16MnR低合金钢板对接立焊单面焊双面成形工艺与探索

阐述了16MnR低合金钢板-板对接立焊单面焊双面成形的打底焊、填充焊、盖面焊的工艺过程及操作要领.重点讨论了提高单面焊双面成形打底焊质量的措施;强调了焊条伸入坡口的相对深度对打底焊、填充焊和盖面焊焊缝高度的重要影响.     

基于数学形态学图像处理的TIG焊接过程正面熔宽控制

焊接过程熔池动态特征信息获取与智能控制一直是焊接界研究的前沿课题.针对TIG焊接过程没有飞溅,熔池形状稳定、清晰的特点,以TIG焊接过程为研究对象,采用机器视觉技术获取焊接动态过程正面熔池图像点,将数学形态学中的二值理论应用于熔池图像的处理,结合模糊逻辑和比例积分微分(PID)闭环控制理论,从弧焊过程熔透质量控制的角度出发,从软件开发到硬件组成,设计了一套焊接过程图像处理及正面熔宽控制系统.结果表明,该系统可以很好地克服焊接过程中的外界干扰,保证焊缝成形的稳定,从而实现了TIG焊质量控制的目标.     

Object tracking based on an online learning network with total error rate minimization

This paper presents a visual object tracking system which is tolerant to external imaging factors such as illumination, scale, rotation, occlusion and background changes. Specifically, an integration of an online version of total-error-rate minimization based projection network with an observation model of particle filter is proposed to effectively distinguish between the target object and the background. A re-weighting technique is proposed to stabilize the sampling of particle filter for stochastic propagation. For self-adaptation, an automatic updating scheme and extraction of training samples are proposed to adjust to system changes online. Our qualitative and quantitative experiments on 16 public video sequences show convincing performances in terms of tracking accuracy and computational efficiency over competing state-of-the-art algorithms.     

Projective Feature Learning for 3D Shapes with Multi‐View Depth Images

Feature learning for 3D shapes is challenging due to the lack of natural paramterization for 3D surface models. We adopt the multi‐view depth image representation and propose Multi‐View Deep Extreme Learning Machine (MVD‐ELM) to achieve fast and quality projective feature learning for 3D shapes. In contrast to existing multi‐view learning approaches, our method ensures the feature maps learned for different views are mutually dependent via shared weights and in each layer, their unprojections together form a valid 3D reconstruction of the input 3D shape through using normalized convolution kernels. These lead to a more accurate 3D feature learning as shown by the encouraging results in several applications. Moreover, the 3D reconstruction property enables clear visualization of the learned features, which further demonstrates the meaningfulness of our feature learning.     

Mesh Denoising using Extended ROF Model with L1 Fidelity

This paper presents a variational algorithm for feature‐preserved mesh denoising. At the heart of the algorithm is a novel variational model composed of three components: fidelity, regularization and fairness, which are specifically designed to have their intuitive roles. In particular, the fidelity is formulated as an L₁ data term, which makes the regularization process be less dependent on the exact value of outliers and noise. The regularization is formulated as the total absolute edge‐lengthed supplementary angle of the dihedral angle, making the model capable of reconstructing meshes with sharp features. In addition, an augmented Lagrange method is provided to efficiently solve the proposed variational model. Compared to the prior art, the new algorithm has crucial advantages in handling large scale noise, noise along random directions, and different kinds of noise, including random impulsive noise, even in the presence of sharp features. Both visual and quantitative evaluation demonstrates the superiority of the new algorithm.     

Semi‐Regular Triangle Remeshing: A Comprehensive Study

Semi‐regular triangle remeshing algorithms convert irregular surface meshes into semi‐regular ones. Especially in the field of computer graphics, semi‐regularity is an interesting property because it makes meshes highly suitable for multi‐resolution analysis. In this paper, we survey the numerous remeshing algorithms that have been developed over the past two decades. We propose different classifications to give new and comprehensible insights into both existing methods and issues. We describe how considerable obstacles have already been overcome, and discuss promising perspectives.     

Computing Minimum Area Homologies

Calculating and categorizing the similarity of curves is a fundamental problem which has generated much recent interest. However, to date there are no implementations of these algorithms for curves on surfaces with provable guarantees on the quality of the measure. In this paper, we present a similarity measure for any two cycles that are homologous, where we calculate the minimum area of any homology (or connected bounding chain) between the two cycles. The minimum area homology exists for broader classes of cycles than previous measures which are based on homotopy. It is also much easier to compute than previously defined measures, yielding an efficient implementation that is based on linear algebra tools. We demonstrate our algorithm on a range of inputs, showing examples which highlight the feasibility of this similarity measure.     

基于轮廓几何稀疏表示的刚性目标模型及其分级检测算法

刚性目标轮廓具有明显几何特性且不易受光照、纹理和颜色等因素影响.结合上述特性和图像稀疏表示原理,提出一种适用于刚性目标的分级检测算法.在基于部件模型(Part-based model, PBM)的框架下,采用匹配追踪算法将目标轮廓自适应地稀疏表示为几何部件的组合,根据部件与目标轮廓的匹配度,构建描述部件空间关系的有序链式结构.利用该链式结构的有序特性逐级缩小待检测范围,以匹配度为权值对各级部件显著图进行加权融合生成目标显著图. PASCAL图像库上的检测结果表明,该检测方法对具有显著轮廓特征的刚性目标有较好的检测结果,检测时耗较现有算法减少约60%~90%.