Search

Abstract Embedding thread lift rhytidectomy, also known as “thread lifting” in China, with the natures of simple operation, less trauma and quick recovery, is progressively used in clinical practice as a new technology of face lifting. Herewith, a brief introduction of the previous advances of thread lifting techniques and materials in the facial beauty industry, combined with the discussion on various types of sutures, common complications, and the site of actions were provided. The main limitations of present thread lifting material include: (1) the use of non-absorbable sutures is liable to cause allergies and a series of complications; (2) the absorbable sutures are easily degradation, and people need to reshape in a relatively short period. Therefore, the high biocompatible spider silk was proposed as a novel material of thread lifting suture and related devices, the advantages and preliminary achievements on spider silk were also addressed. Graphic Abstract

In the past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper,we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images., Comment: Accepted to IEEE TPAMI

This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 and GID-15 datasets, this challenge proposes three tasks for oriented object detection, horizontal object detection, and semantic segmentation of common categories in aerial images. This challenge received a total of 146 registrations on the three tasks. Through the challenge, we hope to draw attention from a wide range of communities and call for more efforts on the problems of learning to understand aerial images., 7 pages, 2 figures, accepted by ICCVW 2021

Automatic extraction of buildings in remote sensing images is an important but challenging task and finds many applications in different fields such as urban planning, navigation and so on. This paper addresses the problem of buildings extraction in very high-spatial-resolution (VHSR) remote sensing (RS) images, whose spatial resolution is often up to half meters and provides rich information about buildings. Based on the observation that buildings in VHSR-RS images are always more distinguishable in geometry than in texture or spectral domain, this paper proposes a geometric building index (GBI) for accurate building extraction, by computing the geometric saliency from VHSR-RS images. More precisely, given an image, the geometric saliency is derived from a mid-level geometric representations based on meaningful junctions that can locally describe geometrical structures of images. The resulting GBI is finally measured by integrating the derived geometric saliency of buildings. Experiments on three public and commonly used datasets demonstrate that the proposed GBI achieves the state-of-the-art performance and shows impressive generalization capability. Additionally, GBI preserves both the exact position and accurate shape of single buildings compared to existing methods.

Wide-area control (WAC) has been shown to be an effective tool for damping low-frequency oscillations in power systems. In the current state of art, WAC is challenged by two main factors - namely, scalability of design and complexity of implementation. In this paper we present a control design called control inversion that bypasses both of these challenges using the idea of clustering. The basic philosophy behind this method is to project the original power system model into a lower-dimensional state-space through clustering and aggregation of generator states, and then designing an LQR controller for the lower-dimensional model. This controller is finally projected back to the original coordinates for wide-area implementation. The main problem is, therefore, posed as finding the projection which best matches the closed-loop performance of the WAC controller with that of a reference LQR controller for damping low-frequency oscillations. We verify the effectiveness of the proposed design using the NPCC 48-machine power system model., Submitted to IEEE Transactions on Control of Network Systems

Recently, deep learning based methods have demonstrated promising results on the graph matching problem, by relying on the descriptive capability of deep features extracted on graph nodes. However, one main limitation with existing deep graph matching (DGM) methods lies in their ignorance of explicit constraint of graph structures, which may lead the model to be trapped into local minimum in training. In this paper, we propose to explicitly formulate pairwise graph structures as a quadratic constraint incorporated into the DGM framework. The quadratic constraint minimizes the pairwise structural discrepancy between graphs, which can reduce the ambiguities brought by only using the extracted CNN features. Moreover, we present a differentiable implementation to the quadratic constrained-optimization such that it is compatible with the unconstrained deep learning optimizer. To give more precise and proper supervision, a well-designed false matching loss against class imbalance is proposed, which can better penalize the false negatives and false positives with less overfitting. Exhaustive experiments demonstrate that our method achieves competitive performance on real-world datasets. The code is available at: https://github.com/Zerg-Overmind/QC-DGM.

This article presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: Feature mixing in edge classification and side mixing during fusing side predictions. The CATS consists of two modules: A novel tracing loss that performs feature unmixing by tracing boundaries for better side edge learning, and a context-aware fusion block that tackles the side mixing by aggregating the complementary merits of learned side edges. Experiments demonstrate that the proposed CATS can be integrated into modern deep edge detectors to improve localization accuracy. With the vanilla VGG16 backbone, in terms of BSDS500 dataset, our CATS improves the F-measure (ODS) of the RCF and BDCN deep edge detectors by 12 and 6 percent, respectively when evaluating without using the morphological non-maximal suppression scheme for edge detection.

Recently, object detection in aerial images has gained much attention in computer vision. Different from objects in natural images, aerial objects are often distributed with arbitrary orientation. Therefore, the detector requires more parameters to encode the orientation information, which are often highly redundant and inefficient. Moreover, as ordinary CNNs do not explicitly model the orientation variation, large amounts of rotation augmented data is needed to train an accurate object detector. In this paper, we propose a Rotation-equivariant Detector (ReDet) to address these issues, which explicitly encodes rotation equivariance and rotation invariance. More precisely, we incorporate rotation-equivariant networks into the detector to extract rotation-equivariant features, which can accurately predict the orientation and lead to a huge reduction of model size. Based on the rotation-equivariant features, we also present Rotation-invariant RoI Align (RiRoI Align), which adaptively extracts rotation-invariant features from equivariant features according to the orientation of RoI. Extensive experiments on several challenging aerial image datasets DOTA-v1.0, DOTA-v1.5 and HRSC2016, show that our method can achieve state-of-the-art performance on the task of aerial object detection. Compared with previous best results, our ReDet gains 1.2, 3.5 and 2.6 mAP on DOTA-v1.0, DOTA-v1.5 and HRSC2016 respectively while reducing the number of parameters by 60\% (313 Mb vs. 121 Mb). The code is available at: \url{https://github.com/csuhan/ReDet}., Comment: Accepted by CVPR2021

Many scientific reports document that asymptomatic and presymptomatic individuals contribute to the spread of COVID-19, probably during conversations in social interactions. Droplet emission occurs during speech, yet few studies document the flow to provide the transport mechanism. This lack of understanding prevents informed public health guidance for risk reduction and mitigation strategies, e.g. the "six-foot rule". Here we analyze flows during breathing and speaking, including phonetic features, using order-of-magnitudes estimates, numerical simulations, and laboratory experiments. We document the spatio-temporal structure of the expelled air flow. Phonetic characteristics of plosive sounds like 'P' lead to enhanced directed transport, including jet-like flows that entrain the surrounding air. We highlight three distinct temporal scaling laws for the transport distance of exhaled material including (i) transport over a short distance ($, Comment: 14 pages, 6 figures

Graph matching (GM), as a longstanding problem in computer vision and pattern recognition, still suffers from numerous cluttered outliers in practical applications. To address this issue, we present the zero-assignment constraint (ZAC) for approaching the graph matching problem in the presence of outliers. The underlying idea is to suppress the matchings of outliers by assigning zero-valued vectors to the potential outliers in the obtained optimal correspondence matrix. We provide elaborate theoretical analysis to the problem, i.e., GM with ZAC, and figure out that the GM problem with and without outliers are intrinsically different, which enables us to put forward a sufficient condition to construct valid and reasonable objective function. Consequently, we design an efficient outlier-robust algorithm to significantly reduce the incorrect or redundant matchings caused by numerous outliers. Extensive experiments demonstrate that our method can achieve the state-of-the-art performance in terms of accuracy and efficiency, especially in the presence of numerous outliers.

This paper presents a fast and parsimonious parsing method to accurately and robustly detect a vectorized wireframe in an input image with a single forward pass. The proposed method is end-to-end trainable, consisting of three components: (i) line segment and junction proposal generation, (ii) line segment and junction matching, and (iii) line segment and junction verification. For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image. Junctions can be treated as the "basins" in the attraction field. The proposed method is thus called Holistically-Attracted Wireframe Parser (HAWP). In experiments, the proposed method is tested on two benchmarks, the Wireframe dataset, and the YorkUrban dataset. On both benchmarks, it obtains state-of-the-art performance in terms of accuracy and efficiency. For example, on the Wireframe dataset, compared to the previous state-of-the-art method L-CNN, it improves the challenging mean structural average precision (msAP) by a large margin ($2.8\%$ absolute improvements) and achieves 29.5 FPS on single GPU ($89\%$ relative improvement). A systematic ablation study is performed to further justify the proposed method., Comment: Accepted by CVPR 2020

As the battery ages, the available energy of the battery will decline obviously, and accurately estimating the available energy of the battery will have important significance for the management and control of the battery system. Four 50Ah lithium iron phosphate (LFP) batteries returned from electric bus as the research object. The maximum charging and discharging current that can be sustained by a cell was tested for 1000 cycles at 25°C, and the one-time energy test was conducted for every 100 cycles, this includes a capacity test with 1/3C current and an increment capacity analyze(ICA) test with 1/20C current. The energy and capacity degeneration characteristics are compared through the above experiments, and the increment energy (IE) curve that reflects the chemical characteristics of the battery is obtained by analogy with ICA. The IE curve is used to analyze the degeneration characteristics of the battery and estimate the available energy of the battery, and verify the correctness and effectiveness of the method.

Kernel adaptive filtering (KAF) is an effective nonlinear learning algorithm, which has been widely used in time series prediction. The traditional KAF is based on the stochastic gradient descent (SGD) method, which has slow convergence speed and low filtering accuracy. Hence, a kernel conjugate gradient (KCG) algorithm has been proposed with low computational complexity, while achieving comparable performance to some KAF algorithms, e.g., the kernel recursive least squares (KRLS). However, the robust learning performance is unsatisfactory, when using KCG. Meanwhile, correntropy as a local similarity measure defined in kernel space, can address large outliers in robust signal processing. On the basis of correntropy, the mixture correntropy is developed, which uses the mixture of two Gaussian functions as a kernel function to further improve the learning performance. Accordingly, this article proposes a novel KCG algorithm, named the kernel mixture correntropy conjugate gradient (KMCCG), with the help of the mixture correntropy criterion (MCC). The proposed algorithm has less computational complexity and can achieve better performance in non-Gaussian noise environments. To further control the growing radial basis function (RBF) network in this algorithm, we also use a simple sparsification criterion based on the angle between elements in the reproducing kernel Hilbert space (RKHS). The prediction simulation results on a synthetic chaotic time series and a real benchmark dataset show that the proposed algorithm can achieve better computational performance. In addition, the proposed algorithm is also successfully applied to the practical tasks of malware prediction in the field of malware analysis. The results demonstrate that our proposed algorithm not only has a short training time, but also can achieve high prediction accuracy.

Object detection in aerial images is an active yet challenging task in computer vision because of the bird’s-eye view perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. In this paper, we propose a RoI Transformer to address these problems. The core idea of RoI Transformer is to apply spatial transformations on RoIs and learn the transformation parameters under the supervision of oriented bounding box (OBB) annotations. RoI Transformer is with lightweight and can be easily embedded into detectors for oriented object detection. Simply apply the RoI Transformer to light head RCNN has achieved state-of-the-art performances on two common and challenging aerial datasets, i.e., DOTA and HRSC2016, with a neglectable reduction to detection speed. Our RoI Transformer exceeds the deformable Position Sensitive RoI pooling when oriented bounding-box annotations are available. Extensive experiments have also validated the flexibility and effectiveness of our RoI Transformer.

This paper presents a region-partition based attraction field dual representation for line segment maps, and thus poses the problem of line segment detection (LSD) as the region coloring problem. The latter is then addressed by learning deep convolutional neural networks (ConvNets) for accuracy, robustness and efficiency. For a 2D line segment map, our dual representation consists of three components: (i) A region-partition map in which every pixel is assigned to one and only one line segment; (ii) An attraction field map in which every pixel in a partition region is encoded by its 2D projection vector w.r.t. the associated line segment; and (iii) A squeeze module which squashes the attraction field to a line segment map that almost perfectly recovers the input one. By leveraging the duality, we learn ConvNets to compute the attraction field maps for raw in-put images, followed by the squeeze module for LSD, in an end-to-end manner. Our method rigorously addresses several challenges in LSD such as local ambiguity and class imbalance. Our method also harnesses the best practices developed in ConvNets based semantic segmentation methods such as the encoder-decoder architecture and the a-trous convolution. In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained. Especially, we advance the performance by 4.5 percents on the WireFrame dataset. Our method is also fast with 6.6~10.4 FPS, outperforming most of existing line segment detectors., Accepted by CVPR 2019

In this paper we present two sets of parallel algorithms for identifying real-time, small-signal dynamic models of power systems using multiple sources of Synchrophasor data. The first problem is posed in terms of identifying the transfer matrix of single-input multiple-output (SIMO) power system models using linear least-squares (LLS), where parallelism can be implemented through parallel execution of matrix multiplications using multiple processors or workers. Given the constraints of sequential communication and limited local memory, which may arise due to multiple applications running in the workers at the same time, a novel scheduling algorithm is proposed to enable flexible deadlines that meet these constraints. The scheduling algorithm minimizes the total time of execution under constraints, and can be solved via integer programming. The second problem is posed as a similar parallel algorithm for identifying a linearized state-variable (SV) model of a power system using both linear and nonlinear least-squares (NLS) in presence of scheduling. The performance of all the algorithms are studied via simulations of an IEEE 145-bus, 50-machine power system model, and compared with their centralized, non-parallel implementation.

Graph matching is an important and persistent problem in computer vision and pattern recognition for finding node-to-node correspondence between graph-structured data. However, as widely used, graph matching that incorporates pairwise constraints can be formulated as a quadratic assignment problem (QAP), which is NP-complete and results in intrinsic computational difficulties. In this paper, we present a functional representation for graph matching (FRGM) that aims to provide more geometric insights on the problem and reduce the space and time complexities of corresponding algorithms. To achieve these goals, we represent a graph endowed with edge attributes by a linear function space equipped with a functional such as inner product or metric, that has an explicit geometric meaning. Consequently, the correspondence between graphs can be represented as a linear representation map of that functional. Specifically, we reformulate the linear functional representation map as a new parameterization for Euclidean graph matching, which is associative with geometric parameters for graphs under rigid or nonrigid deformations. This allows us to estimate the correspondence and geometric deformations simultaneously. The use of the representation of edge attributes rather than the affinity matrix enables us to reduce the space complexity by two orders of magnitudes. Furthermore, we propose an efficient optimization strategy with low time complexity to optimize the objective function. The experimental results on both synthetic and real-world datasets demonstrate that the proposed FRGM can achieve state-of-the-art performance.

This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images. Assuming that the distorted lines generated by fisheye projection should be straight after rectification, we propose a novel deep neural network to impose explicit geometry constraints onto processes of the fisheye lens calibration and the distorted image rectification. In addition, considering the nonlinearity of distortion distribution in fisheye images, the proposed network fully exploits multi-scale perception to equalize the rectification effects on the whole image. To train and evaluate the proposed model, we also create a new large-scale dataset labeled with corresponding distortion parameters and well-annotated distorted lines. Compared with the state-of-the-art methods, our model achieves the best published rectification quality and the most accurate estimation of distortion parameters on a large set of synthetic and real fisheye images.

This paper presents regional attraction of line segment maps, and hereby poses the problem of line segment detection (LSD) as a problem of region coloring. Given a line segment map, the proposed regional attraction first establishes the relationship between line segments and regions in the image lattice. Based on this, the line segment map is equivalently transformed to an attraction field map (AFM), which can be remapped to a set of line segments without loss of information. Accordingly, we develop an end-to-end framework to learn attraction field maps for raw input images, followed by a squeeze module to detect line segments. Apart from existing works, the proposed detector properly handles the local ambiguity and does not rely on the accurate identification of edge pixels. Comprehensive experiments on the Wireframe dataset and the YorkUrban dataset demonstrate the superiority of our method. In particular, we achieve an F-measure of 0.831 on the Wireframe dataset, advancing the state-of-the-art performance by 10.3 percent., Comment: Accepted to IEEE TPAMI. arXiv admin note: text overlap with arXiv:1812.02122

This paper considers the problem of composite consensus control and cooperative adaptive learning of a class of linear uncertain multi-agent systems (MASs). The objective is to jointly achieve leader-following consensus tracking and accurate identification of unknown system parameters for all follower agents. A new cooperative adaptive consensus control protocol is proposed, which consists of a discontinuous nonlinear state-feedback control law and a series of filters for cooperative adaptation. Attractiveness of this new protocol lies in its utilization of not only relative plant state information but also relative estimate parameter information. The consensus and learning performance is rigorously analyzed using Lyapunov function approach. It is shown that exponential convergence of both consensus tracking errors to zero and adaptation parameters to their true values can be achieved simultaneously under a mild cooperative finite-time excitation (cFTE) condition. This cFTE condition significantly relaxes many existing excitation conditions (e.g., persistent excitation) for exponential parameter convergence in adaptive control systems. A numerical example is used to demonstrate the proposed approach.

The majority of control designs for wind power systems rest upon the simplifying assumption that every wind turbine and generator (WTG) inside a wind farm has identical dynamics, and, hence, can be aggregated into a single WTG admitting a single controller. In reality, however, this assumption does not hold because of wake effect due to which the small-signal models of turbines in a given row may be similar, but those between different rows can be significantly dissimilar. In this paper we propose a hierarchical control design to address these types of heterogeneous models of WTGs in a wind farm. Our approach is to group all turbines in a row as a cluster, design a cluster-level aggregate controller by averaging of states, make these aggregate controllers exchange average state information through a local communication network, and thereafter project the aggregate controller back to the original WTGs for implementation. Simulations validating the effectiveness of this hierarchical controller are shown for the IEEE 68-bus benchmark power system with one wind farm.

Data stream analysis aims at extracting discriminative information for classification from continuously incoming samples. It is extremely challenging to detect novel data while updating the model in an efficient and stable fashion, especially for the chunk data. This paper proposes a fast factorization-free kernel learning method to unify novelty detection and incremental learning for unlabeled chunk data streams in one framework. The proposed method constructs a joint reproducing kernel Hilbert space from known class centers by solving a linear system in kernel space. Naturally, unlabeled data can be detected and classified among multi-classes by a single decision model. And projecting samples into the discriminative feature space turns out to be the product of two small-sized kernel matrices without needing such time-consuming factorization like QR-decomposition or singular value decomposition. Moreover, the insertion of a novel class can be treated as the addition of a new orthogonal basis to the existing feature space, resulting in fast and stable updating schemes. Both theoretical analysis and experimental validation on real-world datasets demonstrate that the proposed methods learn chunk data streams with significantly lower computational costs and comparable or superior accuracy than the state of the art.

Recently, many graph matching methods that incorporate pairwise constraint and that can be formulated as a quadratic assignment problem (QAP) have been proposed. Although these methods demonstrate promising results for the graph matching problem, they have high complexity in space or time. In this paper, we introduce an adaptively transforming graph matching (ATGM) method from the perspective of functional representation. More precisely, under a transformation formulation, we aim to match two graphs by minimizing the discrepancy between the original graph and the transformed graph. With a linear representation map of the transformation, the pairwise edge attributes of graphs are explicitly represented by unary node attributes, which enables us to reduce the space and time complexity significantly. Due to an efficient Frank-Wolfe method-based optimization strategy, we can handle graphs with hundreds and thousands of nodes within an acceptable amount of time. Meanwhile, because transformation map can preserve graph structures, a domain adaptation-based strategy is proposed to remove the outliers. The experimental results demonstrate that our proposed method outperforms the state-of-the-art graph matching algorithms.

Instead of assuming a closed-world environment comprising a fixed number of objects, modern pattern recognition systems need to recognize outliers, identify anomalies, or discover entirely new objects, which is known as zero-shot object recognition. However, many existing zero-shot learning methods are not efficient enough to incrementally update themselves with new samples mixed with known or novel class labels. In this paper, we propose an incremental zero-shot learning framework (IIAP/QR) based on indirect-attribute-prediction (IAP) model. Firstly, a fast incremental classifier based on null space based linear discriminant analysis with QR-updating (NLDA/QR) is put forward, which can solve small-sample-size (SSS) problem and unequal-sample-size (USS) problem that usually occur in incremental learning using the centroid of each class as input. Then with the probabilistic inference of Class-Attribute layer and Attribute-Zero shot classification layer, IIAP/QR model can efficiently update itself for the insertion of both new samples to the existing class and totally novel classes with comparable recognition accuracy for zero-shot object recognition.

In this paper we present a Linear Quadratic Gaussian (LQG) control design for large-dimensional network dynamic systems using the idea of network clustering. When networks have tens of thousands of nodes spread over a wide geographical span, the design of conventional output feedback controllers becomes numerically challenging, and their implementation requires a large number of communication links. Our proposed algorithm bypasses these difficulties by clustering the network nodes using structural properties of its closed-loop transfer matrix. The cluster assignment is applied for constructing a structured projection matrix P, which is used to pose a significantly lower-dimensional controller design. The problem is, therefore, posed in terms of finding the optimal set of clusters or P that minimizes the ℋ 2 -norm of the error between the transfer matrices of the full-order network with a conventional LQG controller and that with the projected LQG controller. We derive an upper bound on this error as a function of P, and design a P that minimizes this bound.

A multi-target localization algorithm based on compressed sensing was proposed in this paper. The issue of multi-target localization was transformed into compressed sensing. The algorithm greatly reduced the amount of wireless network’s communication data by transferring most of the computing work to the central server. This method made full uses of the priori information of the signal and the support set. It combined Kalman filter with Bayesian compressed sensing to improve the localization accuracy and noise immunity. Simulation results showed that the proposed method has good noise immunity, robustness and localization accuracy compared with traditional localization methods.

Image style transform technology refers to the use of a convolutional neural network to extract the style of a famous painting, thereby converting the input image into a corresponding style image. The current methods are mainly divided into two types, namely, the style transform method proposed by Gatys and the fast image style transform method (FNST) proposed by Li Feifei. The common problem between the two methods is that the hardware requirements are high, which is not conducive to a wide range of popularization and application. In order to use image style transform on more terminals and even mobile phones, research h on lightweight and fast image style transform is of great significance. This paper draws on the deep-wise split convolution in MobileNets to prun the convolutional layer in the loss network. After the pruning, the parameter content is only 11% of the original model; the residual component in Image Transform Net is trimmed. The parameter content was reduced by 96% compared to the original model. However, the amount of parameters in the process of weight reduction is greatly reduced, which may lead to the degradation of the stylized effect. It is proved by experiments that the style degradation of the method is not obvious, that is to say that the performance loss caused by the reduction of the parameter quantity is acceptable.

Junctions play an important role in the characterization of local geometric structures in images, the detection of which is a longstanding and challenging task. Existing junction detectors usually focus on identifying the junction locations and the orientations of the junction branches while ignoring their scales; however, these scales also contain rich geometric information. This paper presents a novel approach to junction detection and characterization that exploits the locally anisotropic geometries of a junction and estimates the scales of these geometries using an \emph{a contrario} model. The output junctions have anisotropic scales --- i.e., each branch of a junction is associated with an independent scale parameter --- and are thus termed anisotropic-scale junctions (ASJs). We then apply the newly detected ASJs for the matching of indoor images, in which there may be dramatic changes in viewpoint and the detected local visual features, e.g., key-points, are usually insufficiently distinctive. We propose to use the anisotropic geometries of our junctions to improve the matching precision for indoor images. Matching results obtained on sets of indoor images demonstrate that our approach achieves state-of-the-art performance in indoor image matching., Comment: This paper has been accepted for publication in the IEEE Transactions on Image Processing

This paper presents an intact scheme of timing synchronization for Multi-Band Orthogonal Frequency Division Multiplexing (MB-OFDM) Ultra Wide Band (UWB) systems. Frame detection and coarse timing are implemented with the Maximum Correlation (MC) method based on the first-band information of the preamble. Fine timing is achieved with the Minimum Energy Ratio (MER) method based on the information of all the three bands. Lag corrections are performed twice to avoid Inter-Symbol Interference (ISI). Simulations show that residual timing error can be kept at a small scale under multipath channels which can be compensated with channel in the frequency domain.

This paper presents a method for SAR image segmentation by relying on active contour model with the non-local processing principle [1]. The idea is to partition a SAR image via computing the patch similarity in the SAR image non-locally, and formulize the segmentation problem with an active contour model. More precisely, after computing the statistical features of SAR images, non-local comparisons between feature patches are used to calculate the active contour energy, which is defined by integrating the interactions between pairs of patches inside and outside the segmented region. A level set method is finally used to minimize the non-local energy. Compared with existing approaches for SAR image segmentation, the only requirement of this method is a local similarity between patches, and it is less sensitive to initial segmentation. The experimental results show the effectiveness and feasibility of the proposed method.

This paper presented an optimization model for the generic multi-commodity logistics network design, in which the objective function was to minimize the total cost, including the location cost and inventory cost and supply and demand cost. The heuristic algorithm was developed for the model. Practical application denotes the optimization method operates rapidly and the result is rational, so it can provide a scientific decision-making support method for the design of the network, it is an effective method for solving large-scale problems, and the cost of total saving is feasibility.

This paper addresses the problem of finding edges of buildings in high-resolution remotely sensed images, which is of great help for subsequent analysis of built-up areas in urban remote sensing. More precisely, we propose a novel algorithm to extract meaningful edges associated to buildings with their saliency, by integrating an edge detection procedure with a junction process. This is inspired by the observation that meaningful junctions mainly emerge around buildings rather than on non-building objects in high-resolution remote sensing images. Thus, given a high-resolution remotely sensed image, we first use an edge detection algorithm, e.g. canny edge extractor, to compute all possible candidate edges of buildings, and then refine those candidates by meaningful junctions around buildings with their significance. The meaningful junctions are provided by an a-contrario junction detector, whose significance is related to the structural saliency in the images. For the evaluation of the proposed method, we test it on a small set of remote sensing images of half-meter resolution from WorldView-2, IKONOS and QuicBird. It demonstrates that our approach can find and locate edges of buildings with high precision and efficiency.