Distance Transform Research Articles

Joint embedding in Hierarchical distance and semantic representation learning for link prediction

The link prediction task aims to predict missing entities or relations in the knowledge graph and is essential for the downstream application. Existing well-known models deal with this task by mainly focusing on representing knowledge graph triplets in the distance space or semantic space. However, they can not fully capture the information of head and tail entities, nor even make good use of hierarchical level information. Thus, in this paper, we propose a novel knowledge graph embedding model for the link prediction task, namely, HIE, which models each triplet (h, r, t) into distance measurement space and semantic measurement space, simultaneously. Moreover, HIE is introduced into hierarchical-aware space to leverage rich hierarchical information of entities and relations for better representation learning. Specifically, we apply distance transformation operation on the head entity in distance space to obtain the tail entity instead of translation-based or rotation-based approaches. Experimental results of HIE on four real-world datasets show that HIE outperforms several existing state-of-the-art knowledge graph embedding methods on the link prediction task and deals with complex relations accurately.

A Distance Transformation Deep Forest Framework With Hybrid-Feature Fusion for CXR Image Classification.

Detecting pneumonia, especially coronavirus disease 2019 (COVID-19), from chest X-ray (CXR) images is one of the most effective ways for disease diagnosis and patient triage. The application of deep neural networks (DNNs) for CXR image classification is limited due to the small sample size of the well-curated data. To tackle this problem, this article proposes a distance transformation-based deep forest framework with hybrid-feature fusion (DTDF-HFF) for accurate CXR image classification. In our proposed method, hybrid features of CXR images are extracted in two ways: hand-crafted feature extraction and multigrained scanning. Different types of features are fed into different classifiers in the same layer of the deep forest (DF), and the prediction vector obtained at each layer is transformed to form distance vector based on a self-adaptive scheme. The distance vectors obtained by different classifiers are fused and concatenated with the original features, then input into the corresponding classifier at the next layer. The cascade grows until DTDF-HFF can no longer gain benefits from the new layer. We compare the proposed method with other methods on the public CXR datasets, and the experimental results show that the proposed method can achieve state-of-the art (SOTA) performance. The code will be made publicly available at https://github.com/hongqq/DTDF-HFF.

A bi-directional distance transformation for the elimination of near-singularity in boundary element method

PurposeIn traditional methods, a one-directional distance transformation is employed to eliminate the near-singularity in the radial direction. However, when the projection point of the source point is near the boundary of the integral element, the near-singularity in the circumferential direction still exists, resulting in large errors in the numerical results. The purpose of this paper is to propose a bi-directional distance transformation for the elimination of near-singularities in two directions arising from the irregular integral element.Design/methodology/approachThe sources of the circumferential near-singularity caused by irregular sub-triangular element are analyzed in this paper. A bi-directional distance transformation based on the (a, β) transformation is proposed to eliminate the near-singularities in the two directions. The (a, β) transformation is initially introduced to separate the integral variables and streamline the implementation of subsequent transformations. In the transformed (a, β) coordinate system, a new distance transformation applied in the circumferential direction is constructed.FindingsWith the proposed method, the radial and circumferential near-singularities are eliminated using two different distance transformations, respectively. Thus, accurate calculations of the nearly singular integrals can be achieved, irrespective of the shape of the integral element.Originality/valueNumerical examples are presented to calculate the nearly singular integrals of different orders over both the linear integral element and the quadratic integral element. Comparative studies demonstrate that the proposed method significantly improves the accuracy of these calculations.

LettuceNet: A Novel Deep Learning Approach for Efficient Lettuce Localization and Counting

Traditional lettuce counting relies heavily on manual labor, which is laborious and time-consuming. In this study, a simple and efficient method for localization and counting lettuce is proposed, based only on lettuce field images acquired by an unmanned aerial vehicle (UAV) equipped with an RGB camera. In this method, a new lettuce counting model based on the weak supervised deep learning (DL) approach is developed, called LettuceNet. The LettuceNet network adopts a more lightweight design that relies only on point-level labeled images to train and accurately predict the number and location information of high-density lettuce (i.e., clusters of lettuce with small planting spacing, high leaf overlap, and unclear boundaries between adjacent plants). The proposed LettuceNet is thoroughly assessed in terms of localization and counting accuracy, model efficiency, and generalizability using the Shanghai Academy of Agricultural Sciences-Lettuce (SAAS-L) and the Global Wheat Head Detection (GWHD) datasets. The results demonstrate that LettuceNet achieves superior counting accuracy, localization, and efficiency when employing the enhanced MobileNetV2 as the backbone network. Specifically, the counting accuracy metrics, including mean absolute error (MAE), root mean square error (RMSE), normalized root mean square error (nRMSE), and coefficient of determination (R2), reach 2.4486, 4.0247, 0.0276, and 0.9933, respectively, and the F-Score for localization accuracy is an impressive 0.9791. Moreover, the LettuceNet is compared with other existing widely used plant counting methods including Multi-Column Convolutional Neural Network (MCNN), Dilated Convolutional Neural Networks (CSRNets), Scale Aggregation Network (SANet), TasselNet Version 2 (TasselNetV2), and Focal Inverse Distance Transform Maps (FIDTM). The results indicate that our proposed LettuceNet performs the best among all evaluated merits, with 13.27% higher R2 and 72.83% lower nRMSE compared to the second most accurate SANet in terms of counting accuracy. In summary, the proposed LettuceNet has demonstrated great performance in the tasks of localization and counting of high-density lettuce, showing great potential for field application.

Numerical Computation of 2D Domain Integrals in Boundary Element Method by (α, β) Distance Transformation for Transient Heat Conduction Problems

When the time-dependent boundary element method, also termed the pseudo-initial condition method, is employed for solving transient heat conduction problems, the numerical evaluation of domain integrals is necessitated. Consequently, the accurate calculation of the domain integrals is of crucial importance for analyzing transient heat conduction. However, as the time step decreases progressively and approaches zero, the integrand of the domain integrals is close to singular, resulting in large errors when employing standard Gaussian quadrature directly. To solve the problem and further improve the calculation accuracy of the domain integrals, an (α, β) distance transformation is presented. Distance transformation is a simple and efficient method for eliminating near-singularity, typically applied to nearly singular integrals. Firstly, the (α, β) coordinate transformation is introduced. Then, a new distance transformation for the domain integrals is constructed by replacing the shortest distance with the time step. With the new method, the integrand of the domain integrals is substantially smoothed, and the singularity arising from small time steps in the domain integrals is effectively eliminated. Thus, more accurate results can be obtained by the (α, β) distance transformation. Different sizes of time steps, positions of source point, and shapes of integration elements are considered in numerical examples. Comparative studies of the numerical results for the domain integrals using various methods demonstrate that higher accuracy and efficiency are achieved by the proposed method.

Factor mismatch measurement of resource-based cities: Evidence from all-round optimization total factor productivity decomposition framework

In-depth analysis of the factors affecting the transformation of resource-based cities can provide effective support for the transformation and development of resource-dependent regions. How to comprehensively identify the factors affecting the transformation of resource-based cities is a complex problem. This study starts from the total factor productivity model and focuses on the two core basic factors that affect the transformation process of cities reliant on resources. Economic benefits and energy efficiency, respectively, from the economic benefit analysis framework and energy efficiency analysis framework for reconstruction, the two frameworks are combined with the use of distorted prices of resource elements to solve the problem that the synergistic effect of economic benefits and energy efficiency can not be measured. In order to quantitatively analyze the factors that affect the development efficiency of cities reliant on resources under the single or synergistic effect of the comprehensive framework, this study optimizes the directional distance function from three perspectives: exogenous weight, direction vector endogeneity, and absolute distance transformation relative distance, thus achieving an accurate assessment transformation efficiency of cities reliant on resources. Considering the impact of the new coronavirus epidemic, this study only selected the data of resource-based cities from 2003 to 2018, and found through model calculation that the impact on the transformation of cities reliant on resources: (1) Labor mismatch is mainly achieved by affecting the structure about the production of resource-based enterprises and industrial human resources; (2) Capital mismatch is mainly realized by affecting the production of resource-based enterprises; (3) Energy mismatch is mainly achieved by affecting high energy consumption enterprises and low production technology level enterprises. Further research shows that the main objects of these factors are the four parts of production technology level, energy consumption, total factor productivity and industrial structure. Through these contents, they affect environmental efficiency and deeply affect the transformation process of resource-based cities.

RectanglingGAN: Deep rectangling for stitched image via image inpainting

The deep rectangling task aims to transform edge-irregular stitched images into standardised rectangular formats using deep learning. Existing deep rectangling solutions rely on mesh-based segmentation and deformation, which introduce global distortions detrimental to subsequent analysis and processing. Therefore, we propose RectanglingGAN to handle missing regions in a distortion-free manner via image inpainting. Unlike generic inpainting models, RectanglingGAN focuses on preserving the quality of edge regions. In particular, we present an adaptive distance transform module to improve the attention of the feature maps to the mask boundaries. The module dynamically selects the appropriate distance transformation scheme according to the image content. Moreover, we introduce the distance-weighted decaying reconstruction loss into the pixel-wise reconstruction, which introduces the spatial location information between the inpainting pixels and the mask boundaries by inverting the distance-transformed mask. By incorporating this loss, the model pays more attention to the quality of generation pixels far from the mask boundary. Extensive experiments validate the effectiveness of RectanglingGAN compared to state-of-the-art methods, highlighting its significant advantages in terms of both the quality and the fidelity of the edge region in generation images.

Weed Detection and Classification with Computer Vision Using a Limited Image Dataset

In agriculture, as precision farming increasingly employs robots to monitor crops, the use of weeding and harvesting robots is expanding the need for computer vision. Currently, most researchers and companies address these computer vision tasks with CNN-based deep learning. This technology requires large datasets of plant and weed images labeled by experts, as well as substantial computational resources. However, traditional feature-based approaches to computer vision can extract meaningful parameters and achieve comparably good classification results with only a tenth of the dataset size. This study presents these methods and seeks to determine the minimum number of training images required to achieve reliable classification. We tested the classification results with 5, 10, 20, 40, 80, and 160 images per weed type in a four-class classification system. We extracted shape features, distance transformation features, color histograms, and texture features. Each type of feature was tested individually and in various combinations to determine the best results. Using six types of classifiers, we achieved a 94.56% recall rate with 160 images per weed. Better results were obtained with more training images and a greater variety of features.

An edge feature-based external calibration of monocular camera and LiDAR using in-orbit data

Multimodal perception represents a vital approach for observing non-cooperative targets in space. The accurate determination of the extrinsic parameters for monocular camera and LiDAR systems serves as the cornerstone for achieving effective space multimodal perception. However, due to factors like launch and operation, these extrinsic parameters can experience drift, thereby compromising the overall performance of the multimodal perception system. To tackle this challenge, this study introduces a novel approach: an edge feature-based external calibration method for monocular camera and LiDAR using in-orbit data. The proposed methodology involves several steps. Firstly, edges are extracted from the image, followed by distance transformation based on the edge image. The subsequent integration of the edge image and distance image yields the search scene image. Then, edge feature is extracted from the point cloud data. Finally, after constructing the objective function, genetic algorithms are used to determine precise external parameters. Simulation results underscore the effectiveness of the proposed algorithm, affirming its ability to achieve high-precision calibration results for external parameters even within intricate spatial environments.

Label-Decoupled Medical Image Segmentation With Spatial-Channel Graph Convolution and Dual Attention Enhancement.

Deep learning-based methods have been widely used in medical image segmentation recently. However, existing works are usually difficult to simultaneously capture global long-range information from images and topological correlations among feature maps. Further, medical images often suffer from blurred target edges. Accordingly, this paper proposes a novel medical image segmentation framework named a label-decoupled network with spatial-channel graph convolution and dual attention enhancement mechanism (LADENet for short). It constructs learnable adjacency matrices and utilizes graph convolutions to effectively capture global long-range information on spatial locations and topological dependencies between different channels in an image. Then a label-decoupled strategy based on distance transformation is introduced to decouple an original segmentation label into a body label and an edge label for supervising the body branch and edge branch. Again, a dual attention enhancement mechanism, designing a body attention block in the body branch and an edge attention block in the edge branch, is built to promote the learning ability of spatial region and boundary features. Besides, a feature interactor is devised to fully consider the information interaction between the body and edge branches to improve segmentation performance. Experiments on benchmark datasets reveal the superiority of LADENet compared to state-of-the-art approaches.

A Deep Vision Sensing-Based Smart Control Method for Apple-Picking Robots Under the Context of Agricultural E-Commerce

The growing development of the agricultural e-commerce industry is promoting the Digital transformation of agricultural production and logistics. Aiming at the problem of labor shortage in apple picking, this paper proposes a performance control method for robot apple picking based on a nonlinear wide convolutional neural network (NLWCNN) and multi-objective cooperative distance transformation algorithm (MOCDTA). This method utilizes deep learning algorithms and visual sensing technology to enable robots to accurately recognize apples and perform autonomous picking operations based on their maturity and position. We have designed a machine learning-based algorithm that enables robots to accurately recognize and distinguish apples of different maturity levels through training on a large amount of sample data. At the same time, we also combined the motion control algorithm of the robot to enable efficient picking operations based on the position and maturity information of the apples. The experimental results indicate that the NLWCNN method can significantly improve the efficiency and accuracy of apple picking, ensure the safety and traceability of agricultural products, increase consumer trust, and promote agricultural product transactions.

PaVa: A novel path-based valley-seeking clustering algorithm

Clustering methods are being applied to a wider range of scenarios involving more complex datasets, where the shapes of clusters tend to be arbitrary. In this paper, we propose a novel Path-based Valley-seeking clustering algorithm for arbitrarily shaped clusters. This work aims to seek the valleys among clusters and then individually extract clusters. Three vital techniques are used in this algorithm. First, path distance (minmax distance) is employed to transform the irregular boundaries among clusters, that is density valleys, into perfect spherical shells. Second, a suitable density measurement, k-distance, is employed to make adjustment on Minimum Spanning Tree, by which a robust minmax distance is calculated. Third, we seek the transformed density valleys by determining their centers and radii. Based on the vital techniques, the main contributions of the proposed algorithm can be summarized as follows. First, the clusters are wrapped in spherical shells after the distance transformation, making the extraction process efficient even with clusters of arbitrary shape. Second, adjusted Minimum Spanning Tree enhances the robustness of minmax distance under different kinds of noise. Last, the number of clusters does not need to be inputted or decided manually due to the individual extraction process. After applying the proposed algorithm to several commonly used synthetic datasets, the results indicate that the Path-based Valley-seeking algorithm is accurate and efficient. The algorithm is based on the dissimilarity of objects, so it can be applied to a wide range of fields. Its performance on real-world datasets illustrates its versatility.

A new distance transformation method of estimating domain integrals directly in boundary integral equation for transient heat conduction problems

Accurate estimation of domain integrals is of crucial importance for the pseudo-initial condition method applied in transient heat conduction analysis. When small time step is used, the integrand of the domain integral changes dramatically and is close to singular. A straightforward evaluation of the domain integrals using Gaussian quadrature may produce large errors. To improve the computational accuracy of two-dimensional domain integrals in boundary integral equation, a new distance transformation method is presented in this paper. The proposed method takes the time step as the transformation parameter, implementing the new transformation in the radial direction directly. With the new distance transformation method, the integrand of the domain integral can be smoother, thus more accurate results can be obtained. Numerical examples have demonstrated the efficiency and accuracy of the proposed method.

DoseDiff: Distance-Aware Diffusion Model for Dose Prediction in Radiotherapy.

Treatment planning, which is a critical component of the radiotherapy workflow, is typically carried out by a medical physicist in a time-consuming trial-and-error manner. Previous studies have proposed knowledge-based or deep-learning-based methods for predicting dose distribution maps to assist medical physicists in improving the efficiency of treatment planning. However, these dose prediction methods usually fail to effectively utilize distance information between surrounding tissues and targets or organs-at-risk (OARs). Moreover, they are poor at maintaining the distribution characteristics of ray paths in the predicted dose distribution maps, resulting in a loss of valuable information. In this paper, we propose a distance-aware diffusion model (DoseDiff) for precise prediction of dose distribution. We define dose prediction as a sequence of denoising steps, wherein the predicted dose distribution map is generated with the conditions of the computed tomography (CT) image and signed distance maps (SDMs). The SDMs are obtained by distance transformation from the masks of targets or OARs, which provide the distance from each pixel in the image to the outline of the targets or OARs. We further propose a multi-encoder and multi-scale fusion network (MMFNet) that incorporates multi-scale and transformer-based fusion modules to enhance information fusion between the CT image and SDMs at the feature level. We evaluate our model on two in-house datasets and a public dataset, respectively. The results demonstrate that our DoseDiff method outperforms state-of-the-art dose prediction methods in terms of both quantitative performance and visual quality.

GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform

GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform

Incremental Distance Transform for Online Motion Planning based on Combined Wavefront

Incremental Distance Transform for Online Motion Planning based on Combined Wavefront

Deep Learning-Based Microscopic Cell Detection using Inverse Distance Transform and Auxiliary Counting.

Microscopic cell detection is a challenging task due to significant inter-cell occlusions in dense clusters and diverse cell morphologies. This paper introduces a novel framework designed to enhance automated cell detection. The proposed approach integrates a deep learning model that produces an inverse distance transform-based detection map from the given image, accompanied by a secondary network designed to regress a cell density map from the same input. The inverse distance transform-based map effectively highlights each cell instance in the densely populated areas, while the density map accurately estimates the total cell count in the image. Then, a custom counting-aided cell center extraction strategy leverages the cell count obtained by integrating over the density map to refine the detection process, significantly reducing false responses and thereby boosting overall accuracy. The proposed framework demonstrated superior performance with F-scores of 96.93%, 91.21%, and 92.00% on the VGG, MBM, and ADI datasets, respectively, surpassing existing state-of-the-art methods. It also achieved the lowest distance error, further validating the effectiveness of the proposed approach. These results demonstrate significant potential for automated cell analysis in biomedical applications.

Panoptic Segmentation with Convex Object Representation

Abstract The accurate representation of objects holds pivotal significance in the realm of panoptic segmentation. Presently, prevalent object representation methodologies, including box-based, keypoint-based and query-based techniques, encounter a challenge known as the ‘representation confusion’ issue in specific scenarios, often resulting in the mislabeling of instances. In response, this paper introduces Convex Object Representation (COR), a straightforward yet highly effective approach to address this problem. COR leverages a CNN-based Euclidean Distance Transform to convert the target instance into a convex heatmap. Simultaneously, it offers a parallel embedding method for encoding the object. Subsequently, COR characterizes objects based on the distinctive embedding vectors of their convex vertices. This paper seamlessly integrates COR into a state-of-the-art query-based panoptic segmentation framework. Experimental findings validate that COR successfully mitigates the representation confusion predicament, enhancing segmentation accuracy. The COR-augmented methods exhibit notable improvements of +1.3 and +0.7 points in PQ on the Cityscapes validation and MS COCO panoptic 2017 validation datasets, respectively.

Relational Reprojection Platform: Non-linear distance transformations of spatial data in R

When mapping relationships across multiple spatial scales, prevailing visualization techniques treat every mile of distance equally, which may not be appropriate for studying phenomena with long-tail distributions of distances from a common point of reference (e.g., retail customer locations, remittance flows, and migration data). While quantitative geography has long acknowledged that non-Cartesian spaces and distances are often more appropriate for analyzing and visualizing real-world data and complex spatial phenomena, commonly available GIS software solutions make working with non-linear distances extremely difficult. Our Relational Reprojection Platform (RRP) fills this gap with a simple stereographic projection engine centering any given data point to the rest of the set, and transforming great circle distances from this point to the other locations using a set of broadly applicable non-linear functions as options. This method of reprojecting data allows users to quickly and easily explore how non-linear distance transformations (including square root and logarithmic reprojections) reveal more complex spatial patterns within datasets than standard projections allow. Our initial release allows users to upload comma separated value (CSV) files with geographic coordinates and data columns and minimal cleaning and explore a variety of spatial transformations of their data. We hope this heuristic tool will enhance the exploratory stages of social research using spatial data.

A deep learning-based automated algorithm for labeling coronary arteries in computed tomography angiography images

ObjectiveUsing two three-dimensional U-Net architectures for myocardium structure extraction and a distance transformation algorithm specifically for the left circumflex artery, we have designed a fully automated algorithm for coronary artery labeling in coronary computed tomography angiography (CCTA) images.MethodsIn this retrospective analysis, a cohort of 157 patients who had undergone coronary computed tomography angiography (CCTA) was included. An automated coronary artery labeling algorithm was developed using a distance transformation approach to delineate the anatomical segments along the centerlines extracted from the CCTA images. A total of 16 segments were successfully identified and labeled. The algorithm’s outcomes were recorded and reviewed by three experts, and the performance of segment detection and labeling was assessed. Additionally, the level of agreement in manually labeled segments between two experts was quantified.ResultsWhen comparing the labels generated by the experts with those produced by the algorithm, it was necessary to modify or eliminate 117 labels (5.4%) out of 2180 segments assigned by the algorithm. The overall accuracy for label presence was 96.2%, with an average overlap of 94.0% between the expert reference and algorithm-generated labels. Furthermore, the average agreement rate between the two experts stood at 95.0%.ConclusionsBased on the labels of the clinical experts, the proposed deep learning algorithm exhibits high accuracy for automatic labeling. Therefore, our proposed method exhibits promising results for the automatic labeling of the coronary arteries and will alleviate the burden on radiologists in the near future.