通用对象识别技术

遵循通用对象识别系统的一般框架,重点讨论了各种特征区域选取、特征区域描述技术,比较了几种主流的识别模型和模型的训练方法,并介绍了对象识别系统的性能评估方法及其常用数据集,最后分析了未来可能的研究发展方向。     

不平衡数据下预算限制的联邦学习激励机制

联邦学习的提出解决了在隐私保护下完成多客户合作的机器学习问题,而激励客户参与联邦学习是模型性能提高的一个重要前提。针对客户数据非独立同分布特征会导致联邦学习性能下降这一问题,考虑预算约束下,设计了基于单位数据成本和数据特征—EMD距离的客户端筛选方式,提出一种有效的联邦学习激励机制（EMD-FLIM）,从理论上证明了机制具有诚实性,即每个客户会诚实披露数据成本和数据分布信息,同时机制具有预算可行性,个人理性及计算有效性。实验结果显示,提出的激励机制在数据分布不平衡情况下模型精度至少能达到数据量最优选择（不考虑激励）下的 94%以上,与不考虑数据分布特征的激励机制相比较,模型精度平均可提高5%以上。     

多尺度特征深度复用的显著性目标检测算法

针对传统显著性目标检测方法在检测不同尺度的多个显著性目标方面的不足,提出了一种多尺度特征深度复用的显著性目标检测算法,网络模型由垂直堆叠的双向密集特征聚合模块和水平堆叠的多分辨率语义互补模块组成。首先,双向密集特征聚合模块基于ResNet骨干网络提取不同分辨率语义特征;然后,依次在top-down和bottom-up两条通路上进行自适应融合,以获取不同层次多尺度表征特征;最后,通过多分辨率语义互补模块对两个相邻层次的多尺度特征进行融合,以消除不同层次上特征之间的相互串扰来增强预测结果的一致性。在五个基准数据集上进行的实验结果表明,该方法在Fmax、Sm、MAE最高能达到0.939、0.921、0.028,且检测速率可达74.6 fps,与其他对比算法相比有着更好的检测性能。     

GGMC算法目标函数值实验分析与算法改进

针对贪心最大割图半监督学习算法（简称GGMC）计算复杂度较高的问题,提出一种改进的贪心最大割图半监督学习算法（简称GGMC-Estop）。依据对GGMC算法优化过程中目标函数变化趋势的实验分析,采取两种在迭代初期停止GGMC算法运行策略,继而通过一次标准的标签传播步骤预测图上所有样本的标记来实施对GGMC的改进。典型数据集的仿真实验结果表明,在取得相近分类性能的同时,改进算法在计算速度上有很大的提高。     

Supply chain coordination under budget constraints

Budget constraints are commonly considered in real decision frameworks; however, the literature has rarely addressed the design of contracts for supply chains with budget-constrained members and in which capital costs are considered. In this article, we study supply chain coordination of budget-constrained members when a financial market is unavailable. We propose a revenue-sharing-and-buy-back (RSBB) contract that combines revenue-sharing (RS) and buy-back (BB) contracts. We compare the performance of RS, BB, and RSBB contracts under a coordinated two-stage supply chain in which members experience budget constraints. Results show that the RS and BB contracts are not feasible under certain budget scenarios, whereas the RSBB contract can always be used to coordinate the supply chain and arbitrarily divide profits. We propose a profit allocation approach to address information symmetry created by undisclosed budget thresholds. Our analytical and numerical results provide insight into how managers select an appropriate contract based on their budget scenarios and capital costs.     

网络入侵检测中的支持向量机主动学习算法

入侵检测系统已经成为网络安全技术的重要组成部分,然而传统的异常入侵检测技术需要通过对大量训练样本的学习,才能达到较高的检测精度,而大量训练样本集的获取在现实网络环境中是比较困难的。文章研究在网络入侵检测中,采用基于支持向量机(SVM)的主动学习算法,解决训练样本获取代价过大带来的问题。文中通过基于SVM的主动学习算法与传统的被动学习算法的对比实验,显示出主动学习算法与传统的学习算法相比,能有效地减少学习样本,极大地提高入侵检测系统的分类性能。     

基于SVM主动学习算法的网络入侵检测系统

入侵检测系统已经成为网络安全技术的重要组成部分。然而，传统的异常入侵检测技术需要通过对大量训练样本的学习才能达到较高的检测精度，而大量训练样本集的获取在现实网络环境中是比较困难的。本文研究在网络入侵检测中采用基于支持向量机（SVM）的主动学习算法，解决训练样本获取代价过大带来的问题。通过基于SVM的主动学习算
算法与传统的被动学习算法的对比实验说明，主动学习算法能有效地减少学习样本数及训练时间，能有效地提高入侵检测系统的分类性能。     

Visual object tracking based on discriminant DCT features

In this paper, a visual object tracking method is proposed based on sparse 2-dimensional discrete cosine transform (2D DCT) coefficients as discriminative features. To select the discriminative DCT coefficients, we give two propositions. The propositions select the features based on estimated mean of feature distributions in each frame. Some intermediate tracking instances are obtained by (a) computing feature similarity using kernel, (b) finding the maximum classifier score computed using ratio classifier, and (c) combinations of both. Another intermediate tracking instance is obtained using incremental subspace learning method. The final tracked instance amongst the intermediate instances are selected by using a discriminative linear classifier learned in each frame. The linear classifier is updated in each frame using some of the intermediate tracked instances. The proposed method has a better tracking performance as compared to state-of-the-art video trackers in a dataset of 50 challenging video sequences.     

Three-dimensional object registration using wavelet features

Recent developments in shape-based modeling and data acquisition have brought three-dimensional models to the forefront of computer graphics and visualization research. New data acquisition methods are producing large numbers of models in a variety of fields. Three-dimensional registration (alignment) is key to the useful application of such models in areas from automated surface inspection to cancer detection and surgery. The algorithms developed in this research accomplish automatic registration of three-dimensional voxelized models. We employ features in a wavelet transform domain to accomplish registration. The features are extracted in a multi-resolutional format, thus delineating features at various scales for robust and rapid matching. Registration is achieved by using a voting scheme to select peaks in sets of rotation quaternions, then separately identifying translation. The method is robust to occlusion, clutter, and noise. The efficacy of the algorithm is demonstrated through examples from solid modeling and medical imaging applications.     

A hierarchical representation for heterogeneous object modeling

A hierarchical representation for heterogeneous object modeling is presented in this paper. To model a heterogeneous object, Boundary representation is used for geometry representation, and a novel Heterogeneous Feature Tree (HFT) structure is proposed to represent the material distributions. HFT structure hierarchically organizes the material variation dependency relationships and is intuitive in modeling different types of material gradations. Based on the HFT structure, a recursive material evaluation algorithm is proposed to dynamically evaluate the material compositions at a specific location. Such a hierarchical representation guarantees complex material gradations and the user's design intent can be intuitively represented. Example heterogeneous objects modeled with this scheme are provided and potential applications are discussed.     

支持向量机(SVM)主动学习方法研究与应用

文中介绍了一种用SVM进行主动学习的方法,解决在某些机器学习问题中,训练样本获取代价过大带来的问题。实验表明,该方法与普通SVM方法相比,在保证SVM分类器性能的前提下,可有效减少学习所需的样本数量。最后设计了一个基于该思想的邮件过滤器模型,依据该模型设计的邮件过滤器将有实时监控、自动更新邮件过滤模块的能力。     

基于采样策略的主动学习算法研究进展

主动学习算法通过选择信息含量大的未标记样例交由专家进行标记,多次循环使分类器的正确率逐步提高,进而在标记总代价最小的情况下获得分类器的强泛化能力,这一技术引起了国内外研究人员的关注.侧重从采样策略的角度,详细介绍了主动学习中学习引擎和采样引擎的工作过程,总结了主动学习算法的理论研究成果,详细评述了主动学习的研究现状和发展动态.首先,针对采样策略选择样例的不同方式将主动学习算法划分为不同类型,进而,对基于不同采样策略的主动学习算法进行了深入地分析和比较,讨论了各种算法适用的应用领域及其优缺点.最后指出了存在的开放性问题和进一步的研究方向.     

学习点云邻域信息的三维物体形状补全

在现实世界中,点云数据的采集方式有激光雷达、双目相机和深度相机,但是在机器人采集过程中由于设备分辨率、周围环境等因素的影响,收集到的点云数据通常是非完整的。为了解决物体形状缺失的问题,提出了一种使用局部邻域信息的三维物体形状自动补全的网络架构。该架构包括点云特征提取网络模块和点云生成网络模块,输入为缺失的点云形状,输出为缺失部分的点云形状,将输入与输出点云形状进行合并完成物体的形状补全。采用倒角距离和测地距离进行评估,实验结果表明,在ShapeNet数据集上,平均倒角距离和平均测地距离均小于多层感知机特征提取网络与PCN网络的值,两值分别为0.000 84和0.028。对于现实中扫描的点云数据进行补全处理也达到了预期效果,说明该网络有较强的泛化性,可以修复不同类别的物体。     

基于时空联合双重约束Snake算法的运动目标分割

提出了一种针对运动目标进行分割的STC（Spatio Temporal Combined） Snake算法。该方法利用待分割帧图像的灰度梯度及其和相邻帧图像的时域信息,构造一种时空联合双重约束的外部能量函数,实现对Snake曲线的变形和收敛。对Snake轮廓进行初始化时,首先将相邻帧图像进行减运算,提取出大致的运动区域,然后再以该区域的外接矩形的长和宽为轴长,在该区域上构造一个椭圆,等间距提取该椭圆形上的N个点,形成Snake的初始化轮廓。实验结果表明,该方法是有效可行的,可精确的分割出非刚体的运动目标。     

Moving object classification using local shape and HOG features in wavelet-transformed space with hierarchical SVM classifiers

This paper proposes an integrated system for the segmentation and classification of four moving objects, including pedestrians, cars, motorcycles, and bicycles, from their side-views in a video sequence. Based on the use of an adaptive background in the red–green–blue (RGB) color model, each moving object is segmented with its minimum enclosing rectangle (MER) window by using a histogram-based projection approach or a tracking-based approach. Additionally, a shadow removal technique is applied to the segmented objects to improve the classification performance. For the MER windows with different sizes, a window scaling operation followed by an adaptive block-shifting operation is applied to obtain a fixed feature dimension. A weight mask, which is constructed according to the frequency of occurrence of an object in each position within a square window, is proposed to enhance the distinguishing pixels in the rescaled MER window. To extract classification features, a two-level Haar wavelet transform is applied to the rescaled MER window. The local shape features and the modified histogram of oriented gradients (HOG) are extracted from the level-two and level-one sub-bands, respectively, of the wavelet-transformed space. A hierarchical linear support vector machine classification configuration is proposed to classify the four classes of objects. Six video sequences are used to test the classification performance of the proposed method. The computer processing times of the object segmentation, object tracking, and feature extraction and classification approaches are 79 ms, 211 ms, and 0.01 ms, respectively. Comparisons with different well-known classification approaches verify the superiority of the proposed classification method.     

基于深度学习的小目标检测综述

目标检测是计算机视觉研究领域的核心问题和最具挑战性的问题之一,随着深度学习技术的广泛应用,目标检测的效率和精度逐渐提升,在某些方面已达到甚至超过人眼的分辨水平.但是,由于小目标在图像中覆盖面积小、分辨率低和特征不明显等原因,现有的目标检测方法对小目标的检测效果都不理想,因此也诞生了很多专门针对提升小目标检测效果的方法....     

Learning optimized features for hierarchical models of invariant object recognition

There is an ongoing debate over the capabilities of hierarchical neural feedforward architectures for performing real-world invariant object recognition. Although a variety of hierarchical models exists, appropriate supervised and unsupervised learning methods are still an issue of intense research. We propose a feedforward model for recognition that shares components like weight sharing, pooling stages, and competitive nonlinearities with earlier approaches but focuses on new methods for learning optimal feature-detecting cells in intermediate stages of the hierarchical network. We show that principles of sparse coding, which were previously mostly applied to the initial feature detection stages, can also be employed to obtain optimized intermediate complex features. We suggest a new approach to optimize the learning of sparse features under the constraints of a weight-sharing or convolutional architecture that uses pooling operations to achieve gradual invariance in the feature hierarchy. The approach explicitly enforces symmetry constraints like translation invariance on the feature set. This leads to a dimension reduction in the search space of optimal features and allows determining more efficiently the basis representatives, which achieve a sparse decomposition of the input. We analyze the quality of the learned feature representation by investigating the recognition performance of the resulting hierarchical network on object and face databases. We show that a hierarchy with features learned on a single object data set can also be applied to face recognition without parameter changes and is competitive with other recent machine learning recognition approaches. To investigate the effect of the interplay between sparse coding and processing nonlinearities, we also consider alternative feedforward pooling nonlinearities such as presynaptic maximum selection and sum-of-squares integration. The comparison shows that a combination of strong competitive nonlinearities with sparse coding offers the best recognition performance in the difficult scenario of segmentation-free recognition in cluttered surround. We demonstrate that for both learning and recognition, a precise segmentation of the objects is not necessary.     

基于Snake模型的视频对象分割和跟踪算法

视频对象的分割是基于内容的视频处理中重要的组成部分。提出并实现了一种半自动视频对象分割和跟踪算法。算法主要基于Williams活动轮廓模型，通过求取轮廓点的局部能量最小值对轮廓线进行更新。轮廓扩张技术用来追踪变形的轮廓边缘。通过对轮廓中心点运动的统计，预测对象的运动方向和大小。实验仿真结果表明，这种改进的Snake算法能够收缩到图像的凹陷部分，而且能较好地跟踪视频对象的运动。     

基于主动对象的Internet服务进化研究

Internet服务系统的维护与进化是当前软件开发领域的一个研究热点．传统的软件工程的生命周期开发方法并不完全适用于Internet服务软件．本文根据Internet服务软件的开发与处理特点，提出了一种采用主动分布式对象方式对Internet服务软件进行分析与处理的软件开发与进化方新范式．该范式利用分布式主动时象的自动侦测与相应处理机制。能够自动的完成大量的Internet应用进化处理需求．     

活动轮廓模型目标跟踪算法综述

目标跟踪是当前计算机视觉领域最活跃的研究主题。首先对基本的跟踪类型进行了介绍;然后讨论了基于活动轮廓模型的图像分割,重点分析了参数活动轮廓模型的梯度矢量流模型（Gradient Vector Flow,GVF）,以及几何活动轮廓模型中的模型;并讨论了基于粒子滤波的目标跟踪算法的研究现状,最后展望了这一领域未来研究的热点。