Centerline Extraction Method Research Articles

Automated Coronary Artery Tracking with a Voronoi-Based 3D Centerline Extraction Algorithm.

Coronary artery disease is one of the leading causes of death worldwide, and medical imaging methods such as coronary artery computed tomography are vitally important in its detection. More recently, various computational approaches have been proposed to automatically extract important artery coronary features (e.g., vessel centerlines, cross-sectional areas along vessel branches, etc.) that may ultimately be able to assist with more accurate and timely diagnoses. The current study therefore validated and benchmarked a recently developed automated 3D centerline extraction method for coronary artery centerline tracking using synthetically segmented coronary artery models based on the widely used Rotterdam Coronary Artery Algorithm Evaluation Framework (RCAAEF) training dataset. Based on standard accuracy metrics and the ground truth centerlines of all 32 coronary vessel branches in the RCAAEF training dataset, this 3D divide and conquer Voronoi diagram method performed exceptionally well, achieving an average overlap accuracy (OV) of 99.97%, overlap until first error (OF) of 100%, overlap of the clinically relevant portion of the vessel (OT) of 99.98%, and an average error distance inside the vessels (AI) of only 0.13 mm. Accuracy was also found to be exceptionally for all four coronary artery sub-types, with average OV values of 99.99% for right coronary arteries, 100% for left anterior descending arteries, 99.96% for left circumflex arteries, and 100% for large side-branch vessels. These results validate that the proposed method can be employed to quickly, accurately, and automatically extract 3D centerlines from segmented coronary arteries, and indicate that it is likely worthy of further exploration given the importance of this topic.

A robust and accurate centerline extraction method of multiple laser stripe for complex 3D measurement

Multiple laser stripe measurement (MLSM) is a vital technique in optical three-dimensional (3D) measurement. The accurate extraction of the laser stripe centerlines plays a decisive role in achieving high measurement accuracy. However, complex 3D measurement scenarios pose challenges due to various interferences, such as optical interference caused by dense stripes and no-ideal distribution caused by non-uniform reflectivity. To address these challenges, we propose an adaptive step size gradient centerline extraction method based on an 2D linear filter. This method incorporates local adaptive variable parameters for fine-tuning while utilizing global parameters. We validate its performance by conducting comprehensive comparative experiments with two commonly used methods. The results demonstrate that our proposed method enables more precise centerline extraction, exhibits enhanced stability, and yields lower measurement errors in complex 3D measurement conditions and highlight the effectiveness and superior performance of our method.

A Space-Refine Paradigm for Automatic Carotid Artery Centerline Extraction in Magnetic Resonance Imaging.

Vessel centerline extraction is essential for carotid stenosis assessment and atherosclerotic plaque identification in clinical diagnosis. Simultaneously, it provides a region of interest identification and boundary initialization for computer-assisted diagnosis tools. In magnetic resonance imaging (MRI) cross-sectional images, the lumen shape and vascular topology result in a challenging task to extract the centerline accurately. To this end, we propose a space-refine framework, which exploits the positional continuity of the carotid artery from frame to frame to extract the carotid artery centerline. The proposed framework consists of a detector and a refinement module. Specifically, the detector roughly extracts the carotid lumen region from the original image. Then, we introduce a refinement module that uses the cascade of regressors from a detector to perform sequence realignment of lumen bounding boxes for each subject. It improves the lumen localization results and further enhances the centerline extraction accuracy. Verified by large carotid artery data, the proposed framework achieves state-of-the-art performance compared to conventional vessel centerline extraction methods or standard convolutional neural network approaches.Clinical relevance- Our proposed framework can be used as an important aid for physicians to quantitatively analyze the carotid artery in clinical practice. It is also used as a new paradigm for extracting the centerline of carotid vessels in computer-assisted tools.

A method of laser stripe centerline extraction based on deep learning for structured light 3D reconstruction

To overcome the stray light noise in the centerline extraction method during line structured light 3D reconstruction process, an end-to-end trainable neural network for laser stripe centerline extraction based on Convolutional Neural Network and Multi-Layer Perception is proposed. The proposed network can self-adapt to a variety of lighting (brightness) conditions and overcome the interference of different stray lights. In addition, unlike prior work on enhancing the accuracy of centerline extraction using deep learning methods that only performs it for noise reduction in pre-processing, the proposed network unifies the noise reduction and prediction processes, so that it can be optimized end-to-end directly on centerline extraction performance. The network learns an intermediate feature representation of noise reduction, which requires less complexity for data annotation, reduces the training difficulty, and has more scalability. Experiments show that the proposed method can perform centerline extraction with relatively high accuracy for laser stripes of different widths, brightness, and inclination, thus obtaining a smooth and stable reconstructed surface in the structured light 3D reconstruction process.

Road extraction from low-cost GNSS-device dense trajectories

ABSTRACT This paper proposes a method for road centerline extraction from dense Global Navigation Satellite System (GNSS) trajectories, collected by using low-cost GNSS-devices, i.e. smartphones. The proposed method basically consists in generating a frequency image by tracking the GNSS trajectories and then by applying the Steger line detector to the generated image to extract the road centerlines. The main motivation of using the Steger algorithm is its capability to detect lines with sub-pixel accuracy. To evaluate the obtained results, reference road centerlines are manually extracted from a georeferenced orthomosaic. The experiments performed demonstrate the high potential of applying the Steger line detector to frequency images, generated by using dense GPS (Global Positioning System) trajectories. The completeness and correctness values for the accomplished experiments were 98% and 99%, respectively. Additionally, the RMSE (Root Mean Square Error) ranged from 0.63 m to 2.39 m, or approximately 1/16 to 1/4 of the expected accuracy (about 10 m) of a point determined by the Single-Point Positioning (SPP) method, which is the GNSS positioning method usually employed by smartphones.

Prior skeleton based online deep reinforcement learning for coronary artery centerline extraction.

Coronary centerline extraction is an essential technique for X-ray coronary angiography (XCA) image analysis, which provides qualitative and quantitative guidance for percutaneous coronary intervention (PCI). In this paper, an online deep reinforcement learning method for coronary centerline extraction is proposed based on the prior vascular skeleton. Firstly, with XCA image preprocessing (foreground extraction and vessel segmentation) results, the improved ZhangSuen image thinning algorithm is used to rapidly extract the preliminary vascular skeleton network. On this basis, according to the spatial-temporal and morphological continuity of the angiography image sequence, the connectivity of different branches is determined using k-means clustering, and the vessel segments are then grouped, screened, and reconnected to obtain the aorta and its major branches. Finally, using the previous results as prior information, an online Deep Q-Network (DQN) reinforcement learning method is proposed to optimize each branch simultaneously. It comprehensively considers grayscale intensity and eigenvector continuity to achieve the combination of data-driven and model-driven without pre-training. Experimental results on clinical images and the third-party dataset demonstrate that the proposed method can accurately extract, restructure, and optimize the centerline of XCA images with a higher overall accuracy than the existing state-of-the-art methods.

Laser center-line extraction method based on normal guidance

在线结构光三维测量系统中，高精度激光条纹中心线提取是提高测量精度的关键。针对现有激光中心线存在提取精度不高、保留细节差等问题，提出了一种基于法线引导的激光中心线提取算法。该算法具体实现步骤为：首先，对图像进行预处理，结合边缘检测和几何中心法对激光线初步提取；然后，用主成分分析法( principal component analysis，PCA)求取其法线，在激光中心点处划分角度八邻域，通过法线角度引导搜寻有效点集；最后，利用灰度重心法对点集进行亚像素提取。实验结果表明：该算法均方根误差与灰度重心法相比提高了0.2339 像素，比Steger算法、方向模板法更好地保留了光条细节，可以更精确地提取光条中心，达到亚像素级的精度。

A novel centerline extraction method for overlapping fish body length measurement in aquaculture images

Information on the length of cultured fish is crucial to evaluate their growth status and biomass. However, existing methods to estimate fish body length are based primarily on manual sampling, which is invasive, time-consuming, and labor-intensive. In contrast, such information can be acquired via noncontact methods relying on images of the animals’ centerlines in an image. The centerline extraction method has been widely applied as an efficient approach. However, the greatest challenge in measuring the length of cultured fish is that of accurately extracting the animals’ centerlines when fish overlap in an image. To address this problem, we propose a method to obtain the centerlines of overlapping fish by processing images captured from a top-view perspective. First, fish contours are segmented using convex-concave points. Second, the contour segmentations belonging to each fish are identified by an algorithm that matches heads to tails; their centerlines are thus extracted and optimized. We conducted both laboratory and on-site experiments, and results show that the proposed method exhibited excellent performance in extracting fish centerline information, even for fish that overlapped in images captured from a top view. Moreover, it also improved on the performance of existing methods in measuring the length of cultured fish from such images.

X-ray coronary centerline extraction based on C-UNet and a multifactor reconnection algorithm

Background and objective: Accurate extraction of the coronary artery centerline is crucial in the processes of coronary artery reconstruction, coronary artery stenosis or lesion detection, and surgical navigation. Furthermore, in clinical medicine, the complex background of angiography, low signal-to-noise ratio, and complex vascular structure make coronary artery centerline extraction challenging. In this study, a direct centerline extraction method is proposed that automatically and accurately extracts vascular centerlines from X-ray coronary angiography images based on deep learning and conventional methods.Methods: In this study, a coronary artery centerline extraction method is proposed that comprises two parts: the preliminary centerline extraction network based on U-Net with a residual network, called C-UNet, and the multifactor centerline reconnection algorithm based on the geometric characteristics of blood vessels.Results: The qualitative and quantitative results demonstrate the effectiveness of the presented method. In this study, three widely used evaluation indices were adopted to evaluate the performance of the method: precision, recall, and F1_Score. The experimental results show that this method can accurately extract coronary artery centerlines.Conclusions: The proposed centerline extraction method accurately extracts centerlines from X-ray coronary angiography images and improves both the accuracy and continuity of centerline extraction.

A 3D Tubular Flux Model for Centerline Extraction in Neuron Volumetric Images.

Digital morphology reconstruction from neuron volumetric images is essential for computational neuroscience. The centerline of the axonal and dendritic tree provides an effective shape representation and serves as a basis for further neuron reconstruction. However, it is still a challenge to directly extract the accurate centerline from the complex neuron structure with poor image quality. In this paper, we propose a neuron centerline extraction method based on a 3D tubular flux model via a two-stage CNN framework. In the first stage, a 3D CNN is used to learn the latent neuron structure features, namely flux features, from neuron images. In the second stage, a light-weight U-Net takes the learned flux features as input to extract the centerline with a spatial weighted average strategy to constrain the multi-voxel width response. Specifically, the labels of flux features in the first stage are generated by the 3D tubular model which calculates the geometric representations of the flux between each voxel in the tubular region and the nearest point on the centerline ground truth. Compared with self-learned features by networks, flux features, as a kind of prior knowledge, explicitly take advantage of the contextual distance and direction distribution information around the centerline, which is beneficial for the precise centerline extraction. Experiments on two challenging datasets demonstrate that the proposed method outperforms other state-of-the-art methods by 18% and 35.1% in F1-measurement and average distance scores at the most, and the extracted centerline is helpful to improve the neuron reconstruction performance.

A Voronoi-Diagram-based method for centerline extraction in 3D industrial line-laser reconstruction using a graph-centrality-based pruning algorithm

Three-dimensional (3D) line-laser scanning is a widely used 3D reconstruction technique in the industry. As a key procedure of 3D line-laser scanning, centerline extraction of laser stripes directly determines the accuracy of reconstructed 3D models. Because of the noise inside laser stripes, centerline extraction methods based on the gray distribution may provide biased results. In order to address this problem, a Voronoi-diagram-based method (VM) for centerline extraction, which can extract centerlines accurately under severe noises, is proposed. To solve the emerging problems when the Voronoi diagram is applied to line-laser stripes, a fast pruning algorithm based on the distribution of graph centrality is proposed, and two centerline extension algorithms based on least square fitting are developed. The experiments are performed on synthetic images and a line-laser 3D scanner to evaluate the method’s accuracy, robustness, and efficiency. The VM method is proved to have better accuracy and robustness than the traditional method. Simulation experiments show that the VM can extract centerlines from noisy images with an average accuracy of 0.35 pixels. Also, 3D reconstruction experiments of a Φ20-mm standard sphere demonstrate an average accuracy of 0.0282 mm. With four-thread acceleration, the proposed method can process images with a resolution of 2448 × 2048 pixels in 0.5 s. The accuracy and speed of the proposed method can be adjusted by changing the parameter related to the density of contour points, which makes this method flexible and widely applicable in applications with different requirements.

A General Spline-Based Method for Centerline Extraction from Different Segmented Road Maps in Remote Sensing Imagery

Road centerline extraction is the foundation for integrating the segmented road map from a remote sensing image into a geographic information system (GIS) database. Considering that existing approaches tend to have a decline in performance for centerline and junction extraction when segmented road structures are irregular, this paper proposes a novel method which models the road network as a sequence of connected spline curves. Based on this motivation, the ratio of cross operators is firstly proposed to detect direction and width features of roads. Then, road pixels are divided into different clusters by local features using three perceptual grouping principles (i.e., direction grouping, proximity grouping, and continuity grouping). After applying a polynomial curve fitting on each cluster using pixel coordinates as observation data, the internal control points are determined according to the adjacency relation between clusters. Finally, road centerlines are generated based on spline fitting with constraints. We test our approach on segmented road maps which were obtained previously by machine recognition, or manual extraction from real optical (WorldView-2) and synthetic aperture radar (TerraSAR-X, Radarsat-2) images. Depending on the accuracy of the input segmented road maps, experimental results from our test data show that both the completeness and correctness of extracted centerlines are over 84% and 68% for optical and radar images, respectively. Furthermore, experiments also demonstrate the advantages of our proposed method, in contrast to existing methods for gaining smooth centerlines and precise junctions.

A welding seam positioning method based on polarization 3D reconstruction and linear structured light imaging

Aiming at the current welding seam tracking problems such as susceptibility to arc light interference, low work efficiency, and poor real-time performance, a single-frame large-field welding seam positioning method combining polarization three-dimensional (3D) reconstruction and linear structured light imaging is proposed. Calculate the surface polarization state of the welding area through the polarization intensity images in four directions, use the degree of polarization and polarization angle to calculate the surface normal vector and integrate to obtain the relative depth value. Design a centerline extraction method based on skeleton extraction and Random Sample Consensus (RANSAC) to obtain the three-dimensional coordinates of the laser stripe. The three-dimensional coordinates of the laser fringe and the relative depth value of the polarization three-dimensional reconstruction are combined to calculate the real three-dimensional point cloud of the weld and the welded part. With this method, only a single frame of image data is acquired prior to welding and the coordinates of the 3D scene within the large field of view of the polarisation camera can be calculated, so there is no interference from arc light. For the weld within 100 mm, the 3D positioning accuracy is 0.2502 mm, which meets the requirements of weld positioning.

Line structured light calibration method and centerline extraction: A review

Line structured light system has made rapid progress in recent years owing to the improvement of camera resolution and image processing technology. The calibration of line structured light system and centerline extraction affect the imaging quality. Hence, numerous innovations have occurred in both line structured light calibration methods and centerline extraction methods. In this paper, key technologies of line structured light calibration are reviewed. Major calibration methods such as vector cross product, linear equation solution, cross ratio invariance, vanishing points and lines, Plücker matrix are analyzed and compared in detail. Methods of centerline extraction are analyzed furthermore. This review concludes with a discussion of the future development of line structured light system, providing a good reference for researchers.

A Self-Supervised Learning Framework for Road Centerline Extraction From High-Resolution Remote Sensing Images

Road extraction from the high-resolution remote sensing image is significant for the land planning, vehicle navigation, etc. The existing road extraction methods normally need many preprocessing and subsequent optimization steps. Therefore, an automatic road centerline extraction method based on the self-supervised learning framework for high-resolution remote sensing image is proposed. This proposed method does not need to manually select training samples and other optimization steps, such as the nonroad area removing. First, the positive sample selection method combining the spectral and shape features is proposed to extract the road sample. Then, the one-class classifier framework is introduced and the random forest positive unlabeled learning classifier is constructed to get the posterior probability of the pixel belonging to road. The shape feature and the posterior probability are combined to form the final road network in the object-oriented way. Finally, the road centerline is obtained through the tensor voting algorithm. In order to verify the effectiveness of the proposed algorithm, high-resolution remote sensing images and benchmark datasets are used to do experiments. The indexes of the completeness ratio, the correctness ratio, and the detection quality are used for the quantitative accuracy evaluation. Compared with the supervised, the unsupervised, and the one-class classification road extraction algorithms, this proposed algorithm achieves high accuracy and efficiency. For the deep learning method comparison, the deep learning method performs well in most cases especially in the complex urban area. However, the deep learning method needs a large number of samples and a long training time, and our self-supervised learning framework does not need the training samples.

DeepWindow: Sliding Window Based on Deep Learning for Road Extraction From Remote Sensing Images

The road centerline extraction is the key step of the road network extraction and modeling. The hand-craft feature engineering in the traditional road extraction methods is unstable, which makes the extracted road centerline deviated from the road center in complex cases and even results in overall extracting errors. Recently, the road centerline extraction methods based on semantic segmentation employing deep neural network greatly outperformed the traditional methods. Nevertheless, the pixel-wise labels for training deep learning models are expensive and the postprocess of road segmentation is error-prone. Inspired by the work of human pose estimation, we propose DeepWindow, a novel method to automatically extract the road network from remote sensing images. DeepWindow uses a sliding window guided by a CNN-based decision function to track the road network directly from the images without the prior of road segmentation. First of all, we design and train a CNN model to estimate the road center points inside a patch. Then, the road seeds are automatically searched patch by patch employing the CNN model. Finally, starting from seeds, our method first estimates the road direction using a Fourier spectrum analysis algorithm and then iteratively tracks the road center-line along the road direction guided by the CNN model. In our method, the CNN model is trained by point annotations, which greatly reduces the training costs comparing to those in semantic model training. Our method achieves comparable performance with the state-of-the-art road extraction methods, and extensive experiments indicate that our method is robust to the point deviation.

A new hierarchical method for automatic road centerline extraction in urban areas using LIDAR data

Road detection and road extraction are important and challenging issues in the fields of photogrammetry and remote sensing. Researchers have conducted wide research in this regard based on multispectral images and achieved relatively useful results. Image-data driven methods have some shortcomings such as shadows, eliminating small and long vehicles, geometric distortions, and occlusions. In recent years, in order to overcome the above limitations and complexities, several attempts have been done based on LIDAR data. The present paper proposes an automatic hierarchical road detection and extraction method. The main goal of this research is to increase the level of continuity of the road detection and extraction processes. This method includes the preprocessing of intensity data using a local minima filter, applying the Mean Shift segmentation to the refined intensity data, and finally integrating it with various nDSM-based Products. The proposed method involves not only considering both small and long vehicles as road features but also neglecting some parts of large parking lots based on the nearby neighborhood of parked vehicles as much as possible as non-road features. The next step was the process of road centerline extraction by adopting a Voronoi-diagram based approach and then removing dangle lines in several iterations. The proposed method was applied to the Vaihingen and Toronto datasets (ISPRS). The completeness of the two datasets is 95.85% and 88%, and the correctness of these datasets are 83.68% and 72.2%, respectively. The results were indicative of the great potential of the proposed method for effective road centerline extraction in urban areas.

An automatic method for road centerline extraction from post-earthquake aerial images

Road vector database plays an important role in post-earthquake relief, rescue and reconstruction. However, due to data privacy policy, it is difficult for general users to obtain high-precision and complete vector data of road network. The OpenStreetMap (OSM) project provides an open-source, global free road dataset, but there are inevitable geo-localization/projection errors, which will lead to large errors in hazard survey analysis. In this paper, we proposed a road centerline correction method using post-earthquake aerial images. Under the constraint of the vector road map (OpenStreetMap), we rectified the centerline by the context feature and spectral gradient feature of post-event images automatically. The experiment implemented on 0.5 m/pixel post-event aerial images of Haiti, 2010, showed that the completeness and extraction quality of proposed method were over 90% and 80% without any manual intervention.

Extraction Method of Coronary Artery Blood Vessel Centerline in CT Coronary Angiography

Aiming at the problem that the traditional coronary artery centerline extraction method is computationally intensive and requires a large number of manual interventions, a fully automatic coronary artery centerline tracking extraction method is proposed. First, adaptive adaptation of coronary vessels was performed based on different Fresenius norms designed for coronary scale. A multi-scale differential operator is constructed based on the vascular gray-scale distribution to establish a discriminant function, thereby obtaining the initial position and tracking direction of the seed point. Then, the new ridge point and tracking direction are optimally detected within the local arc length of the initial direction to ensure that the correct ridge position can still be obtained with large error interference. Finally, the pseudo vascular centerline is removed using the vascular topology feature detection method. The experimental results show that the method can accurately extract the blood vessel center line, direction vector and other information in the coronary angiography image without manual intervention, and can be used in the computer-assisted diagnosis and treatment process of clinical cardiovascular disease.

Development, Implementation and Validation of an Automatic Centerline Extraction Algorithm for Complex 3D Objects

Although centerlines (aka ‘skeletons’ or ‘medial axes’) are among the most efficient ways to represent items in digital images, and obtaining these from 2D shapes is relatively straight forward, extracting centerlines from 3D objects has remained a challenge—particularly if they are not smooth or uniform. Therefore, we have developed a novel 3D centerline extraction method for discrete binary objects using a ‘divide and conquer’ approach, in which any 3D object is sliced into a series of 2D images (in the X, Y and Z directions), a geometric (Voronoi) algorithm is applied to each planar image to extract the 2D centerlines, and the information is recombined (using an intersection technique) to obtain the centerline of the original 3D object. Validation of this approach was performed using a ground truth benchmark, standard 3D database objects, and more complex anatomical structures (segmented from medical imaging data). The algorithm consistently performed well for objects of moderate complexity, but occasionally left discontinuities in the extracted 3D skeletons of the most complex objects. Therefore, in order to deal with such cases, an optional 3D interpolation step—based on Delaunay triangles and a spherical search to establish the nearest neighboring points in 3D space—was developed to allow continuous centerlines to be extracted from even the most complex anatomical structures tested. As a result, we anticipate that this approach could have wide-ranging applications, including data reduction for large microscopy and other 3D imaging datasets, automatic quantification of medical imaging data along anatomical structures, and others.