. As the accuracy of positional transformations primarily depends on the matching accuracy of corresponding points rather than the accuracy of multiple plane fitting, this method provides better relative positional relationships between the two surfaces compared to conventional methods. The results of several real experiments well validated the practicality and accuracy of the proposed method.

Highly adaptive multi-modal image matching based on tuning-free filtering and enhanced sketch features

The generalizability and adaptiveness of multi-modal image matching (MMIM) techniques are hampered by the nonlinear radiometric differences that vary in a highly non-uniform manner across different modal combinations. A major challenge is the extensive filter tuning required by many filter-based matching methods to mitigate the impact of radiometric aberrations. Additionally, the low correct matching rate resulting from the non-repeatability and low similarity of local or detailed features presents another significant obstacle. In this paper, we introduce a novel MMIM framework, called Adaptive Matching with enhanced Edge Sketches (AMES), for reducing manual interference in filter parameter configuration and improving the correct matching rate of extracted feature points. Specifically, AMES trains a support vector regression model to adaptively predict the optimized filtering parameters for each test image using its internal statistical factors as input. We also propose a sketch feature enhancement method, based on fusing multi-scale moment maps through principal component analysis, for cross-modal adaptive feature point extraction. We generate matching results by applying feature descriptors within the Log-Polar window and performing outlier removal following a coarse-to-fine strategy. In an evaluation involving four datasets comprising 1055 image pairs with 26 different cross-modal combinations, the assessment of 10,599 manually measured checkpoints demonstrates that AMES surpasses the state-of-the-art in terms of success rate, correct matching rate, point coverage, average matching accuracy, and spatial distribution uniformity. Our source code and multi-modal image datasets are publicly available at https://dpcv.whu.edu.cn/zm1/gksjj.htm.

Covalent Organic Framework-Structured Raman Probes for Ultrasensitive In Vivo Bioimaging.

Organic Raman probes, including polymers and small molecules, have attracted great attention in biomedical imaging owing to their excellent biocompatibility. However, the development of organic Raman probes is usually hindered by a mismatch between their absorption spectra and wavelength-fixed excitation, which makes it difficult to achieve resonance excitation necessary to obtain strong Raman signals. Herein, we introduce a covalent organic framework (COF) into the fine absorption spectrum regulation of organic Raman probes, resulting in their significant Raman signal enhancement. In representative examples, a polymer poly(diketopyrrolopyrrole-p-phenylenediamine) (DPP-PD) and a small molecule azobenzene are transformed into the corresponding COF-structured Raman probes. Their absorption peaks show an accurate match of less than 5 nm with the NIR excitation. As such, the COF-structured Raman probes acquire highly sensitive bioimaging capabilities compared to their precursors with negligible signals. By further mechanism studies, we discover that the crystallinity and size of COFs directly affect the π-conjugation degree of Raman probes, thus changing their bandgaps and absorption spectra. Our study offers a universal and flexible method for improving the signal performance of organic Raman probes without changing their structural units, making it more convenient to obtain the highly sensitive organic Raman probes for in vivo bioimaging.

Spatial-aware contrastive learning for cross-domain medical image registration.

With the rapid advancement of medical imaging technologies, precise image analysis and diagnosis play a crucial role in enhancing treatment outcomes and patient care. Computed tomography (CT) and magnetic resonance imaging (MRI), as pivotal technologies in medical imaging, exhibit unique advantages in bone imaging and soft tissue contrast, respectively. However, cross-domain medical image registration confronts significant challenges due to the substantial differences in contrast, texture, and noise levels between different imaging modalities. The purpose of this study is to address the major challenges encountered in the field of cross-domain medical image registration by proposing a spatial-aware contrastive learning approach that effectively integrates shared information from CT and MRI images. Our objective is to optimize the feature space representation by employing advanced reconstruction and contrastive loss functions, overcoming the limitations of traditional registration methods when dealing with different imaging modalities. Through this approach, we aim to enhance the model's ability to learn structural similarities across domain images, improve registration accuracy, and provide more precise imaging analysis tools for clinical diagnosis and treatmentplanning. With prior knowledge that different domains of images (CT and MRI) share same content-style information, we extract equivalent feature spaces from both images, enabling accurate cross-domain point matching. We employ a structure resembling that of an autoencoder, augmented with designed reconstruction and contrastive losses to fulfill our objectives. We also propose region mask to solve the conflict between spatial correlation and distinctiveness, to obtain a better representation space. Our research results demonstrate the significant superiority of the proposed spatial-aware contrastive learning approach in the domain of cross-domain medical image registration. Quantitatively, our method achieved an average Dice similarity coefficient (DSC) of 85.68%, target registration error (TRE) of 1.92 mm, and mean Hausdorff distance (MHD) of 1.26 mm, surpassing current state-of-the-art methods. Additionally, the registration processing time was significantly reduced to 2.67 s on a GPU, highlighting the efficiency of our approach. The experimental outcomes not only validate the effectiveness of our method in improving the accuracy of cross-domain image registration but also prove its adaptability across different medical image analysis scenarios, offering robust support for enhancing diagnostic precision and patient treatmentoutcomes. The spatial-aware contrastive learning approach proposed in this paper introduces a new perspective and solution to the domain of cross-domain medical image registration. By effectively optimizing the feature space representation through carefully designed reconstruction and contrastive loss functions, our method significantly improves the accuracy and stability of registration between CT and MRI images. The experimental results demonstrate the clear advantages of our approach in enhancing the accuracy of cross-domain image registration, offering significant application value in promoting precise diagnosis and personalized treatment planning. In the future, we look forward to further exploring the application of this method in a broader range of medical imaging datasets and its potential integration with other advanced technologies, contributing more innovations to the field of medical image analysis andprocessing.

BY-SLAM: Dynamic Visual SLAM System Based on BEBLID and Semantic Information Extraction.

SLAM is a critical technology for enabling autonomous navigation and positioning in unmanned vehicles. Traditional visual simultaneous localization and mapping algorithms are built upon the assumption of a static scene, overlooking the impact of dynamic targets within real-world environments. Interference from dynamic targets can significantly degrade the system's localization accuracy or even lead to tracking failure. To address these issues, we propose a dynamic visual SLAM system named BY-SLAM, which is based on BEBLID and semantic information extraction. Initially, the BEBLID descriptor is introduced to describe Oriented FAST feature points, enhancing both feature point matching accuracy and speed. Subsequently, FasterNet replaces the backbone network of YOLOv8s to expedite semantic information extraction. By using the results of DBSCAN clustering object detection, a more refined semantic mask is obtained. Finally, by leveraging the semantic mask and epipolar constraints, dynamic feature points are discerned and eliminated, allowing for the utilization of only static feature points for pose estimation and the construction of a dense 3D map that excludes dynamic targets. Experimental evaluations are conducted on both the TUM RGB-D dataset and real-world scenarios and demonstrate the effectiveness of the proposed algorithm at filtering out dynamic targets within the scenes. On average, the localization accuracy for the TUM RGB-D dataset improves by 95.53% compared to ORB-SLAM3. Comparative analyses against classical dynamic SLAM systems further corroborate the improvement in localization accuracy, map readability, and robustness achieved by BY-SLAM.

A Low Mismatch Current Charge Pump Applied to Phase-Locked Loops.

This paper presents a charge pump circuit with a wide output range and low current mismatch applied to phase-locked loops. In this designed structure, T-shaped analog switches are adopted to suppress the non-ideal effects of clock feedthrough, switching time mismatch, and charge injection. A source follower and current splitting circuits are proposed to improve the matching accuracy of the charging and discharging currents and reduce the current mismatch rate. A rail-to-rail high-gain amplifier with a negative feedback connection is introduced to suppress the charge-sharing effect of the charge pump. A cascode current mirror with a high output impedance is used to provide the charge and discharge currents for the charge pump, which not only improves the current accuracy of the charge pump but also increases the output voltage range. The proposed charge pump is designed and simulated based on a 65 nm CMOS process. The results show that when the power supply voltage is 1.2 V, the output current of the charge pump is 100 μA, the output voltage is in the range of 0.2~1 V, and the maximum current mismatch rate and current variation rate are only 0.21% and 1.4%, respectively.

Combining multimodal diffusion-weighted imaging and morphological parameters for detecting lymph node metastasis in cervical cancer.

Accurate detection of lymph node metastasis (LNM) is crucial for determining the tumor stage, selecting optimal treatment, and estimating the prognosis for cervical cancer. This study aimed to assess the diagnostic efficacy of multimodal diffusion-weighted imaging (DWI) and morphological parameters alone or in combination, for detecting LNM in cervical cancer. In this prospective study, we enrolled consecutive cervical cancer patients who received multimodal DWI (conventional DWI, intravoxel incoherent motion DWI, and diffusion kurtosis imaging) before treatment from June 2022 to June 2023. The largest lymph node (LN) observed on each side on imaging was matched with that detected on pathology to improve the accuracy of LN matching. Comparison of the diffusion and morphological parameters of LNs and the primary tumor between the positive and negative LN groups. A combined diagnostic model was constructed using multivariate logistic regression, and the diagnostic performance was evaluated using receiver operating characteristic curves. A total of 93 cervical cancer patients were enrolled: 35 with LNM (48 positive LNs were collected), and 58 without LNM (116 negative LNs were collected). The area under the curve (AUC) values for the apparent diffusion coefficient, diffusion coefficient, mean diffusivity, mean kurtosis, long-axis diameter, short-axis diameter of LNs, and the largest primary tumor diameter were 0.716, 0.720, 0.716, 0.723, 0.726, 0.798, and 0.744, respectively. Independent risk factors included the diffusion coefficient, mean kurtosis, short-axis diameter of LNs, and the largest primary tumor diameter. The AUC value of the combined model based on the independent risk factors was 0.920, superior to the AUC values of all the parameters mentioned above. Combining multimodal DWI and morphological parameters improved the diagnostic efficacy for detecting cervical cancer LNM than using either alone.

A novel deformation measurement method for rotating blade based on PSO-ILS image correlation matching and mismatch correction

Abstract Aiming at the problem of small measurement range and difficult measurement of traditional contact sensor method in the rotating state of aero-engine blades, this paper proposes a novel deformation measurement method for rotating blade based on image correlation matching and mismatch correction. Firstly, a Particle Swarm Optimization-Iterative Local Search image intelligent matching algorithm is proposed, which effectively balances global search and local optimization, and the image matching displacement accuracy reaches 10−3 pixel. Secondly, a mismatch point detection method based on multi-scale local Root Mean Square is proposed, and the high-precision detection of mismatch points is realized by considering the influence of local structure. Finally, through the hierarchical refinement of the sub-pixel level mismatch point correction method, the mismatch point is corrected in the two iterative stages of global search and local optimization. The corrected mismatch point response value K is reduced by 99% compared with that before correction, which further improves the accuracy of deformation field calculation. In the experiment, the deformation of the rotating blade of 4500 RPM is measured, which proves that the image intelligent matching algorithm and the deformation field calculation method proposed in this paper can provide new methods and technical support for the accurate measurement of the blade surface deformation.

Research on a Matching Method for Vehicle-Borne Laser Point Cloud and Panoramic Images Based on Occlusion Removal

Vehicle-borne mobile mapping systems (MMSs) have been proven as an efficient means of photogrammetry and remote sensing, as they simultaneously acquire panoramic images, point clouds, and positional information along the collection route from a ground-based perspective. Obtaining accurate matching results between point clouds and images is a key issue in data application from vehicle-borne MMSs. Traditional matching methods, such as point cloud projection, depth map generation, and point cloud coloring, are significantly affected by the processing methods of point clouds and matching logic. In this study, we propose a method for generating matching relationships based on panoramic images, utilizing the raw point cloud map, a series of trajectory points, and the corresponding panoramic images acquired using a vehicle-borne MMS as input data. Through a point-cloud-processing workflow, irrelevant points in the point cloud map are removed, and the point cloud scenes corresponding to the trajectory points are extracted. A collinear model based on spherical projection is employed during the matching process to project the point cloud scenes to the panoramic images. An algorithm for vectorial angle selection is also designed to address filtering out the occluded point cloud projections during the matching process, generating a series of matching results between point clouds and panoramic images corresponding to the trajectory points. Experimental verification indicates that the method generates matching results with an average pixel error of approximately 2.82 pixels, and an average positional error of approximately 4 cm, thus demonstrating efficient processing. This method is suitable for the data fusion of panoramic images and point clouds acquired using vehicle-borne MMSs in road scenes, provides support for various algorithms based on visual features, and has promising applications in fields such as navigation, positioning, surveying, and mapping.

RoBERTa-GCN: A New Method for Relation Extraction in Automobile Accessory Domain

The automotive industry's rapid expansion has sparked increasing interest in the realm of automotive accessories. Navigating vast information landscapes to find accurate matches has become paramount. Leveraging cutting-edge information technologies, such as knowledge graphs and graph database-based question-answering systems, offers a crucial avenue for enhancing search efficiency. Addressing challenges posed by the domain's specialized terminology and intricate relationships, this paper introduces an innovative approach that combines a pre-trained model (RoBERTa) with graph convolutional networks (GCN). Initially, the text undergoes processing through the pre-trained model, yielding semantic feature vectors that enhance comprehension of industry-specific terminology. Subsequently, a graph convolutional network (GCN) is employed to process these semantic vectors, capturing a broader scope of neighboring vector node information. This approach not only strengthens the relationships between semantic information but also captures the intricate interconnections among entities. Ultimately, an automotive accessory query knowledge graph question-answering system is constructed using extracted entity relationship triplets. Experimental results demonstrate that the proposed RoBERTa-GCN model outperforms other baseline models, achieving an impressive F1 score of 83.93%. This research significantly enhances query capabilities and exhibits versatility in handling natural language inputs from diverse users.

Matching constraint extraction for analog integrated circuits layout via edge classify

Achieving matching constraints between various components is important in analog integrated circuit (IC) layout design, as it can reduce the impact of layout parasitics on the performance of IC. When automating analog integrated circuit layout design, identifying accurate matching constraints is an essential step before placement and routing. The matching relationship between devices strongly depends on circuit's topology and design expertise. This work focuses on differential circuits with various topologies and proposes a supervised learning framework that incorporates symmetry analysis. The heterogeneous multi-relationship graph representation is proposed to capture circuit's topology and extract matching constraints. Additionally, a symmetry analysis algorithm and filtering method based on matching levels are investigated to enhance the model's performance. The experimental results demonstrate that this work maintains a low false alarm rate and outperforms other matching constraint detection algorithms in terms of F1 score and accuracy.

Automatic construction and optimization method of enterprise data asset knowledge graph based on graph attention network

Traditional knowledge graph construction methods often rely on a large amount of human intervention and specialized knowledge, which seems inefficient and error-prone when dealing with massive, multi-source, and heterogeneous data assets of enterprises. To address this issue, a Multi Neighborhood Awareness Network (MNAN) model was proposed, which combines a multi language pre training model based on Bidirectional Encoder Representations from Transformers (BERT) and a Graph Convolutional Neural Network (GCN). By introducing an improved attention mechanism to deeply explore the neighborhood characteristics of entities, the accuracy and efficiency of entity matching are enhanced. In addition, to improve the integrity of the knowledge graph, a dynamic graph attention network (RDGAT) model based on graph attention network fusion relationship features is proposed. Through dynamic attention mechanism and relationship fusion strategy, deep learning of relationship features is carried out to optimize the completion performance of the knowledge graph spectrum. The performance test results show that the Hits@1 metric of the multi-neighborhood perceptual network model is close to 90% as the proportion of aligned entity seeds increases to 50%; the average inverse rank of the dynamic graph attention network on the test dataset improves by 6.3%. The experimental results show that the research-proposed knowledge graph fusion and complementation model exhibits significant effectiveness in automatically identifying and integrating large-scale, multi-source heterogeneous data at the enterprise level, and can significantly improve the automation level and accuracy of knowledge graph construction. The research method has achieved significant results in the data asset knowledge graph of petroleum enterprises and other fields, providing strong support for applications such as intelligent search, recommendation systems, and semantic analysis.

Enhanced Object Detection in Autonomous Vehicles through LiDAR—Camera Sensor Fusion

To realize accurate environment perception, which is the technological key to enabling autonomous vehicles to interact with their external environments, it is primarily necessary to solve the issues of object detection and tracking in the vehicle-movement process. Multi-sensor fusion has become an essential process in efforts to overcome the shortcomings of individual sensor types and improve the efficiency and reliability of autonomous vehicles. This paper puts forward moving object detection and tracking methods based on LiDAR—camera fusion. Operating based on the calibration of the camera and LiDAR technology, this paper uses YOLO and PointPillars network models to perform object detection based on image and point cloud data. Then, a target box intersection-over-union (IoU) matching strategy, based on center-point distance probability and the improved Dempster–Shafer (D–S) theory, is used to perform class confidence fusion to obtain the final fusion detection result. In the process of moving object tracking, the DeepSORT algorithm is improved to address the issue of identity switching resulting from dynamic objects re-emerging after occlusion. An unscented Kalman filter is utilized to accurately predict the motion state of nonlinear objects, and object motion information is added to the IoU matching module to improve the matching accuracy in the data association process. Through self-collected data verification, the performances of fusion detection and tracking are judged to be significantly better than those of a single sensor. The evaluation indexes of the improved DeepSORT algorithm are 66% for MOTA and 79% for MOTP, which are, respectively, 10% and 5% higher than those of the original DeepSORT algorithm. The improved DeepSORT algorithm effectively solves the problem of tracking instability caused by the occlusion of moving objects.

Enhanced large-scale building extraction evaluation: developing a two-level framework using proxy data and building matching

ABSTRACT Deep learning-based building extraction methods have widespread applications in diverse fields. However, the evaluation of large-scale extraction results remains challenging, due to traditional evaluation metrics rely on manually created ground-truth samples and the lack of comprehensive reference-building data for developing countries. To address these problems, we proposed a two-level framework for evaluating large-scale footprint extraction. First, we utilised global open-source population and land use data as the proxy data, to assess grid-level completeness for the areas with insufficient reference data. Second, we introduced an improved two-way area-overlapping method to match the extracted footprints with the reference buildings, thereby enabling a comprehensive evaluation of the study region. Tested in Hyogo Prefecture and Numazu City, Japan, the results demonstrated a 2.6-% improvement in grid classification accuracy and an increase of 0.53 in the completeness correlation, compared with the results obtained using a single proxy indicator. Moreover, the optimised matching method achieved an outstanding semantic matching accuracy of 99%, with high efficiency and robustness in multi-scale matching. Therefore, the proposed approach can effectively evaluate large-scale footprint extraction results and interpret their semantic relationship with actual buildings, applicable globally regardless of the availability of reference building datasets.

Enhancing Map Matching Accuracy Using Backtracking Technique

Map matching integrates positioning data with road network information to accurately identify a vehicle exact location on a specific road. Modern location-based services heavily rely on accurate map matching techniques to match observed trajectories with road networks. This paper presents a novel map matching approach that leverages topological information and integrates the backtracking technique to enhance the accuracy and robustness of map matching. By considering the logical relationships between road segments, our method achieves excellent results in scenarios with complex road geometries and challenging urban environments. We integrate the backtracking technique to address noise and ambiguity in trajectory data, resulting in improved precision and a reduced likelihood of false matches. Extensive experimentation using real-world trajectory datasets in Beijing validates the effectiveness of our approach, highlighting its superiority over traditional methods. The algorithm accuracy achieved as high as 99.92%. The results of the evaluation demonstrate that the proposed approach exhibits superior performance compared to earlier map-matching algorithms in both simple and complex road networks. Additionally, it can be effectively implemented on GPS datasets with different time intervals. In addition to the obvious map matching applications of our technology, it has the potential to be adapted across domains, with implications in transportation, urban planning, and location-based services. This paper not only presents a substantial advancement in map matching but also opens new avenues for location-based analyses enhancing and services across various domains.