3D clipping algorithm for feature mapping across domains

This paper describes an algorithm based on 3D clipping for mapping feature models across domains. The problem is motivated by the need to identify feature models corresponding to different domains. Feature mapping (also referred to as feature conversion) involves obtaining a feature model in one domain given a feature model in another. This is in contrast to feature extraction which works from the boundary representation of the part. Most techniques for feature mapping have focused on obtaining negative feature models only. We propose an algorithm that can convert a feature model with mixed features (both positive and negative) to a feature model containing either only positive or only negative features.The input to the algorithm is a feature model in one domain. The algorithm for mapping this model to another feature model is based on classification of faces of features in the model and 3D clipping. 3D clipping refers to the splitting of a solid by a surface. The feature mapping process involves three major steps. In the first step, faces forming the features in the input model are classified with respect to one another. The spatial arrangement of faces is used next to derive the dependency relationship amongst features in the input model and a Feature Relationship Graph (FRG) is constructed. In the second step, using the FRG, features are clustered and interactions between features (if any) are resolved. In the final step, the 3D clipping algorithm is used to determine the volumes corresponding to the features in the target domain. These volumes are then classified to identify the features for obtaining the feature model in the target domain. Multiple feature sets (where possible) can be obtained by varying the sequence of faces used for clipping. Results of implementation are presented.     

Boundary analysis and geometric completion for recognition of interacting machining features

Features are the basic elements which transform CAD data into instructions necessary for automatic generation of manufacturing process plans. In this paper, a hybrid of graph-based and hint-based techniques is proposed to automatically extract interacting features from solid models. The graph-based hints generated by this approach are in geometrical and topological compliance with their corresponding features. They indicate whether the feature is 2.5D, floorless or 3D. To reduce the product model complexity while extracting features, a method to remove fillets existing in the boundary of a 2.5D feature is also proposed. Finally, three geometric completion algorithms, namely, Base-Completion, Profile-Completion and 3D-volume generation algorithms are proposed to generate feature volumes. The base-completion and profile-completion algorithms generate maximal volumes for 2.5D features. The 3D volume generation algorithm extracts 3D portions of the part.     

基于特征融合及自适应模型更新的相关滤波目标跟踪算法

针对单一特征目标跟踪算法因背景干扰、目标遮挡造成的跟踪失败问题,以及跟踪过程中每帧进行模型更新容易造成错误更新和实时性差的问题,提出了一种基于特征融合及自适应模型更新策略的相关滤波目标跟踪算法-多特征自适应相关滤波目标跟踪算法。该算法在特征提取阶段将边缘特征及HOG特征加权融合作为目标特征,加强对边缘特征的学习;在模型更新阶段通过计算预测区域与真实区域的奇异值特征向量相似度,并结合设定的阈值判断是否需要进行模型更新,通过自适应更新的方式减少模型的更新次数。在标准测试视频集下验证所提算法,并与两种经典相关滤波算法进行比较,结果表明该算法能够较好地适应背景干扰及目标遮挡问题,跟踪目标的平均中心误差减少了9.05像素,平均距离精度提高12.2%,平均重叠率提高4.53%。     

基于特征选择与时间一致性稀疏外观模型的目标追踪算法

为了更有效利用追踪目标的判别特征信息,提高目标追踪的精度和鲁棒性,在粒子滤波追踪框架下提出基于特征选择与时间一致性稀疏外观模型的目标追踪算法.首先,采集目标的正负模板和候选目标,根据特征选择模型对正负模板和候选目标进行特征选择,去除多余的干扰信息,得到关键的特征信息.然后,利用正负模板和候选目标的特征建立多任务稀疏表示模型,引入时间一致性正则项,促进更多的候选目标与先前帧的追踪结果具有稀疏表示的相似性.最后,求解多任务稀疏表示模型,得到判别稀疏相似图,获取每个候选目标的判别分,根据目标追踪结果更新正负模板.实验表明,即使在复杂的环境下,文中算法仍然比其它一些追踪算法具有更高的准确性.     

基于双重注意力孪生网络的实时视觉跟踪

为了解决全卷积孪生网络（SiamFC）跟踪算法在跟踪目标经历剧烈的外观变化时容易发生模型漂移从而导致跟踪失败的问题，提出了一种双重注意力机制孪生网络（DASiam）去调整网络模型并且不需要在线更新。首先，主干网络使用修改后表达能力更强的并适用于目标跟踪任务的VGG网络；然后，在网络的中间层加入一个新的双重注意力机制去动态地提取特征，这种机制由通道注意机制和空间注意机制组成，分别对特征图的通道维度和空间维度进行变换得到双重注意特征图；最后，通过融合两个注意机制的特征图进一步提升模型的表征能力。在三个具有挑战性的跟踪基准库即OTB2013、OTB100和2017年视觉目标跟踪库（VOT2017）实时挑战上进行实验，实验结果表明，以40 frame/s的速度运行时，所提算法在OTB2013和OTB100上的成功率指标比基准SiamFC分别高出3.5个百分点和3个百分点，并且在VOT2017实时挑战上面超过了2017年的冠军SiamFC，验证了所提出算法的有效性。     

基于语义特征抽取的文本聚类研究

基于向量空间模型(VSM)的文本聚类会出现向量维度过高以及缺乏语义信息的问题,导致聚类效果出现偏差。为解决以上问题,引入《知网》作为语义词典,并改进词语相似度算法的不足。利用改进的词语语义相似度算法对文本特征进行语义压缩,使所有特征词都是主题相关的,利用调整后的TF-IDF算法对特征项进行加权,完成文本特征抽取,降低文本表示模型的维度。在聚类中,将同一类的文本划分为同一个簇,利用簇中所有文本的特征词完成簇的语义特征抽取,簇的表示模型和文本的表示模型有着相同的形式。通过计算簇之间的语义相似度,将相似度大于阈值的簇合并,更新簇的特征,直到算法结束。通过实验验证,与基于K-Means和VSM的聚类算法相比,文中算法大幅降低了向量维度,聚类效果也有明显提升。     

基于痕迹的特征模型解释技术研究

提出了一种基于痕迹的特征模型多重解释新方法,通过一次分解两次组合形成零件所有可能的制造特征模型,首先,制造特征模型中的特征被分解为最小国呀体;然后利用残留在最小加工体中的特征痕迹,重构零件所有可能的制造特征;根据制造特征模型的存在条件,建立制造特征模型方程,该多解方程的解就是零件制造特征模型的多重解释。     

Feature Generation Using General Constructor Functions

Most classification algorithms receive as input a set of attributes of the classified objects. In many cases, however, the supplied set of attributes is not sufficient for creating an accurate, succinct and comprehensible representation of the target concept. To overcome this problem, researchers have proposed algorithms for automatic construction of features. The majority of these algorithms use a limited predefined set of operators for building new features. In this paper we propose a generalized and flexible framework that is capable of generating features from any given set of constructor functions. These can be domain-independent functions such as arithmetic and logic operators, or domain-dependent operators that rely on partial knowledge on the part of the user. The paper describes an algorithm which receives as input a set of classified objects, a set of attributes, and a specification for a set of constructor functions that contains their domains, ranges and properties. The algorithm produces as output a set of generated features that can be used by standard concept learners to create improved classifiers. The algorithm maintains a set of its best generated features and improves this set iteratively. During each iteration, the algorithm performs a beam search over its defined feature space and constructs new features by applying constructor functions to the members of its current feature set. The search is guided by general heuristic measures that are not confined to a specific feature representation. The algorithm was applied to a variety of classification problems and was able to generate features that were strongly related to the underlying target concepts. These features also significantly improved the accuracy achieved by standard concept learners, for a variety of classification problems.     

Global-patch-hybrid template-based arbitrary object tracking with integral channel features

Arbitrary object tracking is a challenging task in computer vision, as many factors affecting the target representation must be considered. A target template based on only the global appearance or on only the local appearance is unable to capture the discriminating information required for the robust performance of a tracker. In this paper, the target appearance is represented using a hybrid of global and local appearances along with a framework to exploit the Integral Channel Features (ICF). The proposed hybrid approach achieves fusion of the conventional global and patch-based approaches for target representation to synergize the advantages of both approaches. The ICF approach under the hybrid approach integrates heterogeneous sources of information of the target and provides feature strength to the hybrid template. The use of ICF also expedites the extraction of the structural and color features from video frames as the features are collected over multiple channels. The target appearance representation is updated based on only samples with appearances similar to the target appearance using clustering and vector quantization. These factors offer the proposed algorithm robustness to occlusion, illumination changes, and in-plane rotation. Further experimentation analyzes the effects of a change in the scale of the bounding box on the tracking performance of the proposed algorithm. The proposed approach outperforms all the state-of-the-art algorithms in all considered scenarios.     

基于Haar-like特征的实时L1-跟踪算法

稀疏表示技术已成功应用于视觉跟踪,但是仍然存在跟踪算法效率低的问题。提出一种基于Haar-like特征的视频跟踪算法,该算法是基于粒子滤波框架的L1-跟踪算法,其特点是运用Haar-like特征及特征块的思想对完备基进行重新构造。将正负小模板由单个像素改为像素块,降低稀疏表示中过完备基的维数,大幅减少稀疏矩阵的计算量;同时,在保证跟踪质量的前提下适当减少目标模板数量,减少稀疏计算的次数,并控制模板更新频率。实验结果表明,所提算法能大幅提高跟踪的实时性,同时很好地解决了跟踪问题中的短时间遮挡、目标物体的形变以及光照变化等问题。     

Incremental Clustering-Based Facial Feature Tracking Using Bayesian ART

Person-independent, emotion specific facial feature tracking have been of interest in the machine vision society for decades. Among various methods, the constrained local model (CLM) has shown significant results in person-independent feature tracking. In 63this paper, we propose an automatic, efficient, and robust method for emotion specific facial feature detection and tracking from image sequences. Considering a 17-point feature model on the frontal face region, the proposed tracking framework incorporates CLM with two incremental clustering algorithms to increase robustness and minimize tracking error during feature tracking. The Patch Clustering algorithm is applied to build an appearance model of face frames by organizing previously encountered similar patches into clusters while the shape Clustering algorithm is applied to build a structure model of face shapes by organizing previously encountered similar shapes into clusters followed by Bayesian adaptive resonance theory (ART). Both models are used to explore the similar features/shapes in the successive images. The clusters in each model are built and updated incrementally and online, controlled by amount of facial muscle movement. The overall performance of the proposed incremental clustering-based facial feature tracking (ICFFT) is evaluated using the FGnet database and the extended Cohn-Kanade (CK+) database. ICFFT demonstrates better results than baseline-method CLM and provides robust tracking as well as improved localization accuracy of emotion specific facial features tracking.     

基于遗传算法的图像检索中特征权重自动调整

综合多种特征的图像检索可以克服使用单一特征带来的问题,如何组织这些特征使其发挥最佳作用是基于内容图像检索中的一个难点。提出了一种基于遗传算法的多特征权重自动赋值方法,首先将图像检索中特征权重调整问题转换为优化问题,进一步利用遗传算法求取权重的最优解,使检索效果达到最好。实验表明,该方法查全率和查准率较高,并且具有较强的鲁棒性和推广能力,对于各种特征和特征表示方法,都能够提供最佳的组合。     

多样性表示的深度子空间聚类算法

针对深度子空间聚类问题中不同层次特征中互补信息挖掘困难的问题,在深度自编码器的基础上,提出了一种在编码器获取的低层和高层特征之间探索互补信息的多样性表示的深度子空间聚类（DRDSC）算法。首先,基于希尔伯特-施密特独立性准则（HSIC）建立了不同层次特征衡量多样性表示模型;其次,在深度自编码器网络结构中引入特征多样性表示模块,从而挖掘有利于提升聚类效果的图像特征;此外,更新了损失函数的形式,有效融合了多层次表示的底层子空间;最后,在常用的聚类数据集上进行了多次实验。实验结果表明,DRDSC在数据集Extended Yale B、ORL、COIL20和Umist上的聚类错误率分别达到1.23%、10.50%、1.74%和17.71%,与高效稠密子空间聚类（EDSC）相比,分别降低了10.41、16.75、13.12和12.92个百分点;与深度子空间聚类（DSC）相比,分别降低了1.44、3.50、3.68和9.17个百分点,说明所提出的DRDSC算法有更好的聚类效果。     

Applications of hybrid optimization techniques for model updating of rotor shafts

This paper presents an approach by combining the genetic algorithm (GA) with simulated annealing (SA) algorithm for enhancing finite element (FE) model updating. The proposed algorithm has been applied to two typical rotor shafts to test the superiority of the technique. It also gives a detailed comparison of the natural frequencies and frequency response functions (FRFs) obtained from experimental modal testing, the initial FE model and FE models updated by GA, SA, and combination of GA and SA (GA–SA). The results concluded that the GA, SA, and GA–SA are powerful optimization techniques which can be successfully applied to FE model updating, but the appropriate choice of the updating parameters and objective function is of great importance in the iterative process. Generally, the natural frequencies and FRFs obtained from FE model updated by GA–SA show the best agreement with experiments than those obtained from the initial FE model and FE models updated by GA and SA independently.     

结合多尺度特征学习与特征对齐的行人重识别

利用卷积神经网络对行人图像提取一个简单的全局特征,在复杂的行人重识别任务中无法获得令人满意的结果。局部特征学习的方式有助于获取更丰富的人体特征,但往往需要图像中的人体具有良好的空间对齐,而且,将人体各部分特征输入到独立的分支学习局部信息,忽略了人体各部分特征间的相关性,限制模型的性能提升。在此背景下,提出了一种新的多尺度特征学习算法,结合全局与局部特征学习得到更好的行人表示,提升复杂场景下模型的识别能力。对骨干网络不同深度输出的行人特征图,通过特征对齐模块对其执行空间变换,实现行人特征在空间上的矫正和对齐,进一步增强模型的泛化性能。在公开的大型行人重识别数据集上,与当前一些流行的方法进行了比较,验证了所提方法的有效性。     

基于稀疏表示和特征选择的LK目标跟踪

为了实现复杂场景中的视觉跟踪, 提出了一种以LK（Lucas-Kanade）图像配准算法为框架, 基于稀疏表示的在线特征选择机制。在视频序列的每一帧, 筛选出一些能够很好区分目标及其相邻背景的特征, 从而降低干扰对跟踪的影响。该算法分别构造前景字典和背景字典, 前景字典来自于第一帧的手动标定, 并随着跟踪结果不断更新, 而背景字典则在每一帧重新构造。同时, 一种新的字典更新策略不仅能有效应对目标的外观变化, 而且通过特征选择机制, 能避免在更新过程中引入干扰, 从而克服了漂移现象。 大量的实验结果表明, 该算法能有效应对视角变化、光照变化以及大面积的局部遮挡等挑战。     

双人交互行为的稀疏表征方法*

提出一种双人交互行为的稀疏表征方法,融合体现全局变化的轨迹特征和突出区域运动的时空特征。首先,采用词袋模型得到轨迹特征的稀疏表示。然后,对提取的时空特征采用三层时空金字塔分解得到多层特征,并对其进行稀疏编码,利用多尺度Maxpooling算法融合得到局部稀疏特征。最后,将2种稀疏特征加权串联得到双人交互行为的稀疏表征。采用基于隐动态条件随机场的识别算法对文中提取的稀疏表征进行验证,通过实验证明其有效性。     

一种用于运动物体检测的自适应更新背景模型

提出一种能自适应更新的背景模型,使得运动物体检测中场景变化时提取的背景能进行相应的更新.该模型利用特征点信息将场景中的像素点分类,并针对不同类别像素点计算其更新速率;然后对像素点采用相应速率进行更新,从而能根据场景不同变化进行自适应更新.实验结果表明,该模型能较好地处理混合高斯模型因采用同一更新速率导致的背景模型更新错误问题.     

基于时间一致性局部颜色特征的无纹理3D物体实时跟踪

针对无纹理3D物体跟踪算法在复杂背景和运动模糊的情况下容易跟踪失败、跟踪速度难以达到强实时等问题,提出一种基于时间一致性局部颜色特征的3D物体实时跟踪算法.首先在物体3D模型投影轮廓法向搜索线上计算像素颜色的加权均值作为局部颜色特征,增强颜色特征在复杂环境中的表征能力,并对局部颜色特征进行时间一致性更新,剔除前景背景颜色相似的局部颜色特征,以避免相似前景背景颜色导致的跟踪失败;然后定义基于局部颜色特征的能量函数,并推导该能量函数的解析导函数;最后改进了优化物体姿态的高斯牛顿法,通过添加阻尼参数防止姿态优化陷入局部极值,提高姿态估计精度和跟踪速度.实验使用7组测试视频验证文中算法,结果表明,该算法能更有效地克服复杂背景和运动模糊的干扰,在未使用并行计算的前提下可实现强实时跟踪.     

基于模糊形状上下文与局部向量相似性约束的配准算法

非刚性点集配准研究是模式识别领域的一项重要基础研究.本文在当前流行的非刚性点集配准算法的基础上提出了两个主要贡献:1)模糊形状上下文(Fuzzy shape context, FSC)特征;2)基于局部向量特征的局部空间向量相似性约束项.本文首先进行基于特征互补的对应关系评估,在这一步骤中定义了模糊形状上下文特征,然后基于模糊形状上下文特征差异和全局特征差异设计了特征互补的高斯混合模型.其次,进行基于约束互补的空间变化更新.在这一步骤中,定义了局部向量特征,建立了局部空间向量相似性约束项.本文算法通过使用特征互补的高斯混合模型进行对应关系评估,并将配准问题转化为可以用期望最大化(Expectation maximization, EM)算法解决的参数优化问题,通过创建包含局部空间向量相似性约束项的能量方程优化了空间变换更新.本文首先测试了模糊形状上下文特征的检索率,然后采用公开数据集测试了算法在点集配准与图像配准的性能.在与当前流行的十种算法的对比实验中,本文算法均给出了精确的配准结果,并在大部分实验中精度超过了当前流行算法.