Hierarchical Segmentation Research Articles

Purely vision-based segmentation of web pages for assistive technology

We use a novel vision-based method to analyze the layout of a web page.Our method produces a hierarchical segmentation of the page reflecting its structure.Vision-based methods are not sensitive to...

AN INTEGRATIVE OBJECT-BASED IMAGE ANALYSIS WORKFLOW FOR UAV IMAGES

In this work, we propose an integrative framework to process UAV images. The overall process can be viewed as a pipeline consisting of the geometric and radiometric corrections, subsequent panoramic mosaicking and hierarchical image segmentation for later Object Based Image Analysis (OBIA). More precisely, we first introduce an efficient image stitching algorithm after the geometric calibration and radiometric correction, which employs a fast feature extraction and matching by combining the local difference binary descriptor and the local sensitive hashing. We then use a Binary Partition Tree (BPT) representation for the large mosaicked panoramic image, which starts by the definition of an initial partition obtained by an over-segmentation algorithm, i.e., the simple linear iterative clustering (SLIC). Finally, we build an object-based hierarchical structure by fully considering the spectral and spatial information of the super-pixels and their topological relationships. Moreover, an optimal segmentation is obtained by filtering the complex hierarchies into simpler ones according to some criterions, such as the uniform homogeneity and semantic consistency. Experimental results on processing the post-seismic UAV images of the 2013 Ya’an earthquake demonstrate the effectiveness and efficiency of our proposed method.

Category independent object discovery via background modeling

Traditional approaches for object discovery assume that there are common characteristics among objects, and then attempt to extract features specific to objects in order to discriminate objects from background. However, the assumption “common features” may not hold, considering different variations between and within objects. Instead, we look at this problem from a different angle: if we can identify background regions, then the rest should belong to foreground. In this paper, we propose to model background to localize possible object regions. Our method is based on the observations: (1) background has limited categories, such as sky, tree, water, ground, etc., and can be easier to recognize, while there are millions of objects in our world with different shapes, colors and textures; (2) background is occluded because of foreground objects. Thus, we can localize objects based on voting from fore/background occlusion boundary. Our contribution lies: (1) we use graph-based image segmentation to yield high quality segments, which effectively leverages both flat segmentation and hierarchical segmentation approaches; (2) we model background to infer and rank object hypotheses. More specifically, we use background appearance and discriminative patches around fore/background boundary to build the background model. The experimental results show that our method can generate good quality object proposals and rank them where objects are covered highly within a small pool of proposed regions.

Automatic Detection of Compound Structures by Joint Selection of Region Groups From a Hierarchical Segmentation

A challenging problem in remote sensing image analysis is the detection of heterogeneous compound structures such as different types of residential, industrial, and agricultural areas that are composed of spatial arrangements of simple primitive objects such as buildings and trees. We describe a generic method for the modeling and detection of compound structures that involve arrangements of an unknown number of primitives in large scenes. The modeling process starts with a single example structure, considers the primitive objects as random variables, builds a contextual model of their arrangements using a Markov random field, and learns the parameters of this model via sampling from the corresponding maximum entropy distribution. The detection task is formulated as the selection of multiple subsets of candidate regions from a hierarchical segmentation where each set of selected regions constitutes an instance of the example compound structure. The combinatorial selection problem is solved by the joint sampling of groups of regions by maximizing the likelihood of their individual appearances and relative spatial arrangements. Experiments using very high spatial resolution images show that the proposed method can effectively localize an unknown number of instances of different compound structures that cannot be detected by using spectral and shape features alone.

Colorization coding based on iterative regression with major group priority

Colorization-based image coding is a new color image compression technique which compresses the color information of a color image into a small set of representative pixels (RP). The main issue in colorization-based coding is to design good RP extraction and colorization methods such that the compression rate and the quality of the reconstructed color become good. In this paper, we propose an iterative local regression method for RP extraction which takes the major group priority into account. It is shown that the problem of computing the RP can be formulated into a local regression problem. The local regions are obtained by performing a hierarchical image segmentation on the luminance channel both in the encoder and the decoder. Then the local regression parameters, i.e., the parameters that express the local relationship between the pixel values in the luminance channel and the chrominance channels are computed by taking the hierarchical structure into account. At the initial stage, the local regression parameters are calculated to fit the major tendency of the pixels in the segmented regions of the largest scale in the hierarchical structure. After that, additional regression parameters are extracted to reduce the remaining residual errors between the original color and the colors reconstructed by the previously computed local regression parameters. By repeating these steps, an RP set is extracted which can colorize the image in the decoder with sufficient detail. Experimental results show that the proposed algorithm performs better than the JPEG standard and conventional colorization-based coding methods in terms of the compression rate, PSNR and SSIM values.

Hierarchical image simplification and segmentation based on Mumford–Shah-salient level line selection

Hierarchies, such as the tree of shapes, are popular representations for image simplification and segmentation thanks to their multiscale structures. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the celebrated Mumford–Shah functional. In this paper, we propose an efficient approach to hierarchical image simplification and segmentation based on the minimization of the piecewise-constant Mumford–Shah functional. This method conforms to the current trend that consists in producing hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and well-defined representation equivalent to the image. Simply put, we compute for each level line of the image an attribute function that characterizes its persistence under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map based on extinction values defined on the tree-based shape space. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the state-of-the-art performance of our method.

Research on Online Collision Detection Algorithm of CNC Machine Tools

Collision detection is the core of the numerical control system of intelligent manufacturing in the manufacturing process of rapid feeding, positioning and cutting. We need to avoid collision between the cutting tools, machine tools and workpiece. Based on the characteristic of five-axis CNC system, we analyze the advantages and disadvantages of Hierarchical Mesh Segmentation and Octree. At last, we use the collision detection algorithm of cuboid and separation axis to optimize the algorithm of traditional NC machine tool collision detection, which improve the detection efficiency and accuracy.

Object-oriented approach to oil spill detection using ENVISAT ASAR images

The growing importance of oil spill detection as part of a rapid response system to oil pollution requires theongoing development of algorithms. The aim of this study was to create amethodology for improving manual classification at the scale of entire water bodies, focusing on its repeatability. This paper took an object-oriented approach to radar image analysis and put particular emphasis on adaptation to thespecificity of seas like the Baltic. Pre-processing using optimised filters enhanced the capability of amultilevel hierarchical segmentation, in order to detect spills of different sizes, forms and homogeneity, which occur as a result of shipping activities. Confirmed spills detected in ENVISAT/ASAR images were used to create a decision-tree procedure that classifies every distinct dark object visible inSAR images into one out of four categories, which reflect growing probability of the oil spill presence: look-alikes, dubious spots, blurred spots and potential oil spills. Our objective was to properly mark known spills on ASAR scenes and to reduce the number of false-positives by eliminating (classifying as background or look-alike) as many objects aspossible from the vast initial number of objects appearing on full-scale images. A number of aspects were taken into account in the classification process. The method’s performance was tested on agroup of 26 oil spills recorded by HELCOM: 96.15% ofthem were successfully identified. The final target group was narrowed down to about 4% ofdark objects extracted from ASAR images. Although aspecialist is still needed to supervise thewhole process of oil spill detection, this method gives an initial view, substantial for further evaluation of the scenes and risk estimation. It may significantly accelerate thepace of manual image analysis and enhance the objectivity of assessments, which are key aspects in operational monitoring systems.

A novel clustering-based image segmentation via density peaks algorithm with mid-level feature

Image segmentation is an important and fundamental task in computer vision. Its performance is mainly influenced by feature representations and segmentation algorithms. In this paper, we propose a novel clustering-based image segmentation approach which can be called ICDP algorithm. It is able to capture the inherent structure of image and detect the nonspherical clusters. Compared to the other segmentation methods based on clustering, there are several advantages as follows: (1) Integral channel features are used to clearly and comprehensively represent the input image by naturally integrating heterogeneous sources of information; (2) cluster number can be determined directly and cluster centers are able to be identified automatically; (3) hierarchical segmentation is easy to be achieved via ICDP algorithm. The PSNR and MSE are applied to quantitatively evaluate the segmentation performance. Experimental results clearly demonstrate the effectiveness of our novel image segmentation algorithm.

Exploratory Approaches for Studying Social Interactions, Dynamics, and Multivariate Processes in Psychological Science

ABSTRACTIn this article, I argue for the need of more use of exploratory techniques to identify dynamics in social interactions. I describe several approaches as they are applied to multivariate time series data. The first approach is an algorithm that searches for periods of variability and stability at the individual level as well as for patterns of overlap in such periods between the two individuals in a couple. These patterns describe the daily ups and downs in the couples' affect and are predictive of the state of the couples 1 to 2 years later. The second approach, hierarchical segmentation, is based on the idea of partitioning the time series in segments with distinct data patterns. In the case of data from dyads, as in the illustration, the patterns can be compared in terms of coherence between the 2 individuals in the dyad. The third approach is based on network analysis, and its use is shown as a method to examine data transitions at the individual and dyadic level as well as system-wide coherence in multivariate systems. For each approach, I provide examples of its use with empirical data. The article ends with general guidelines and recommendations for researchers interested in using exploratory methods as a way to examine psychological processes.

A supervised hierarchical segmentation of remote-sensing images using a committee of multi-scale convolutional neural networks

This paper presents a supervised, hierarchical remote-sensing image segmentation technique using a committee of multi-scale convolutional neural networks. With existing techniques, segmentation is ...

Edge-based cuing for detection of benthic camouflage

Locating marine organisms in their natural habitats is important for understanding ocean biodiversity. Many species are often camouflaged in their surroundings, rendering them hard to detect. Our increasing ability to image large areas of the ocean floor produces millions of images, which must be inspected to spot the occasional organism. This calls for automation of camouflage detection. We investigate reliable detectability of marine camouflage by looking for structural regularities as cues to locating organisms in their natural settings. We study skates and flounder, which use different mechanisms to avoid detection. We introduce a simple edge-based criterion for detecting local structural regularity to reduce the image area to be inspected for likely presence of camouflaged organisms. This sets the stage for efficient use of more complex algorithms to confirm detections and aid in marine census. We also study the possibility of detecting octopuses based on a simple measure of texture applied to a hierarchical segmentation of octopus images.

A Spectral-Spatial Classification of Hyperspectral Images Based on the Algebraic Multigrid Method and Hierarchical Segmentation Algorithm

The algebraic multigrid (AMG) method is used to solve linear systems of equations on a series of progressively coarser grids and has recently attracted significant attention for image segmentation due to its high efficiency and robustness. In this paper, a novel spectral-spatial classification method for hyperspectral images based on the AMG method and hierarchical segmentation (HSEG) algorithm is proposed. Our method consists of the following steps. First, the AMG method is applied to hyperspectral imagery to construct a multigrid structure of fine-to-coarse grids based on the anisotropic diffusion partial differential equation (PDE). The vertices in the multigrid structure are then considered as the initial seeds (markers) for growing regions and are clustered to obtain a sequence of segmentation results. In the next step, a maximum vote decision rule is employed to combine the pixel-wise classification map and the segmentation maps. Finally, a final classification map is produced by choosing the optimal grid level to extract representative spectra. Experiments based on three different types of real hyperspectral datasets with different resolutions and contexts demonstrate that our method can obtain 3.84%–13.81% higher overall accuracies than the SVM classifier. The performance of our method was further compared to several marker-based spectral-spatial classification methods using objective quantitative measures and a visual qualitative evaluation.

A supervised hierarchical segmentation of remote-sensing images using a committee of multi-scale convolutional neural networks

ABSTRACTThis paper presents a supervised, hierarchical remote-sensing image segmentation technique using a committee of multi-scale convolutional neural networks. With existing techniques, segmentation is achieved through fine-tuning a set of predefined feature detectors. However, such a solution is not robust since the introduction of new sensors or applications would require novel features and techniques to be developed. Conversely, the proposed method achieves segmentation through a set of learnt feature detectors. In order to learn feature detectors, the proposed method exploits a committee of convolutional neural networks that perform multi-scale analysis on each band in order to derive individual confidence maps on region boundaries. Confidence maps are then inter-fused in order to produce a fused confidence map. Furthermore, the fused map is intra-fused using a morphological scheme into a hierarchical segmentation map. The proposed method is quantitatively compared to baseline techniques on a publicly available data set. The results presented in this paper highlight the improved accuracy of the proposed method.

An Investigation of Image Segmentation Method for Remotely Sensed Hyperspectral Images with Region Object Aggregations

An important aspect of spectral image analysis is identification of materials present in the object or scene being imaged. Since multi-spectral or hyper spectral imagery is generally low resolution, it is possible for pixels in the image to contain several materials. A paramount issue in image processing area is to design and implement an efficient segmentation and classification techniques demanding optimal resources. This paper presents a survey on all prominent region growing segmentation techniques analyzing each one and thus sorting out an optimal and promising technique. Finally study the importance of the best merge region growing normally produces segmentations with closed connected region objects. Recognizing that spectrally similar objects often appear in spatially separate locations, present an approach for tightly integrating best merge region growing with nonadjacent region object aggregation, which we call hierarchical segmentation or HSeg. The effectiveness of the proposed methodology is illustrated by comparing its performance with the state-of-the-art methods on synthetic and real hyper spectral image data sets. The reported results give clear evidence of the relevance of using both spatial and spectral information in hyper spectral image segmentation.

Purely vision-based segmentation of web pages for assistive technology

We propose a system for analyzing the structure of a web page based on purely visual information, rather than on implementation details. This is advantageous because regardless of the complexity of the underlying implementation, the web page is designed to be easily interpreted visually. Our method produces a hierarchical segmentation reflecting the visual structure of the rendered page. This rich information about the presentation of the web page can be used by other systems which produce alternate presentations more suitable for users with visual or cognitive disabilities.

A Hierarchical Classification and Segmentation Scheme for Processing Sensor Data.

Detecting short-duration events from continuous sensor signals is a significant challenge in the domain of wearable devices and health monitoring systems. Time-series segmentation refers to the challenge of subdividing a continuous stream of data into discrete windows, which can be individually processed using statistical classifiers or other algorithms. In this paper, we propose an algorithm for segmenting time-series signals and detecting short-duration data in the domain of lightweight embedded systems with real-time constraints. First, we demonstrate an approach for signal segmentation using a simple binary classifier. Next, we show how a novel two-stage classification algorithm can reduce computational overhead compared to a single-stage approach. Our proposed scheme is benchmarked using an audio-based nutrition-monitoring case study.

An Active Learning Framework for Hyperspectral Image Classification Using Hierarchical Segmentation

Augmenting spectral data with spatial information for image classification has recently gained significant attention, as classification accuracy can often be improved by extracting spatial information from neighboring pixels. In this paper, we propose a new framework in which active learning (AL) and hierarchical segmentation (HSeg) are combined for spectral–spatial classification of hyperspectral images. The spatial information is extracted from a best segmentation obtained by pruning the HSeg tree using a new supervised strategy. The best segmentation is updated at each iteration of the AL process, thus taking advantage of informative labeled samples provided by the user. The proposed strategy incorporates spatial information in two ways: 1) concatenating the extracted spatial features and the original spectral features into a stacked vector and 2) extending the training set using a self-learning-based semi-supervised learning (SSL) approach. Finally, the two strategies are combined within an AL framework. The proposed framework is validated with two benchmark hyperspectral datasets. Higher classification accuracies are obtained by the proposed framework with respect to five other state-of-the-art spectral–spatial classification approaches. Moreover, the effectiveness of the proposed pruning strategy is also demonstrated relative to the approaches based on a fixed segmentation.

Integrating Hierarchical Segmentation Maps With MRF Prior for Classification of Hyperspectral Images in a Bayesian Framework

This paper presents a new spectral-spatial classification method for hyperspectral (HS) images. The proposed method is based on integrating hierarchical segmentation results into Markov random field (MRF) spatial prior in the Bayesian framework. This work includes two main contributions. First, statistical region merging (SRM) segmentation algorithm is extended to a hierarchical version, HSRM. Second, a method for extracting a multilevel “fuzzy no-border/border” map from HSRM segmentation hierarchy is proposed, which are then exploited as weighting coefficients to modify the spatial prior of MRF-based multilevel logistic (MLL) model. The proposed method, named as MRF + HSRM, addresses the common problem of MRF-based methods, i.e., over-smoothing of classification result. Several experiments are conducted using real HS images to evaluate the performance of the proposed method in comparison with conventional MRF, and some state-of-the-art weighted MRF and object-based classifiers. To estimate the class conditional probability distribution in Bayesian framework, probabilistic support vector machine (SVM) and subspace multinomial logistic regression (MLRsub) classifiers are used. The experimental results demonstrate that the proposed method is able to generate more homogeneous regions similar to MRF-based methods, while preserving class boundaries as accurately as segmentation-based methods. The overhead computational burden of the proposed hierarchical segmentation stage is negligible considering the improvement it offers in classification results.

Morphological probabilistic hierarchies for texture segmentation

Abstract A general methodology is introduced for texture segmentation in binary, scalar, or multispectral images. Textural information is obtained from morphological operations on images. Starting from a fine partition of the image in regions, hierarchical segmentations are designed in a probabilistic framework by means of probabilistic distances conveying the textural or morphological information, and of random markers accounting for the morphological content of the regions and of their spatial arrangement. The probabilistic hierarchies are built from binary or multiple fusion of regions.