视频图像序列中运动目标的提取与跟踪

提出一种摄像机静止条件下视频图像运动目标提取与跟踪的方法。本文首先提出了一种有效的阴影去除算法检测运动目标,然后采用基于目标颜色直方图的相关匹配,使用Bhattacharyya系数度量目标模型与预测模型间的相似度,选出最优相似模型作为当前的目标模型,实现了对目标的跟踪。实验结果表明该算法是可行有效的。     

基于OpenCV的室内环境下多目标跟踪

室内环境下多运动目标跟踪的核心问题是目标的快速识别和准确匹配,目标的快速识别关键在于目标对象的特征提取,寻找不变的特征值.针对以上两个问题,采用基于颜色直方图的特征提取方法并用欧氏距离匹配法实现特征值的相似度匹配.提出的区域相应和特征匹配相结合的多运动目标跟踪算法解决了因为快速运动和长时间遮挡而引起的目标跟踪丢失问题.     

基于改进Hausdorff距离的人脸匹配方法

提出了一种基于改进Hausdorff距离的人脸相似度匹配的方法,该方法首先将人脸划分为脸型、双眼、鼻、嘴等几个特征点集,分别计算各部分的改进Hausdorff距离,然后进行加权计算相似度。利用该方法,在ASM（主动形状模型）定位人脸的基础上进行了人脸检索。实验表明,利用人脸相似度计算方法对人脸特征库进行搜索,达到了较好的效果。同时结合ASM自动人脸检测,本方法可以全自动完成人脸匹配,应用于人脸识别及数字娱乐等领域。     

基于模型和区域相关融合的鲁棒跟踪算法

提出了一种模型部分匹配的相似度量方法,利用匹配的完整度、归一化的匹配点相对于模型的偏移量期望和方差的加权和作为相似性度量。在此基础上建立模型匹配算法,利用模型匹配和区域相关融合的方法进行目标跟踪。算法能够在摄像机静止和运动的情况下进行稳定的跟踪,能够适应目标的部分遮挡、光照和姿态的变化。利用参数化的模型能够在复杂的背景环境中实现实时的多目标跟踪。     

结合深度度量学习的血缘关系识别

目的 人脸图像分析是计算机视觉和模式识别领域的重要研究方向之一,基于人脸图像的血缘关系识别是对给定的一对或一组人脸图像,判断其是否存在某种血缘关系。人脸血缘关系识别不仅在生物特征识别领域有着重要研究价值,而且在社交媒体挖掘、失散家庭成员寻找等社会生活领域中有重要的应用价值。针对当前大多数算法都是基于传统机器学习方法,提出一种采用深度度量学习进行人脸图像血缘关系研究的新方法。方法 目前深度学习算法能很好地理解单张人脸图像,但是多个主体间的关系探究仍然是计算机视觉领域富有挑战性的问题之一。为此,提出一种基于深度度量学习的父母与子女的血缘关系识别方法。首先使用超过5 000 000张人脸图像的样本集训练一个深度卷积神经网络FaceCNN并提取父母与子女的人脸图像深度特征,之后引入判别性度量学习方法,使得具有血缘关系的特征尽可能地靠近,反之则尽可能地远离。然后对特征进行分层非线性变换使其具有更强判别特性。最后根据余弦相似度分别计算父亲、母亲和孩子的相似度并利用相似概率值得到双亲和孩子的综合相似度得分。结果 算法在TSKinFace数据集上验证了FaceCNN提取特征与深度度量学习结合进行血缘关系识别的有效性,最终在该数据集上父母与儿子和女儿的血缘关系识别准确率分别达到87.71%和89.18%,同时算法在进行血缘度量学习和双亲相似度计算仅需要3.616 s。结论 提出的血缘关系识别方法,充分利用深度学习网络良好的表征和学习能力,不仅耗时少,而且有效地提高了识别准确率。     

基于两级分类器串行的人脸识别

在分析人脸特征提取和分类器的基础上,提出一种两级分类器串行结合的模型进行人脸识别。在第一级分类器中利用极坐标傅立叶变换提取全局特征通过相似度匹配进行粗略的筛选,第二级分类器中利用改进的协同神经网络,基于原始灰度图像的小波变换提取内在特征,进行精细识别。研究分析了分类器串行结合模型中阈值的选取与系统精度、速度间的关系。在自建人脸库和Yale B人脸库上的实验结果表明,两级分类器串行的识别模型在保证较高系统识别率的前提下可以提升系统的速度。     

带相关反馈的基于深度神经网络模型的人脸检索方法

针对大规模人脸检索问题,提出了一种带相关反馈的基于深度神经网络模型的人脸检索方法.首先利用卷积神经网络对人脸进行特征提取,再利用传统的检索方法进行人脸检索,在检索环节之后加入相关反馈环节.根据用户反馈的结果,将样本分成正例和负例,作为反馈环节的训练样本,完成反馈环节的训练.实验表明,该方法能够显著提高人脸检索的准确率.     

基于深度特征分析的双线性图像相似度匹配算法

基于内容的图像检索一直面临"语义鸿沟"的难题,特征选择对语义学习结果有着直接的影响;而传统距离度量方法往往从单一角度进行相似性计算,不能很好地表示出图像之间的相似度。为了解决以上问题,提出基于深度特征分析的双线性图像相似度匹配的方法。首先,将图像数据集在卷积神经网络模型上进行微调训练,然后利用训练好的卷积神经网络对图像进行特征提取,获得全连接层输出的特征之后,通过双线性相似性度量方法得到图像间相似度的大小,通过对相似度的大小排序,返回最相似的图像实例。在Caltech101和Caltech256数据集上的对比实验显示,所提算法的平均查准率、TopK查准率和查全率均优于对比算法,验证了所提算法的有效性。     

基于深度学习卷积神经网络的民航旅客人脸智能识别方法

在民航旅客人脸识别中,由于人脸特征提取差,导致识别准确率低,因此提出基于深度学习卷积神经网络的民航旅客人脸智能识别方法。首先,利用深度学习卷积神经网络检测人脸,获取人脸位置并标记关键特征点;其次,基于人脸姿态校正提取关键特征,利用三角对线理论融合人脸特征;最后,通过计算待检测图像与数据集中图像的余弦相似度,实现人脸智能识别。实验结果表明,该方法的识别准确率在92%以上,证明其具备可行性。     

无重叠视域的多摄像机之间的目标匹配

在无重叠视域的多摄像机监控中,由于不同摄像机的视域差别和视域分离,同一运动目标在不同的视域中的成像可能会非常不同,因此在这种情况下对运动目标进行匹配是一项具有挑战性的工作。提出了一种可以容忍光照的不同,在无重叠视域的多摄像机下进行目标匹配的方法。该方法经过初始聚类和K-means聚类对目标进行主颜色谱的提取,利用EMKM算法改善K-means对初始中心点的依赖性,把提取出来的主颜色谱直方图作为目标的特征,然后利用特征相似度测量来判定任意两个物体之间是否匹配;当无法对某些物体进行准确匹配时,再利用SIFT特征进行下一步匹配。该方法也可以用于有重叠视域的多摄像机目标匹配中,通过与其他匹配方法相结合,提高匹配的准确度。实验结果证实了该方法具有较高的准确度。     

Human detection using a mobile platform and novel features derived from a visual saliency mechanism

Human detection is a key ability to an increasing number of applications that operates in human inhabited environments or needs to interact with a human user. Currently, most successful approaches to human detection are based on background substraction techniques that apply only to the case of static cameras or cameras with highly constrained motions. Furthermore, many applications rely on features derived from specific human poses, such as systems based on features derived from the human face which is only visible when a person is facing the detecting camera. In this work, we present a new computer vision algorithm designed to operate with moving cameras and to detect humans in different poses under partial or complete view of the human body. We follow a standard pattern recognition approach based on four main steps: (i) preprocessing to achieve color constancy and stereo pair calibration, (ii) segmentation using depth continuity information, (iii) feature extraction based on visual saliency, and (iv) classification using a neural network. The main novelty of our approach lies in the feature extraction step, where we propose novel features derived from a visual saliency mechanism. In contrast to previous works, we do not use a pyramidal decomposition to run the saliency algorithm, but we implement this at the original image resolution using the so-called integral image. Our results indicate that our method: (i) outperforms state-of-the-art techniques for human detection based on face detectors, (ii) outperforms state-of-the-art techniques for complete human body detection based on different set of visual features, and (iii) operates in real time onboard a mobile platform, such as a mobile robot (15 fps).     

A new matching strategy for content based image retrieval system

Adopting effective model to access the desired images is essential nowadays with the presence of a huge amount of digital images. The present paper introduces an accurate and rapid model for content based image retrieval process depending on a new matching strategy. The proposed model is composed of four major phases namely: features extraction, dimensionality reduction, ANN classifier and matching strategy. As for the feature extraction phase, it extracts a color and texture features, respectively, called color co-occurrence matrix (CCM) and difference between pixels of scan pattern (DBPSP). However, integrating multiple features can overcome the problems of single feature, but the system works slowly mainly because of the high dimensionality of the feature space. Therefore, the dimensionality reduction technique selects the effective features that jointly have the largest dependency on the target class and minimal redundancy among themselves. Consequently, these features reduce the calculation work and the computation time in the retrieval process. The artificial neural network (ANN) in our proposed model serves as a classifier so that the selected features of query image are the input and its output is one of the multi classes that have the largest similarity to the query image. In addition, the proposed model presents an effective feature matching strategy that depends on the idea of the minimum area between two vectors to compute the similarity value between a query image and the images in the determined class. Finally, the results presented in this paper demonstrate that the proposed model provides accurate retrieval results and achieve improvement in performance with significantly less computation time compared with other models.     

An IR and visible image sequence automatic registration method based on optical flow

IR–visible camera registration is required for multi-sensor fusion and cooperative processing. Image sequences can provide motion information, which is useful for sequence registration. The existing methods mainly focus on registration using moving objects which are observed by both cameras. However, accurate motion feature extraction for a whole moving object is difficult, because of the complex environment and different imaging mechanism of two sensors. To overcome this problem, we use motion features associated with single pixels in the two image sequences to carry out automatic registration. A normalized optical flow time sequence for each image pixel is constructed. The matching of pixels between the IR image and the visible light image is carried out using a fast similarity measurement and a three stage correspondence selection method. Finally cascaded random sample consensus is adopted to remove outlying matches, and least-square method and Levenberg–Marquardt method are used to estimate the transformation from the IR image to the visible image. The effectiveness of our method is demonstrated using several real datasets and simulated datasets.     

一种特征加权融合人脸识别方法

针对传统人脸识别算法在非限制条件下识别准确率不高的问题,提出了一种特征加权融合人脸识别方法(DLWF⁺)。根据人脸面部左眼、右眼、鼻子、嘴、下巴等5个器官位置,将人脸图像划分成5个局部采样区域;将得到的5个局部采样区域和整幅人脸图像分别输入到对应的神经网络中进行网络权值调整,完成子网络的构建;利用softmax回归求出6个相似度向量并组成相似度矩阵与权向量相乘得出最终的识别结果。经ORL和WFL人脸库上进行实验验证,识别准确率分别达到97%和91.63%。实验结果表明:该算法能够有效提高人脸识别能力,与传统识别算法相比在限制条件和非限制条件下都具有较高的识别准确率。     

基于多级纹理特征的深度信念网络人脸识别算法

为解决人脸特征提取过程中局部特征缺失的问题,借助局部二值模式(LBP)与方向梯度直方图(HOG)提出一种基于多级纹理特征融合的深度信念网络人脸识别算法。以提取局部纹理特征以及边缘纹理特征为出发点,对人脸图像进行三级纹理特征提取。使用MB-LBP提取初级纹理特征;在此基础上进行改进的CS-LBP图像特征提取作为二级纹理特征;使用HOG算子在二级纹理特征上完成三级纹理特征提取。将二级和三级纹理特征直方图顺序串联融合后输入到深度信念网络(DBN)逐层贪婪训练,优化网络参数,并用优化的网络在ORL、YELA人脸标准库中进行测试,识别率均在92%以上。该算法与传统算法(SVM、PCA)相比较拥有更好的人脸识别效果,同时也表明了局部纹理特征的改善为识别过程的特征提取提供强有力的保障,为人脸识别的进一步研究开拓新思路。     

均衡化特征匹配的非刚体细胞形态跟踪

提出利用均衡化特征匹配来进行非刚性细胞形体跟踪的方法。采用重启动的随机游走方法建立并求解特征匹配概率模型,利用双向均衡方法对匹配邻接矩阵进行均衡化处理,得到指定目标与待跟踪目标之间的精确匹配,以获得目标的定位跟踪结果。同时利用特征匹配结果进行目标的自动标定,并应用图像分割方法进行目标的精确轮廓跟踪。实验结果表明,将该方法应用于视频中动态背景下的运动细胞形态跟踪时,在背景相似度较高及目标迅速移动的条件下,表现出了良好的性能,与同类方法相比可获得较高的定位精度以及更为准确的目标轮廓。     

3-D Head Model Retrieval Using a Single Face View Query

In this paper, a novel 3D head model retrieval approach is proposed, in which only a single 2D face view query is required. The proposed approach will be important for multimedia application areas such as virtual world construction and game design, in which 3D virtual characters with a given set of facial features can be rapidly constructed based on 2D view queries, instead of having to generate each model anew. To achieve this objective, we construct an adaptive mapping through which each 2D view feature vector is associated with its corresponding 3D model feature vector. Given this estimated 3D model feature vector, similarity matching can then be performed in the 3D model feature space. To avoid the explicit specification of the complex relationship between the 2D and 3D feature spaces, a neural network approach is adopted in which the required mapping is implicitly specified through a set of training examples. In addition, for efficient feature representation, principal component analysis (PCA) is adopted to achieve dimensionality reduction for facilitating both the mapping construction and the similarity matching process. Since the linear nature of the original PCA formulation may not be adequate to capture the complex characteristics of 3D models, we also consider the adoption of its nonlinear counterpart, i.e., the so-called kernel PCA approach, in this work. Experimental results show that the proposed approach is capable of successfully retrieving the set of 3D models which are similar in appearance to a given 2D face view.     

深度特征融合的非刚性三维形状局部匹配

针对海量、异构三维形状匹配与智能检索技术的需求,提出了一种基于级联卷积神经网络(F-PointCNN)深度特征融合的三维形状局部匹配方法.首先,采用特征袋模型,提出几何图像表示方法,该几何图像不仅能够有效区分同类异构的非刚性三维模型,而且能够揭示大尺度不完整三维模型的结构相似性.其次,构建级联卷积神经网络学习框架F-P...