Distance-based Segmentation Research Articles

Partial hard occluded target reconstruction of Fourier single pixel imaging guided through range slice

Fourier single pixel imaging utilizes pre-programmed patterns for laser spatial distribution modulation to reconstruct intensity image of the target through reconstruction algorithms. The approach features non-locality and high anti-interference performance. However, Poor image quality is induced when the target of interest is occluded in Fourier single pixel imaging. To address the problem, a deep learning-based image inpainting algorithm is employed within Fourier single pixel imaging to reconstruct partially obscured targets with high quality. It applies a distance-based segmentation method to segment obscured regions and the target of interest. Additionally, it utilizes an image inpainting network that combines multi-scale sparse convolution and transformer architecture, along with a reconstruction network that integrates Channel Attention Mechanism and Attention Gate modules to reconstruct complete and clear intensity images of the target of interest. The proposed method significantly expands the application scenarios and improves the imaging quality of Fourier single pixel imaging. Simulation and real-world experimental results demonstrate that the proposed method exhibits the high inpainting and reconstruction capacity in the conditions of hard occlusion and down-sampling.

FCM with Spatial Constraint Multi-Kernel Distance-Based Segmentation and Optimized Deep Learning for Flood Detection

Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmland, and infrastructure. To address this, it is necessary to devise and employ an effective flood management system that can immediately identify flood areas to initiate relief measures as soon as possible. Therefore, this research work develops an effective flood detection method, named Anti- Corona-Shuffled Shepherd Optimization Algorithm-based Deep Quantum Neural Network (ACSSOA-based Deep QNN) for identifying the flooded areas. Here, the segmentation process is performed using Fuzzy C-Means with Spatial Constraint Multi-Kernel Distance (MKFCM_S) wherein the Fuzzy C-Means (FCM) is modified with Spatial Constraints Based on Kernel-Induced Distance (KFCM_S). For flood detection, Deep QNN has been used wherein the training progression of Deep QNN is done using designed optimization algorithm, called ACSSOA. Besides, the designed ACSSOA is newly formed by the hybridization of Anti Corona Virus Optimization (ACVO) and Shuffled Shepherd Optimization Algorithm (SSOA). The devised method was evaluated using the Kerala Floods database, and it acquires the segmentation accuracy, testing accuracy, sensitivity, and specificity with highest values of 0.904, 0.914, 0.927, and 0.920, respectively.

RHM-δ-GLMB Tracking Algorithm on the Focal Plane for UAV Cluster Targets

This paper offers a new tracking algorithm for clustered targets of focal plane unmanned aerial vehicles (UAVs) by integrating the random hypersurface model (RHM) model into the δ-generalized label multi-Bernoulli (δ-GLMB) filter to guarantee a robust UAV cluster target tracking on such focal planes. We first investigated the infrared imaging features of UAV cluster targets by emphasizing the target imaging size and dispersion. Next, we designed an elliptical RHM-based measurement model to map the measurement, state parameters, scaling factors, and errors to pseudo-measurement "0", followed by establishing a pseudo-measurement equation to reflect the target’s extended shape size. Then, in order to enhance measurement estimation accuracy, the RHM model was implemented with the δ-GLMB filter and Gamma-Gaussian mixture, which can perform a real-time estimate of the targets’ centroid motion state and extended state. We also used the grid-based fast density-based spatial clustering of applications with noise (DBSCAN) segmentation algorithm to overcome the distance-based segmentation method restrictions for infrared radiation (IR) measurement data and diminish the algorithm’s complexity even more in the measurement update. Extensive simulations demonstrated that this algorithm outperformed existing matching filtering algorithms in the target centroid motion and extended states. Our investigations also revealed that the algorithm was less vulnerable to clutter and more adaptive, making it more straightforward to accomplish reliable tracking of UAV cluster targets.

Culture vs. distance: comparing the effects of geographic segmentation variables on tourists\u2019 destination images based on social media data

Culture and distance are two major factors for geographically segmenting tourists in tourism marketing and advertising. Previous empirical studies on the destination image, however, have examined extensively the effect of the culture while inadequately the effect of the distance, let alone comparing the effects of the two variables. Using social media data, this study compares the effect of distance-based segments of tourists with that of culture-based segments in producing diverse perceived images of a destination. From Sina Weibo data, 282,532 Chinese mainland tourists who visited Suzhou, China during 2012–2016 and their perceived destination images are extracted and analyzed. The main results include: 1) for distance-based segments, the image differences increased with distance and the short-haul tourists perceived a more comprehensive image than the long-haul tourists; 2) for culture-based segments, the image differences were clear and relatively complex, while tourists from Wuyue cultural region had similar image perceptions with the local visitors; 3) the q-statistic of the Geodetector method shows that the culture-based segmentation can explain 65.8% of image variations while the distance-based segmentation can explain 46.6% of image variations, suggesting that culture is a more appropriate variable to segment the tourism market.

Individual tree detection and crown segmentation based on metabolic theory from airborne laser scanning data

Laser scanning technology has enabled to study three-dimensional (3D) structures in forests. For example, airborne laser scanning (ALS) point cloud has been applied to detect individual trees and segment tree crowns. However, the accuracy of such approach remains a challenge because of the intersected crowns and complicated understories. We developed a metabolic theory-based algorithm for individual tree detection and crown segmentation from ALS data. The algorithm is composed of two parts, of which one is an unscaled transporting distance-based top-to-bottom detection approach, and the other is a scaled transporting distance-based segmentation approach. The unscaled transporting distance for detection is the absolute distance from tree root to crown and then to ALS point based on the tree structure models, whereas the scaled transporting distance for segmentation is the unscaled distance that is scaled by an initial tree height obtained during detection. This is based on a basic metabolic theory that vascular plants tend to minimize the material transporting distance from root to leaves. Hence, seven types of materials transporting distance models were built based on monopodial branching structure or crown-centered structure. The performance of the proposed approach was then further examined and compared with two typical canopy height model-based approaches and one typical point cloud-based approach, taking forest in Oxfordshire, UK, as a case study. The results showed that our approach can reach a recall of 1.00, a precision of 0.96, and an F-score of 0.98 and can reach to much higher accuracy for tree height (R2 = 0.8045) than the comparison approaches (R2 < 0.2) in the study plot. One of the main reasons that led to such low accuracy of comparison approaches is much overestimation of understory height with a mean error that is 2.9 times higher than that of our approach on average. Furthermore, ALS point-to-point level accuracy assessment shows 9.7% more ALS points were truly assigned in our approach than that of comparison approaches. It is noticed that the algorithm presented is not sensitive to the two key parameters: p (a percentage determining the threshold of unscaled transporting distances) ranging from 32.0% to 34.0% and λ (the proportion between the assumed crown center height and tree height) ranging from 0.70 to 0.90 based on our data set. Such high accuracy of our approach can greatly improve detections of individual tree and crown segmentation, especially in delineating understories in complex-structured forest.

A sensitivity analysis of probability maps in deep-learning-based anatomical segmentation.

PurposeDeep‐learning‐based segmentation models implicitly learn to predict the presence of a structure based on its overall prominence in the training dataset. This phenomenon is observed and accounted for in deep‐learning applications such as natural language processing but is often neglected in segmentation literature. The purpose of this work is to demonstrate the significance of class imbalance in deep‐learning‐based segmentation and recommend tuning of the neural network optimization objective.MethodsAn architecture and training procedure were chosen to represent common models in anatomical segmentation. A family of 5‐block 2D U‐Nets were independently trained to segment 10 structures from the Cancer Imaging Archive's Head‐Neck‐Radiomics‐HN1 dataset. We identify the optimal threshold for our models according to their Dice score on the validation datasets and consider perturbations about the optimum. A measure of structure prominence in segmentation datasets is defined, and its impact on the optimal threshold is analyzed. Finally, we consider the use of a 2D Dice objective in addition to binary cross entropy.ResultsWe observe significant decreases in perceived model performance with conventional 0.5‐thresholding. Perturbations of as little as ±0.05 about the optimum threshold induce a median reduction in Dice score of 11.8% for our models. There is statistical evidence to suggest a weak correlation between training dataset prominence and optimal threshold (Pearson r=0.92 and p≈10‐4). We find that network optimization with respect to the 2D Dice score itself significantly reduces variability due to thresholding but does not unequivocally create the best segmentation models when assessed with distance‐based segmentation metrics.ConclusionOur results suggest that those practicing deep‐learning‐based contouring should consider their postprocessing procedures as a potential avenue for improved performance. For intensity‐based postprocessing, we recommend a mixed objective function consisting of the traditional binary cross entropy along with the 2D Dice score.

Global River Monitoring Using Semantic Fusion Networks

Global river monitoring is an important mission within the remote sensing society. One of the main challenges faced by this mission is generating an accurate water mask from remote sensing images (RSI) of rivers (RSIR), especially on a global scale with various river features. Aiming at better water area classification using semantic information, this paper presents a segmentation method for global river monitoring based on semantic clustering and semantic fusion. Firstly, an encoder–decoder network (AEN)-based architecture is proposed to obtain the semantic features from RSIR. Secondly, a clustering-based semantic fusion method is proposed to divide semantic features of RSIR into groups and train convolutional neural networks (CNN) models corresponding to each group using data augmentation and semi-supervised learning. Thirdly, a semantic distance-based segmentation fusion method is proposed for fusing the CNN models result into final segmentation mask. We built a global river dataset that contains multiple river segments from each continent of the world based on Sentinel-2 satellite imagery. The result shows that the F1-score of the proposed segmentation method is 93.32%, which outperforms several state-of-the-art algorithms, and demonstrates that grouping semantic information helps better segment the RSIR in global scale.

High-Throughput Segmentation of Tiled Biological Structures using Random-Walk Distance Transforms.

Various 3D imaging techniques are routinely used to examine biological materials, the results of which are usually a stack of grayscale images. In order to quantify structural aspects of the biological materials, however, they must first be extracted from the dataset in a process called segmentation. If the individual structures to be extracted are in contact or very close to each other, distance-based segmentation methods utilizing the Euclidean distance transform are commonly employed. Major disadvantages of the Euclidean distance transform, however, are its susceptibility to noise (very common in biological data), which often leads to incorrect segmentations (i.e., poor separation of objects of interest), and its limitation of being only effective for roundish objects. In the present work, we propose an alternative distance transform method, the random-walk distance transform, and demonstrate its effectiveness in high-throughput segmentation of three microCT datasets of biological tilings (i.e., structures composed of a large number of similar repeating units). In contrast to the Euclidean distance transform, the random-walk approach represents the global, rather than the local, geometric character of the objects to be segmented and, thus, is less susceptible to noise. In addition, it is directly applicable to structures with anisotropic shape characteristics. Using three case studies—tessellated cartilage from a stingray, the dermal endoskeleton of a starfish, and the prismatic layer of a bivalve mollusc shell—we provide a typical workflow for the segmentation of tiled structures, describe core image processing concepts that are underused in biological research, and show that for each study system, large amounts of biologically-relevant data can be rapidly segmented, visualized, and analyzed.

Joint consideration of energy‐efficiency and coverage‐preservation in microsensor networks

AbstractThis paper presents an energy‐efficient and coverage‐preserving communication protocol which distributes a uniform energy load to the sensors in a wireless microsensor network. This protocol, called Distance‐based Segmentation (DBS), is a cluster‐based protocol that divides the entire network into equal‐area segments and applies different clustering policies to each segment to (1) reduce total energy dissipation and (2) balance the energy load among the sensors. Therefore, it prolongs the lifetime of the network and improves the sensing coverage. Moreover, the proposed routing protocol does not need any centralized support from a certain node which is at odds with aiming to establish a scalable communication protocol. Results from extensive simulations on two different network configurations show that by lowering the number of wasteful transmissions in the network, the DBS can achieve as much as a 20% reduction in total dissipated energy as compared with current cluster‐based protocols. In addition, this protocol is able to distribute energy load more evenly among the sensors in the network. Hence, it yields up to a 66% increase in the useful network lifetime. According to the simulation results, the sensing coverage degradation of the DBS is considerably slower than that of the other cluster‐based protocols. Copyright © 2009 John Wiley &amp; Sons, Ltd.

Level Set Hyperspectral Image Classification Using Best Band Analysis

We present a supervised hyperspectral classification procedure consisting of an initial distance-based segmentation method that uses best band analysis (BBA), followed by a level set enhancement that forces localized region homogeneity. The proposed method is tested on two hyperspectral images of an urban and rural nature. The proposed method is compared to the maximum likelihood (ML) method using BBA. Quantitative results are compared using segmentation and classification accuracies. Results show that both the initial classification using BBA features and the level set enhancement produced high-quality ground cover maps and outperformed the ML method, as well as previous studies by the authors. For example, with the compact airborne spectrographic imager image, the ML method resulted in accuracies les95.5%, whereas the level set segmentation approach resulted in accuracies as high as 99.7%.

Novel Multistage Three-Dimensional Medical Image Segmentation: Methodology and Validation

In this paper, we propose a novel multistage method for three-dimensional (3-D) segmentation of medical images and a new radial distance-based segmentation validation approach. For the 3-D segmentation method, we first employ a morphological recursive erosion operation to reduce the connectivity between the region of interest and its surrounding neighborhood; then we design a hybrid segmentation method to achieve an initial result. The hybrid approach integrates an improved fast marching method and a morphological reconstruction algorithm. Finally, a morphological recursive dilation is employed to recover any lost structure from the first stage of the multistage method. This approach is tested on 12 CT and 3 MRI images of the brain, heart, and kidney, to demonstrate the effectiveness and accuracy of this technique across a variety of imaging modalities and organ systems. In order to validate the multistage segmentation method, a novel radial distance-based validation method is proposed that uses a global accuracy (GA) measure. The GA is calculated based on local radial distance errors (LRDE), where LRDE are calculated on the radii emitted from points along the skeleton of the object rather than the centroid, in order to accommodate more complicated organ structures. The experimental results demonstrate that the proposed multistage segmentation method is fast and accurate, with comparable performance to existing segmentation methods, but with a significantly higher execution speed.

Classification using distance-based segmentation—application to the analysis of EEG signals

The algorithm described in this paper first analyses the trajectory of observations in the space to distinguish observations corresponding to classes from observations corresponding to transition sequences between classes. This first step is called ‘segmentation’ since it arranges data into segments: class segments and transition segments. Segments are then merged using a hierarchical clustering method until classes and transition sequences are interlaced. This algorithm has been applied to classify sleep EEG samples.