TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture,Layout, and Context

This paper details a new approach for learning a discriminative model of object classes, incorporating texture, layout, and context information efficiently. The learned model is used for automatic visual understanding and semantic segmentation of photographs. Our discriminative model exploits texture-layout filters, novel features based on textons, which jointly model patterns of texture and their spatial layout. Unary classification and feature selection is achieved using shared boosting to give an efficient classifier which can be applied to a large number of classes. Accurate image segmentation is achieved by incorporating the unary classifier in a conditional random field, which (i) captures the spatial interactions between class labels of neighboring pixels, and (ii) improves the segmentation of specific object instances. Efficient training of the model on large datasets is achieved by exploiting both random feature selection and piecewise training methods. High classification and segmentation accuracy is demonstrated on four varied databases: (i) the MSRC 21-class database containing photographs of real objects viewed under general lighting conditions, poses and viewpoints, (ii) the 7-class Corel subset and (iii) the 7-class Sowerby database used in He et al. (Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 695–702, June 2004), and (iv) a set of video sequences of television shows. The proposed algorithm gives competitive and visually pleasing results for objects that are highly textured (grass, trees, etc.), highly structured (cars, faces, bicycles, airplanes, etc.), and even articulated (body, cow, etc.). J. Shotton is now working at Toshiba Corporate Research & Development Center, Kawasaki, Japan.     

Guaranteeing hard real-time traffic with legitimately short deadlines with the timed token protocol

Synchronous bandwidth, defined as the maximum time a node is allowed to send its synchronous messages while holding the token, is a sensitive parameter for deadline guarantees of synchronous messages in any timed token network. In order to offer such guarantees, synchronous bandwidth has to be allocated carefully to each individual node. This paper studies the synchronous bandwidth allocated to those synchronous message streams whose deadlines are less than twice the Target Token Rotation Time (TTRT). A new approach for allocating synchronous bandwidth to such streams, which can be used with any previously published local synchronous bandwidth allocation (SBA) for guaranteeing a general synchronous message set with its minimum deadline (D_min) no less than 2 · TTRT, is proposed. The proposed scheme can be applied efficiently in practice to any general synchronous message set with D_min > TTRT. Numerical examples are presented to demonstrate the enhanced performance of this new local scheme over any of the previously published local SBA schemes.     

A priori and a posteriori analysis for a locking-free low order quadrilateral hybrid finite element for Reissner–Mindlin plates

This paper proposes a quadrilateral finite element method of the lowest order for Reissner–Mindlin (R–M) plates on the basis of Hellinger–Reissner variational principle, which includes variables of displacements, shear stresses and bending moments. This method uses continuous piecewise isoparametric bilinear interpolation for the approximation of transverse displacement and rotation. The piecewise-independent shear stress/bending moment approximation is constructed by following a self-equilibrium criterion and a shear-stress-enhanced condition. A priori and reliable a posteriori error estimates are derived and shown to be uniform with respect to the plate thickness t. Numerical experiments confirm the theoretical results.     

Probabilistic fusion of stereo with color and contrast for bilayer segmentation

This paper describes models and algorithms for the real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from color/contrast or from stereo alone is known to be error-prone. Here, color, contrast, and stereo matching information are fused to infer layers accurately and efficiently. The first algorithm, layered dynamic programming (LDP), solves stereo in an extended six-state space that represents both foreground/background layers and occluded regions. The stereo-match likelihood is then fused with a contrast-sensitive color model that is learned on-the-fly and stereo disparities are obtained by dynamic programming. The second algorithm, layered graph cut (LGC), does not directly solve stereo. Instead, the stereo match likelihood is marginalized over disparities to evaluate foreground and background hypotheses and then fused with a contrast-sensitive color model like the one used in LDP. Segmentation is solved efficiently by ternary graph cut. Both algorithms are evaluated with respect to ground truth data and found to have similar performance, substantially better than either stereo or color/contrast alone. However, their characteristics with respect to computational efficiency are rather different. The algorithms are demonstrated in the application of background substitution and shown to give good quality composite video output.     

Runtime analysis of the (mu+1) EA on simple Pseudo-Boolean functions

Although Evolutionary Algorithms (EAs) have been successfully applied to optimization in discrete search spaces, theoretical developments remain weak, in particular for population-based EAs. This paper presents a first rigorous analysis of the (mu+1) EA on pseudo-Boolean functions. Using three well-known example functions from the analysis of the (1+1) EA, we derive bounds on the expected runtime and success probability. For two of these functions, upper and lower bounds on the expected runtime are tight, and on all three functions, the (mu+1) EA is never more efficient than the (1+1) EA. Moreover, all lower bounds grow with mu. On a more complicated function, however, a small increase of mu probably decreases the expected runtime drastically.This paper develops a new proof technique that bounds the runtime of the (mu+1) EA. It investigates the stochastic process for creating family trees of individuals; the depth of these trees is bounded. Thereby, the progress of the population towards the optimum is captured. This new technique is general enough to be applied to other population-based EAs.     

Semi‐Solid Processing of Metal Alloys

Semi‐solid metal casting is an innovative technology for the production of near‐net‐shape parts with demanding mechanical properties. The paper describes different processing routes and materials for semi‐solid‐metal casting (SSM), which have been investigated and also partially developed at the Foundry‐Institute of Aachen University. The standard thixocasting process for aluminium, highly reactive magnesium alloys and steel alloys with high melting points was investigated under variation of a wide range of process parameters. Specially adapted pre‐material production and reheating methods were developed for different materials and their application and future potential is pointed out. The thixocasting experiments were executed on a modified high pressure die‐casting machine with a specially designed “step‐die” providing wall thicknesses from 0.5 to 25 mm. The mechanical properties were tested in dependence of the wall thickness and the metal velocity. The results of these examination show high tensile strength values in combination with very good elongations. The rheocasting process is a new SSM‐forming method with liquid melt as feed‐stock and a high recycling potential. The research results of RCP‐technology (Rheo‐Container‐Process) invented at the Foundry‐Institute and of the Cooling‐Channel‐Process for aluminium and magnesium alloys are promising and are presented in this paper. Studies on semi‐solid processing of magnesium alloys and mixtures of them were conducted by Thixomolding^TM. To establish the most adequate process parameters, the temperature and the mixture relations were varied. Using a mould for tensile test specimens, the mechanical properties and the microstructure evolution could be evaluated. The chemical composition of the different phases was determined using SEM and EDX technologies. Evaluations of the flowing properties were conducted using a spiral mould with a total length of 2m and a cross section of 20mm x 1.5mm.     

无磁钢20Mn23AlV保护渣液渣和渣圈性能变化对连铸的影响

对高铝无磁钢20Mn23AIV(/%:0.14～0.20C、21.50～25.00Mn、1.50～2.50Al、0.04～0.10V)200 mm板坯连铸过程结晶器保护渣液渣和渣圈的化学组成、理化性能和结晶矿相进行了对比分析。保护渣原渣组成为(/%):31.91CaO、30.30SiO₂、6.58Al₂O₃、1.12MgO、3.02MnO、7.73Na₂0、7.10F。结果表明,连铸开浇后15 min,液渣和渣圈中的SiO₂含量分别降低至22%和18%, Al₂O₃含量分别提高至20.5%和25.5%,其碱度由原渣的1.05分别提高至1.7和2.0。此时液渣及渣圈的熔化温度和粘度大幅度增加,转折温度大幅度降低;渣圈的化学成分及理化性能的变化幅度均大于液渣。连铸开浇15 min后液渣及渣圈的成分与性能均趋于稳定。高熔点相钙铝黄长石的析出是促使渣圈形成的重要原因。     

Effect of size and shape of metal particles to improve hardness and electrical properties of carbon nanotube reinforced copper and copper alloy composites

Utilizing the extra-ordinary properties of carbon nanotube (CNT) in metal matrix composite (MMC) for macroscopic applications is still a big challenge for science and technology. Very few successful attempts have been made for commercial applications due to the difficulties incorporating CNTs in metals with up-scalable processes. CNT reinforced copper and copper alloy (bronze) composites have been fabricated by well-established hot-press sintering method of powder metallurgy. The parameters of CNT–metal powder mixing and hot-press sintering have been optimized and the matrix materials of the mixed powders and composites have been evaluated. However, the effect of shape and size of metal particles as well as selection of carbon nanotubes has significant influence on the mechanical and electrical properties of the composites. The hardness of copper matrix composite has improved up to 47% compared to that of pure copper, while the electrical conductivity of bronze composite has improved up to 20% compared to that of the pure alloy. Thus carbon nanotube can improve the mechanical properties of highly-conductive low-strength copper metals, whereas in low-conductivity high-strength copper alloys the electrical conductivity can be improved.     

An analysis on decentralized adaptive MAC protocols for cognitive radio networks

The scarcity of bandwidth in the radio spectrum has become more vital since the demand for more and more wireless applications has increased. Most of the spectrum bands have been allocated although many studies have shown that these bands are significantly underutilized most of the time. The problem of unavailability of spectrum and inefficiency in its utilization has been smartly addressed by the cognitive radio (CR) technology which is an opportunistic network that senses the environment, observes the network changes, and then uses knowledge gained from the prior interaction with the network to make intelligent decisions by dynamically adapting their transmission characteristics. In this paper, some of the decentralized adaptive medium access control (MAC) protocols for CR networks have been critically analyzed, and a novel adaptive MAC protocol for CR networks, decentralized non-global MAC (DNG-MAC), has been proposed. The results show the DNG-MAC outperforms other CR-MAC protocols in terms of time and energy efficiency.