Simple Linear Iterative Clustering Research Articles

Change Detection Based on Existing Vector Polygons and Up-to-Date Images Using an Attention-Based Multi-Scale ConvTransformer Network

Vector polygons represent crucial survey data, serving as a cornerstone of national geographic censuses and forming essential data sources for detecting geographical changes. The timely update of these polygons is vital for governmental decision making and various industrial applications. However, the manual intervention required to update existing vector polygons using up-to-date high-resolution remote sensing (RS) images poses significant challenges and incurs substantial costs. To address this, we propose a novel change detection (CD) method for land cover vector polygons leveraging high-resolution RS images and deep learning techniques. Our approach begins by employing the boundary-preserved masking Simple Linear Iterative Clustering (SLIC) algorithm to segment RS images. Subsequently, an adaptive cropping approach automatically generates an initial sample set, followed by denoising using the efficient Visual Transformer and Class-Constrained Density Peak-Based (EViTCC-DP) method, resulting in a refined training set. Finally, an enhanced attention-based multi-scale ConvTransformer network (AMCT-Net) conducts fine-grained scene classification, integrating change rules and post-processing methods to identify changed vector polygons. Notably, our method stands out by employing an unsupervised approach to denoise the sample set, effectively transforming noisy samples into representative ones without requiring manual labeling, thus ensuring high automation. Experimental results on real datasets demonstrate significant improvements in model accuracy, with accuracy and recall rates reaching 92.08% and 91.34%, respectively, for the Nantong dataset, and 93.51% and 92.92%, respectively, for the Guantan dataset. Moreover, our approach shows great potential in updating existing vector data while effectively mitigating the high costs associated with acquiring training samples.

Multispectral Pedestrian Detection Based on Prior-Saliency Attention and Image Fusion

Detecting pedestrians in varying illumination conditions poses a significant challenge, necessitating the development of innovative solutions. In response to this, we introduce Prior-AttentionNet, a pedestrian detection model featuring a Prior-Attention mechanism. This model leverages the stark contrast between thermal objects and their backgrounds in far-infrared (FIR) images by employing saliency attention derived from FIR images via UNet. However, extracting salient regions of diverse scales from FIR images poses a challenge for saliency attention. To address this, we integrate Simple Linear Iterative Clustering (SLIC) superpixel segmentation, embedding the segmentation feature map as prior knowledge into UNet’s decoding stage for comprehensive end-to-end training and detection. This integration enhances the extraction of focused attention regions, with the synergy of segmentation prior and saliency attention forming the core of Prior-AttentionNet. Moreover, to enrich pedestrian details and contour visibility in low-light conditions, we implement multispectral image fusion. Experimental evaluations were conducted on the KAIST and OTCBVS datasets. Applying Prior-Attention mode to FIR-RGB images significantly improves the delineation and focus on multi-scale pedestrians. Prior-AttentionNet’s general detector demonstrates the capability of detecting pedestrians with minimal computational resources. The ablation studies indicate that the FIR-RGB+ Prior-Attention mode markedly enhances detection robustness over other modes. When compared to conventional multispectral pedestrian detection models, Prior-AttentionNet consistently surpasses them by achieving higher mean average precision and lower miss rates in diverse scenarios, during both day and night.

Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G.

Diabetic retinopathy disease contains lesions (e.g., exudates, hemorrhages, and microaneurysms) that are minute to the naked eye. Determining the lesions at pixel level poses a challenge as each pixel does not reflect any semantic entities. Furthermore, the computational cost of inspecting each pixel is expensive because the number of pixels is high even at low resolution. In this work, we propose a hybrid image processing method. Simple Linear Iterative Clustering with Gaussian Filter(SLIC-G) for the purpose of overcoming pixel constraints. The SLIC-G image processing method is divided into two stages: (1) simple linear iterative clustering superpixel segmentation and (2) Gaussian smoothing operation. In such a way, a large number of new transformed datasets are generated and then used for model training. Finally, two performance evaluation metrics that are suitable for imbalanced diabetic retinopathy datasets were used to validate the effectiveness of the proposed SLIC-G. The results indicate that, in comparison to prior published works' results, the proposed SLIC-G shows better performance on image classification of class imbalanced diabetic retinopathy datasets. This research reveals the importance of image processing and how it influences the performance of deep learning networks. The proposed SLIC-G enhances pre-trained network performance by eliminating the local redundancy of an image, which preserves local structures, but avoids over-segmented, noisy clips. It closes the research gap by introducing the use of superpixel segmentation and Gaussian smoothing operation as image processing methods in diabetic retinopathy-related tasks.

A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas

ABSTRACT To enhance the accuracy of land use classification in mining areas, the Object-based Convolutional Neural Network (OCNN) method has been widely used. However, existing researches tend to neglect the importance of decision-level fusion, focusing only on feature-level fusion. This study proposes a new classification framework with Multi-level Fusion of Object-based analysis and CNN (MFOCNN) to achieves high-accuracy land use classification in mining areas. First, Simple Linear Iterative Cluster (SLIC) is employed to generate image objects, which serve as the basic unit for classification. Second, an improved DenseNet is proposed to extract deep features from image patches, which represent image objects, and provide the classification result. Third, handcrafted features including spectral, textural and geometric of the image objects are extracted and fused with the deep features to obtain the classification result with random forest classifier. Finally, the Dempster-Shafer (DS) evidence theory is applied to fuse the two previously described classification results at the decision-level to obtain the final result. Experiments conducted in the mining areas of Erdos using Gaofen-6 images demonstrate that the proposed MFOCNN achieves the best visual performance and accuracy among all tested methods. The MFOCNN, with its feature-level fusion and decision-level fusion, significantly improves the accuracy of land use classification in mining areas. The results suggest that the proposed MFOCNN is a promising method for achieving high-accuracy land use classification in mining areas.

Sagittal balance parameters measurement on cervical spine MR images based on superpixel segmentation.

Introduction: Magnetic Resonance Imaging (MRI) is essential in diagnosing cervical spondylosis, providing detailed visualization of osseous and soft tissue structures in the cervical spine. However, manual measurements hinder the assessment of cervical spine sagittal balance, leading to time-consuming and error-prone processes. This study presents the Pyramid DBSCAN Simple Linear Iterative Cluster (PDB-SLIC), an automated segmentation algorithm for vertebral bodies in T2-weighted MR images, aiming to streamline sagittal balance assessment for spinal surgeons. Method: PDB-SLIC combines the SLIC superpixel segmentation algorithm with DBSCAN clustering and underwent rigorous testing using an extensive dataset of T2-weighted mid-sagittal MR images from 4,258 patients across ten hospitals in China. The efficacy of PDB-SLIC was compared against other algorithms and networks in terms of superpixel segmentation quality and vertebral body segmentation accuracy. Validation included a comparative analysis of manual and automated measurements of cervical sagittal parameters and scrutiny of PDB-SLIC's measurement stability across diverse hospital settings and MR scanning machines. Result: PDB-SLIC outperforms other algorithms in vertebral body segmentation quality, with high accuracy, recall, and Jaccard index. Minimal error deviation was observed compared to manual measurements, with correlation coefficients exceeding 95%. PDB-SLIC demonstrated commendable performance in processing cervical spine T2-weighted MR images from various hospital settings, MRI machines, and patient demographics. Discussion: The PDB-SLIC algorithm emerges as an accurate, objective, and efficient tool for evaluating cervical spine sagittal balance, providing valuable assistance to spinal surgeons in preoperative assessment, surgical strategy formulation, and prognostic inference. Additionally, it facilitates comprehensive measurement of sagittal balance parameters across diverse patient cohorts, contributing to the establishment of normative standards for cervical spine MR imaging.

Brain MR Image Classification Using Superpixel-Based Deep Transfer Learning.

Nowadays, brain MR (Magnetic Resonance) images are widely used by clinicians to examine the brain's anatomy to look into various pathological conditions like cerebrovascular incidents and neuro-degenerative diseases. Generally, these diseases can be identified with the MR images as "normal" and "abnormal" brains in a two-class classification problem or as disease-specific classes in a multi-class problem. This article presents an ensemble transfer learning-inspired deep architecture that uses the simple linear iterative clustering (SLIC)-based superpixel algorithm along with convolutional neural network (CNN) to classify the MR images as normal or abnormal. Superpixel algorithm segments the input MR images into clusters of regions defined by similarity measures using perceptual feature space. These superpixel images are beneficial as they can provide a compact and meaningful role in computationally demanding applications. The superpixel images are then fed to the deep convolutional neural network (CNN) to classify the images. Three brain MR image datasets, NITR-DHH, DS-75, and DS-160, are used to conduct the experimentation. Through the use of deep transfer learning, the model achieves performance accuracy of 88.15% (NITR-DHH), 98.15% (DS-160), and 98.33% (DS-75) even with the small-scale medical image dataset. The experimentally obtained results demonstrate that the proposed method is promising and efficient for clinical applications for diagnosing different brain diseases via MR images.

A Deep Learning Model to Inspect Image Forgery on SURF Keypoints of SLIC Segmented Regions

Copy-Move Forgery (CMF) is a common form of image manipulation attack that involves copying and pasting a part of an image to another position within the same image. This study proposes a Deep Learning (DL) model for detecting CMF, particularly in the presence of various malicious attacks. The proposed approach involves several steps, including converting the input image to grayscale, preprocessing the image using the Simple Linear Iterative Clustering (SLIC) algorithm to generate superpixel partitions, and then extracting keypoint features using the Speeded Up Robust Features (SURF) detector. Finally, a Generative Adversarial Network (GAN) is employed for feature description and matching. To assess the effectiveness of the approach, the types of features used for copy-move forgery were addressed. The proposed approach was examined under rotation, blurring, jpg compression, and scaling attacks. Furthermore, experimental results showed that the proposed approach can detect multiple CMFs with high accuracy. Finally, the proposed method was compared with recent state-of-the-art methods.

Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods

Abstract. Remote sensing extraction of glacial lakes is an effective way of monitoring water body distribution and outburst events. At present, the lack of glacial lake datasets and the edge recognition problem of semantic segmentation networks lead to poor accuracy and inaccurate outlines of glacial lakes. Therefore, this study constructed a high-resolution dataset containing seven types of glacial lakes and proposed a refined glacial lake extraction method, which combines the LinkNet50 network for rough extraction and simple linear iterative clustering (SLIC) dense conditional random field (DenseCRF) for optimization. The results show that (1) with Google Earth images of 0.52 m resolution in the study area, the recall, precision, F1 score, and intersection over union (IoU) of glacial lake extraction based on the proposed method are 96.52 %, 92.49 %, 94.46 %, and 90.69 %, respectively, and (2) with the Google Earth images of 2.11 m resolution in the Qomolangma National Nature Reserve, 2300 glacial lakes with a total area of 65.17 km2 were detected by the proposed method. The area of the minimum glacial lake that can be extracted is 160 m2 (less than 6×6 pixels). This method has advantages in small glacial lake extraction and refined outline detection, which can be applied to extracting glacial lakes in the high-Asia region with high-resolution images.

Corrections to “Underground Defects Detection Based on GPR by Fusing Simple Linear Iterative Clustering Phash (SLIC-Phash) and Convolutional Block Attention Module (CBAM)-YOLOv8”

Corrections to “Underground Defects Detection Based on GPR by Fusing Simple Linear Iterative Clustering Phash (SLIC-Phash) and Convolutional Block Attention Module (CBAM)-YOLOv8”

Scale dependence of forest fragmentation and its climate sensitivity in a semi-arid mountain: Comparing Landsat, Sentinel and Google Earth data

Landscape fragmentation is generally viewed as an indicator of environmental stresses or risks, but the fragmentation intensity assessment also depends on the scale of data and the definition of spatial unit. This study aimed to explore the scale-dependence of forest fragmentation intensity along a moisture gradient in Yinshan Mountain of North China, and to estimate environmental sensitivity of forest fragmentation in this semi-arid landscape. We developed an automatic classification algorithm using simple linear iterative clustering (SLIC) and Gaussian mixture model (GMM), and extracted tree canopy patches from Google Earth images (GEI), with an accuracy of 89.2% in the study area. Then we convert the tree canopy patches to forest category according to definition of forest that tree density greater than 10%, and compared it with forest categories from global land use datasets, FROM-GLC10 and GlobeLand30, with spatial resolutions of 10 m and 30 m, respectively. We found that the FROM-GLC10 and GlobeLand30 datasets underestimated the forest area in Yinshan Mountain by 16.88% and 21.06%, respectively; and the ratio of open forest (OF, 10% < tree coverage < 40%) to closed forest (CF, tree coverage > 40%) areas in the underestimated part was 2:1. The underestimations concentrated in warmer and drier areas occupied mostly by large coverage of OFs with severely fragmented canopies. Fragmentation intensity of canopies positively correlated with spring temperature while negatively correlated with summer precipitation and terrain slope. When summer precipitation was less than 300 mm or spring temperature higher than 4 °C, canopy fragmentation intensity rose drastically, while the forest area percentage kept stable. Our study suggested that the spatial configuration, e.g., sparseness, is more sensitive to drought stress than area percentage. This highlights the importance of data resolution and proper fragmentation measurements for forest patterns and environmental interpretation, which is the base of reliable ecosystem predictions with regard to the future climate scenarios.

SLIC-Occ: functional segmentation of occupancy images improves precision of EC50 images

BackgroundDrug occupancy studies with positron emission tomography imaging are used routinely in early phase drug development trials. Recently, our group introduced the Lassen Plot Filter, an extended version of the standard Lassen plot to estimate voxel-level occupancy images. Occupancy images can be used to create an EC50 image by applying an Emax model at each voxel. Our goal was to apply functional clustering of occupancy images via a clustering algorithm and produce a more precise EC50 image while maintaining accuracy.MethodA digital brain phantom was used to create 10 occupancy images (corresponding to 10 different plasma concentrations of drug) that correspond to a ground truth EC50 image containing two bilateral local “hot spots” of high EC50 (region-1: 25; region-2: 50; background: 6–10 ng/mL). Maximum occupancy was specified as 0.85. An established noise model was applied to the simulated occupancy images and the images were smoothed. Simple Linear Iterative Clustering, an existing k-means clustering algorithm, was modified to segment a series of occupancy images into K clusters (which we call “SLIC-Occ”). EC50 images were estimated by nonlinear estimation at each cluster (post SLIC-Occ) and voxel (no clustering). Coefficient of variation images were estimated at each cluster and voxel, respectively. The same process was also applied to human occupancy data produced for a previously published study.ResultsVariability in EC50 estimates was reduced by more than 80% in the phantom data after application of SLIC-Occ to occupancy images with only minimal loss of accuracy. A similar, but more modest improvement was achieved in variability when SLIC-Occ was applied to human occupancy images.ConclusionsOur results suggest that functional segmentation of occupancy images via SLIC-Occ could produce more precise EC50 images and improve our ability to identify local “hot spots” of high effective affinity of a drug for its target(s).

An efficient framework for optic disk segmentation and classification of Glaucoma on fundus images

Accurately segmenting the Optic Disk is a crucial step in classifying Glaucoma using Fundus images. Machine learning and artificial intelligence techniques are widely used in Glaucoma detection, and the main indicators observed in Fundus images are the presence of Papillary Atrophy, Cup to Disc Ratio values, diminishing Neural Retinal Rim (NRR), the Inferior Superior Nasal Temporal (ISNT) rule, and Cup Diameter. In this research, we investigated various segmentation and classification techniques that can be applied to Optic disk segmentation and classification of normal and glaucomatous eyes. The proposed method will be beneficial to clinicians and healthcare workers in facilities with limited resources. In this paper, histogram processing is used to determine the type of image, and based on this information; we decide whether the image requires segmentation. Some datasets in the standard dataset contain complete retinal images while others include segmented optic disks. The segmented images are directly given as input for classification using the proposed Convolutional Neural Network (CNN). For complete retinal images, segmentation is performed using the Simple Linear Iterative clustering (SLIC) and normalized graph cut algorithm. The proposed framework's performance is compared with that of pretrained neural networks, including VGG19, InceptionV3, and ResNet50V2, using major metrics. We trained and tested these architectures with 3115 images from six standard datasets. Our proposed framework outperforms all with an accuracy of 96.33 %.

Weakly-supervised structural surface crack detection algorithm based on class activation map and superpixel segmentation

This paper proposes a weakly-supervised structural surface crack detection algorithm that can detect the crack area in an image with low data labeling cost. The algorithm consists of a convolutional neural networks Vgg16-Crack for classification, an improved and optimized class activation map (CAM) algorithm for accurately reflecting the position and distribution of cracks in the image, and a method that combines superpixel segmentation algorithm simple linear iterative clustering (SLIC) with CAM for more accurate semantic segmentation of cracks. In addition, this paper uses Bayesian optimization algorithm to obtain the optimal parameter combination that maximizes the performance of the model. The test results show that the algorithm only requires image-level labeling, which can effectively reduce the labor and material consumption brought by pixel-level labeling while ensuring accuracy.

Global superpixel-merging via set maximum coverage

Due to better boundary adherence and low computational cost, the superpixel segmentation algorithm SLIC (simple linear iterative clustering) has been widely applied in vision-based applications. However, limit to unavoidable over-segmentation problem, one has to consider region-merging to reconstruct entire objects from the segmented superpixels (or called regions). The existing region-merging methods are generated from data clustering, and avoidably suffer from error-merging, slow convergence speed, or easily dropping in LOCAL optimal problems, especially for high-resolution RS (remote sensing) images. In this paper, instead of data clustering, we propose a fast GLOBAL method based on Set Maximum Coverage, termed as MaxCov-merging. Theoretically, the existence of the maximum coverage is proved by using Bayes optimal decision principle. To speed up MaxCov-merging, some heuristic strategies are also provided. Finally, extensive verification and comparison are carried on the public and our collected high-resolution images. Compared with the state-of-the-art methods, the comparison shows the superiority of our MaxCov in terms of the performance of globality, ease of use and fast region-merging speed.

Automatic Detection Method for Black Smoke Vehicles Considering Motion Shadows.

Various statistical data indicate that mobile source pollutants have become a significant contributor to atmospheric environmental pollution, with vehicle tailpipe emissions being the primary contributor to these mobile source pollutants. The motion shadow generated by motor vehicles bears a visual resemblance to emitted black smoke, making this study primarily focused on the interference of motion shadows in the detection of black smoke vehicles. Initially, the YOLOv5s model is used to locate moving objects, including motor vehicles, motion shadows, and black smoke emissions. The extracted images of these moving objects are then processed using simple linear iterative clustering to obtain superpixel images of the three categories for model training. Finally, these superpixel images are fed into a lightweight MobileNetv3 network to build a black smoke vehicle detection model for recognition and classification. This study breaks away from the traditional approach of "detection first, then removal" to overcome shadow interference and instead employs a "segmentation-classification" approach, ingeniously addressing the coexistence of motion shadows and black smoke emissions. Experimental results show that the Y-MobileNetv3 model, which takes motion shadows into account, achieves an accuracy rate of 95.17%, a 4.73% improvement compared with the N-MobileNetv3 model (which does not consider motion shadows). Moreover, the average single-image inference time is only 7.3 ms. The superpixel segmentation algorithm effectively clusters similar pixels, facilitating the detection of trace amounts of black smoke emissions from motor vehicles. The Y-MobileNetv3 model not only improves the accuracy of black smoke vehicle recognition but also meets the real-time detection requirements.

More appropriate DenseNetBL classifier for small sample tree species classification using UAV-based RGB imagery

To effectively classify tree species within datasets characterized by limited samples, we introduced a novel approach named DenseNetBL, founded upon the fusion of the DenseNet architecture and a pivotal bottleneck layer. This bottleneck layer, encompassing a compact convolutional component, played a central role in our methodology. The evaluation of DenseNetBL was conducted under varying conditions, encompassing small-sample tree species data, extensive remote sensing datasets, and state-of-the-art classifiers. Furthermore, a quantitative assessment was executed to extract tree species areas. This was achieved by quantifying pixel areas within manually delineated tree species maps and classifier-generated counterparts. The findings of our study indicated that, in scenarios devoid of pre-trained weights, DenseNetBL consistently outperformed its DenseNet counterpart with equivalent layer numbers. In the realm of small-sample situations, both the Swin Transformer and Vision Transformer exhibited inferior performance when juxtaposed with DenseNet and DenseNetBL. Remarkably, among the shallow architectures, DenseNet33BL showcased superior aptitude for small-sample tree species classification, culminating in the most commendable results (Overall Accuracy (OA) = 0.901, Kappa = 0.892). Conversely, the Vision Transformer yielded the least favorable classification outcomes (OA = 0.767, Kappa = 0.708). The amalgamation of DenseNet33BL and simple linear iterative clustering emerged as the optimal strategy for attaining robust tree species area extraction results across two prototypical forests. In contrast, DenseNet121 exhibited suboptimal performance in the same forests, attaining the least satisfactory tree species area extraction results. These comprehensive findings underscore the efficacy of our DenseNetBL approach in addressing the challenges associated with small-sample tree species classification and accurate tree species area extraction.

Experimental study on instability mechanism and critical intensity of rainfall of high-steep rock slopes under unsaturated conditions

Two critical factors, namely intense precipitation and intricate excavation, can trigger rock mass disasters in mining operations. In this study, an indoor rainfall system was developed to precisely regulate the flow and intensity of precipitation. A large-scale model experiment was conducted on a self-designed physical simulation experiment platform to investigate the failure and instability of high-steep rock slopes under unsaturated conditions. The real-time reproduction of the progressive failure process in high-steep rock slopes enabled the determination of the critical rainfall intensity and revealed the mechanism underlying slope instability. Experiment results indicated that rainfall may be the primary factor contributing to rock mass instability, while continuous pillar mining exacerbates the extent of rock mass failure. The critical failure stage of high-steep rock slopes occurs at a rainfall intensity of 40 mm/h, whereas a rainfall exceeding 50 mm can induce critical instability and precipitation reaching up to 60 mm will result in slope failure. The improved region growing segmentation method (IRGSM) was subsequently employed for image recognition of rock mass deformation in underground mines. Herein an error comparison with the simple linear iterative cluster (SLIC) superpixel method and the original region growing segmentation method (ORGSM) showed that the average identification error in the X and Y directions by the method was reduced significantly (1.82% and 1.80% in IRGSM; 4.70% and 6.26% in SLIC; 9.45% and 12.40% in ORGSM). Ultimately, the relationship between rainfall intensity and failure probability was analyzed using the Monte Carlo method. Moreover, the stability assessment criteria of rock slope under unsaturated condition were quantitatively and accurately evaluated.

Optic disc detection based on fully convolutional network and weighted matrix recovery model.

Eye diseases often affect human health. Accurate detection of the optic disc contour is one of the important steps in diagnosing and treating eye diseases. However, the structure of fundus images is complex, and the optic disc region is often disturbed by blood vessels. Considering that the optic disc is usually a saliency region in fundus images, we propose a weakly-supervised optic disc detection method based on the fully convolution neural network (FCN) combined with the weighted low-rank matrix recovery model (WLRR). Firstly, we extract the low-level features of the fundus image and cluster the pixels using the Simple Linear Iterative Clustering (SLIC) algorithm to generate the feature matrix. Secondly, the top-down semantic prior information provided by FCN and bottom-up background prior information of the optic disc region are used to jointly construct the prior information weighting matrix, which more accurately guides the decomposition of the feature matrix into a sparse matrix representing the optic disc and a low-rank matrix representing the background. Experimental results on the DRISHTI-GS dataset and IDRiD dataset show that our method can segment the optic disc region accurately, and its performance is better than existing weakly-supervised optic disc segmentation methods. Graphical abstract of optic disc segmentation.

Superpixel-based change detection for GPR time-lapse slices using fuzzy c-means and the Markov random field method

Ageing and complex underground utility infrastructure present a significant challenge for modern society, requiring long-term monitoring and maintenance to prevent economic and social costs associated with infrastructure degradation and failure. In this study, we proposed an unsupervised superpixel-based change-detection method using ground-penetrating radar time-lapse slices combining fuzzy c-means and the Markov random field model to investigate an invisible subsurface change due to buried void using time-series measurements. First, simple linear iterative clustering was applied to the difference image, which was generated using paired time-lapse images after intensity registration to create different scales superpixel maps. Then, fuzzy c-means clustering was used to generate superpixel-based change maps. Finally, the Markov random field model was used to integrate the information of adjacent neighbourhoods in three dimensions to iteratively refine the change map. We designed two underground cavities (one representing shallow local voids and the other representing voids near pipeline networks) to verify the capability and adaptability of the proposed method. The experimental results demonstrate the feasibility of the method, with F1-scores of 0.82, 0.69, 0.69, and 0.65 and kappa coefficients of 0.81, 0.69, 0.68, and 0.64. Our method represents a significant contribution to the field of GPR-based change detection and has the potential to improve the long-term monitoring and maintenance of complex underground utility infrastructure.

A Robust SLIC Based Approach for Segmentation Using Canny Edge Detector

An accurate image segmentation in noisy environment is complex and challenging. Unlike existing state-of-the-art methods that use superpixels for successful segmentation, we propose a new approach for noise-robust SLIC (Simple Linear Iterative Clustering) segmentation that incorporates a Canny edge detector. By leveraging Canny edge information, the proposed method modifies the pixel intensity distance measurement to overcome boundary adherence challenge. Furthermore, we adopt a selective approach to update cluster centers, focusing on pixels that contribute less to the noise. Extensive experiments on synthetic noisy images demonstrate the effectiveness of our approach. It significantly improves SLIC's performance in noisy image segmentation and boundary adherence, making it a promising technique for vision processing tasks.