Merging Criterion Research Articles

A method of determining flame radiation fraction induced by interaction burning of tri-symmetric propane fires in open space based on weighted multi-point source model

The interaction of multiple fires may lead to a higher flame height and more intense radiation flux than a single fire, which increases the possibility of flame spread and risks to the surroundings. Experiments were conducted using three burners with identical heat release rates (HRRs) and propane as the fuel at various spacings. The results show that flames change from non-merging to merging as the spacing decreases, which result in a complex evolution of flame height and merging point height. To facilitate the analysis, a novel merging criterion based on the dimensionless spacing S/zc was proposed. For non-merging flames (S/zc > 0.368), the flame height is almost identical to a single fire; for merging flames (S/zc ⩽ 0.368), based on the relationship between thermal buoyancy B and thrust P (the pressure difference between the inside and outside of the flame), a quantitative analysis of the flame height, merging point height, and air entrainment was formed, and the calculated merging flame heights show a good agreement with the measured experimental values. Moreover, the multi-point source model was further improved, and radiation fraction of propane was calculated. The data obtained in this study would play an important role in calculating the external radiation of propane fire.

Flame interaction and tilting behavior of two tandem adjacent hydrocarbon turbulent diffusion flames in crosswind: An experimental quantification and characterization

This study presents an experimental investigation into the flame interaction and tilting behaviors of two tandem adjacent hydrocarbon turbulent diffusion flames in crosswind, which has not been well quantified in the past. Comprehensive experiments involving 204 tests were carried out employing two 15 cm square burners of various distances and two liquid fuels of representative soot production abilities, in crosswinds up to 6 m/s generated by a wind tunnel. The flame tilt angles were measured to quantify their interactions for flame merging and non-merging conditions. Results showed that the flame merging criterion extended under crosswind, especially for n-heptane fire with longer flame length. The tilt angles of merged flames were found to be smaller than that of single diffusion flame (SDF) and upstream diffusion flame (UDF) with the same crosswind speed for non-merging condition at relative larger separation distance. For flame non-merging condition, downstream diffusion flame (DDF)'s flame tilt angle values were lower than that of UDF due to the first flame shelter effect, and became smaller for larger separation distance at a given crosswind. According to their dynamic behaviors for non-merging condition, the ratio of flame tilt angle of DDF to that of UDF against a modified Fr* number fell into four regimes. The effective crosswind speed for DDF under crosswind momentum prevailed condition was proposed on account of the effects of the fire separation distance, the UDF's flame height and buoyancy flux. Non-dimensional formula was proposed to characterize their flame tilt angles for merging and non-merging flames respectively.

THE ROLE OF NIGERIA IN THE ECOWAS AND ITS SUPPORT TOWARDS THE COMMON PROPOSED CURRENCY ECO

Nigeria is the arrowhead of the Economic Community of West African State (ECOWAS), which was emerged in Lagos on May 28, 1975, as a regional institution consisting of fifteen nations. The essence of the establishment is to integrate the region into the single economic bloc and to ensure sole currency existence, which has been on the agenda of the head of the state conference. The study adopted regional integration theory and employed Qualitative Document Analysis (QDA) in order to elaborate on the big-brother and sub-regional leader role of Nigeria in the region. The study found that loyalty to colonialism and the francophone country's long-existing monetary cooperation towards France was the strong blockade of the proposal as well as the member state was unable to reach-up to the merging criteria, which resulted in the shift and delays on the establishment of the common currency date. It was also discovered that on the efforts to embark on the process, two fast track approaches were being agreed upon towards the realization of the common currency. The first track meeting was held in Accra, Ghana, in April 2000, proposing that the West African Economic and Monetary Union (WAEMU) were to create a second Monetary Union by July 2005 termed the West African Monetary Zone (WAMZ), mainly comprising of Anglophone countries. The second track was stressing on the consequent merging of the WAMZ and WAEMU to form a common currency union in the region. The study went further to provide some suggestions toward the implementation of the common currency in the region.
 Keywords: Nigeria, ECOWAS, Single Currency, Regional Leader.

SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING OBJECT-BASED MARKOV RANDOM FIELD BASED ON HIERARCHICAL SEGMENTATION TREE WITH AUXILIARY LABELS

Abstract. In the remote sensing imagery, spectral and texture features are always complex due to different landscapes, which leads to misclassifications in the results of semantic segmentation. The object-based Markov random field provides an effective solution to this problem. However, the state-of-the-art object-based Markov random field still needs to be improved. In this paper, an object-based Markov Random Field model based on hierarchical segmentation tree with auxiliary labels is proposed. A remote sensing imagery is first segmented and the object-based hierarchical segmentation tree is built based on initial segmentation objects and merging criteria. And then, the object-based Markov random field with auxiliary label fields is established on the hierarchical tree structure. A probabilistic inference is applied to solve this model by iteratively updating label field and auxiliary label fields. In the experiment, this paper utilized a Worldview-3 image to evaluate the performance, and the results show the validity and the accuracy of the presented semantic segmentation approach.

Machine learning-assisted region merging for remote sensing image segmentation

With the increasing popularity of OBIA, many scholars advocate that image segmentation plays a significant role in remote sensing image processing. Numerous segmentation algorithms for remote sensing images are based on region merging. Although good improvement is achieved, their accuracy is still dependent on parameter settings, leading to a low level of automation. To overcome this issue, this work proposes a new region merging method by using a random forest (RF) classifier. Unlike the traditional region merging methods that all adopt a scale threshold to determine whether a merging can be conducted, the new algorithm relies on a trained RF to decide the result of a merging test. Various merging criteria are simultaneously employed as feature variables of the RF model, enhancing the quality of the proposed scheme. The major problem in this work is how to train the RF classifier since the merging test samples need to be obtained in the iterative steps of a region merging process, which involves a huge number of human–computer interactions even for a small image. To simplify it, a sample collection strategy based on a set of three-scale segmentation results is devised. Representative merging test samples can be obtained by using this method. To validate the proposed technique, four Gaofen-2 images are used for training sample collection, and the most interesting result is that the samples extracted from one image can apply to others. Some images captured by Orbview-3, GeoEye-1, and Worldview-2 further indicate the robust performance of the new algorithm and the samples acquired in this work.

Deviation based clustering for unsupervised person re-identification

Recently, unsupervised person re-identification (re-ID) has gained a lot of attention, since it does not depend on intensive manual annotation and is more practical to deploy in the real world directly. An inspiring method, the Bottom-up Clustering (BUC), achieves the state-of-the-art among unsupervised re-ID methods and outperforms most semi-supervised and transfer learning algorithms. The BUC utilizes the minimum-distance between samples in different clusters as the merging criterion, and the number of samples as the penalization term. However, the minimum-distance criterion only considers one pair of samples between two clusters, and cannot exploit the information of all samples in clusters. The penalization, intuitively, is unsuitable for the dataset with irregular sample quantity. To relieve this problem, we propose a deviation based clustering re-ID approach, which takes the inter- and intra-cluster deviation into consideration. The inter-cluster deviation denotes the increase of deviation after merging two clusters, considering all samples between the two clusters to merge. The intra-cluster deviation, working as penalization, denotes the distance between samples and the center in each cluster, and thus it can help to mitigate the side-effect of irregular datasets. The two criterions can reflect the inter- and intra- dispersion precisely. Based on these criterions, we group similar samples into clusters and utilize the cluster identities as a pseudo annotation to train our model. To evaluate our proposed approach, we implement abundant experiments on two popular re-ID datasets, where one has irregular sample quality (i.e., Market-1501) and the other has regular sample quality (i.e., DukeMTMC-reID). Evaluations show that our method outperforms BUC by 1.8% on Rank-1 (i.e., 68.0% accuracy) and 2.1% on mAP (i.e., 40.4% accuracy) for the Market-1501 dataset, and well maintains the benefit of BUC on the DukeMIMC-reID dataset with the accuracy of 47.8% in Rank-1 and 27.0% in mAP.

Boundary constrained voxel segmentation for 3D point clouds using local geometric differences

In 3D point cloud processing, the spatial continuity of points is convenient for segmenting point clouds obtained by 3D laser scanners, RGB-D cameras and LiDAR (light detection and ranging) systems in general. In real life, the surface features of both objects and structures give meaningful information enabling them to be identified and distinguished. Segmenting the points by using their local plane directions (normals), which are estimated by point neighborhoods, is a method that has been widely used in the literature. The angle difference between two nearby local normals allows for measurement of the continuity between the two planes. In real life, the surfaces of objects and structures are not simply planes. Surfaces can also be found in other forms, such as cylinders, smooth transitions and spheres. The proposed voxel-based method developed in this paper solves this problem by inspecting only the local curvatures with a new merging criteria and using a non-sequential region growing approach. The general prominent feature of the proposed method is that it mutually one-to-one pairs all of the adjoining boundary voxels between two adjacent segments to examine the curvatures of all of the pairwise connections. The proposed method uses only one parameter, except for the parameter of unit point group (voxel size), and it does not use a mid-level over-segmentation process, such as supervoxelization. The method checks the local surface curvatures using unit normals, which are close to the boundary between two growing adjacent segments. Another contribution of this paper is that some effective solutions are introduced for the noise units that do not have surface features. The method has been applied to one indoor and four outdoor datasets, and the visual and quantitative segmentation results have been presented. As quantitative measurements, the accuracy (based on the number of true segmented points over all points) and F1 score (based on the means of precision and recall values of the reference segments) are used. The results from testing over five datasets show that, according to both measurement techniques, the proposed method is the fastest and achieves the best mean scores among the methods tested.

Shallow cumuli cover and its uncertainties from ground-based lidar–radar data and sky images

Abstract. Cloud cover estimates of single-layer shallow cumuli obtained from narrow field-of-view (FOV) lidar–radar and wide-FOV total sky imager (TSI) data are compared over an extended period (2000–2017 summers) at the established United States Atmospheric Radiation Measurement mid-continental Southern Great Plains site. We quantify the impacts of two factors on hourly and sub-hourly cloud cover estimates: (1) instrument-dependent cloud detection and data merging criteria and (2) FOV configuration. Enhanced observations at this site combine the advantages of the ceilometer, micropulse lidar (MPL) and cloud radar in merged data products. Data collected by these three instruments are used to calculate narrow-FOV cloud fraction (CF) as a temporal fraction of cloudy returns within a given period. Sky images provided by TSI are used to calculate the wide-FOV fractional sky cover (FSC) as a fraction of cloudy pixels within a given image. To assess the impact of the first factor on CF obtained from the merged data products, we consider two additional subperiods (2000–2010 and 2011–2017 summers) that mark significant instrumentation and algorithmic advances in the cloud detection and data merging. We demonstrate that CF obtained from ceilometer data alone and FSC obtained from sky images provide the most similar and consistent cloud cover estimates; hourly bias and root-mean-square difference (RMSD) are within 0.04 and 0.12, respectively. However, CF from merged MPL–ceilometer data provides the largest estimates of the multiyear mean cloud cover, about 0.12 (35 %) and 0.08 (24 %) greater than FSC for the first and second subperiods, respectively. CF from merged ceilometer–MPL–radar data has the strongest subperiod dependence with a bias of 0.08 (24 %) compared to FSC for the first subperiod and shows no bias for the second subperiod. The strong period dependence of CF obtained from the combined ceilometer–MPL–radar data is likely results from a change in what sensors are relied on to detect clouds below 3 km. After 2011, the MPL stopped being used for cloud top height detection below 3 km, leaving the radar as the only sensor used in cloud top height retrievals. To quantify the FOV impact, a narrow-FOV FSC is derived from the TSI images. We demonstrate that FOV configuration does not modify the bias but impacts the RMSD (0.1 hourly, 0.15 sub-hourly). In particular, the FOV impact is significant for sub-hourly observations, where 41 % of narrow- and wide-FOV FSC differ by more than 0.1. A new “quick-look” tool is introduced to visualize impacts of these two factors through integration of CF and FSC data with novel TSI-based images of the spatial variability in cloud cover. The influence of cloud field organization, such cloud streets parallel to the wind direction, on narrow- and wide-FOV cloud cover estimates can be visually assessed.

A minimum spanning tree based partitioning and merging technique for clustering heterogeneous data sets

Clustering being an unsupervised learning technique, has been used extensively for knowledge discovery due to its less dependency on domain knowledge. Many clustering techniques were proposed in the literature to recognize the cluster of different characteristics. Most of them become inadequate either due to their dependency on user-defined parameters or when they are applied on multi-scale datasets. Hybrid clustering techniques have been proposed to take the advantage of both Partitional and Hierarchical techniques by first partitioning the dataset into several dense sub-clusters and merging them into actual clusters. However, the universality of the partition and merging criteria are not sufficient to capture many characteristics of the clusters. Minimum spanning tree (MST) has been used extensively for clustering because it preserves the intrinsic nature of the dataset even after the sparsification of the graph. In this paper, we propose a parameter-free, minimum spanning tree based efficient hybrid clustering algorithm to cluster the multi-scale datasets. In the first phase, we construct a MST of the dataset to capture the neighborhood information of data points and employ box-plot, an outlier detection technique on MST edge weights for effectively selecting the inconsistent edges to partition the data points into several dense sub-clusters. In the second phase, we propose a novel merging criterion to find the genuine clusters by iteratively merging only the pairs of adjacent sub-clusters. The merging technique involves both dis-connectivity and intra-similarity using the topology of two adjacent pairs which helps to identify the arbitrary shape and varying density clusters. Experiment results on various synthetic and real world datasets demonstrate the superior performance of the proposed technique over other popular clustering algorithms.

Hybrid image segmentation method based on anisotropic Gaussian kernels and adjacent graph region merging.

Image segmentation is a key technique in image analysis for object identification. In this paper, a hybrid segmentation method is proposed, which is based on the Anisotropic Gaussian Kernel (ANGK) edge detector and region adjacent graph (RAG) merging algorithm. An anisotropic directional derivative filter is constructed by angled ANGK to detect the edge contour of original images. Based on the gradient magnitude pattern of the edge contour from ANGK processing, watershed transform is adopted to produce initial partition (coarse segmentation result). Finally, combined with the RAG region merging algorithm, the proposed method performs fine segmentation by merging similar fragmented regions (initial partition) iteratively. Additionally, statistic similarity measure and shape cost function in merging cost are also introduced. They provide quantitative criteria for region merging, which have critical influences on the detection result. A series of experiments are conducted to evaluate the performance of this method, and a preferable localization accuracy as well as noise robustness is proved. Compared with conventional edge and region based methods, the proposed one has a superior segmentation effect. Another advantage is that the problem of oversegmentation can be solved effectively.

PLSD: A Perceptually Accurate Line Segment Detection Approach

Most existing line segment detection methods suffer from the over-segmentation phenomenon. An improved line segment detection method is presented in this work, which can generate more and longer line segments, yet still accurately reflect the structural details of the image. Line segment grouping, line segment validation and a multiscale framework are adopted to reach this end. Specifically, smart grouping rules are introduced to locate potential homologous line segments (derived from the same boundaries). Novel merging criteria based on Helmholtz principle is then used to evaluate the meaningfulness between separate line segments and their merged ones. The improved multiscale framework facilitates line segments merging in detection and post-detection processes, yielding more high-quality line segments. Finally, the proposed method is compared with four leading methods on the famous public dataset, YorkUrban-LineSegment. Experimental results demonstrate that the method has good continuity and outperforms the leading methods in F-measure.

Multi-Layers Saliency Detection Based on Spectral Density Peaks Clustering

Saliency detection obtains the whole salient object by simulating human visual system, but the detection accuracy is seriously influenced by the small-scale and highcontrast regions in foreground or background, especially when dealing with objects with complex construe. This problem is common in natural images and forms a fundamental challenge for prior methods. To solve the above problem, we propose the multi-layers approach based on spectral density peaks clustering, in which the information from different saliency layers are fused to extract saliency object in complex scene, and we propose a criterion of salient region merging in order to light whole salient object. The experimental results show that the proposed method improves saliency detection on many images that cannot be handled well traditionally.

Efficient Algorithms for Hierarchical Graph-Based Segmentation Relying on the Felzenszwalb–Huttenlocher Dissimilarity

Hierarchical image segmentation provides a region-oriented scale-space, i.e. a set of image segmentations at different detail levels in which the segmentations at finer levels are nested with respect to those at coarser levels. However, most image segmentation algorithms, among which a graph-based image segmentation method relying on a region merging criterion was proposed by Felzenszwalb–Huttenlocher in 2004, do not lead to a hierarchy. In order to cope with a demand for hierarchical segmentation, Guimarães et al. proposed in 2012 a method for hierarchizing the popular Felzenszwalb–Huttenlocher method, without providing an algorithm to compute the proposed hierarchy. This paper is devoted to providing a series of algorithms to compute the result of this hierarchical graph-based image segmentation method efficiently, based mainly on two ideas: optimal dissimilarity measuring and incremental update of the hierarchical structure. Experiments show that, for an image of size 321 × 481 pixels, the most efficient algorithm produces the result in half a second whereas the most naive one requires more than 4 h.

A Multi-Threshold Segmentation for Tree-Level Parameter Extraction in a Deciduous Forest Using Small-Footprint Airborne LiDAR Data

The development of new approaches to tree-level parameter extraction for forest resource inventory and management is an important area of ongoing research, which puts forward high requirements for the capabilities of single-tree segmentation and detection methods. Conventional methods implement segmenting routine with same resolution threshold for overstory and understory, ignoring that their lidar point densities are different, which leads to over-segmentation of the understory trees. To improve the segmentation accuracy of understory trees, this paper presents a multi-threshold segmentation approach for tree-level parameter extraction using small-footprint airborne LiDAR (Light Detection And Ranging) data. First, the point clouds are pre-processed and encoded to canopy layers according to the lidar return number, and multi-threshold segmentation using DSM-based (Digital Surface Model) method is implemented for each layer; tree segments are then combined across layers by merging criteria. Finally, individual trees are delineated, and tree parameters are extracted. The novelty of this method lies in its application of multi-resolution threshold segmentation strategy according to the variation of LiDAR point density in different canopy layers. We applied this approach to 271 permanent sample plots of the University of Kentucky’s Robinson Forest, a deciduous canopy-closed forest with complex terrain and vegetation conditions. Experimental results show that a combination of multi-resolution threshold segmentation based on stratification and cross-layer tree segments merging method can provide a significant performance improvement in individual tree-level forest measurement. Compared with DSM-based method, the proposed multi-threshold segmentation approach strongly improved the average detection rate (from 52.3% to 73.4%) and average overall accuracy (from 65.2% to 76.9%) for understory trees. The overall accuracy increased from 75.1% to 82.6% for all trees, with an increase of the coefficient of determination R2 by 20 percentage points. The improvement of tree detection method brings the estimation of structural parameters for single trees up to an accuracy level: For tree height, R2 increased by 5.0 percentage points from 90% to 95%; and for tree location, the mean difference decreased by 23 cm from 105 cm to 82 cm.

Cluster-Volume-Based Merging Approach for Incrementally Evolving Fuzzy Gaussian Clustering—eGAUSS+

In this article, a new dynamic merging approach for incrementally evolving clustering is presented. This means that the cluster partitions are incrementally learned on-line from streams of data. The criterion of merging is based on the comparison between the sum of volumes of two clusters that fulfill the criteria of a minimal number of samples in the cluster and the expected volume of the newly generated merged cluster. The newly generated merged cluster is conducted by using the weighted averaging of cluster centers and the calculation of the joint covariance matrix from the covariance matrices of the clusters. It has been shown that the proposed new evolving algorithm eGAUSS+ together with the new merging concept is very easy to implement, can work on higher-dimensional data sets, can perform all necessary computation on-line, and can produce reliable clusters.

Hierarchical Segmentation Evaluation of Region-Based Image Hierarchy

Multiscale image segmentation plays an important role in object-based image analysis (OBIA) applications, and the evaluation of segmentation quality is a hot topic for OBIA community. Recently, with the increasing use of multiscale and hierarchical strategy in OBIA works, region-based image hierarchies have attracted increasing attentions. A region-based image hierarchy (i.e., binary partition tree and scale-sets hierarchy) is a tree-like structure, and it can be used to record multiscale segmentation results. Although many methods have been employed to evaluate multiscale segmentation, they cannot be applied to evaluate a region-based image hierarchy directly. In this study, a hierarchical segmentation evaluation approach was proposed to evaluate the upper-bound accuracy of a region-based image hierarchy. In our study, an image hierarchy is implemented using a region merging process, and organized as a scale-indexed binary partition tree; the best matching segment of each reference polygon is then selected by scanning whole hierarchy; and finally, the similarity between reference polygons and corresponding best matching segments are used to evaluate the overall performance of the hierarchy. Two high spatial resolution images (GaoFen-2 and QuickBird) and three region merging criteria were used to evaluate the effectiveness of the proposed approach. Moreover, the proposed method was compared with traditional multiscale evaluation strategies. The experimental results have demonstrated the effectiveness of the proposed approach, as well as the advantages compared to existing approaches.

Web Text Categorization Based on Statistical Merging Algorithm in Big Data Environment

In the field of modern information technology, how to find information quickly, accurately and comprehensively that users really needed has become the focus of research in this field. In this article, a feature selection method based on a complex network is proposed for the structure and content characteristics of large-scale web text information. The preprocessed web text is converted into a complex network. The nodes in the network correspond to the entries in the text. The edges of the network correspond to the links between the entries in the text, and the degree of nodes and the aggregation system are used. Second, the text classification method is studied from the point of view of data sampling, and a text classification method based on density statistics is proposed. This method uses not only the density information of the text feature set in the classification process, but also the use of statistical merging criteria to get the text. The difference information of each feature has a better classification effect for large text collections.

Cluster Validity Measures Based Agglomerative Hierarchical Clustering for Network Data

The Louvain method is a method of agglomerative hierarchical clustering (AHC) that uses modularity as the merging criterion. Modularity is an evaluation measure for network partitions. Cluster validity measures are also used to evaluate cluster partitions and to determine the optimal number of clusters. Several cluster validity measures are constructed considering the geometric features of clusters. These measures and modularity are considered to be the same concept in the viewpoint of evaluating cluster partitions. In this paper, cluster validity measures based agglomerative hierarchical clustering (CVAHC) is proposed as a novel clustering method for network data. The cluster validity measures are used as a merging criterion and an evaluation measure for network data in the proposed method. Numerical experiments show that Dunn’s and Xie-Beni’s indices for network partitions are useful for network clustering.

Unmanned Aerial Vehicle Remote Sensing Image Segmentation Method by Combining Superpixels with multi-features Distance Measure

Image segmentation is the foundation and key step of object-level classification and change detection. In this paper, a segmentation method of UAV remote sensing image based on multi-features distance measure and superpixels is proposed. First, the simple linear iterative clustering (SLIC) algorithm is used to segment the unmanned aerial vehicle (UAV) remote sensing image to obtain the initial superpixels. Then the distance measures of the spectral, texture, shape and area features are used as the criterion for initial superpixels merging. Finally, merger termination when the number of regions reaches the set number. Two groups of UAV remote sensing images are selected to evaluate the experimental results through visual evaluation. The experimental results show that the proposed method can be used to aggregate objects of different scales, and the segmentation effect is satisfactory.

Unsupervised evaluation-based region merging for high resolution remote sensing image segmentation

Image segmentation has a remarkable influence on the classification accuracy of object-based image analysis. Accordingly, how to raise the performance of remote sensing image segmentation is a key issue. However, this is challenging, primarily because it is difficult to avoid over-segmentation errors (OSE) and under-segmentation errors (USE). To solve this problem, this article presents a new segmentation technique by fusing a region merging method with an unsupervised segmentation evaluation technique called under- and over-segmentation aware (UOA), which is improved by using edge information. Edge information is also used to construct the merging criterion of the proposed approach. To validate the new segmentation scheme, five scenes of high resolution images acquired by Gaofen-2 and Ziyuan-3 multispectral sensors are chosen for the experiment. Quantitative evaluation metrics are employed in the experiment. Results indicate that the proposed algorithm obtains the lowest total error (TE) values for all test images (0.3791, 0.1434, 0.7601, 0.7569, 0.3169 for the first, second, third, fourth, fifth image, respectively; these values are averagely 0.1139 lower than the counterparts of the other methods), as compared to six state-of-the-art region merging-based segmentation approaches, including hybrid region merging, hierarchical segmentation, scale-variable region merging, size-constrained region merging with edge penalty, region merging guided by priority, and region merging combined with the original UOA. Moreover, the performance of the proposed method is better for artificial-object-dominant scenes than the ones mainly covering natural geo-objects.