Superpixel Methods Research Articles

Adaptive Superpixel-Level CFAR Detector for SAR Inshore Dense Ship Detection

Ship monitoring is an important application of synthetic aperture radar (SAR). The constant false alarm rate (CFAR) methods are commonly used for ship detection. However, CFAR detectors usually face challenges for inshore dense ship detection. Due to the significant mixture of ship candidates and sea clutters within the clutter window, the detection threshold may be overestimated leading to many missed detections. To mitigate this issue, a superpixel-level CFAR detector is proposed. The main contribution contains two aspects. First, a labeling procedure is established for pure clutter superpixels and mixture superpixels discrimination in terms of unsupervised clustering. Second, a nonlocal topology strategy is proposed to adaptively determine a sufficient number of pure clutter superpixels for detection threshold estimation. In this vein, an adaptive superpixel-level CFAR approach is constructed and validated with Radarsat-2, Sentinel-1, and AIRSARShip-1 data sets. Comparison studies demonstrate the superiority of the proposed method. Compared with a traditional CFAR detector and two recent superpixel methods, the proposed method achieves clearly better performance for inshore dense ship regions.

Convex and Compact Superpixels by Edge- Constrained Centroidal Power Diagram.

Superpixel segmentation, as a central image processing task, has many applications in computer vision and computer graphics. Boundary alignment and shape compactness are leading indicators to evaluate a superpixel segmentation algorithm. Furthermore, convexity can make superpixels reflect more geometric structures in images and provide a more concise over-segmentation result. In this paper, we consider generating convex and compact superpixels while satisfying the constraints of adhering to the boundary as far as possible. We formulate the new superpixel segmentation into an edge-constrained centroidal power diagram (ECCPD) optimization problem. In the implementation, we optimize the superpixel configurations by repeatedly performing two alternative operations, which include site location updating and weight updating through a weight function defined by image features. Compared with existing superpixel methods, our method can partition an image into fully convex and compact superpixels with better boundary adherence. Extensive experimental results show that our approach outperforms existing superpixel segmentation methods in boundary alignment and compactness for generating convex superpixels.

Superpixels With Content-Adaptive Criteria.

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.

Image superpixel segmentation based on hierarchical multi-level LI-SLIC

In computer vision, superpixel segmentation has been widely used as a very important preprocessing to reduce the number of image primitives for subsequent image processing tasks. To improve the segmentation accuracy and the robustness to noise, a hierarchical multi-level segmentation framework is developed in this paper. First, original image is initially segmented by a local information based simple liner iterative clustering (LI-SLIC) method. Then, the initial generated superpixels are further segmented hierarchically by LI-SLIC to ensure that all pixels contained within each superpixel belong to a same object. Finally, to eliminate over-segmentation and reduce the number of superpixels, adjacent superpixels belonging to a same object are merged based on the probability distribution similarity. The proposed method does not require setting the seeds or number of the superpixels to be generated in advance, which can segment image into an appropriate number of superpixels without under- or over- segmentation automatically according to its content. Experiments are conducted on two public datasets Berkeley and 3Dircadb, and the results demonstrate that our method is more effective and accurate than many existing superpixel methods and shows a great advantage in dealing with images corrupted by various noises.

Efficient Superpixel Generation Method Based on Image Complexity

Superpixel methods are widely used in the preprocessing stage as a method to reduce computational complexity by simplifying images while maintaining the characteristics of the images in the computer vision applications. It is common to generate superpixels of similar size and shape based on the pixel values rather than considering the characteristics of the image. In this paper, we propose a method to control the sizes and shapes of generated superpixels, considering the contents of an image. The proposed method consists of two steps. The first step is to over-segment an image so that the boundary information of the image is well preserved. In the second step, generated superpixels are merged based on similarity to produce the target number of superpixels, where the shapes of superpixels are controlled by limiting the maximum size and the proposed roundness metric. Experimental results show that the proposed method preserves the boundaries of the objects in an image more accurately than the existing method.

Fuzzy SLIC: Fuzzy Simple Linear Iterative Clustering

Most superpixel methods are sensitive to noise and cannot control the superpixel number precisely. To solve these problems, in this paper, we propose a robust superpixel method called fuzzy simple linear iterative clustering (Fuzzy SLIC), which adopts a local spatial fuzzy C-means clustering and dynamic fuzzy superpixels. We develop a fast and precise superpixel number control algorithm called onion peeling (OP) algorithm. Fuzzy SLIC is insensitive to most types of noise, including Gaussian, salt and pepper, and multiplicative noise. The OP algorithm can control the superpixel number accurately without reducing much computational efficiency. In the validation experiments, we tested the Fuzzy SLIC and OP algorithm and compared them with state-of-the-art methods on the BSD500 and Pascal VOC2007 benchmarks. The experiment results show that our methods outperform state-of-the-art techniques in both noise-free and noisy environments.

DECOMPOSING IMAGES INTO TRIANGLES BY DELAUNAY POINT PROCESSES

Abstract. We propose a method for decomposing images into triangles. Contrary to superpixel methods, our output representation both preserves the geometric information disseminated in input images, and has an attractive storage capacity. Our method relies on the flexibility and efficiency of Delaunay point processes to address the problem. These stochastic models distribute points interacting between each other through Delaunay triangulations. The mechanism for distributing points combines several complementary ingredients including image discontinuity preservation, radiometric homogeneity inside atomic regions as well as priors on the shape of these regions. Said differently, sampled points and induced shapes work in tandem. The potential of our approach is shown through comparisons with existing oversegmentation methods and applications to vision problems.

Rooted Spanning Superpixels

This paper proposes a new approach for superpixel segmentation. It is formulated as finding a rooted spanning forest of a graph with respect to some roots and a path-cost function. The underlying graph represents an image, the roots serve as seeds for segmentation, each pixel is connected to one seed via a path, the path-cost function measures both the color similarity and spatial closeness between two pixels via a path, and each tree in the spanning forest represents one superpixel. Originating from the evenly distributed seeds, the superpixels are guided by a path-cost function to grow uniformly and adaptively, the pixel-by-pixel growing continues until they cover the whole image. The number of superpixels is controlled by the number of seeds. The connectivity is maintained by region growing. Good performances are assured by connecting each pixel to the similar seed, which are dominated by the path-cost function. It is evaluated by both the superpixel benchmark and supervoxel benchmark. Its performance is ranked as the second among top performing state-of-the-art methods. Moreover, it is much faster than the other superpixel and supervoxel methods.

Superpixel Region Merging Based on Deep Network for Medical Image Segmentation

Automatic and accurate semantic segmentation of pathological structures in medical images is challenging because of noisy disturbance, deformable shapes of pathology, and low contrast between soft tissues. Classical superpixel-based classification algorithms suffer from edge leakage due to complexity and heterogeneity inherent in medical images. Therefore, we propose a deep U-Net with superpixel region merging processing incorporated for edge enhancement to facilitate and optimize segmentation. Our approach combines three innovations: (1) different from deep learning--based image segmentation, the segmentation evolved from superpixel region merging via U-Net training getting rich semantic information, in addition to gray similarity; (2) a bilateral filtering module was adopted at the beginning of the network to eliminate external noise and enhance soft tissue contrast at edges of pathogy; and (3) a normalization layer was inserted after the convolutional layer at each feature scale, to prevent overfitting and increase the sensitivity to model parameters. This model was validated on lung CT, brain MR, and coronary CT datasets, respectively. Different superpixel methods and cross validation show the effectiveness of this architecture. The hyperparameter settings were empirically explored to achieve a good trade-off between the performance and efficiency, where a four-layer network achieves the best result in precision, recall, F-measure, and running speed. It was demonstrated that our method outperformed state-of-the-art networks, including FCN-16s, SegNet, PSPNet, DeepLabv3, and traditional U-Net, both quantitatively and qualitatively. Source code for the complete method is available at https://github.com/Leahnawho/Superpixel-network.

A New Method for Image Superpixel Segmentation

Considering the problem that the existing superpixel methods are usually unable to set an appropriate number of generated superpixels automatically and unable to adhere to image boundaries effectively, a new superpixel method is proposed in this paper, which utilizes local information to perform multi-level simple linear iterative clustering to generate superpixels. First, original image is initially segmented by Simple Liner Iterative Clustering based on Local Information (LI-SLIC). Then, each superpixel is segmented iteratively until its color standard deviation is lower than a predefined threshold. Finally, the over-segmented superpixels are merged based on the color differences between adjacent superpixels. Experiments on Berkeley, Pascal VOC and 3Dircadb databases, as well as comparison with other methods indicate that the proposed method can adhere to image boundaries more accurately, and can prevent over- and under- segmentations more effectively.

Superpixel Segmentation Using Dynamic and Iterative Spanning Forest

As constituent parts of image objects, superpixels can improve several higher-level operations. However, image segmentation methods might have their accuracy seriously compromised for reduced numbers of superpixels. We have investigated a solution based on the Iterative Spanning Forest (ISF) framework. In this work, we present Dynamic ISF (DISF) -- a method based on the following steps. (a) It starts from an image graph and a seed set with considerably more pixels than the desired number of superpixels. (b) The seeds compete among themselves, and each seed conquers its most closely connected pixels, resulting in an image partition (spanning forest) with connected superpixels. In step (c), DISF assigns relevance values to seeds based on superpixel analysis and removes the most irrelevant ones. Steps (b) and (c) are repeated until the desired number of superpixels is reached. DISF has the chance to reconstruct relevant edges after each iteration, when compared to region merging algorithms. As compared to other seed-based superpixel methods, DISF is more likely to find relevant seeds. It also introduces dynamic arc-weight estimation in the ISF framework for more effective superpixel delineation, and we demonstrate all results on three datasets with distinct object properties.

Context-Aware Superpixel and Bilateral Entropy-Image Coherence Induces Less Entropy.

Superpixel clustering is one of the most popular computer vision techniques that aggregates coherent pixels into perceptually meaningful groups, taking inspiration from Gestalt grouping rules. However, due to brain complexity, the underlying mechanisms of such perceptual rules are unclear. Thus, conventional superpixel methods do not completely follow them and merely generate a flat image partition rather than hierarchical ones like a human does. In addition, those methods need to initialize the total number of superpixels, which may not suit diverse images. In this paper, we first propose context-aware superpixel (CASP) that follows both Gestalt grouping rules and the top-down hierarchical principle. Thus, CASP enables to adapt the total number of superpixels to specific images automatically. Next, we propose bilateral entropy, with two aspects conditional intensity entropy and spatial occupation entropy, to evaluate the encoding efficiency of image coherence. Extensive experiments demonstrate CASP achieves better superpixel segmentation performance and less entropy than baseline methods. More than that, using Pearson’s correlation coefficient, a collection of data with a total of 120 samples demonstrates a strong correlation between local image coherence and superpixel segmentation performance. Our results inversely support the reliability of above-mentioned perceptual rules, and eventually, we suggest designing novel entropy criteria to test the encoding efficiency of more complex patterns.

Improve the quality of holographic image with complex-amplitude metasurface.

Complex-amplitude hologram can provide a high-quality image that is free of twin image and zero-order noise. Multi-SLMs methods, single SLM with space-division modulations and super pixel methods were striving to meet the requirements of complex amplitude modulation. In this work, we propose an ultra-thin dielectric metasurface to improve the quality of holographic image by loading complex amplitude hologram. This metasurface controls the amplitude and phase simultaneously and independently in transmission mode. The multipole expansion method is applied to analyze the mechanism. The polarization conversion efficiency can be up to 99% and the diffraction efficiency is 71%. The simulations verify that the quality of holographic image could be greatly improved by a complex-amplitude metasurface.

COMPARISON OF PIXEL AND REGION-BASED APPROACHES FOR TREE SPECIES MAPPING IN ATLANTIC FOREST USING HYPERSPECTRAL IMAGES ACQUIRED BY UAV

Abstract. The objective of this work was the comparison of two different classification approaches to detect four different tree species of a highly diverse tropical Atlantic Forest area. In order to achieve the objective, images were acquired with the Rikola hyperspectral camera onboard the UX4 UAV. The study area is in the Western part of São Paulo State, a tropical Atlantic Forest area protected by governmental laws, which contains areas already deforested in the past and which are currently in regeneration. The tested approaches were one based only in the pixel values and other one based in regions. After the image acquisition, the images were radiometrically and geometrically processed. In addition, an airborne laser scanning point cloud was used to calculate the canopy height model of the area, which was used to detect the individual tree crowns with the superpixels method. Those superpixels were used to the region-based classification and to feature extraction. A total of 28 features were extracted where 25 correspond to the spectral bands acquired with the Rikola camera and three correspond to the three first principal components of the images. The features were extracted from the 91 samples recognized during a field work. From the total of samples, 19 were separated to validate the classification results. The chosen classifier was the Random Forests and the results presented a kappa coefficient of 18.20% and 36.57% for the pixel-based and region-based classifications showing that the second one had a better performance.

Mineral grains recognition using computer vision and machine learning

Identifying and counting individual mineral grains composing sand is an important component of many studies in environment, engineering, mineral exploration, ore processing and the foundation of geometallurgy. Typically, silt (32-128μm) and sand (128-1000μm) sized grains will be characterized under an optical microscope or a scanning electron microscope. In both cases, it is a tedious and costly process. Therefore, in this paper, we introduce an original computational approach in order to automate mineral grains recognition from numerical images obtained with a simple optical microscope. To the best of our knowledge, it is the first time that the current computer vision based on machine learning algorithms is tested for the automated recognition of such mineral grains. In more details, this work uses the simple linear iterative clustering segmentation to generate superpixels and many of them allow isolating sand grains, which is not possible with classical segmentation methods. Also, the approach has been tested using convolutional neural networks (CNNs). However, CNNs did not give as good results as the superpixels method. The superpixels are also exploited to extract features related to a sand grain. These image characteristics form the raw dataset. Prior to proceed with the classification, a data cleaning stage is necessary to get a usable dataset for machine learning algorithms. In addition, we present a comparison of performances of several algorithms. The overall obtained results are approximately 90% and demonstrate the concept of mineral recognition from a sample of sand grains provided by a numerical image.

High-dimensional features of adaptive superpixels for visually degraded images

This study presents a novel and highly efficient superpixel algorithm, namely, depth-fused adaptive superpixel (DFASP), which can generate accurate superpixels in a degraded image. In many applications, particularly in actual scenes, vision degradation, such as motion blur, overexposure, and underexposure, often occurs. Well-known color-based superpixel algorithms are incapable of producing accurate superpixels in degraded images because of the ambiguity of color information caused by vision degradation. To eliminate this ambiguity, we use depth and color information to generate superpixels. We map the depth and color information to a high-dimensional feature space. Then, we develop a fast multilevel clustering algorithm to produce superpixels. Furthermore, we design an adaptive mechanism to adjust the color and depth information automatically during pixel clustering. Experimental results demonstrate that regardless of boundary recall, under segmentation error, run time, or achievable segmentation accuracy, DFASP is better than state-of-the-art superpixel methods.

Three‐dimensional‐based landmark tracker employing a superpixels method for neuroscience, biomechanics, and biology studies

AbstractExamining locomotion has improved our basic understanding of motor control and aided in treating motor impairment. Mice and rats are premier models of human disease and increasingly the model systems of choice for basic neuroscience. High frame rates (250 Hz) are needed to quantify the kinematics of these running rodents. Manual tracking, especially for multiple markers, becomes time‐consuming and impossible for large sample sizes. Therefore, the need for automatic segmentation of these markers has grown in recent years. Here, we address this need by presenting a method to segment the markers using the simple linear iterative clustering superpixel method. The two‐dimensional coordinates on the image plane are projected to a three‐dimensional (3D) domain using direct linear transform and a 3D Kalman filter has been used to predict the position of markers based on the speed and position of markers from the previous frames. A probabilistic function is used to find the best match from among superpixels. The method is evaluated for different difficulties for tracking of the markers, and it achieves 95% correct labeling of markers. Finally, the method was used to analyze data from an ongoing study seeking to improve recovery from spinal cord injury in rats

PSDSD-A Superpixel Generating Method Based on Pixel Saliency Difference and Spatial Distance for SAR Images.

Superpixel methods are widely used in the processing of synthetic aperture radar (SAR) images. In recent years, a number of superpixel algorithms for SAR images have been proposed, and have achieved acceptable results despite the inherent speckle noise of SAR images. However, it is still difficult for existing algorithms to obtain satisfactory results in the inhomogeneous edge and texture areas. To overcome those problems, we propose a superpixel generating method based on pixel saliency difference and spatial distance for SAR images in this article. Firstly, a saliency map is calculated based on the Gaussian kernel function weighted local contrast measure, which can not only effectively suppress the speckle noise, but also enhance the fuzzy edges and regions with intensity inhomogeneity. Secondly, superpixels are generated by the local k-means clustering method based on the proposed distance measure, which can efficiently sort pixels to different clusters. In this step, the distance measure is calculated by combining the saliency difference and spatial distance with a proposed adaptive local compactness parameter. Thirdly, post-processing is utilized to clean up small segments. The evaluation experiments on the simulated SAR image demonstrate that our proposed method dramatically outperforms four state-of-the-art methods in terms of boundary recall, under-segmentation error, and achievable segmentation accuracy under almost all of the experimental parameters at a moderate segment speed. The experiments on real-world SAR images of different sceneries validate the superiority of our method. The superpixel results of the proposed method adhere well to the contour of targets, and correctly reflect the boundaries of texture details for the inhomogeneous regions.

ISEC: Iterative over-segmentation via edge clustering

Several image pattern recognition tasks rely on superpixel generation as a fundamental step. Image analysis based on superpixels facilitates domain-specific applications, also speeding up the overall processing time of the task. Recent superpixel methods have been designed to fit boundary adherence, usually regulating the size and shape of each superpixel in order to mitigate the occurrence of undersegmentation failures. Superpixel regularity and compactness sometimes imposes an excessive number of segments in the image, which ultimately decreases the efficiency of the final segmentation, specially in video segmentation. We propose here a novel method to generate superpixels, called iterative over-segmentation via edge clustering (ISEC), which addresses the over-segmentation problem from a different perspective in contrast to recent state-of-the-art approaches. ISEC iteratively clusters edges extracted from the image objects, providing adaptive superpixels in size, shape and quantity, while preserving suitable adherence to the real object boundaries. All this is achieved at a very low computational cost. Experiments show that ISEC stands out from existing methods, meeting a favorable balance between segmentation stability and accurate representation of motion discontinuities, which are features specially suitable to video segmentation.

Decomposition-Feature-Iterative-Clustering-Based Superpixel Segmentation for PolSAR Image Classification

Compared with traditional pixel-based polarimetric synthetic aperture radar (PolSAR) image classification methods, superpixel-based methods take advantages of the spatial information of pixels, so they can overcome the influence of speckle noise on the classification result. Since traditional superpixel methods do not utilize the scattering characteristics of a PolSAR image, the boundaries of the superpixels are poorly preserved. The inaccuracy of superpixel segmentation boundaries has a negative impact on the subsequent classification. In this letter, we propose a decomposition-feature-iterative-clustering (DFIC) superpixel segmentation method for PolSAR images. The DFIC method innovatively introduces the decomposition features in generating superpixels, so the superpixel segmentation boundaries are well preserved. Because we selectively utilize superpixel information to classify the PolSAR images by setting a threshold, the effect of superpixel segmentation inaccuracy on the classification results is reduced. Experiments on two real PolSAR images demonstrate that the proposed method outperforms several state-of-the-art superpixel methods, and that the DFIC superpixel-based classification obtains better results than the other pixel-based methods.