一种基于随机化视觉词典组和查询扩展的目标检索方法

在目标检索领域,当前主流的解决方案是视觉词典法(Bag of Visual Words, BoVW),然而,传统的BoVW方法具有时间效率低、内存消耗大以及视觉单词同义性和歧义性的问题。针对以上问题,该文提出了一种基于随机化视觉词典组和查询扩展的目标检索方法。首先,该方法采用精确欧氏位置敏感哈希(Exact Euclidean Locality Sensitive Hashing, E2LSH)对训练图像库的局部特征点进行聚类,生成一组支持动态扩充的随机化视觉词典组;然后,基于这组词典构建视觉词汇分布直方图和索引文件;最后,引入一种查询扩展策略完成目标检索。实验结果表明,与传统方法相比,该文方法有效地增强了目标对象的可区分性,能够较大地提高目标检索精度,同时,对大规模数据库有较好的适用性。     

基于随机化视觉词典组和上下文语义信息的目标检索方法

 传统的视觉词典法(Bag of Visual Words,BoVW)具有时间效率低、内存消耗大以及视觉单词同义性和歧义性的问题,且当目标区域所包含的信息不能正确或不足以表达用户检索意图时就得不到理想的检索结果.针对这些问题,本文提出了基于随机化视觉词典组和上下文语义信息的目标检索方法.首先,该方法采用精确欧氏位置敏感哈希(Exact Euclidean Locality Sensitive Hashing,E²LSH)对局部特征点进行聚类,生成一组支持动态扩充的随机化视觉词典组;然后,利用查询目标及其周围的视觉单元构造包含上下文语义信息的目标模型;最后,引入K-L散度(Kullback-Leibler divergence)进行相似性度量完成目标检索.实验结果表明,新方法较好地提高了目标对象的可区分性,有效地提高了检索性能.     

基于弱监督E2LSH和显著图加权的目标分类方法

在目标分类领域,当前主流的目标分类方法是基于视觉词典模型,而时间效率低、视觉单词同义性和歧义性及单词空间信息的缺失等问题严重制约了其分类性能。针对这些问题,该文提出一种基于弱监督的精确位置敏感哈希(E2LSH)和显著图加权的目标分类方法。首先,引入E2LSH算法对训练图像集的特征点聚类生成一组视觉词典,并提出一种弱监督策略对E2LSH中哈希函数的选取进行监督,以降低其随机性,提高视觉词典的区分性。然后,利用GBVS(Graph-Based Visual Saliency)显著度检测算法对图像进行显著度检测,并依据单词所处区域的显著度值为其分配权重;最后,利用显著图加权的视觉语言模型完成目标分类。在数据集Caltech-256和Pascal VOC 2007上的实验结果表明,所提方法能够较好地提高词典生成效率,提高目标表达的分辨能力,其目标分类性能优于当前主流方法。     

基于改进欧式聚类算法的双目主动视觉点云目标检测研究

双目视觉立体匹配时,在同色调表面因为缺乏纹理信息,不仅计算量大且匹配度低, 而且生成的 场景中的点云又具有非结构化、近密远疏的性质, 因此,提高双目视觉匹配的精度与速度, 以及准确分割点 云目标, 一直是点云获取及目标检测中的难点问题。 针对以上问题, 本文首先提出了一种融合主动激光 的 3D 点云目标采集方法, 快速准确地获得原始点云数据; 其次提出了一种基于欧式聚类的改进算法, 使用距离阈值和角度阈值作为阈值分割判断条件进行分段聚类, 得到边界明确的 3D 点云目标检测框。 实验结果表明:所设计的 3D 点云成像系统能够有效获取前方物体的 3D 点云信息,且具有比激光雷达成 本低、易实现、信息丰富等优势;改进后的欧式聚类算法能有效改善传统算法对阈值较为敏感导致的物 体易出现欠分割或过分割的问题, 提高了目标检测的准确率, 在室内场景下具有良好的检测效果。     

一种基于T-分布随机近邻嵌入的聚类集成方法

该文将T-分布随机近邻嵌入(TSNE)引入到聚类集成问题中,提出一种基于TSNE的聚类集成方法。首先通过TSNE最小化超图邻接矩阵的行对应的高维数据点与低维映射点分布之间的KL散度,使得高维空间结构在低维空间得以保持,然后在低维空间运行层次聚类算法获得最终的聚类结果。在基准数据集上的实验结果表明： TSNE能够提高层次聚类算法的聚类质量,该文方法获得了优于主流聚类集成方法的结果。     

一种基于聚类和集成学习的混合脉冲去交错方法

在现代复杂电磁环境下,来自不同辐射源的信号在时域、空域和频域高度重叠交错。传统的脉冲去交错方法在应对相似脉冲参数方面的表现不尽人意。提出了一种利用聚类和集成学习解决问题的方法。该方法利用脉冲的多个参数进行聚类,通过所提取的能够表达脉冲序列趋势的特征对集成学习模型进行训练,利用训练好的模型对聚类的信号组群进行判断,是否属于同一个辐射源。对所提方法进行仿真的结果表明该方法能有效地进行混合脉冲去交错。     

基于K-medoids聚类的贝叶斯集成算法

朴素贝叶斯分类算法由于其计算高效在生活中应用广泛。本文根据集成算法的差异性特征,聚类算法聚类点的选择方式的可变性,提出了基于K-medoids聚类技术的贝叶斯集成算法,朴素贝叶斯的泛化性能得到了提升。首先,通过样本集训练出多个朴素贝叶斯基分类器模型;然后,为了增大基分类器之间的差异性,利用K-medoids算法对基分类器在验证集上的预测结果进行聚类;最后,从每个聚类簇中选择泛化性能最佳的基分类器进行集成学习,最终结果由简单投票法得出。将该算法应用于UCI数据集,并与其他类似算法进行比较可得,本文提出的基于K-medoids聚类的贝叶斯集成算法(NBKME)提高了数据集的分类准确率。     

利用本体集成和特征聚类的网页分类研究

网页分类存在着新词多、特征维数高的问题,提出了一种新的网页分类方法。首先利用桥本体对分类领域本体进行集成,建立多本体语义标注模型,对文本特征进行降维。在此基础上,对不同类标号的关健词进行聚类,解决新词无法识别的问题,同时考虑网页标签的不同权重,用改进的SVM模型对中文网页进行分类。实验结果表明,上述方’法改进了传统SVM分类器的性能。     

一种改进的K-Modes聚类算法

传统的K-Modes算法采用0-1简单匹配方法计算对象与类中心(Modes)之间的距离,并将每个对象分配到离它最近的类中去。采用基于频率方法重新计算各类的类中心(Modes)、定义目标函数,然而,对象的归类方法和目标函数的定义没有充分考虑分类数据的特点。对此,提出一种改进的K-Modes算法,采用期望熵最小的衡量方法进行归类,并且采用期望熵作为新的目标函数。通过实验将该算法与传统的K-Modes算法进行比较,表明该算法是更有效的。     

一种基于多重模糊聚类的红外目标分割算法

提出了一种基于多重模糊聚类的红外目标分割算法。为了实现目标的准确分割,先将原始红外图像进行四划分得到四个子图像,在各个子图像上分别进行模糊C均值聚类,再对图像进行横纵二划分各得到两个子图像,并将四划分时得到的聚类结果约束在二划分的聚类过程中,最后将二划分得到的聚类结果约束到原始图像的聚类过程中,并在其中加入邻域空间约束。此方法可有效增强背景和目标区域像素点的各自凝聚性和抗干扰性,有效提高聚类分割结果的准确性。实验结果表明,多重模糊聚类目标分割算法能准确地实现红外图像目标区域和背景区域的分离,是一种可行的目标分割算法。     

一种用于图像分类的改进的有偏特征采样方法

为了模拟图像分类任务中待分类目标的可能分布,使特征采样点尽可能集中于目标区域,基于Yang的有偏采样算法提出了一种改进的有偏采样算法。原算法将目标基于区域特征出现的概率和显著图结合起来,计算用于特征采样的概率分布图,使用硬编码方式对区域特征进行编码,导致量化误差较大。改进的算法使用局部约束性编码代替硬编码,并且使用更为精确的后验概率计算方式以及空间金字塔框架,改善了算法性能。在PASCAL VOC 2007和2010两个数据集上进行实验,平均精度比随机选取的特征采样方法能够提高约0.5%,验证了算法的有效性。     

Bayesian salient object detection based on saliency driven clustering

Salient object detection is essential for applications, such as image classification, object recognition and image retrieval. In this paper, we design a new approach to detect salient objects from an image by describing what does salient objects and backgrounds look like using statistic of the image. First, we introduce a saliency driven clustering method to reveal distinct visual patterns of images by generating image clusters. The Gaussian Mixture Model (GMM) is applied to represent the statistic of each cluster, which is used to compute the color spatial distribution. Second, three kinds of regional saliency measures, i.e, regional color contrast saliency, regional boundary prior saliency and regional color spatial distribution, are computed and combined. Then, a region selection strategy integrating color contrast prior, boundary prior and visual patterns information of images is presented. The pixels of an image are divided into either potential salient region or background region adaptively based on the combined regional saliency measures. Finally, a Bayesian framework is employed to compute the saliency value for each pixel taking the regional saliency values as priority. Our approach has been extensively evaluated on two popular image databases. Experimental results show that our approach can achieve considerable performance improvement in terms of commonly adopted performance measures in salient object detection.     

Re-identification framework for long term visual object tracking based on object detection and classification

In this paper, we address the problem of long-term visual object tracking and we present an efficient real-time single object tracking system suitable for integration in autonomous platforms that need to encompass intelligent capabilities. We propose a novel long-term tracking framework for classification based re-detection and tracking, that incorporates state estimation, object re-identification and automated management of tracking and detection results. Our method integrates a novel object re-identification technique which efficiently filters a number of detection candidates and systematically corrects the tracking results. Through extensive experimental validation on the UAV123, UAV20L and TLP datasets, we demonstrate the effectiveness of the proposed system and its advantage over several state-of-the art trackers. The results furthermore highlight the proposed tracker’s ability to handle challenges arising from real-world and long-term scenarios, such as variations in pose, scale, occlusions and out-of-view situations. Furthermore, we propose a variant that is suitable for deployment on autonomous robots, such as Unmanned Aerial Vehicles.     

Spatial object clustering and buffering

Researchers have increasingly been interested in applying object technology to geographic information systems and other spatial database systems development for its modeling power and functionality. To ensure high performance of such systems, we've studied clustering and buffering strategies for storing polygon objects. Our experiments using real data help evaluate the strategies' performance     

A scalable monitoring approach based on aggregation and refinement

Network monitoring is an integral part of any network management system. In order to ensure end-to-end service quality stated in service level agreements (SLAs), managers of a service provider network need to gather quality-of-service (QoS) measurements from multiple nodes in the network. For a large network with over thousands of flows with end-to-end SLAs, the information exchanged between network nodes and a central network management system (NMS) could be substantial. We propose a mechanism called aggregation and refinement based monitoring (ARM) to reduce the amount of information exchange. ARM is a generic mechanism that can be configured to run with different objectives, including threshold-based, rank-based and percentile-based. The mechanism enables the NMS to collect data from network nodes using a dynamic QoS data aggregation/refinement technique, and to process these information differently depending on its measurement objective. Our simulation results show that for these various objectives, the selective refinement process is able to validate SLAs quickly, is an order of magnitude more efficient than a simple polling scheme, and performs well across a wide range of traffic loads     

Video abstraction based on the visual attention model and online clustering

With the fast evolution of digital video, research and development of new technologies are greatly needed to lower the cost of video archiving, cataloging and indexing, as well as improve the efficiency and accessibility of stored video sequences. A number of methods to respectively meet these requirements have been researched and proposed. As one of the most important research topics, video abstraction helps to enable us to quickly browse a large video database and to achieve efficient content access and representation. In this paper, a video abstraction algorithm based on the visual attention model and online clustering is proposed. First, shot boundaries are detected and key frames in each shot are extracted so that consecutive key frames in a shot have the same distance. Second, the spatial saliency map indicating the saliency value of each region of the image is generated from each key frame and regions of interest (ROI) is extracted according to the saliency map. Third, key frames, as well as their corresponding saliency map, are passed to a specific filter, and several thresholds are used so that the key frames containing less information are discarded. Finally, key frames are clustered using an online clustering method based on the features in ROIs. Experimental results demonstrate the performance and effectiveness of the proposed video abstraction algorithm.     

基于深度学习物体检测的视觉跟踪方法

提出了一种基于深度学习物体检测的视觉跟踪方法。该方法利用深度学习在特征表达上的优势,采用基于回归的深度检测模型SSD （Single Shot Multibox Detector）提取候选目标,并结合颜色直方图特征和HOG （Histogram of Oriented Gradient）特征进行目标筛选,实现目标跟踪。为了提升深度检测模型的物体检测性能,文中构建了多尺度目标搜索图,可在一张图上实现不同尺度的目标检测。在标准跟踪测试库上选取八个具有代表性的跟踪视频序列,并选取六种具有代表性的跟踪方法进行了对比测试。结果表明,文中所提方法在跟踪效果上,整体优于参与对比的其他算法,且对于物体姿态变化、尺寸变化、旋转变化、光照变化、复杂背景杂波等影响因素具有较好的鲁棒性。     

A novel video salient object extraction method based on visual attention

This paper addresses a novel approach to automatically extract video salient objects based on visual attention mechanism and seeded object growing technique. First, a dynamic visual attention model to capture the object motions by global motion estimation and compensation is constructed. Through combining it with a static attention model, a saliency map is formed. Then, with a modified inhibition of return (MIOR) strategy, the winner-take-all (WTA) neural network is used to scan the saliency map for the most salient locations selected as attention seeds. Lastly, the particle swarm optimization (PSO) algorithm is employed to grow the attention objects modeled by Markov random field (MRF) from the seeds. Experiments verify that our presented approach could extract both of stationary and moving salient objects efficiently.     

一种改进的Camshift目标跟踪方法

为了解决单特征在目标跟踪中无法准确描述目标的问题,提出了一种多特征融合的实时目标跟踪方法。该方法将角点特征、轮廓特征融入传统的Camshift算法中,结合原有的颜色特征对目标进行描述。解决了传统算法易受同色物体干扰,抗遮挡性能差等问题。实验结果表明,该方法能够实现对目标的实时跟踪,当目标遮挡的时间较短时能够很好地识别目标,具有较高的鲁棒性。