Search

Superpixel-based segmentation has been widely used as a primary prepossessing step to simplify the subsequent image processing tasks. Since determining the number of clusters is subjective and varies based on the type of image, the segmentation algorithm may provide over-segmented or under-segmented superpixels. This paper proposes an image segmentation method to improve the SLIC superpixel by region merging. It aims to improve the segmentation accuracy without defining a precise number of superls. The color difference between superpixels is employed as a homogeneity criterion for the merging process. The Berkeley dataset is used with different quantitative performance metrics to evaluate the proposed model's performance. Results obtained from probabilistic rand index (PRI), boundary recall, and under-segmentation error proved the ability of the proposed algorithm to provide comparable segmentation with a reduced number of clusters. [ABSTRACT FROM AUTHOR]

Interactive image segmentation uses a priori information to guide the acquisition of the people ' s interesting parts of an image, but existing algorithms cannot balance efficiency and accuracy. To solve this problem, this paper proposed a fast interactive segmentation algorithm based on superpixel and random walk (random walk on superpixel, SPRW) . Firstly, it presegmented the image into superpixel regions with local similarity and used pixel colour averages to represent the superpixel regions. Secondly, it built the F-B graph structure based on manually labelled a priori information and extended the range of the random walk, obtained the hard segmentation results using the random walk solution. Finally, this paper proposed the improved matting algorithm (fast robust matting, FRB ) for the unsmooth boundaries of segmentation results and performed the secondary process to obtain soft segmentation results. Experiments on the BSDSOO and MSRC datasets confirm that the proposed hard method is superior to other algorithms in terms of time and average intersection ratio, while experiments on the Alpha Matting dataset demonstrate that the proposed soft algorithm improves efficiency and accuracy. In addition, the experiment of replacing the background of a life photograph demonstrates the application value of the proposed algorithm. [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]

Superpixel as a fundamental processing unit can significantly reduce the computational complexity of subsequent computer vision tasks. In this paper, an Adaptive High-Precision (AHP) superpixel segmentation algorithm is proposed. Three major schemes are proposed in this algorithm. First, a scheme of generating the initial number of superpixels adaptively is proposed by calculating the histogram peak value of L-component corresponding to the smallest salient region. In addition, we show that the isolated pixels are not only existent but also abundant. Instead of using distance-measurement of color and position space, we reclassify each isolated pixel just relying on the LAB color space. Furthermore, the detection and re-segmentation scheme of the under-segmentation superpixels is adopted according to the standard deviation and mean value of the L-component, which can re-segment each under-segmentation superpixel directly without measuring the distance between each under-segmentation pixel and new centroid. The proposed algorithm has linear computational complexity and the merits of adaptivity and high precision. Experiments on the Berkeley segmentation dataset demonstrate the effectiveness and feasibility of the proposed schemes, and they also prove AHP can achieve high-precision superpixel segmentation results in comparison with the state-of-the-art algorithms on standard metrics. [ABSTRACT FROM AUTHOR]

We present a novel superpixel generation algorithm based on a new definition of geodesic distance, called bilateral geodesic distance. In contrast to the traditional geodesic distance, the new bilateral geodesic distance of two pixels considers the distance between their positions as well as their color difference. Superpixel generation is essentially a problem of clustering image pixels with respect to a set of properly selected seeds. We first use an adaptive hexagonal subdivision method to determine the initial seed-based image gradient. Then, we use the bilateral geodesic distance to measure the similarity between the pixels and the seeds. We apply an improved fast marching method to generate superpixels’ contour regions with the expansion velocities dependent on a new gradient formulation that depends on the seeds’ properties. The experimental results indicate that our algorithm is not only much faster than the structure-based method, which uses conventional geodesic distance, but also outperforms the existing methods in terms of region compactness and region boundary regularity. [ABSTRACT FROM AUTHOR]

Existing interactive image segmentation methods heavily rely on manual input, i.e. a sufficient quantity and correct locations of labels. In this paper, we propose a new interactive segmentation algorithm which aims to reduce human intervention and to generate high-quality segmentation results. In contrast to most energy minimizing based segmentation methods, the segmentation is cast as multi-classification in our proposed method. First, the input image is segmented into superpixels by using different methods. Then we build a dictionary consisting of all obtained superpixels and reconstruct samples represented by certain labeled superpixels. Finally, we learn a discriminative projection matrix through Fishers linear discriminant analysis (FLDA) algorithm, which learns a discriminative subspace for classification. The unlabeled superpixels are grouped into foreground or background, via calculating their minimal norm. Our method can capture long range grouping cues and reduce the sensitivity with respect to input label quantity and location of labels, by the combination of superpixels and discriminative dictionary. Extensive experiments are conducted both on MSRC and another challenging database in order to demonstrate the effectiveness of the proposed method. Quantitative and qualitative results show that our method is competitive to the state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Superpixel segmentation for polarimetric synthetic aperture radar (PolSAR) images plays a key role in remote-sensing tasks, such as ship detection and land-cover classification. However, the existing methods cannot directly generate multi-scale superpixels in a hierarchical style and they will take a long time when multi-scale segmentation is executed separately. In this article, we propose an effective and accurate hierarchical superpixel segmentation method, by introducing a minimum spanning tree (MST) algorithm called the Boruvka algorithm. To accurately measure the difference between neighboring pixels, we obtain the scattering mechanism information derived from the model-based refined 5-component decomposition (RFCD) and construct a comprehensive dissimilarity measure. In addition, the edge strength map and homogeneity measurement are considered to make use of the structural and spatial distribution information in the PolSAR image. On this basis, we can generate superpixels using the distance metric along with the MST framework. The proposed method can maintain good segmentation accuracy at multiple scales, and it generates superpixels in real time. According to the experimental results on the ESAR and AIRSAR datasets, our method is faster than the current state-of-the-art algorithms and preserves somewhat more image details in different segmentation scales. [ABSTRACT FROM AUTHOR]

An efficient and effective unsupervised single moving object detection framework is presented in this paper. Given the sparsely labelled trajectory points, we adopt a coarse-to-fine strategy to detect and segment the foreground from the background. The superpixel level coarse segmentation reduces the complexity of subsequent processing, and the pixel level refinement improves the segmentation accuracy. A distance measurement is devised in the coarse segmentation stage to measure the similarities between generated superpixels, which can then be used for clustering. Moreover, a Quadmap is introduced to facilitate the refinement in the fine segmentation stage. According to the experiments, our algorithm is effective and efficient, and favorable results can be achieved compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Image segmentation refers to the process to divide an image into meaningful non-overlapping regions according to human perception, which has become a classic topic since the early ages of computer vision. A lot of research has been conducted and has resulted in many applications. While many segmentation algorithms exist, there are only a few sparse and outdated summarizations available. Thus, in this paper, we aim to provide a comprehensive review of the recent progress in the field. Covering 190 publications, we give an overview of broad segmentation topics including not only the classic unsupervised methods, but also the recent weakly-/semi-supervised methods and the fully-supervised methods. In addition, we review the existing influential datasets and evaluation metrics. We also suggest some design choices and research directions for future research in image segmentation. [ABSTRACT FROM AUTHOR]

High spatial resolution (HSR) image segmentation is considered to be a major challenge for object-oriented remote sensing applications that have been extensively studied in the past. In this paper, we propose a fast and efficient framework for multiscale and multifeatured hierarchical image segmentation (MMHS). First, the HSR image pixels were clustered into a small number of superpixels using a simple linear iterative clustering algorithm (SLIC) on modern graphic processing units (GPUs), and then a region adjacency graph (RAG) and nearest neighbors graph (NNG) were constructed based on adjacent superpixels. At the same time, the RAG and NNG successfully integrated spectral information, texture information, and structural information from a small number of superpixels to enhance its expressiveness. Finally, a multiscale hierarchical grouping algorithm was implemented to merge these superpixels using local-mutual best region merging (LMM). We compared the experiments with three state-of-the-art segmentation algorithms, i.e., the watershed transform segmentation (WTS) method, the mean shift (MS) method, the multiresolution segmentation (MRS) method integrated in commercial software, eCognition9, on New York HSR image datasets, and the ISPRS Potsdam dataset. Computationally, our algorithm was dozens of times faster than the others, and it also had the best segmentation effect through visual assessment. The supervised and unsupervised evaluation results further proved the superiority of the MMHS algorithm. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of objects similarity measurement of traditional cultural pattern segmentation and adaptively determine the number of segmentations, we propose an adaptive segmentation algorithm based on a new superpixel Log-Euclidean Gaussian metric (SLEGM) in this paper. We first propose to use the SLEGM to effectively characterize superpixels for more accurate measurement of their similarity. Because the space of Gaussians sample covariance matrix distribution is not a linear space but a Riemannian manifold, we map this manifold via matrix logarithm into a linear space, which enables us to handle Gaussians with Euclidean operations. Under the SLEGM framework, we develop an improved spectral clustering algorithm that can adaptively determine the number of clusters to achieve the adaptive segmentation for the traditional culture pattern. Extensive evaluations on the Berkeley Segmentation Data Set (BSDS500) benchmark verify that our algorithm outperforms the state-of-the-art techniques of the same category under four evaluation metrics, achieving 74.3% F-measure, 13.52% under segmentation error, 83.4% boundary recall and 97.79% achievable segmentation accuracy. Further experiments on our challenging Traditional Cultural Pattern Database (TCPD) indicate the effectiveness of our algorithm for segmenting the complex patterns. • A new SLEGM is proposed to effectively characterize the superpixels. • A new algorithm for adaptively determining the number of clusters is designed. • An adaptive image segmentation algorithm based on SLEGM is realized. • The proposed algorithm outperforms state-of-the-art algorithms of the same category. [ABSTRACT FROM AUTHOR]

Extended from superpixel segmentation by adding an additional constraint on temporal consistency, supervoxel segmentation is to partition video frames into atomic segments. In this work, we propose a novel scheme for supervoxel segmentation to address the problem of new and moving objects, where the segmentation is performed on every two consecutive frames and thus each internal frame has two valid superpixel segmentations. This scheme provides coarse-grained parallel ability, and subsequent algorithms can validate their result using two segmentations that will further improve robustness. To implement this scheme, a voxel-related Gaussian mixture model (GMM) is proposed, in which each supervoxel is assumed to be distributed in a local region and represented by two Gaussian distributions that share the same color parameters to capture temporal consistency. Our algorithm has a lower complexity with respect to frame size than the traditional GMM. According to our experiments, it also outperforms the state-of-the-art in accuracy. [ABSTRACT FROM AUTHOR]

A fast and accurate segmentation algorithm in a hierarchical way based on a recursive superpixel technique is presented. We propose a superpixel energy formulation in which the trade-off between data fidelity and regularization is dynamically determined based on the local residual in the energy optimization procedure. We also present an energy optimization algorithm that allows a pixel to be shared by multiple regions to improve the accuracy and appropriate the number of segments. The qualitative and quantitative evaluations demonstrate that our algorithm, combining the proposed energy and optimization, outperforms the conventional k-means algorithm by up to 29.10% in F-measure. We also perform comparative analysis with state-of-the-art algorithms in the hierarchical segmentation. Our algorithm yields smooth regions throughout the hierarchy as opposed to the others that include insignificant details. Our algorithm overtakes the other algorithms in terms of balance between accuracy and computational time. Specifically, our method runs 36.48% faster than the region-merging approach, which is the fastest of the comparing algorithms, while achieving a comparable accuracy. [ABSTRACT FROM AUTHOR]