Unsupervised multistage image classification using hierarchical clustering with a Bayesian similarity measure.

A new multistage method using hierarchical clustering for unsupervised image classification is presented. In the first phase, the multistage method performs segmentation using a hierarchical clustering procedure which confines merging to spatially adjacent clusters and generates an image partition such that no union of any neighboring segments has homogeneous intensity values. In the second phase, the segments resulting from the first stage are classified into a small number of distinct states by a sequential merging operation. The region-merging procedure in the first phase makes use of spatial contextual information by characterizing the geophysical connectedness of a digital image structure with a Markov random field, while the second phase employs a context-free similarity measure in the clustering process. The segmentation procedure of region merging is implemented as a hierarchical clustering algorithm whereby a multiwindow approach using a pyramid-like structure is employed to increase computational efficiency while maintaining spatial connectivity in merging. From experiments with both simulated and remotely sensed data, the proposed method was determined to be quite effective for unsupervised analysis. In particular, the region-merging approach based on spatial contextual information was shown to provide more accurate classification of images with smooth spatial patterns.     

Stereo matching based on multi-direction polynomial model

This paper presents a segmentation based stereo matching algorithm. For the purposes of both preserving the shape of object surfaces and being robust to under segmentations, we introduce a new scene formulation where the reference image is divided into overlapping lines. The disparity value and the index of pixels on lines are modeled by polynomial functions. Polynomial functions are propagated among lines to obtain smooth surfaces via solving energy minimizing problems. Finally, the disparity of pixels is estimated from the disparity fields provided by lines. Because lines in multiple directions implicitly segment different objects in an under segmentation region, our method is robust for under segmented regions where it is usually difficult for conventional region based methods to produce satisfactory results. Experimental results demonstrate that the proposed method has an outstanding performance compared with the current state-of-the-art methods. The scene representation method in this work is also a powerful approach to surface based scene representations.     

Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions

This paper describes a dense stereo matching algorithm for epipolar rectified images. The method applies colour segmentation on the reference image. Our basic assumptions are that disparity varies smoothly inside a segment, while disparity boundaries coincide with the segment borders. The use of these assumptions makes the algorithm capable of handling large untextured regions, estimating precise depth boundaries and propagating disparity information to occluded regions, which are challenging tasks for conventional stereo methods. We model disparity inside a segment by a planar equation. Initial disparity segments are clustered to form a set of disparity layers, which are planar surfaces that are likely to occur in the scene. Assignments of segments to disparity layers are then derived by minimization of a global cost function. This cost function is based on the observation that occlusions cannot be dealt with in the domain of segments. Therefore, we propose a novel cost function that is defined on two levels, one representing the segments and the other corresponding to pixels. The basic idea is that a pixel has to be assigned to the same disparity layer as its segment, but can as well be occluded. The cost function is then effectively minimized via graph-cuts. In the experimental results, we show that our method produces good-quality results, especially in regions of low texture and close to disparity boundaries. Results obtained for the Middlebury test set indicate that the proposed method is able to compete with the best-performing state-of-the-art algorithms.     

基于均值漂移滤波及谱分类的海面舰船红外目标分割

提出了一种有效的海面舰船红外目标分割方法.利用均值漂移方法的不连续保持性滤波特性,滤除海面的强杂波干扰,同时又不损失舰船目标的信息.根据滤波得到的区域构建区域邻接图,采用基于最大最小SST图划分算法对区域邻接图的节点进行划分.划分结果最终将图像分为天空背景、海面背景以及舰船目标3个部分.由于采用区域节点来表征图像,较之采用原始图像象素节点表示,其节点个数大大减少,从而使算法的计算效率得到很大提高.实验结果也表明提出两步算法具有优越的性能,能够在海面强杂波干扰的情况下有效提取舰船红外目标.     

Hybrid image segmentation using watersheds and fast region merging

A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds. An edge-preserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate estimate of the image gradient. Then, an initial partitioning of the image into primitive regions is produced by applying the watershed transform on the image gradient magnitude. This initial segmentation is the input to a computationally efficient hierarchical (bottom-up) region merging process that produces the final segmentation. The latter process uses the region adjacency graph (RAG) representation of the image regions. At each step, the most similar pair of regions is determined (minimum cost RAG edge), the regions are merged and the RAG is updated. Traditionally, the above is implemented by storing all RAG edges in a priority queue. We propose a significantly faster algorithm, which additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, one-pixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with two-dimensional/three-dimensional (2-D/3-D) magnetic resonance images are presented.     

Depth segmentation in real-world scenes based on U–V disparity analysis

Depth segmentation has the challenge of separating the objects from their supporting surfaces in a noisy environment. To address the issue, a novel segmentation scheme based on disparity analysis is proposed. First, we transform a depth scene into the corresponding U-V disparity map. Then, we conduct a region-based detection method to divide the object region into several targets in the processed U-disparity map. Thirdly, the horizontal plane regions may be mapped as slant lines in the V-disparity map, the Random Sample Consensus (RANSAC) algorithm is improved to fit such multiple lines. Moreover, noise regions are reduced by image processing strategies during the above processes. We respectively evaluate our approach on both real-world scenes and public data sets to verify the flexibility and generalization. Sufficient experimental results indicate that the algorithm can efficiently segment and label a full-view scene into a group of valid regions as well as removing surrounding noise regions.     

三维激光扫描数据的网格简化

针对三维激光扫描仪获得的彩色人头数据集压缩问题，提出了基于区域分割的顶点合并网格简化算法。该算法分为区域分割和网格简化两个阶段。在对三维彩色人头数据集进行区域分割的基础上，把网格点分为：区域边界点（在顶点合并操作中，它只能与边界点合并）和区域内部点，然后根据区域加权的误差评价函数进行网格简化。实验表明，该算法压缩比高，网格简化质量好。     

基于引导滤波及视差图融合的立体匹配

立体匹配是双目视觉领域的重要研究方向.为在保证图片纹理区域匹配精度的同时降低弱纹理区域的误匹配率,提出一种基于引导滤波及视差图融合的立体匹配方法.首先,根据图像颜色相似性将图片划分为纹理较丰富区域和弱纹理区域.接着,分别采用不同参数的引导滤波进行代价聚合及视差计算,得到两张视差图.然后依据纹理区域划分的结果对获得的两张视差图进行融合.最后,通过左右一致性检测、加权中值滤波等视差优化步骤得到最终视差图.对Middlebury测试平台上标准图像对的实验结果表明,该方法在6组弱纹理图像上的平均误匹配率为9.67％,较传统引导滤波立体匹配算法具有更高的匹配精度.     

3D reconstruction from stereo images for interactions between real and virtual objects

The 3D reconstruction algorithm in a stereo image pair for realizing mutual occlusion and interactions between the real and virtual world in an image synthesis is proposed. A two-stage algorithm, consisting of disparity estimation and regularization is used to locate a smooth and precise disparity vector. The hierarchical disparity estimation technique increases the efficiency and reliability of the estimation process, and edge-preserving disparity field regularization produces smooth disparity fields while preserving discontinuities that result from object boundaries. Depth information concerning the real scene is then recovered from the estimated disparity fields by stereo camera geometry. Simulation results show that the proposed algorithm provides accurate and spatially correlated disparity vector fields in various types of images, and the reconstructed 3D model produces a natural space in which the real world and virtual objects interact with each other as if they were in the same world.     

采用几何复杂度的室外场景图像分割和深度生成

本文提出一种采用几何复杂度的室外场景图像几何分割和深度生成算法。该算法首先通过图像中主要线段的角度统计分布将室外场景图像的几何结构规划为四种类型;然后,利用meanshift分割算法将输入图像分割成若干小区域,依据该图像的场景几何结构将这些小的区域逐步融合成为三个大的区域,每个区域具有一致的深度分布特点,由此实现输入图像的几何分割;最后,根据几何类型定义标准的深度图,结合输入图像的几何分割结果获得图像的深度图。实验结果表明可以通过简单的线段角度统计分布实现图像的几何分割,并进一步获得图像的深度图,与已有算法相比,提出的算法可以更好地保持深度图细节,更接近场景的真实的深度信息。      

Stereo disparity analysis using phase correlation

The determination of disparity in a stereo pair of images is a key factor in obtaining three-dimensional information about a scene. The authors describe how phase correlation can be used to aid stereo disparity analysis. An algorithm has been developed that identifies high-confidence candidate disparity vectors which are evaluated blockwise over the image. The vectors can be used as input to a subsequent area-matching process applied element by element     

对基于图像分割与合并的相位展开算法的改进

为了提高基于图像分割与合并的相位展开算法的精度,对已有的一种算法进行多方面改进,采取区域不等分措施,使得区域信息完整、准确再现;针对不同区域的噪声及欠采样情况,分别采取不同的相位展开算法;对分块合并时重叠区域进行加权叠加处理。利用仿真和实测数据对算法进行了验证,结果表明,改进算法能更准确、快速地恢复出被测物体的相位信息。改进后的算法不但适合于超大规模图像的相位展开,也适合于部分区域条纹过密的包裹相位图的展开。     

Adaptive parametric estimation and classification of remotelysensed imagery using a pyramid structure

An unsupervised region-based image segmentation algorithm implemented with a pyramid structure has been developed. Rather than depending on traditional local splitting and merging of regions with a similarity test of region statistics, the algorithm identifies the homogeneous and boundary regions at each level of the pyramid; the global parameters of each class are then estimated and updated with the values of the homogeneous regions represented at that level of the pyramid using mixture distribution estimation. The image is then classified through the pyramid structure. Classification results obtained for both simulated and SPOT imagery are presented     

Efficient morphological segmentation using a new connected operator

An efficient segmentation algorithm for region-based coding is proposed. A new connected operator based on both size and contrast is presented and an efficient region merging algorithm which preserves high quality in terms of the number of regions is proposed. Experimental results show that the proposed algorithm achieves a good performance in terms of the image quality and the number of regions     

Motion and structure from point correspondences with errorestimation: planar surfaces

The determination of motion and structure of a planar scene from monocular image sequences, is studied. A new and simpler linear algorithm, that gives closed-form solutions for motion and structure parameters using point correspondences between two images, assuming that the coplanar points undergo a rigid motion in 3-D space, is presented. A series of analytical results is established. From two perspective views of a planar scene which is undergoing a rigid motion, there are generally two (normalized) interpretations for motion parameters and the positions of the object plane. These two interpretations, one vertical and the other illusive, are both valid in the sense that they render the same pair of images. The authors identify all the special cases in which the number of interpretations is not two, and derive necessary and sufficient geometrical conditions for those special cases to occur. The approach to error estimation is based on the first-order perturbation. The estimated errors provide quantitative assessment for the accuracy of the solutions. They also indicate degenerate or nearly degenerate configurations in the presence of noise     

Plane surface detection and reconstruction using segment-based tensor voting

A Segment-based Tensor Voting (SBTV) algorithm is presented for planar surface detection and reconstruction of man-made objects. Our work is inspired by piecewise planar stereo reconstruction. During the vital procedure to detect and label the planar surface, the two main contributions are: first, tensor voting is used for obtaining the geometry attribute of the 3D points cloud. The candidate planar patches are generated through scene image segment of low variation of color and intensity. Second, we over-segment the scene image into the segment and the candidate 3D planar patch is generated. The SBTV algorithm is used on 3D points cloud sets to identify the co-plane on the candidate patch. After detecting every planar patch, the geometry architecture of object is obtained. The experiments demonstrate the effectiveness of our proposed approach on either outdoor or indoor datasets.     

Integrated method for boundary delineation of agricultural fieldsin multispectral satellite images

Most agricultural statistics are calculated per field, and it is well known that classification procedures for homogeneous objects produce better results than per-pixel classification. In this study, a multispectral segmentation method for automated delineation of agricultural field boundaries in remotely sensed images is presented. Edge information from a gradient edge detector is integrated with a segmentation algorithm. The multispectral edge detector uses all available multispectral information by adding the magnitudes and directions of edges derived from edge detection in single bands. The addition is weighted by edge direction, to remove "noise" and to enhance the major direction. The resulting edge from the edge detection algorithm is combined with a segmentation method based on a simple ISODATA algorithm, where the initial centroids are decided by the distances to the edges from the edge detection step. From this procedure, the number of regions will most likely exceed the actual number of fields in the image and merging of regions is performed. By calculating the mean and covariance matrix for pixels of neighboring regions, regions with a high generalized likelihood-ratio test quantity will be merged. In this way, information from several spectral bands (and/or different dates) can be used for delineating field borders with different characteristics. The introduction of the ISODATA classifier compared with a previously used region growing procedure improves the output. Some results are compared with manually extracted field boundaries     

Fault Surface Detection in 3-D Seismic Data

A novel approach to the automatic extraction of geological faults from three-dimensional (3-D) seismic data is described, and qualitative and quantitative comparisons of manually and automatically picked fault geometries interpreted from both high and medium quality 3-D seismic datasets are presented. An algorithm has been developed that allows semiautomated identification, extraction, and modeling of fault surfaces imaged in 3-D seismic datasets. Based on a multistage approach, the algorithm operates initially at a small spatial scale, identifying local discontinuities in the seismic horizons, and then gradually considers larger and larger segments of fault surfaces until a set of complete fault surfaces are identified. A large portion of the work involves merging of segments of fault surfaces, performed using a highest confidence first (HCF) stratagem, taking into consideration the context of the resultant fault geometry. We show that results from the automated fault picker compare favorably with a manually labeled set of faults surfaces interpreted from a high-quality dataset. Last, we present an estimate of the savings in human operator time that can be made by using the automated approach, indicating savings of multiple person-days for the multigigabyte datasets that typify the petroleum industry.     

EFFICIENT IMAGE SEGMENTATION FOR SEMANTIC OBJECT GENERATION

This letter presents an efficient and simple image segmentation method for semantic object spatial segmentation.First,the image is filtered using contour-preserving filters.Then it is quasi-flat labeled.The small regions near the contour are classified as uncertain regions and are eliminated by region growing and merging.Further region merging is used to reduce the region number.The simulation results show its efficiency and simplicity,It can preserve the semantic object shape while emphasize on the perceptual complex part of the object.So it conforms to the humann visual perception very well.     

A SAR Image Segment Method Using Gray Level Reduction Based on Graph in ICA Space

This paper proposes a new SAR image seg-mentation method based on graph and gray level reduction in Independent component analysis (ICA) space. Firstly, according to the grayscale information of SAR image, ef-fective use of gray level reduction for initial segmentation can group the pixels with same or similar values to the same homogeneous region, which can address the problem of over-segmentation. Secondly, the features of regions are extracted in ICA space, and then the similarity degree can be calculated by Euclidean distance. The initial regions are merged in fully connected graph based on minimum spanning tree in ICA space. The process of region merging is divided into two phases; the first phrase is merging the different regions with the largest similarity degree, the sec-ond will focus on updating the fully connected graph for iteration. Finally, experimental and comparative results on synthetic and real SAR images verify the efficiency of the proposed algorithm.