Fast Segmentation Algorithm Research Articles

A novel locally statistical active contour model for SAR image segmentation and faster algorithm

Abstract In this paper, a novel locally statistical active contour model (LACM) based on the Aubert-Aujol (AA) denoising model and variational level set method is proposed, which can be used for SAR image segmentation with intensity inhomogeneity. By simple transformation, a fast segmentation algorithm with a global optimization solver can be obtained. Experiments using some challenging synthetic images and Envisat SAR images demonstrate the superiority of our proposed models with respect to classic models. Further, we can find that the structure of the proposed algorithm is the same as that of the Transformer or RNN. We will study the nature of the above two types of algorithms to propose a more effective segmentation algorithm based on the energy model.

Accurate neuron segmentation method for one-photon calcium imaging videos combining convolutional neural networks and clustering

One-photon fluorescent calcium imaging helps understand brain functions by recording large-scale neural activities in freely moving animals. Automatic, fast, and accurate active neuron segmentation algorithms are essential to extract and interpret information from these videos. One-photon imaging videos’ low resolution, high noise, and high background fluctuation pose significant challenges. Here, we develop a software pipeline to address the challenges of processing one-photon calcium imaging videos. We extend our previous two-photon active neuron segmentation algorithm, Shallow U-Net Neuron Segmentation (SUNS), to better suppress background fluctuations in one-photon videos. We also develop additional neuron extraction (ANE) to locate small or dim neurons missed by SUNS. To train our segmentation method, we create ground truth neurons by developing a manual labeling pipeline assisted with semi-automatic refinement. Our method is more accurate and faster than state-of-the-art techniques when processing simulated videos and multiple experimental datasets acquired over various brain regions with different imaging conditions.

Fast Segmentation Algorithm of USV Accessible Area Based on Attention Fast Deeplabv3

Fast Segmentation Algorithm of USV Accessible Area Based on Attention Fast Deeplabv3

Model-based hybrid variational level set method applied to lung cancer detection

<p>The precise segmentation of lung lesions in computed tomography (CT) scans holds paramount importance for lung cancer research, offering invaluable information for clinical diagnosis and treatment. Nevertheless, achieving efficient detection and segmentation with acceptable accuracy proves to be challenging due to the heterogeneity of lung nodules. This paper presents a novel model-based hybrid variational level set method (VLSM) tailored for lung cancer detection. Initially, the VLSM introduces a scale-adaptive fast level-set image segmentation algorithm to address the inefficiency of low gray scale image segmentation. This algorithm simplifies the (Local Intensity Clustering) LIC model and devises a new energy functional based on the region-based pressure function. The improved multi-scale mean filter approximates the image’s offset field, effectively reducing gray-scale inhomogeneity and eliminating the influence of scale parameter selection on segmentation. Experimental results demonstrate that the proposed VLSM algorithm accurately segments images with both gray-scale inhomogeneity and noise, showcasing robustness against various noise types. This enhanced algorithm proves advantageous for addressing real-world image segmentation problems and nodules detection challenges.</p>

Obstacle detection and obstacle-surmounting planning for a wheel-legged robot based on Lidar

PurposeThis paper aims to investigate an autonomous obstacle-surmounting method based on a hybrid gait for the problem of crossing low-height obstacles autonomously by a six wheel-legged robot. The autonomy of obstacle-surmounting is reflected in obstacle recognition based on multi-frame point cloud fusion.Design/methodology/approachIn this paper, first, for the problem that the lidar on the robot cannot scan the point cloud of low-height obstacles, the lidar is driven to rotate by a 2D turntable to obtain the point cloud of low-height obstacles under the robot. Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping algorithm, fast ground segmentation algorithm and Euclidean clustering algorithm are used to recognize the point cloud of low-height obstacles and obtain low-height obstacle in-formation. Then, combined with the structural characteristics of the robot, the obstacle-surmounting action planning is carried out for two types of obstacle scenes. A segmented approach is used for action planning. Gait units are designed to describe each segment of the action. A gait matrix is used to describe the overall action. The paper also analyzes the stability and surmounting capability of the robot’s key pose and determines the robot’s surmounting capability and the value scheme of the surmounting control variables.FindingsThe experimental verification is carried out on the robot laboratory platform (BIT-6NAZA). The obstacle recognition method can accurately detect low-height obstacles. The robot can maintain a smooth posture to cross low-height obstacles, which verifies the feasibility of the adaptive obstacle-surmounting method.Originality/valueThe study can provide the theory and engineering foundation for the environmental perception of the unmanned platform. It provides environmental information to support follow-up work, for example, on the planning of obstacles and obstacles.

EWSeg: a fast segmentation algorithm for images based on edge linking and watershed constraints

In this paper, we propose a two-stage algorithm, named watershed-constrained image segmentation, for exploring complete edge-closed regions from edges. In the first stage, the input image is pre-processed and the image gradient information is obtained using a gradient operator. Anchors are then obtained from the gradient information. Finally, initial edges are obtained by intelligently connecting the anchors. In the second stage, a marker-based watershed algorithm is adopted to obtain marker points from the gradient information obtained in the first stage. A Gaussian filtered image is then used as the input image to obtain a watershed hyper-segmented edge map. Finally, complete edge-closed regions are obtained by combining the initial edges and the hyper-segmented edge map and searching for weak edges. The image segmentation results are then obtained from the edge-closed regions, demonstrating the excellent performance of our proposed algorithm on various images and videos.

A fast and efficient numerical algorithm for image segmentation and denoising

<abstract><p>Image segmentation is the process of partitioning an image into homogenous regions, and represents one of the most fundamental and important procedures in image processing. Image denoising is a process to remove unwanted noise from a digital image, enhancing its visual quality. Various algorithms, like non-local means and deep learning-based approaches, have been developed to remove noise while preserving important image details. Currently, the prevalent application of pattern recognition technology is achieved through the implementation of image segmentation algorithms. In this study, we present a new, highly efficient, and fast computational scheme specifically developed for a phase-field mathematical model of image segmentation. The numerical methodology is based on an operator splitting method (OSM). The split operators are solved by using closed-form analytic solutions and a finite difference method (FDM) with an alternating direction explicit (ADE) method. To show the notable efficiency and rapid computational performance of the proposed computational algorithm, we conduct a series of numerical experiments. Through these computational tests, we confirm a significant contribution to the advancement of methodologies employed in the critical domain of image processing.</p></abstract>

О сегментации опухолей головного мозга по МРТ-изображениям с применением методов глубокого обучения

Segmentation of a brain tumor is one of the most difficult tasks in the analysis of medical images. The purpose of brain tumor segmentation is to create an accurate outline of brain tumor areas. Gliomas are the most common type of brain tumors. Diagnosis of patients with this disease is based on the analysis of the results of magnetic resonance imaging and segmentation of the tumor boundaries manually. However, due to the time-consuming nature of the manual segmentation process and errors, there is a need for a fast and reliable automatic segmentation algorithm. In recent years, deep learning methods have shown promising effectiveness in solving various computer vision problems, such as image classification, object detection and semantic segmentation. A number of methods based on deep learning have been applied to segmentation of brain tumors, and promising results have been achieved. The article proposes a hybrid method for solving the problem of segmentation of brain tumors based on its MRI images based on the U-Net architecture, the encoder of which uses a model of a deep convolutional neural network pre-trained on a set of ImageNet images. Among such models were used VGG16, VGG19, MobileNetV2, Inception, ResNet50, EfficientNetb7, InceptionResnetV2, DenseNet201, DenseNet121. Based on the hybrid method, the TL-U-Net model was implemented, and numerical experiments were carried out to train it with different encoder models for segmentation of brain tumors based on its MRI images. Computer experiments on a set of MRI images of the brain showed the effectiveness of the proposed approach, the best encoder model turned out to be the neural network Densenet121, which provided indicators of segmentation accuracy MeanIoU=90.34%, MeanDice=94.33%, accuracy=94.17%. The obtained estimates of segmentation accuracy are comparable or exceed similar estimates obtained by other researchers.

Population-based change-point detection for the identification of homozygosity islands.

This work is motivated by the problem of identifying homozygosity islands on the genome of individuals in a population. Our method directly tackles the issue of identification of the homozygosity islands at the population level, without the need of analysing single individuals and then combine the results, as is made nowadays in state-of-the-art approaches. We propose regularized offline change-point methods to detect changes in the parameters of a multidimensional distribution when we have several aligned, independent samples of fixed resolution. We present a penalized maximum likelihood approach that can be efficiently computed by a dynamic programming algorithm or approximated by a fast binary segmentation algorithm. Both estimators are shown to converge almost surely to the set of change-points without the need of specifying a priori the number of change-points. In simulation, we observed similar performances from the exact and greedy estimators. Moreover, we provide a new methodology for the selection of the regularization constant which has the advantage of being automatic, consistent, and less prone to subjective analysis. The data used in the application are from the Human Genome Diversity Project (HGDP) and is publicly available. Algorithms were implemented using the R software R Core Team (R: A Language and Environment for Statistical Computing. Vienna (Austria): R Foundation for Statistical Computing, 2020.) in the R package blockcpd, found at https://github.com/Lucas-Prates/blockcpd.

Pulmonary Nodule Segmentation Framework Based on Fine-Tuned and Pretrained Deep Neural Network Using CT Images

Deep learning is one of the most rapidly growing and emerging technologies in pulmonary nodule segmentation. However, the different shape, size, and location of the nodules make it extremely difficult to segment correctly. The purpose of this study is to obtain a fast and accurate segmentation algorithm with less number of stages. A fine-tuned dual skip connection-based segmentation framework is proposed that integrates pretrained residual neural network (ResNet) 152 with the U-Net architecture, namely, ResiU-Net. Nine different pretrained and fine-tuned encoder backbones, such as ResNet18, ResNet 34, ResNet 50, ResNet 101, ResNet 152, SEResNet18, SE-ResNet34, ResNext 101, and ResNext 50 are compared and the proposed ResiU-Net approach gives the best results. Also, the fine-tuned ResiU-Net performs better than nontuned ResiU-Net. 1224 computed tomography patient images with different nodule shapes and sizes are selected. The proposed method achieves 97.44% F score, 95.02% intersection over union score, 94.87% dice score, 0.34% binary cross-entropy loss, and 0.7585 combined dice coefficient and binary focal loss. The proposed ResiU-Net outperforms the state-of-the-art methods and reports the best evaluation metrics. The time taken by the model to train is 43 min. Hence, the proposed model is a fast and accurate segmentation approach.

Fast segmentation algorithm of PCB image using 2D OTSU improved by adaptive genetic algorithm and integral image

Fast segmentation algorithm of PCB image using 2D OTSU improved by adaptive genetic algorithm and integral image

The fast image segmentation algorithms using dynamic programming for modals of image histograms

A machine learning method is now considered capable of accurately segmenting images. However, one significant disadvantage of this strategy is that it requires a lengthy training phase and an extensive training dataset. This article uses an image segmentation by histogram thresholding approach that does not require training to overcome this difficulty. This article proposes straightforward and time-optimal algorithms, which are guaranteed by mathematical proofs. Furthermore, we experiment with the proposed algorithms using 100 images from a standard database. The results show that, while their performances are not significantly different, the two proposed methods are roughly 10 and 20 times faster than the most simple and optimal method, Brute Force. They also show that the proposed algorithms can deal with bimodal images and images with various shapes of the image histogram. Because our proposed algorithms are the most efficient and effective. As a result, they can be used for real-time segmentations and as a pre-processing approach for multiple object segmentation.

Automatic retrieval of volcanic SO2 emission source from TROPOMI products

Volcanic sulfur dioxide (SO2) satellite observations are key for monitoring volcanic activity, and for mitigation of the associated risks on both human health and aviation safety. Automatic analysis of this data source, including robust source emission retrieval, is in turn essential for near real-time monitoring applications. We have developed fast and accurate SO2 plume classifier and segmentation algorithms using classic clustering, segmentation and image processing techniques. These algorithms, applied to measurements from the TROPOMI instrument onboard the Sentinel-5 Precursor platform, can help in the accurate source estimation of volcanic SO2 plumes originating from various volcanoes. In this paper, we demonstrate the ability of different pixel classification methodologies to retrieve SO2 source emission with a good accuracy. We compare the algorithms, their strengths and shortcomings, and present plume classification results for various active volcanoes throughout the year 2021, including examples from Etna (Italy), Sangay and Reventador (Ecuador), Sabancaya and Ubinas (Peru), Scheveluch and Klyuchevskoy (Russia), as well as Ibu and Dukono (Indonesia). The developed algorithms, shared as open-source code, contribute to improving analysis and monitoring of volcanic emissions from space.

Fast and accurate superpixel segmentation algorithm with a guidance image

Superpixels are generated by automatically grouping image pixels into lots and lots of compact segments. In computer vision, it is widely used as an effective way to reduce the number of image primitives for subsequent tasks and for recognizing objects’ contours due to its excellent boundary adhesion. The primary concerns of a superpixel generation algorithm are its efficiency and accuracy. In this document, we aim to propose a fast and precise superpixel segmentation algorithm with a guidance image. Specifically, we introduce a rolling filter that can remove details while well preserving the boundaries to obtain the guidance image. In the meantime, we introduce a robust edge confidence operator to accurately detect image boundaries. From this, we define a distance measurement with adaptive parameters for each image. In this way, we can adapt and accurately group pixels into regions according to the new distance measurement. Furthermore, we adopt a noniterative framework to generate superpixels in real time by processing all pixels once. The experimental results show that the proposed methodology achieves state-of-the-art performance on two sets of reference data while operating in real time.

Fast Segmentation Method of Sonar Images for Jacket Installation Environment

It has remained a hard nut for years to segment sonar images of jacket installation environment, most of which are noisy images with inevitable blur after noise reduction. For the purpose of solutions to this problem, a fast segmentation algorithm is proposed on the basis of the gray value characteristics of sonar images. This algorithm is endowed with the advantage in no need of segmentation thresholds. To realize this goal, we follow the undermentioned steps: first, calculate the gray matrix of the fuzzy image background. After adjusting the gray value, the image is divided into three regions: background region, buffer region and target regions. After filtering, we reset the pixels with gray value lower than 255 to binarize images and eliminate most artifacts. Finally, the remaining noise is removed by morphological processing. The simulation results of several sonar images show that the algorithm can segment the fuzzy sonar images quickly and effectively. Thus, the stable and feasible method is testified.

A Fast Multiplane Segmentation Algorithm for Sparse 3-D LiDAR Point Clouds by Line Segment Grouping

This article describes an approach for extracting multiple planar regions in 3-D point clouds from spinning multibeam LiDARs. This technique benefits from the intrinsic structure of LiDARs and projective geometry, which allows us to extract line segments efficiently in 2-D space and then cluster those line segments to form planes. To extract planes from line primitives, we introduce a novel line segment grouping approach by alternatively searching candidate plane seeds of adjacent line segments and breadth-first searching for neighboring lines fallen on the seeded plane. Exhaustive experiments have been conducted with simulation, realistic data, and a public plane segmentation evaluation benchmark. Experimental results show that our method works well on sparse point clouds with the fastest running speed compared to state-of-the-art methods.

A novel method for signal labeling and precise location in a variable parameter milling process based on the stacked-BiLSTM-CRF and FLOSS

Unlabeled time series signals collected during manufacturing typically have low value density and must be labeled and intercepted according to the specific application scenario. During variable-parameter milling, particularly high-precision machining, machining parameters vary, and associated discrepancies in vibration signals are small. In this scenario, signal features that are extracted by hand or via deep learning methods cannot typically distinguish machining states via classification models. To solve this problem, a sequence labeling model developed using a stacked bidirectional long short-term memory network with a conditional random field layer (stacked-BiLSTM-CRF) is proposed in this study to automatically label and intercept vibration signals. The stacked BiLSTM receives the shallow features obtained by the short-time Fourier transform of the vibration signals and then outputs the extracted deep features to capture the before and after dependence of the signals. The stacked BiLSTM is then extended by stacking a CRF layer to explicitly model the dependence of signal labels. In a more accurate labeling scenario, the fast low-cost online semantic segmentation algorithm (FLOSS) is used to acquire more fine-grained signal boundary locations after obtaining the frame-level signal label using the stacked BiLSTM-CRF model. In addition, to evaluate model performance, a novel evaluation index for signal labeling is proposed. The feasibility and effectiveness of the proposed method are verified using the vibration signals collected from variable parameter cutting experiments, and results show that the proposed model achieves the best labeling performance of tested methods in nearly all scenarios.

Lightweight deep learning methods for panoramic dental X-ray image segmentation

Dental X-ray image segmentation is helpful for assisting clinicians to examine tooth conditions and identify dental diseases. Fast and lightweight segmentation algorithms without using cloud computing may be required to be implemented in X-ray imaging systems. This paper aims to investigate lightweight deep learning methods for dental X-ray image segmentation for the purpose of deployment on edge devices, such as dental X-ray imaging systems. A novel lightweight neural network scheme using knowledge distillation is proposed in this paper. The proposed lightweight method and a number of existing lightweight deep learning methods were trained on a panoramic dental X-ray image data set. These lightweight methods were evaluated and compared by using several accuracy metrics. The proposed lightweight method only requires 0.33 million parameters (sim 7.5 megabytes) for the trained model, while it achieved the best performance in terms of IoU (0.804) and Dice (0.89) comparing to other lightweight methods. This work shows that the proposed method for dental X-ray image segmentation requires small memory storage, while it achieved comparative performance. The method could be deployed on edge devices and could potentially assist clinicians to alleviate their daily workflow and improve the quality of their analysis.

Clustering Analysis of Voltage Sag Events Based on Waveform Matching

Voltage sags are a serious problem within power supplies, which pose threats to both residential electricity and industrial manufacturing. Since any one sag may be recorded by multiple monitoring devices from different substations, the issue of redundant information in data arises. In this regard, a novel method for voltage sag events based on projection technology, shape dynamic time warping (shapeDTW), and spectral clustering is proposed. The main contributions of this paper may be summarized as follows: (1) We present a new method for extracting the voltage anomaly waveform, which is a fast projection segmentation algorithm (FPSA). The voltage sag waveform is only a part of the voltage anomaly waveform, so the voltage anomaly waveform contains more information. (2) ShapeDTW and spectral clustering are used to match and cluster voltage anomaly waveforms, so as to achieve the normalization of voltage sag events. (3) In practical engineering, the proposed method in the paper can be used to obtain the impact of voltage sags, reduce computational complexity, and ease the workload of the operation and maintenance engineers. Experiments were conducted using voltage sag data from voltage sag events recorded by the 10 kV monitoring points in Beijing, China. The results showed the effectiveness and reliability of our proposed methods.

Real-time iris segmentation model based on lightweight convolutional neural network

Iris segmentation is an important task in the iris recognition system. Traditional iris segmentation methods are susceptible to irrelevant noise. At present, segmentation methods based on convolutional neural networks (CNNs) have become the main trend in addressing the task. Although these networks achieve promising segmentation performance on the advanced graphics processor, they require a lot of computation and time, which are far from meeting the standards of real-time iris segmentation. To this end, a precise and fast iris segmentation algorithm is proposed. First, an efficient feature extraction network that combines depth-wise separable convolution with dilated convolution is designed to reduce model parameters while maintaining segmentation accuracy. Then, an attention mechanism is introduced to suppress noise interference and enhance the discriminability of the iris region. Finally, an auxiliary training branch is proposed to overcome the vanishing gradient problem. Experimental results show that the proposed method not only achieves state-of-the-art performance but also is more efficient in terms of required parameters, calculated load, and storage space. Specifically, the model parameter is only 0.1 million (M), and the average prediction time is <0.03 seconds (S).