Set Of Candidate Points Research Articles

Boosting Point Set-Based Network with Optimal Transport Optimization for Oriented Object Detection

When handling complex remote sensing scenarios, rotational angle information can improve detection accuracy and enhance algorithm robustness, providing support for fine-grained detection. Point set representation is one of the most commonly used methods in arbitrary-oriented object detection tasks, leveraging discrete feature points to represent oriented targets and achieve high accuracy in angle prediction. However, due to the inherent discreteness of point set representation, it is prone to significant impact from isolated points and representational ambiguity in harsh application scenarios, leading to inaccurate detection. To address this issue, an efficient aerial object detector named BE-Det is proposed, which uses the optimal transport (OT) strategy to constrain the positions of isolated points. Additionally, a candidate point set quality evaluation scheme is designed to effectively assess the quality of candidate point sets. Experimental results on two challenging aerial datasets demonstrate that the proposed method outperforms several advanced detection methods.

Three-Dimensional Reconstruction of Zebra Crossings in Vehicle-Mounted LiDAR Point Clouds

In the production of high-definition maps, it is necessary to achieve the three-dimensional instantiation of road furniture that is difficult to depict on traditional maps. The development of mobile laser measurement technology provides a new means for acquiring road furniture data. To address the issue of traffic marking extraction accuracy in practical production, which is affected by degradation, occlusion, and non-standard variations, this paper proposes a 3D reconstruction method based on energy functions and template matching, using zebra crossings in vehicle-mounted LiDAR point clouds as an example. First, regions of interest (RoIs) containing zebra crossings are obtained through manual selection. Candidate point sets are then obtained at fixed distances, and their neighborhood intensity features are calculated to determine the number of zebra stripes using non-maximum suppression. Next, the slice intensity feature of each zebra stripe is calculated, followed by outlier filtering to determine the optimized length. Finally, a matching template is selected, and an energy function composed of the average intensity of the point cloud within the template, the intensity information entropy, and the intensity gradient at the template boundary is constructed. The 3D reconstruction result is obtained by solving the energy function, performing mode statistics, and normalization. This method enables the complete 3D reconstruction of zebra stripes within the RoI, maintaining an average planar corner accuracy within 0.05 m and an elevation accuracy within 0.02 m. The matching and reconstruction time does not exceed 1 s, and it has been applied in practical production.

A Persistent Scatterer Point Selection Method for Deformation Monitoring of Under-Construction Cross-Sea Bridges Using Statistical Theory and GMM-EM Algorithm

Using traditional algorithms to identify persistent scatterer (PS) points is challenging during bridge construction because of short-term changes at construction sites, such as earthworks, as well as the erection and dismantling of temporary structures. To address this issue, this study proposes a PS point selection method based on statistical theory and Gaussian Mixture Model-Expectation Maximization (GMM-EM) algorithm. This method adopts amplitude information as an incoherence evaluation indicator. Furthermore, the statistical median of the amplitude dispersion index and amplitude mean is screened twice to extract a set of candidate points, including PS points that exhibit stable backscattering over long durations. Temporal coherence is simultaneously used as the coherence evaluation indicator. Another candidate point set is obtained by extracting high-coherence PS points using the GMM-EM algorithm. These sets of candidate points are then combined to obtain a final PS points set. In the experiment, the deformation monitoring of the under-construction Shenzhen-Zhongshan Cross-Sea Bridge in China was selected as a case study, with 28 Sentinel-1A images used as the data source for PS selection and deformation information extraction. The results show that the proposed method enhanced the density and quality of PS points on the under-construction cross-sea bridge compared to existing PS selection methods, thus offering higher reliability. Deformation analysis further revealed fluctuating deformation trends at characteristic points of the Shenzhen-Zhongshan Cross-Sea Bridge, indicating the occurrence of elastic deformation during its construction.

Extraction of Tooth Cusps based on DBSCAN Density Clustering and Neighborhood Search Algorithm.

A good tooth cusp extraction is helpful in evaluating the effect of cosmetic dental work in virtual tooth surgery. We propose a new tooth cusp extraction, which integrates the DBSCAN (density-based spatial clustering of applications with noise) clustering algorithm with the neighborhood search algorithm to extract tooth cusp from a three-dimensional cloud-point tooth model. This method used the point cloud height and curvature to screen out the dented point set. Then we employ the DBSCAN clustering algorithm to segment different feature regions of the tooth surface and generate the candidate point set. Finally, the candidate point set was accurately located at the tooth apex through the neighborhood search algorithm and the traversal search method of non-maximum suppression. The experimental results show that the proposed method is superior to the traditional watershed algorithm-based methods by calculating the recall rate and accuracy rate, and also has higher extraction speed and extraction precision than manual extraction methods.

An evaluation of GPU filters for accelerating the 2D convex hull

The Convex Hull is one of the most relevant structures in computational geometry, with many applications such as in computer graphics, robotics, and data mining. Despite the advances in the new algorithms in this area, it is often needed to improve the performance to solve more significant problems quickly or in real-time processing. This work presents an experimental evaluation of GPU filters to reduce the cost of computing the 2D convex hull. The techniques first perform a preprocessing of the input set, filtering all points within an eight-vertex polygon to obtain a reduced set of candidate points. We use parallel computation and the use of the Manhattan distance as a metric to find the vertices of the polygon and perform the point filtering. For the filtering stage we study different approaches; from custom CUDA kernels to libraries such as Thrust and Cub. Four types of point distributions are tested: a normal distribution (favorable case), uniform (favorable case), circumference (the worst case), and a case where points are shifted randomly from the circumference (intermediate case). The experimental evaluation shows that the GPU filtering algorithm can be up to 17.5× faster than a sequential CPU implementation, and the whole convex hull computation can be up to 160× faster than the fastest implementation provided by the CGAL library for a uniform distribution and 23× for a normal distribution.

Алгоритм нахождения оптимального расположения распределительных центров для доставки заказов с использованием методов неконтролируемого машинного обучения

The problem of automating the finding of centers of mass for a system of objects on the Earth's surface is considered. This task often arises, for example, in the course of optimizing the logistics network of the company in quickening the order delivery to the customers. Automation of this process contributes to the optimization of the staff involved, improves the quality of decisions on the development of logistics networks by estimating the situation based on data. The authors of the article suggest to use the modified metric K-means machine learning algorithm for determining the optimal locations of distribution centers of the delivery of goods to settlements. Such centers can significantly reduce transportation costs, as well as provide a high level of customer service quality. The research is also touches upon the more complicated cases of using the chosen method for finding warehouse locations, since the process depends on the logistics strategy of the company. The data were analyzed and a set of features suitable for the clustering algorithm as weights was determined. The data were processed and transformed to apply the algorithm. There has been developed a class for finding distances between points on the highways. The optimal number of clusters is calculated. The clustering algorithm has been modified in terms of calculating distances between objects. With the modified algorithm, a set of candidate points for the location of distribution centers was obtained.

Uniform and Competency-Based 3D Keypoint Detection for Coarse Registration of Point Clouds with Homogeneous Structure

Recent advances in 3D laser scanner technology have provided a large amount of accurate geo-information as point clouds. The methods of machine vision and photogrammetry are used in various applications such as medicine, environmental studies, and cultural heritage. Aerial laser scanners (ALS), terrestrial laser scanners (TLS), mobile mapping laser scanners (MLS), and photogrammetric cameras via image matching are the most important tools for producing point clouds. In most applications, the process of point cloud registration is considered to be a fundamental issue. Due to the high volume of initial point cloud data, 3D keypoint detection has been introduced as an important step in the registration of point clouds. In this step, the initial volume of point clouds is converted into a set of candidate points with high information content. Many methods for 3D keypoint detection have been proposed in machine vision, and most of them were based on thresholding the saliency of points, but less attention had been paid to the spatial distribution and number of extracted points. This poses a challenge in the registration process when dealing with point clouds with a homogeneous structure. As keypoints are selected in areas of structural complexity, it leads to an unbalanced distribution of keypoints and a lower registration quality. This research presents an automated approach for 3D keypoint detection to control the quality, spatial distribution, and the number of keypoints. The proposed method generates a quality criterion by combining 3D local shape features, 3D local self-similarity, and the histogram of normal orientation and provides a competency index. In addition, the Octree structure is applied to control the spatial distribution of the detected 3D keypoints. The proposed method was evaluated for the keypoint-based coarse registration of aerial laser scanner and terrestrial laser scanner data, having both cluttered and homogeneous regions. The obtained results demonstrate the proper performance of the proposed method in the registration of these types of data, and in comparison to the standard algorithms, the registration error was diminished by up to 56%.

An Efficient 3-D Positioning Approach to Minimize Required UAVs for IoT Network Coverage

Using unmanned aerial vehicles (UAVs) to cover users in wireless networks has increased in recent years. Deploying UAVs in appropriate positions is important to cover users and nodes properly. In this article, we propose an efficient approach to determine the minimum number of required UAVs and their optimal positions. To this end, we use an iterative algorithm that updates the number of required UAVs at each iteration. To determine the optimal position for the UAVs, we present a mathematical model and solve it accurately after linearizing. One of the inputs of the mathematical model is a set of candidate points for UAV deployments in 2-D space. The mathematical model selects a set of points among candidate points and determines the altitude of each UAV. To provide a suitable set of candidate points, we also propose a candidate point selection method: the MergeCells method. The simulation results show that the proposed approach performs better than the 3-D P-median approach introduced in the literature. We also compare different candidate point selection approaches, and we show that the MergeCells method outperforms other methods in terms of the number of UAVs, user data rates, and simulation time.

The Art Gallery Problem is ∃ℝ-complete

The Art Gallery Problem (AGP) is a classic problem in computational geometry, introduced in 1973 by Victor Klee. Given a simple polygon 풫 and an integer k , the goal is to decide if there exists a set G of k guards within 풫 such that every point p ∈ 풫 is seen by at least one guard g ∈ G . Each guard corresponds to a point in the polygon 풫, and we say that a guard g sees a point p if the line segment pg is contained in 풫. We prove that the AGP is ∃ ℝ-complete, implying that (1) any system of polynomial equations over the real numbers can be encoded as an instance of the AGP, and (2) the AGP is not in the complexity class NP unless NP = ∃ ℝ. As a corollary of our construction, we prove that for any real algebraic number α, there is an instance of the AGP where one of the coordinates of the guards equals α in any guard set of minimum cardinality. That rules out many natural geometric approaches to the problem, as it shows that any approach based on constructing a finite set of candidate points for placing guards has to include points with coordinates being roots of polynomials with arbitrary degree. As an illustration of our techniques, we show that for every compact semi-algebraic set S ⊆ [0, 1] 2 , there exists a polygon with corners at rational coordinates such that for every p ∈ [0, 1] 2 , there is a set of guards of minimum cardinality containing p if and only if p ∈ S . In the ∃ ℝ-hardness proof for the AGP, we introduce a new ∃ ℝ-complete problem ETR-INV. We believe that this problem is of independent interest, as it has already been used to obtain ∃ ℝ-hardness proofs for other problems.

A reliable location design of unmanned vending machines based on customer satisfaction

The location problem of unmanned vending machine is challenging due to the variety of customer preferences and random breakdown in service. In this paper, we present an optimization model for reliable location design of unmanned vending machines, with the goal to minimize total costs and maximize customer satisfaction. We solve the problem through a two-stage approach in order to mine customers preference from their behaviours and improve design reliability. At the first stage, we design a multi-dimensional measurement to mine customers’ preferences and satisfaction based on their behavioural information. At the second stage, we use a clustering method to analyse the set of candidate points from a systematic perspective. Candidate points with similar locations and customer preferences will be clustered into one “demand zone” and the mutual rescue strategy is considered when breakdown occurred. An experimental study is designed based on the proposed approach and solved by combinational genetic algorithm.

Candidate point selection using a self-attention mechanism for generating a smooth volatility surface under the SABR model

In real markets, generating a smooth implied volatility surface requires an interpolation of the calibrated parameters by using smooth parametric functions. For this interpolation, practitioners do not use all the discrete parameter points but manually select candidate parameter points through time-consuming adjustments (e.g., removing outliers, comparing with the surface from the previous day, and considering daily market indexes) to generate a smooth and robust surface. In this paper, we propose neural network models that assist practitioners in generating a smooth implied volatility surface under the SABR (Hagan et al., 2002) model. Utilizing the self-attention mechanism of a transformer network (Vaswani et al., 2017) as a backbone network, we design two models: one that orders the parameter points by their likelihood to be selected as candidate parameter points and one that determines the candidate point set among the combinations of high-priority points. Experimental results from a 3-year period of real market S&P500 and KOSPI200 data show that the combination of two models can assist practitioners in the point selection task.

LRVRG: a local region-based variational region growing algorithm for fast mandible segmentation from CBCT images.

To segment the mandible from cone-beam computed tomography (CBCT) images efficiently and accurately for the 3D mandible model is essential for subsequent research and diagnosis. This paper proposes a local region-based variational region growing algorithm, which integrates local region and shape prior to segment the mandible accurately. Firstly, we select initial seeds in the CBCT image and then calculate candidate point sets and the local region energy function of each point. If a point reduces the energy, it is selected to be a pixel of the foreground region. By multiple iterations, the mandible segmentation of the slice can be obtained. Secondly, the segmented result of the previous slice is adopted as the shape prior to the next slice until all of the slices in CBCT are segmented. At last, the final mandible model is reconstructed by the Marching Cubes algorithm. The experimental results on CBCT datasets illustrate the LRVRG algorithm can obtain satisfied 3D mandible models from CBCT images and it can solve the fuzzy problem effectively. Furthermore, quantitative comparisons with other methods demonstrate the proposed method achieves the state-of-the-art performance in mandible segmentation. Experiments demonstrate that our method is efficient and accurate for the mandible model segmentation.

Deployment optimization of wireless mesh networks in wind turbine condition monitoring system

This study aims to propose a deployment optimization method based on IEEE 802.11 heterogeneous wireless mesh networks (WMNs) for the condition monitoring system (CMS) of wind turbines. This method can provide a flexible, low-cost, and easy-to-implement network framework for wind farms in harsh environments, thereby avoiding interference of the newly installed CMS on the communication network of the SCADA system. The K-medoids clustering algorithm transforms the continuous space location problem into the discrete space location problem. Moreover, the mesh client (MC) coverage and backbone network connectivity issues are considered to ensure that the generated candidate point set can meet the coverage and connectivity requirements without generating numerous redundant nodes. Firstly, according to the characteristics of the model, the K-medoids clustering algorithm is used to obtain a set of candidate points of mesh routers (MRs) that meet the coverage rate. Secondly, a reasonable connection algorithm is proposed according to the constraints, and the optimal deployment is selected from the candidate points. Thirdly, taking the number of hops from MR to MG and the priority of MC as the weight. The path planning with the least number of MRs and load balancing is obtained by constructing a minimum spanning tree (MST) based on the improved Kruskal algorithm. Finally, Multi-channel inter-frequency networking technology is adopted to reduce interference between co-channels and between adjacent channels. The result shows that the method proposed can minimize network operating costs, meet the capacity requirements of MC, and reduce link losses.

Optimal design for kernel interpolation: Applications to uncertainty quantification

The paper is concerned with classic kernel interpolation methods, in addition to approximation methods that are augmented by gradient measurements. To apply kernel interpolation using radial basis functions (RBFs) in a stable way, we propose a type of quasi-optimal interpolation points, searching from a large set of candidate points, using a procedure similar to designing Fekete points or power function maximizing points that use pivot from a Cholesky decomposition. The proposed quasi-optimal points results in smaller condition number, and thus mitigates the instability of the interpolation procedure when the number of points becomes large. Applications to parametric uncertainty quantification are presented, and it is shown that the proposed interpolation method can outperform sparse grid methods in many interesting cases. We also demonstrate the new procedure can be applied to constructing gradient-enhanced Gaussian process emulators.

ASAMS: An Adaptive Sequential Sampling and Automatic Model Selection for Artificial Intelligence Surrogate Modeling.

Surrogate Modeling (SM) is often used to reduce the computational burden of time-consuming system simulations. However, continuous advances in Artificial Intelligence (AI) and the spread of embedded sensors have led to the creation of Digital Twins (DT), Design Mining (DM), and Soft Sensors (SS). These methodologies represent a new challenge for the generation of surrogate models since they require the implementation of elaborated artificial intelligence algorithms and minimize the number of physical experiments measured. To reduce the assessment of a physical system, several existing adaptive sequential sampling methodologies have been developed; however, they are limited in most part to the Kriging models and Kriging-model-based Monte Carlo Simulation. In this paper, we integrate a distinct adaptive sampling methodology to an automated machine learning methodology (AutoML) to help in the process of model selection while minimizing the system evaluation and maximizing the system performance for surrogate models based on artificial intelligence algorithms. In each iteration, this framework uses a grid search algorithm to determine the best candidate models and perform a leave-one-out cross-validation to calculate the performance of each sampled point. A Voronoi diagram is applied to partition the sampling region into some local cells, and the Voronoi vertexes are considered as new candidate points. The performance of the sample points is used to estimate the accuracy of the model for a set of candidate points to select those that will improve more the model’s accuracy. Then, the number of candidate models is reduced. Finally, the performance of the framework is tested using two examples to demonstrate the applicability of the proposed method.

Fast Method of Registration for 3D RGB Point Cloud with Improved Four Initial Point Pairs Algorithm.

Three-dimensional (3D) point cloud registration is an important step in three-dimensional (3D) model reconstruction or 3D mapping. Currently, there are many methods for point cloud registration, but these methods are not able to simultaneously solve the problem of both efficiency and precision. We propose a fast method of global registration, which is based on RGB (Red, Green, Blue) value by using the four initial point pairs (FIPP) algorithm. First, the number of different RGB values of points in a dataset are counted and the colors in the target dataset having too few points are discarded by using a color filter. A candidate point set in the source dataset are then generated by comparing the similarity of colors between two datasets with color tolerance, and four point pairs are searched from the two datasets by using an improved FIPP algorithm. Finally, a rigid transformation matrix of global registration is calculated with total least square (TLS) and local registration with the iterative closest point (ICP) algorithm. The proposed method (RGB-FIPP) has been validated with two types of data, and the results show that it can effectively improve the speed of 3D point cloud registration while maintaining high accuracy. The method is suitable for points with RGB values.

Automatic digital ECG signal extraction and normal QRS recognition from real scene ECG images

Background and objectiveElectrocardiogram (ECG) is one of the most important tools for assessing cardiac function and detecting potential heart problems. However, most of the current ECG report records remain on the paper, which makes it difficult to preserve and analyze the data. Moreover, paper records could result in the loss significant data, which brings inconvenience to the subsequent clinical diagnosis or artificial intelligence-assisted heart health diagnosis. Taking digital pictures is an intuitive way of preserving these files and can be done simply using smartphones or any other devices with cameras. However, these real scene ECG images often have some image noise that hinders signal extraction. How to eliminate image noise and extract ECG binary image automatically from the noisy and low-quality real scene images of ECG reports is the first problem to be solved in this paper. Next, QRS recognition is implemented on the extracted binary images to determine key points of ECG signals. 1D digital ECG signal is also extracted for accessing the exact values of the extracted points. In light of these tasks, an automatic digital ECG signal extraction and normal QRS recognition from real scene ECG images is proposed in this paper. MethodsThe normal QRS recognition approach for real scene ECG images in this paper consists of two steps: ECG binary image extraction from ECG images using a new two-layer hierarchical method, and the subsequent QRS recognition based on a novel feature-fusing method. ECG binary image extraction is implemented using sub-channel filters followed by an adaptive filtering algorithm. According to the ratio between pixel and real value of ECG binary image, 1D digital ECG signal is obtained. The normal QRS recognition includes three main steps: establishment of candidate point sets, feature fusion extraction, and QRS recognition. Two datasets are introduced for evaluation including a real scene ECG images dataset and the public Non-Invasive Fetal Electrocardiogram Database (FECG). ResultsThrough the experiment on real scene ECG image, the F1 score for Q, R, S detection is 0.841, 0.992, and 0.891, respectively. The evaluation on the public FECG dataset also proves the robustness of our algorithm, where F1 score for R is 0.992 (0.996 for thoracic lead) and 0.988 for thoracic S wave. ConclusionsThe proposed method in this article is a promising tool for automatically extracting digital ECG signals and detecting QRS complex in real scene ECG images with normal QRS.

Fully-automated tongue detection in ultrasound images

Tracking the tongue in ultrasound images provides information about its shape and kinematics during speech. Current methods for detecting/tracking the tongue require manual initialization or training using large amounts of labeled images. In this article, we propose a solution to convert a semi-automatic tongue contour tracking system to a fully-automatic one. This work introduces a new method for extracting tongue contours in ultrasound images that requires no training nor manual intervention. The method consists in an image enhancement step based on phase symmetry, followed by skeletonization and clustering steps, leading to a set of candidate points that can be used to fit an active contour to the image and subsequently initialize a tracking algorithm. Two novel quality measures were also developed that predict the reliability of the segmentation result so that an image with a reliable contour can be chosen to confidently initialize fully automated tongue tracking. This is achieved by automatically generating and choosing a set of points that can replace the manually segmented points for a semi-automated tracking approach. This paper also improves the accuracy of tracking by incorporating two criteria to reset the tracking algorithm from time to time. Experiments show that fully automated and semi-automated methods result in very similar mean sum of distances errors, respectively, indicating that the proposed automatic initialization does not significantly alter accuracy. Moreover, further results show that tracking accuracy is improved when using the new segmentation technique within the proposed re-initialization scheme.

A filtering technique for fast Convex Hull construction in R2

This work presents an optimization technique that reduces the computational cost for building the Convex Hull from a set of points. The proposed method pre-processes the input set, filtering all points inside an eight-vertex polygon in O(n) time and returns a reduced set of candidate points, ordered and distributed across four priority queues. Experimental results show that for a normal distribution of points in two-dimensional space, the filtering approach in conjunction with the Graham scan is up to 10× faster than the qhull library, and between 1.7× to 10× faster than the Convex Hull methods available in the CGAL library. Results on the worst case scenario (when all points lie in the circumference) show that a slight random radial displacement of the points make this method the fastest one. Moreover, when increasing the magnitude of this displacement, the performance of the proposed method scales at a faster rate than the other methods. In terms of memory efficiency, the proposed implementation manages to use from 3× to 6× less memory than the other methods. The reason behind this memory improvement is because the proposed method stores indices of the input arrays, avoiding duplicates of the original floating points. Furthermore, the approach extends the problem size up to n≤240 by employing 5-byte indices (instead of 8-bytes) when n≥232. The optimization technique presented in this work has shown to be significantly useful in accelerating the computation of the Convex Hull, and it is not limited just to the combination with the Graham scan, but it can also be used in conjunction with other Convex Hull algorithms.

AUTOMATIC DETECTION AND CHARACTERISATION OF POWER LINES AND THEIR SURROUNDINGS USING LIDAR DATA

Abstract. Light Detection and Ranging (LiDAR) is nowadays one of the most used tools to obtain geospatial data. In this paper, a method to detect and characterise power lines of both high and low voltage and their surroundings from 3D LiDAR point clouds exclusively is proposed. First, to identify points of the power lines a global search of candidate points is carried out based on the height of each point compared to its neighbours. Then, the Hough Transform (HT) is applied on the set of candidate points to extract the catenaries that belong to each power line, allowing the identification of each conductor individually. Finally, conductors located on the same power line are grouped, their geometric characteristics analysed, and the quantitative features of the surroundings are computed. A very high accuracy of power line classification is reached with these methods, while the computational time is optimised by efficient memory usage and parallel implementation of the code.