Search

Sea fog detection is a challenging and essential issue in satellite remote sensing. Although conventional threshold methods and deep learning methods can achieve pixel-level classification, it is difficult to distinguish ambiguous boundaries and thin structures from the background. Considering the correlations between neighbor pixels and the affinities between superpixels, a correlation context-driven method for sea fog detection is proposed in this letter, which mainly consists of a two-stage superpixel-based fully convolutional network (SFCNet), named SFCNet. A fully connected Conditional Random Field (CRF) is utilized to model the dependencies between pixels. To alleviate the problem of high cloud occlusion, an attentive Generative Adversarial Network (GAN) is implemented for image enhancement by exploiting contextual information. Experimental results demonstrate that our proposed method achieves 91.65% mIoU and obtains more refined segmentation results, performing well in detecting fogs in small, broken bits and weak contrast thin structures, as well as detects more obscured parts. [ABSTRACT FROM AUTHOR]

Efficient analysis of Haematoxylin and Eosin stained histopathology images has become a challenge in digital pathology work-flow. We propose a Multi-view Attention Superpixel-guided Generative Adversarial Network (MASG-GAN) to achieve the multi-task learning for nuclei segmentation and benign-malignant tissue classification. Firstly, a novel superpixel segmentation approach driven by Bounded Asymmetric Gaussian Mixture Model (BAGMM) is presented for generating superpixel-prior probability map with high-level semantics. Then, we develop a generator network that integrates student-branch and teacher-branch. Concretely, the teacher-branch takes superpixel-prior probability map as input and guides the student-branch for accurate segmentation and classification. Then in generator, we build a light-weight U-shaped block (LUB) that consists of depthwise separable convolutions with mini encoding-decoding structure to reduce network computational cost. Finally, a Multi-view Attention Module (MVAM) is designed for further enhance the segmentation quality of nuclei with small area and unclear boundary. Extensive experiments on five benchmark datasets demonstrate that our pipeline outperforms some state-of-the-art methods, especially in terms of efficiency. [ABSTRACT FROM AUTHOR]

For the co-saliency detection algorithm of an RGBD image that may have incomplete detection of common salient regions and unclear boundaries, we proposed an improved co-saliency detection method of RGBD images based on superpixels and hypergraphs. First, we optimized the depth map based on edge consistency, and introduced the optimized depth map into the SLIC algorithm to obtain the better superpixel segmentation results of RGBD images. Second, the color features, optimized depth features and global spatial features of superpixels were extracted to construct a weighted hypergraph model to generate saliency maps. Finally, we constructed a weighted hypergraph model for co-saliency detection based on the relationship of color features, global spatial features, optimized depth features and saliency features among images. In addition, in order to verify the impact of the symmetry of the optimized depth information on the co-saliency detection results, we compared the proposed method with two types of models, which included considering depth information and not considering depth information. The experimental results on Cosal150 and Coseg183 datasets showed that our improved algorithm had the advantages of suppressing the background and detecting the integrity of the common salient region, and outperformed other algorithms on the metrics of P-R curve, F-measure and MAE.

Graph filtering is an important part of graph signal processing and a useful tool for image denoising. Existing graph filtering methods, such as adaptive weighted graph filtering (AWGF), focus on coefficient shrinkage strategies in a graph-frequency domain. However, they seldom consider the image attributes in their graph-filtering procedure. Consequently, the denoising performance of graph filtering is barely comparable with that of other state-of-the-art denoising methods. To fully exploit the image attributes, we propose a guided intra-patch smoothing AWGF (AWGF-GPS) method for single-image denoising. Unlike AWGF, which employs graph topology on patches, AWGF-GPS learns the topology of superpixels by introducing the pixel smoothing attribute of a patch. This operation forces the restored pixels to smoothly evolve in local areas, where both intra- and inter-patch relationships of the image are utilized during patch restoration. Meanwhile, a guided-patch regularizer is incorporated into AWGF-GPS. The guided patch is obtained in advance using a maximum-a-posteriori probability estimator. Because the guided patch is considered as a sketch of a denoised patch, AWGF-GPS can effectively supervise patch restoration during graph filtering to increase the reliability of the denoised patch. Experiments demonstrate that the AWGF-GPS method suitably rebuilds denoising images. It outperforms most state-of-the-art single-image denoising methods and is competitive with certain deep-learningmethods. In particular, it has the advantage of managing images with significant noise. [ABSTRACT FROM AUTHOR]

Diabetic Retinopathy (DR) is a severe complication of chronic diabetes causing significant visual deterioration and may lead to blindness with delay of being treated. Exudative diabetic maculopathy, a form of macular edema where hard exudates (HE) develop, is a frequent cause of visual deterioration in DR. The detection of HE comprises a significant role in the DR diagnosis. In this paper, an automatic exudates detection method based on superpixel multi-feature extraction and patch-based deep convolutional neural network is proposed. Firstly, superpixels, regarded as candidates, are generated on each resized image using the superpixel segmentation algorithm called Simple Linear Iterative Clustering (SLIC). Then, 25 features extracted from resized images and patches are generated on each feature. Patches are subsequently used to train a deep convolutional neural network, which distinguishes the hard exudates from the background. Experiments conducted on three publicly available datasets (DiaretDB1, e-ophtha EX and IDRiD) demonstrate that our proposed methodology achieved superior HE detection when compared with current state-of-art algorithms. [ABSTRACT FROM AUTHOR]

Copyright of Remote Sensing for Natural Resources is the property of Remote Sensing for Natural Resources Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Guangdong University of Technology is the property of Journal of Guangdong University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

One open issue of target detection for synthetic aperture radar (SAR) images is the capture effect from the clutter edge and the interfering outliers, including surrounding targets in the multitarget environment, sidelobes, and ghosts. To address this issue, a superpixel-level constant false-alarm rate (CFAR) detector is proposed based on the truncated Gamma statistics for the multilook intensity SAR data. Superpixel segmentation serves as a preprocessing procedure to divide the SAR image into meaningful patches. By automatic clutter truncation in the superpixel-level background clutter window, the real clutter samples are preserved. The experimental results with real SAR images demonstrate that the proposed method achieves better goodness-of-fit performance for the real clutter background with outlier exclusion, yielding a higher target detection rate in the multitarget environments. [ABSTRACT FROM AUTHOR]

Data augmentation is an important paradigm for boosting the generalization capability of deep learning in image classification tasks. Image augmentation using cut-and-paste strategies has shown very good performance improvement for deep learning. However, these existing methods often overlook the image's discriminative local context and rely on ad hoc regions consisting of square or rectangular local regions, leading to the loss of complete semantic object parts. In this work, we attempt to overcome these limitations and propose a superpixel-wise local-context-aware efficient image fusion approach for data augmentation. Our approach requires only one forward propagation using a superpixel attention-based label fusion with less computational complexity. The model is trained using a combination of a global classification of the fused (augmented) image loss, a superpixel-wise weighted local classification loss, and a superpixel-based weighted contrastive learning loss. The last two losses are based on the superpixel-aware attentive embeddings. Thus, the resulting deep encoder can learn both local and global features of the images while capturing object-part local context and information. Experiments on diverse benchmark image datasets indicate that the proposed method out-performs many region-based augmentation methods for visual recognition. We have demonstrated its effectiveness not only on CNN models but also on transformer models. The codes are accessible at https://github.com/DanielaPlusPlus/SAFuse. • We note the potential drawbacks of existing Cutmix augmentation strategies. • We present a superpixel-based pairwise image fusion for data augmentation. • It can capture the most discriminative semantically image regions. • Selected superpixels are contrasted and classified; fused images are classified. • We perform extensive experiments with different CNN and Transformer backbones. [ABSTRACT FROM AUTHOR]

In the intra-hour time scale, shielding of solar radiation by clouds is the main reason for the fluctuation of photovoltaic, so cloud parameters are important for intra-hour solar irradiance and photovoltaic power forecasting. Extracting cloud regions from cloud images provides a basis for quantifying cloud size and shape. It is difficult to detect clouds in these three cases, such as clouds in circumsolar region, clouds in haze weather and thin clouds at cloud edge. Aiming at such problems, this study firstly establishes a clear sky library based on pixel-level sun positions and haze conditions to deal with the complex changes of sky brightness. Then this study proposes a cloud detection method for ground-based images, which performs two segmentations on the cloud image. The initial segmentation process is a combination method that uses clear sky library method when the sun is visible and uses adaptive threshold method when the sun is occluded. The secondary segmentation process is based on superpixels and local threshold method, which restores some thin clouds that are easily ignored. Finally, for the influence of ghosts, this study summarizes the position and color features of ghosts, and uses different color channel information to deal with them. [Display omitted] [ABSTRACT FROM AUTHOR]

Superpixels can define meaningful local regions within a hyperspectral image (HSI) and have become the building blocks of various HSI classification methods. The superpixels in HSIs consist of multiple spectral pixels, sharing a similar structure with the data in multi-instance learning (MIL). However, the potential of MIL methods in the field of HSI classification has been rarely explored. In this paper, we propose the superpixel-based multi-scale multi-instance learning (MSMIL) framework, enhancing the superpixel representation with MIL for the first time. Segmenting the HSIs with superpixels, MSMIL converts the HSI classification into MIL problems and extracts superpixel representations via the MIL method, namely multi-instance factor analysis (MIFA). Compared with the existing methods focusing exclusively on the local information, MIFA utilizes the deviations from an overall generative model to describe the superpixels, retaining both the local and the global information. Moreover, MSMIL introduces multi-scale superpixels and a spectral–spatial decision fusion strategy for further refinement, where the results of multi-scale superpixel maps are weighted according to prediction certainty and spatial consistency. The proposed method is evaluated on four benchmark datasets and achieves competitive results. For example, MSMIL outperforms the comparison methods with a margin of 5% overall accuracy on the Indian Pines dataset, when 2% pixels are selected as the training set. • Convert hyperspectral classification into multi-instance learning (MIL) problems. • Enhance the superpixel representation with MIL methods. • Retain both the local and global information during superpixel feature extraction. • Utilize prediction certainty and spatial consistency for decision fusion. • The superiority of proposed framework (MSMIL) was shown on four benchmarks. [ABSTRACT FROM AUTHOR]

The just noticeable distortion (JND) model reveals the visibility limitation. Human eyes hold different attention and sensitivity to different regions owing to different contributions to the perceptual quality. In this paper, a superpixel-wise JND model based on region (RJND) is proposed. First, an image is segmented into superpixels by the simple linear iterative clustering (SLIC). Then, region color contrast is calculated for each region and foveation regions are selected for the image. Based on the human visual perception, a region weighting model is established by incorporating region color contrast and foveation regions modulation. Considering the contrast masking (CM) effect is not perfect, we introduce the texture coarseness combined with CM effect for a more accurate visual masking effect. Finally, a new region JND model is established by combining the region weighting model and the coarseness modulation. The experimental results demonstrate the proposed RJND model can decrease PSNR more efficiently compared with some existing JND models when achieving nearly the same subjective perceptual quality. It can remove much more visual redundancy.

Image haze removal is critical for autonomous driving. However, it is a challenging task for the existing image dehazing algorithms to eliminate the block effect completely and handle objects similar to light (such as snowy objects and white buildings). To address this problem, we propose a novel single-image dehazing method based on superpixels and Markov random field. We obtain the transmission map in the superpixel domain to eliminate the block/halo effect and introduce Markov random field to revise the transmission map in the superpixel domain. The key idea is that the sparsely distributed, incorrectly estimated transmittances can be corrected by properly characterizing the spatial dependencies between the incorrectly estimated superpixels and the neighbouring well-estimated superpixels. The experimental results demonstrate that the proposed method outperforms state-of-the-art image dehazing methods.

Although various methods can effectively segment synthetic aperture radar (SAR) images, we found that the method combining superpixel and image edge information can get better results. To solve the problem that common SAR image segmentation methods often segment pixels incorrectly in edge region, a superpixel boundary-based edge description algorithm (SpBED) is proposed. First, an edge detection method with three edge detectors is used. Therefore, accurate strong edges of SAR images can be extracted, and false edges that are easy to appear in a single detection method can be effectively eliminated. Then the weak edges of the image are extracted by superpixel generation algorithm. The extracted weak edges can supplement the edge information that is difficult to extract by edge detection. Superpixel boundaries are also used to carry the strong edges, so that the strong and weak edges can be completely represented by superpixel boundaries. Finally, boundary constraint superpixel smoothing is used to reduce the effects of noise, and k-means algorithm is performed on superpixels. Since edge information is carried by superpixels, it effectively guarantees the segmentation accuracy in edge region. Compared with seven state-of-the-art algorithms, segmentation results on simulated images and real images demonstrate the effectiveness of the proposed SpBED.

The rapid and accurate detection of damaged buildings after an earthquake are critical for emergency response. Given the difference in the textures of damaged parts and those of the original buildings, damaged buildings can be accurately detected through textural heterogeneity. However, quantitatively detecting damaged buildings using such heterogeneity from post-earthquake images is difficult. Therefore, we propose a method of automatically extracting house damage information from post-quake high-resolution optical remote sensing imagery through the multiscale fusion of spectral and textural features, which can be achieved in three steps. Firstly, the textural and spectral features of the images are enhanced at the pixel level. Secondly, the resulting feature images are fused at the feature level and the fused feature images are segmented using superpixels. Lastly, a post-quake house damage index model is constructed. Results show an overall accuracy of 76.75%, 75.35% and 83.25% for three different types of imagery. This finding indicates that the proposed algorithm can be used to extract damage information from multisource remote sensing data and provide useful guidance for post-disaster rescue and assessment based on regional house damage conditions.

Morphological features have shown promising performances for hyperspectral image (HSIs) classification, as they can efficiently extract the multilevel spatial information of HSIs. However, the objects in the scenes are always with different sizes and shapes, making it difficult to excavate spatial information of important structures completely by the existing morphological methods. To address this problem, we propose a novel two-stage framework based on morphology and superpixel. Specifically, we propose self-dual saliency profiles (SPs) based on a saliency measure considering the grayscale contrast within objects and edge information. SPs are hierarchical features that characterize spatial information for salient objects whose saliency index is the significant local maxima. The SPs are constructed based on a two-step algorithm. First, all salient objects of different shapes in the scene are preserved, and the undesired spatial details are discarded by attribute filters based on the saliency measure. Second, the morphological feature is generated based on the organization structure of salient objects in the scene, which provides hierarchical spatial features of the image. Then, the superpixel segmentation is performed on each of the extracted SPs on the basis of the spatial information of salient objects. And, two types of superpixel-based features are extracted from SPs to exploit the information in SPs. The extracted innersuperpixel and intersuperpixel features are fused with spectral information to produce the classification map. The experiments conducted on three HSIs show that, the proposed approach significantly outperforms the other state-of-the-art methods.

Automatic and reliable segmentation of the pancreas is an important but difficult task for various clinical applications, such as pancreatic cancer radiotherapy and computer-aided diagnosis (CAD). The main challenges for accurate CT pancreas segmentation lie in two aspects: (1) large shape variation across different patients, and (2) low contrast and blurring around the pancreas boundary. In this paper, we propose a two-stage, ensemble-based fully convolutional neural network (FCN) to solve the challenging pancreas segmentation problem in CT images. First, candidate region generation is performed by classifying patches generated by superpixels. Second, five FCNs based on the U-Net architecture are trained with different objective functions. For each network, 2.5D slices are used as the input to provide 3D image information complementarily without the need for computationally expensive 3D convolutions. Then, an ensemble model is utilized to combine the five output segmentation maps and achieve the final segmentation. The proposed method is extensively evaluated on a publicly available dataset of 82 manually segmented CT volumes via 4-fold cross-validation. Experimental results show its superior performance compared with several state-of-the-art methods with a Dice coefficient of 84.10±4.91% and Jaccard coefficient of 72.86±6.89%.

The superpixel-based multiple kernels model uses the average value of all pixels within superpixel as the spatial feature, which results in inaccurate extraction of edge pixels. To solve this problem, a local binary patterns and superpixel-based multiple kernels method is proposed for hyperspectral image (HSI) classification. First, the original HSI is segmented into multiple superpixels by using the entropy rate superpixel segmentation algorithm. On the HSI with superpixel index, the spectral kernel is second obtained by combining the spectral feature map with the radial basis kernel (RBF). By introducing local binary pattern (LBP) and weighted average filtering into RBF, the spatial kernels are obtained within and among superpixels. Finally, the combined kernel containing the abovementioned three kernels is inputted into the support vector machine classifier to generate a classification map. The experimental procedure in this article uses LBP to extract the information in superpixels, which effectively prevents the loss of edge features in superpixels. The experimental results show that the proposed method is superior to the state-of-the-art classifiers for HSI classification.

The road network is of great importance to the modern traffic system, which changes frequently as its high speed of development. Simultaneously, a growing number of satellites provide a considerable number of remote sensing images that can be used for road extraction. However, most existing methods cannot get accurate results in the high-resolution remote sensing, since the complex background like the shadows and occlusions. Consequently, we proposed a method utilizing the volunteered geographic information data to extract the road from satellite images. At first, from Mapbox platform, the Volunteered Geographic Information data, OpenStreetMap vector tiles are collected to guide the downloading of corresponding road satellite images. Then a level set method is used to extract the road areas from the satellite images supported by the road vector. After that, a superpixel method is applied to improve the road areas by fusing the superpixels with the previous results. Experiments are performed on the satellite images from Mapbox, Google, and Yahoo in the Tianjin Port district on accuracy and efficiency. Experimental results demonstrate that our approach is more accurate and of higher performance than the other two state-of-the-art methods.

Superpixel is an essential tool for computer vision. In practice, classic superpixel algorithms do not exhibit good boundary adherence with fewer superpixels, which will greatly hamper further analysis. To remedy the defect, a superpixel boundary optimization framework is proposed in this paper. There are three steps in the framework. Firstly, based on the proposed information measure function, the under-segmented superpixels generated by classic superpixel algorithms are screened out. Secondly, with the two invariant centroids method, these under-segmented superpixels are re-segmented to improve the accuracy in boundary adherence. Finally, smaller superpixels are merged to maintain the same number with initial superpixels. Quantitative evaluations on the BSDS500 exhibit that the performance of the classic superpixel algorithms is improved by employing the framework, especially on the condition of fewer superpixels.

Diabetic retinopathy (DR) is an eye abnormality caused by chronic diabetes that affected patients worldwide. Hard exudate is an important and observable sign of DR and can be used for early diagnosis. In this paper, an automatic hard exudates segmentation method is proposed in order to aid ophthalmologists to diagnose DR in the early stage. We utilized the SLIC superpixel algorithm to generate sample patches, thus overcoming the difficulty of the limited and imbalanced dataset. Furthermore, a U-net based network architecture with inception modules and residual connections is proposed to conduct end-to-end hard exudate segmentation, and focal loss is utilized as the loss function. Extensive experiments have been conducted on the IDRiD dataset to evaluate the performance of the proposed method. The reported sensitivity, specificity, and accuracy achieve 96.38%, 97.14%, and 97.95% respectively, which demonstrates the effectiveness and superiority of our method. The achieved segmentation results prove the potential of the method for clinical diagnosis.

We present a novel technique to distinguish between an original image and its histogram equalized version. Histogram equalization and superpixel segmentation such as SLIC (simple linear iterative clustering) are very popular image processing tools. Based on these two concepts, we introduce a method for finding whether an image (grayscale) is histogram equalized or not. Because sometimes we see images that look visually similar but they are actually processed or changed by some image enhancement process such as histogram equalization. We can merely infer whether the image is dark, bright or has a small dynamic range. Moreover, we also compare the result of SLIC superpixels with three other superpixel segmentation algorithms namely, quick shift, watersheds, and Felzenszwalb’s segmentation algorithm

We discuss requirements for the multispectral remote sensing (RS) data utilized in the author's technique for estimating plant species concentration to detect arable land colonization by tree and shrubbery vegetation. The study is carried out using available high-resolution remote sensing data of two arable land plots. The paper considers the influence of resolution, combinations of spectral channels of RS data, as well as the season RS data is acquired on the quality of identification of elementary vegetation classes that form the basis of the plant community – a fallow land. A fallow land represents a piece of arable land that has not been cultivated for a long time. The study was conducted using a technology that is based on image superpixel segmentation. We found out that for determining tree and shrub vegetation, it is preferable to use RS data acquired in autumn, namely, in late September. The combination of red and blue spectral channels turned out to be the best for the analysis of tree-shrub vegetation against the background of grassy plant communities, and the presence of a near-infrared channel is necessary to range the various grassy plant communities in different classes. RS data with a spatial resolution of 2.5 m can be used to define tree-shrub plant communities with a high closeness of crowns (90 % or more), but cannot be used to classify isolated trees. Trees and shrubs (with a height of 8 m) can be classified in images with a spatial resolution of 0.8 m. An increase in spatial resolution does not improve the quality of the classification. The highest accuracies achieved for the land areas studied are 90 % and 83 %. Therefore, the suggested technology can be used in arable land expertise.

Abstract Background The automatic glioma segmentation is of great significance for clinical practice. This study aims to propose an automatic method based on superpixel for glioma segmentation from the T2 weighted Magnetic Resonance Imaging. Methods The proposed method mainly includes three steps. First, we propose an adaptive superpixel generation algorithm based on simple linear iterative clustering version with 0 parameter (ASLIC0). This algorithm can acquire a superpixel image with fewer superpixels and better fit the boundary of region of interest (ROI) by automatically selecting the optimal number of superpixels. Second, we compose a training set by calculating the statistical, texture, curvature and fractal features for each superpixel. Third, Support Vector Machine (SVM) is used to train classification model based on the features of the second step. Results The experimental results on Multimodal Brain Tumor Image Segmentation Benchmark 2017 (BraTS2017) show that the proposed method has good segmentation performance. The average Dice, Hausdorff distance, sensitivity, and specificity for the segmented tumor against the ground truth are 0.8492, 3.4697 pixels, 81.47, and 99.64%, respectively. The proposed method shows good stability on high- and low-grade glioma samples. Comparative experimental results show that the proposed method has superior performance. Conclusions This provides a close match to expert delineation across all grades of glioma, leading to a fast and reproducible method of glioma segmentation.

To overcome the difficulty of similarity expression and the effects of speckle noise in unsupervised classification of Polarimetric Synthetic Aperture Radar (PolSAR) images, a novel unsupervised PolSAR image terrain classification algorithm based on Tensor Product Graph (TPG) diffusion has been developed herein. Generally, TPG diffusion is usually utilized for optical image segmentation or image retrieval. In the present study, it can be used for PolSAR image terrain classification. TPG diffusion can robustly estimate geodesic distances; therefore, it can be used for mining the intrinsic affinity between data points. First, the PolSAR image is over-segmented into many superpixels. Second, seven features are extracted based on the segmented superpixels to form a feature vector and construct a similarity matrix by using the Gaussian kernel. Third, TPG diffusion is performed on this similarity matrix to obtain another similarity matrix with stronger discriminability by propagating affinity information along the mainfold structure of data to achieve the global affinity measure. Finally, spectral clustering based on the diffused similarity matrix is adopted to perform terrain classification. Extensive experiments conducted on both simulated and real-world PolSAR images demonstrate that our approach can effectively combine neighborhood information and achieve higher classification accuracy, compared to four other competitive state-of-the-art methods.

Accurate lung parenchyma segmentation plays an important role in lung disease diagnosis, which contributes to improving the survival rate and prognostic conditions. However, image noises, complex thorax tissue structures, large individual diferences, and so on make lung segmentation a complex task. In this paper, an automatic lung parenchyma segmentation algorithm based on superpixels and matrix degree of grey incidences is presented to address the problem. Lung CT image is first preprocessed with a group of morphological operations and then divided into a set ofsuperpixels. Then, matrix grey incidence is utilized to classify the superpixels of the thorax into lung tissues and pleural tissues after the reference superpixels were extracted. Finally, the segmentation results are refined with a contour correction approach based on corner detection and convex hull to facilitate accurate lung contours. The segmentation results of our algorithm are compared with ground truths, and experimental results show that the proposed algorithm achieves high accuracy, and the average Jaccard's similarity index is more than 92%. [ABSTRACT FROM AUTHOR]

Superpixels are widely used in computer vision applications. Most of the existing superpixel methods use established criteria to indiscriminately process all pixels, resulting in superpixel boundary adherence and regularity being unnecessarily inter-inhibitive. This study builds upon a previous work by proposing a new segmentation strategy that classifies image content into meaningful areas containing object boundaries and meaningless parts that include color-homogeneous and texture-rich regions. Based on this classification, we design two distinct criteria to process the pixels in different environments to achieve highly accurate superpixels in content-meaningful areas and keep the regularity of the superpixels in content-meaningless regions. Additionally, we add a group of weights when adopting the color feature, successfully reducing the undersegmentation error. The superior accuracy and the moderate compactness achieved by the proposed method in comparative experiments with several state-of-the-art methods indicate that the content-adaptive criteria efficiently reduce the compromise between boundary adherence and compactness. [ABSTRACT FROM AUTHOR]

We propose a novel algorithm for the restoration of a degraded hyperspectral image. The proposed algorithm exploits the spatial as well as the spectral redundancy of a degraded hyperspectral image in order to restore it without having any prior knowledge about the type of degradation present. Our work uses superpatches to exploit the spatial and spectral redundancies. We formulate a restoration algorithm incorporating structural similarity index measure as the data fidelity term and nuclear norm as the regularization term. The proposed algorithm is able to cope with additive Gaussian noise, signal dependent Poisson noise, mixed Poisson-Gaussian noise and can restore a hyperspectral image corrupted by dead lines and stripes. As we demonstrate with the aid of extensive experiments, our algorithm is capable of recovering the spectra even in the case of severe degradation. A comparison with the state-of-the-art low rank hyperspectral image restoration methods via experiments with real world and simulated data establishes the competitiveness of the proposed algorithm with the existing methods. [ABSTRACT FROM AUTHOR]

Multi-exposure image fusion (MEF) algorithms have been used to merge a stack of low dynamic range images with various exposure levels into a well-perceived image. However, little work has been dedicated to predicting the visual quality of fused images. In this work, we propose a novel and efficient objective image quality assessment (IQA) model for MEF images of both static and dynamic scenes based on superpixels and an information theory adaptive pooling strategy. First, with the help of superpixels, we divide fused images into large- and small-changed regions using the structural inconsistency map between each exposure and fused images. Then, we compute the quality maps based on the Laplacian pyramid for large- and small-changed regions separately. Finally, an information theory induced adaptive pooling strategy is proposed to compute the perceptual quality of the fused image. Experimental results on three public databases of MEF images demonstrate the proposed model achieves promising performance and yields a relatively low computational complexity. Additionally, we also demonstrate the potential application for parameter tuning of MEF algorithms. [ABSTRACT FROM AUTHOR]

Spectral clustering is a popular clustering algorithm, which has a large number of applications in image segmentation tasks. However, its applicability becomes difficult for high-resolution images due to high computational complexity. In this paper, we first propose a novel Fast Spectral Clustering algorithm based on quad-tree decomposition. The algorithm focuses on the spectral clustering at the superpixel level and its time complexity is O (n log n) + O (m) + O (m 3 2 ) , its space complexity is O(m), where n and m represent the number of pixels and superpixels in an image, respectively. Then we propose Multiscale Fast Spectral Clustering by improving Fast Spectral Clustering, which is a bottom-up method based on the quad-tree and the related hierarchical structure. In this method, according to the hierarchical structure generated by the quad-tree, treating the child node's segmentation result as the superpixel of the parent node, the child nodes at the fine level can be merged into the parent nodes at the coarse level. The time complexity of Multiscale Fast Spectral Clustering is O (n log n) and its space complexity is O(m). Extensive experiments on both the Weizmann and BSDS500 segmentation datasets demonstrate that Multiscale Fast Spectral Clustering outperforms Normalized cut, a classical spectral clustering method, in terms of lower computational complexity and memory cost, with comparable clustering accuracy. [ABSTRACT FROM AUTHOR]

Generating a sufficient number of regions with high accuracy is an important objective in the region proposal generation techniques. This paper presents a new, robust, and effective approach, which is based on the bottom-up segmentation, to produce a pool of well-quality regions. After image segmentation, the segmented candidates are expanded into the surrounding regions. The suggested algorithm produces some enlarged regions, which better cover objects and stuff. The proposed process can be applied in three different modes, namely fixed_mode, all_mode, and efficient_mode. The fixed_mode extends each region into parts of all the adjacent regions using an extension controller, which considers adjacent sequential pixels for each point on the region boundary. In all_mode, the current region is merged with all the adjacent regions to generate a larger region. The efficient_mode is then implemented using the accumulation of the results from both the fixed_mode and all_mode. Besides, the algorithm can be repeated in the fixed_mode and all_mode by considering a variety of values for the extension controller factor. No features are required to be extracted in the proposed algorithm, except for the image segmentation stage. In this study, four challenging datasets known as MSRC, VOC2007, VOC2012, and COCO 2017 are used to compare the proposed algorithm with other segmentation and region proposal algorithms. As a significant advantage compared to well-known region proposal algorithms, our approach achieves a greater Recall with the desirable number of regions. Furthermore, the algorithm shows a good improvementin extraction of small, medium, and large objects. [ABSTRACT FROM AUTHOR]

Visual object tracking is to locate an object of interest in a sequence of consecutive video frames, which is widely applied in many high-level computer vision tasks such as intelligent video surveillance and robotics. It is of great challenges for visual tracking methods to handle large target appearance variations caused by pose deformation, fast motion, occlusion, and surrounding environments in real-time videos. In this paper, inspired by human attention cognitive saliency model, we propose a visual tracking method based on salient superpixels which integrates the target appearance similarity and cognitive saliency, and helps to location inference and appearance model updating. The saliency of superpixel is detected by graph model and manifold ranking. We cluster the superpixels of the first four target boxes into a set corresponding to object foreground and model the target appearance with color descriptors. While tracking, the relevance is computed between the candidate superpixels and the target appearance set. We also propose an iterative threshold segmentation method to distinguish the foreground and background of superpixels based on saliency and relevance. To increase the accuracy of location inference, we explore particle filter in both confidence estimation and sampling procedures. We compared our method with the existing techniques in OTB100 dataset in terms of precision based on center location error and success rate based on overlap, and the experimental results show that our proposed method achieved substantially better performance. Promising results have shown that the proposed salient superpixel-based approach is effective to deformation, occlusion, and other challenges in object tracking. [ABSTRACT FROM AUTHOR]

Superpixel-based clustering approach gains attention as an efficient pre-processing step for image segmentation during the last decade. In general, color similarity and position of the pixels are used as similarity metrics for segmentation. In this proposed work, a two-level object segmentation framework is proposed, where the mid-level cues are meritoriously utilized for efficient object segmentation. In the first level, a superpixel-based object boundary gimmicking algorithm with improved distance measure is used to gimmick the cluster boundaries. To make the picture visualization as human vision friendly, the regular clusters are decomposed literally only at the required places to adhere with object boundaries. Spurious Clusters are identified and merged to remove the noisy superpixels. As a post-processing step, superpixel-based optimized conditional random field (CRF) with random association (SOCRA) algorithm is proposed for efficient segmentation. Here homogeneity of the superpixel is imposed by optimized CRF to augment the object clusters with random associations. CRFs are employed for its excellent capability to characterize the relationship among the random variables. Extensive performance evaluation shows the proposed boundary gimmicking approach significantly competes with the state-of-the-art methods. Results obtained with Berkeley segmentation dataset (BSDS300) are compared with state-of-the-art methods in terms of under segmentation error, boundary recall, and achievable segmentation accuracy. [ABSTRACT FROM AUTHOR]

In this article, the authors suggested a rotation-invariant local binary pattern-based weighted generalized closest neighbor (RILBP-WGCN) method for HSI classification. The proposed RILBP is an enhanced texture-based classification paradigm that utilizes local binary pattern filter for some designated bands to generate a broad sketch of spatial texture information. Likewise, the proposed WGCN technique efficiently maintains the spatial uniformity between the nearby pixels via utilizing a local weight scheme and point-to-set distance. Also, as a postprocessing step, a label enhancement method is included for additional enhancement of the label uniformity as well as increases the performance of classification method. The color composite remotely sensed image of the initial three subsequent bands is segmented into several consistent regions by utilizing the graph-based superpixel segmentation technique. Then, extracted super pixels have been made extra homogeneous by utilizing a segment grouping process. Finally, advanced decision-level fusion is also applied on the retrieved local LBP features and unique spectral features, where linear opinion pool executes a serious role for concatenating the probabilistic outcomes of numerous spectral as well as texture features. The authors evaluated the proposed technique by comparing them with the seven competing methods on numerous datasets related to HSI classification. Evaluation results confirmed that the classification effects of proposed RILBP-WGCN algorithm are significantly better in contrast to other competing classification schemes. [ABSTRACT FROM AUTHOR]

Given that existing salient object detection methods cannot effectively predict the fine contours of salient objects when extracting local or global contexts and features, we propose a novel contour self-compensated network (CSCNet) to generate a more accurate saliency map with complete contour. Unlike the common binary saliency detection, we reconstruct the salient object detection problem into a multi-classification problem of the background, the salient object, and the salient contour, where the salient contour is used as the third label for ground truth. Meanwhile, the image and its superpixel map are concatenated as the input of our network to add more edge information. Also, a penalty loss is proposed to restrict the spatial relationship between the background, objects, and their contours. Experimentally, we evaluate the proposed CSCNet on six benchmark datasets in both accuracy and efficiency and evaluate the attribute-based performance on the SOC dataset. Compared with 13 state-of-the-art algorithms, our CSCNet can detect salient objects more accurately and completely without adding too many convolutional layers and parameters. [ABSTRACT FROM AUTHOR]

As one of the most popular preprocessing steps in computer vision fields, superpixel generation algorithm has been extensively studied in recent years. Researchers have to find a way to produce superpixels with both accuracy and computationally efficiency. Inspired by the real-time superpixel segmentation method using density-based spatial clustering of applications with noise (DBSCAN), we propose a two-stage, non-iterative superpixel segmentation approach. In the first stage, we produce the initial regions. To make the superpixels attach to most object boundaries well, we define an adaptive parameter based on the boundary probability map in the distance measurement. At the same time, we adopt the averaging colors of region to represent the cluster center feature. In the second stage, we merge small regions to produce superpixels. To make them have uniform sizes, we take the initial region size into consideration and define a new distance measurement between the two neighboring regions. In the whole framework, we process all the pixels only once. We test the proposed method on the public data sets. The experimental results show that our proposed algorithm outperforms the most compared approaches with accuracy and has competitive speed with the real-time methods (e.g., DBSCAN). [ABSTRACT FROM AUTHOR]

Computer-assisted algorithms have become a mainstay of biomedical applications to improve accuracy and reproducibility of repetitive tasks like manual segmentation and annotation. We propose a novel pipeline for red blood cell detection and counting in thin blood smear microscopy images, named RBCNet, using a dual deep learning architecture. RBCNet consists of a U-Net first stage for cell-cluster or superpixel segmentation, followed by a second refinement stage Faster R-CNN for detecting small cell objects within the connected component clusters. RBCNet uses cell clustering instead of region proposals, which is robust to cell fragmentation, is highly scalable for detecting small objects or fine scale morphological structures in very large images, can be trained using non-overlapping tiles, and during inference is adaptive to the scale of cell-clusters with a low memory footprint. We tested our method on an archived collection of human malaria smears with nearly 200,000 labeled cells across 965 images from 193 patients, acquired in Bangladesh, with each patient contributing five images. Cell detection accuracy using RBCNet was higher than 97 %. The novel dual cascade RBCNet architecture provides more accurate cell detections because the foreground cell-cluster masks from U-Net adaptively guide the detection stage, resulting in a notably higher true positive and lower false alarm rates, compared to traditional and other deep learning methods. The RBCNet pipeline implements a crucial step towards automated malaria diagnosis. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This letter introduces a novel spatial–spectral classification method for hyperspectral images (HSIs) based on a structural-kernel collaborative representation (SKCR), which considers one weak assumption of spatial neighborhood that of the pixels in a superpixel belong to the same class when exploiting contextual information in HSI. The proposed method consists of the following steps. First, a superpixel segmentation strategy is used to construct self-adaptive regions for the HSI. Then, the structural information within each superpixel block is extracted based on the density peak and K nearest neighbors. Next, dual kernels are separately utilized for the exploitation of the spectral and the spatial information. Finally, the dual kernels are combined and incorporated into a support-vector-machine classifier. Since the weak assumption of spatial neighborhood is well considered in the collaborative representation, the proposed method showed excellent classification performance for two widely used real hyperspectral data sets even when the number of training samples was relatively small. [ABSTRACT FROM AUTHOR]

Low-rank subspace representations have been observed to be well-suited to hyperspectral imagery, which tends to have a global structure composed of a small number of ground-cover signatures, and additional graph-based regularization can further incorporate local information. However, in the context of unsupervised classification, existing approaches typically limit consideration to simple graphs built on spectral information alone. In contrast, a hypergraph-based low-rank subspace clustering is proposed to capture a more complex manifold structure. In addition, basing the hypergraph on a superpixel segmentation of the image exploits structure that is meaningful both spatially as well as spectrally. The experimental results reveal performance for the proposed superpixel-hypergraph approach superior to that of competing techniques representative of several prominent classes of unsupervised classification for hyperspectral imagery. [ABSTRACT FROM AUTHOR]

To facilitate measuring crystal sizes during batch crystallization at high-solid concentrations by using an invasive imaging system, an in situ imaging measurement strategy based on edge detection and superpixel is proposed for the ambiguous boundary problem of large amounts of crystals. Firstly, an image filtering is employed to cope with image degradation caused by noise disturbance and suspension turbulence in the crystallizer. Subsequently, an image segmentation method is developed by utilizing improved edge detection and superpixel, which can be easily performed for crystal extraction. Accordingly, crystal size measurement can be developed for evaluation of the crystal size distribution. The experiment results on α-form L-glutamic acid present the effectiveness of the proposed method.