基于视觉字典的移动机器人闭环检测方法研究

针对移动机器人同步定位和地图构建(SLAM)的闭环检测问题,提出了一种基于视觉字典的闭环检测方法。该方法首先使用SURF算法对每一帧图像进行特征提取,生成视觉单词,构建视觉字典树,再基于"词袋"(Bag of Words,Bo W)对场景建模,通过计算图像视觉单词的匹配度估计图像间的相似度。为提高闭环检测的成功率,运用贝叶斯滤波与相似度来计算闭环假设的后验概率分布。同时,为提高系统的实时性,引入了内存管理机制。实验结果显示该方法是有效的。     

基于视觉词典的单目视觉闭环检测算法

针对移动机器人单目视觉同步定位与地图构建中的闭环检测问题,文中设计一种基于视觉词典的闭环检测算法。算法对采集的每帧图像通过SURF进行特征提取,应用模糊K均值算法对检测的视觉特征向量进行分类,在线构建表征图像的视觉词典。为精确表征局部视觉特征与视觉单词间的相似关联,利用混合高斯模型建立视觉词典中的每一视觉单词的概率模型,实现图像基于视觉词典的概率向量表示,通过向量的内积来计算图像间的相似度。为保证闭环检测的成功率,应用贝叶斯滤波融合历史闭环检测与相似度信息来计算闭环假设的后验概率分布。另外,引入浅层记忆与深度记忆两种内存管理机制来保证算法执行的快速性。实验结果证明该方法的有效性。     

视觉SLAM中闭环检测算法的研究

在基于人工视觉的移动机器人导航中,闭环检测是机器人准确构建地图及定位的一个重要问题。本文研究的闭环检测算法结合了计算机视觉中的词袋技术和视觉词典技术,在对图像进行处理时利用了BRIEF+FAST关键点的方法,利用离线阶段生成的词典树将二进制描述子空间离散化。训练图像生成的图像数据库结构主要由等级词袋、倒置索引和直接索引组成。倒置索引和直接索引提高了算法的效率。为了保证闭环检测结果的可靠性,对于匹配的图像还要进行验证。重点详述了一种高效的闭环检测算法,相对一般的基于概率的闭环检测,在硬件设备相同的情况下,本算法效率更高。     

室外环境下移动机器人视觉SLAM算法改进

闭环探测效率不高、视觉节点冗余度大制约着移动机器人视觉导航系统的性能.为了解决这个问题,从两个方面对视觉SLAM算法的关键环节进行了改进:在机器人导航的闭环探测环节采用了一种新的场景相似性测量方法,有效地提高了闭环探测的效率;在视觉节点的生成环节,算法采用了场景之间共有信息量减少的减量式节点探测方法,有效地降低了地图节点的冗余度.仿真和移动机器人实验对方法的有效性和实时性进行了验证,实验结果表明,移动机器人在视觉导航过程中,闭环探测的有效性达到99％以上,平均计算时间为0.03s,地图节点冗余度为0,使得导航系统在闭环探测和构建的地图质量两个方面的性能得到了进一步的提升.     

基于语义位置验证的鲁棒闭环检测算法

针对现有闭环检测算法因视觉干扰而产生的闭环误判问题,提出一种利用场景语义信息进行验证的闭环检测算法.该算法通过视觉词袋库模型检索闭环候选帧,用后验方法剔除算法可能产生的错误闭环.后验方法首先将场景中的语义信息抽象为语义节点;然后提取包含邻域信息的节点特征,并以此匹配图像间的语义节点,降低算法对于动态物体干扰的敏感性.随后,算法基于图像间的匹配语义节点构建相对位置网络,根据网络相似度验证闭环帧,提高闭环检测算法在具有相似纹理的场景中应对感知混淆的鲁棒性.实验结果表明,语义位置验证算法能够显著提升视觉词袋模型的检测准确率.与其他经典算法相比,所提出的闭环检测算法具备更快速、更准确的检测性能.     

随机维哈希量化视词字典的目标检索方法

基于视词字典树的算法由于高效性使其在基于大规模图像数据库的目标检索领域得到了广泛地应用。该类算法属于从文字搜索领域借鉴来的"视觉词袋"的算法。这种算法中的一个关键步骤是将高维特征向量量化成视词。将这种量化过程看作高维特征向量的最近邻搜索问题,并且提出一种随机维哈希(RDH)算法用于索引视词字典。实验结果证明,该算法比基于字典树的算法具有更高的量化精度,从而可以显著提高目标检索性能。     

基于局部语义拓扑图的视觉SLAM闭环检测

针对视觉SLAM(同步定位与地图创建)中现有的闭环检测方法容易产生假阳性检测的问题,利用YOLOv3目标检测算法获取场景中的语义信息,以DBSCAN(density-based spatial clustering of application with noise)算法修正错误检测和遗漏检测,构建语义节点,对关键帧形成局部语义拓扑图.利用图像特征和目标类别信息进行语义节点匹配,计算不同语义拓扑图中对应边的变换关系,得到关键帧之间的相似度,并根据连续关键帧的相似度变化情况进行闭环的判断.在公开数据集上的实验表明,目标聚类有效地提高了室内场景下的闭环检测准确性.与单纯利用传统视觉特征的算法相比,本文算法能够获得更加准确的闭环检测结果.     

一种基于历史模型集的改进闭环检测算法

为了提高移动机器人同时定位与地图创建(SLAM)问题中闭环检测的准确率和实时性,提出了一种基于历史模型集的改进闭环检测算法.首先,在基于Kinect传感器的帧到模型配准模型的基础上,增加特征描述向量并使用加权方法对其进行更新,从而构建历史模型集,并利用视觉词典树(visual vocabulary tree)对历史模型集和当前帧数据进行场景描述;其次,以反比例函数代替最小值函数,使两幅图像在单个节点的相似性得分函数得以优化,从而得到改进的金字塔TF-IDF(词频-逆向文件频率)得分匹配方法.一方面,改进方法能够减少感知歧义,提高闭环检测的准确率;另一方面,利用改进方法对当前帧数据与历史模型集的从属关系进行有效判断,与传统逐帧比较方法相比,比较次数明显减少,闭环检测的实时性得到较大提高.再次,使用改进的金字塔TF-IDF得分匹配方法对当前帧数据和候选历史模型集所包含的关键帧进行相似性分析,进而提取候选闭环;最后,从时间连续性和对极几何约束两个方面剔除误正闭环.数据集和实际场景对比实验均表明,相比于IAB-MAP(incremental appearance-based mapping)、FAB-MAP(fast appearance-based mapping)和RTAB-MAP(real-time appearance-based mapping),本文的闭环检测算法具有更好的实时性,且在确保100%准确率的情况下,具有更高的召回率.     

基于优化视觉词袋模型的图像分类方法

针对视觉词袋（BOV）模型中过大的视觉词典会导致图像分类时间代价过大的问题,提出一种加权最大相关最小相似（W-MR-MS）视觉词典优化准则。首先,提取图像的尺度不变特征转换（SIFT）特征,并用K-Means算法对特征聚类生成原始视觉词典;然后,分别计算视觉单词与图像类别间的相关性,以及各视觉单词间的语义相似性,引入一个加权系数权衡两者对图像分类的重要程度;最后,基于权衡结果,删除视觉词典中与图像类别相关性弱、与视觉单词间语义相似性大的视觉单词,从而达到优化视觉词典的目的。实验结果表明,在视觉词典规模相同的情况下,所提方法的图像分类精度比传统基于K-Means算法的图像分类精度提高了5.30%;当图像分类精度相同的情况下,所提方法的时间代价比传统K-Means算法下的时间代价降低了32.18%,因此,所提方法具有较高的分类效率,适用于图像分类。     

图像重排序中与查询相关的图像相似性度量

现今的图像搜索引擎主要利用图像周围文本信息为图像排序,根据图像内容重排序可以进一步提高搜索性能。图像相似性的度量对重排序算法的性能至关重要。然而已有的相似性度量没有考虑针对不同的查询,图像的相似性应该不同。提出一种与查询相关的相似性度量方法,将基于全局特征的相似性,基于局部特征的相似性,以及视觉单词同时出现率融合到一个迭代算法中,挖掘出与查询相关的图像信息,计算图像相似性。在Bing图像搜索引擎上的实验结果证明本文提出的相似性度量方法优于基于全局特征,局部特征,或它们线性组合的相似性。     

Hierarchical Classifiers for Robust Topological Robot Localization

This paper presents a novel appearance-based technique for topological robot localization and place recognition. A vocabulary of visual words is formed automatically, representing local features that frequently occur in the set of training images. Using the vocabulary, a spatial pyramid representation is built for each image by repeatedly subdividing it and computing histograms of visual words at increasingly fine resolutions. An information maximization technique is then applied to build a hierarchical classifier for each class by learning informative features. While top-level features in the hierarchy are selected from the coarsest resolution of the representation, capturing the holistic statistical properties of the images, child features are selected from finer resolutions, encoding more local characteristics, redundant with the information coded by their parents. Exploiting the redundancy in the data enables the localization system to achieve greater reliability against dynamic variations in the environment. Achieving an average classification accuracy of 88.9% on a challenging topological localization database, consisting of twenty seven outdoor places, demonstrates the advantages of our hierarchical framework for dealing with dynamic variations that cannot be learned during training.     

Constructing a discriminative visual vocabulary with macro and micro sense of visual words

Visual vocabulary representation approach has been successfully applied to many multimedia and vision applications, including visual recognition, image retrieval, and scene modeling/categorization. The idea behind the visual vocabulary representation is that an image can be represented by visual words, a collection of local features of images. In this work, we will develop a new scheme for the construction of visual vocabulary based on the analysis of visual word contents. By considering the content homogeneity of visual words, we design a visual vocabulary which contains macro-sense and micro-sense visual words. The two types of visual words are appropriately further combined to describe an image effectively. We also apply the visual vocabulary to construct image retrieving and categorization systems. The performance evaluation for the two systems indicates that the proposed visual vocabulary achieves promising results.     

基于局部时空特征方向加权的人体行为识别

目的 对人体行为的描述是行为识别中的关键问题,为了能够充分利用训练数据从而保证特征对行为的高描述性,提出了基于局部时空特征方向加权的人体行为识别方法。方法 首先,将局部时空特征的亮度梯度特征分解为3个方向(X、Y、Z)分别来描述行为, 通过直接构造视觉词汇表分别得到不同行为3方向特征描述子集合的标准视觉词汇码本,并利用训练视频得到每个行为的标准3方向词汇分布;进而,根据不同行为3方向特征描述子集合的标准视觉词汇码本,分别计算测试视频相应的3方向的词汇分布,并利用与各行为标准3方向词汇分布的加权相似性度量进行行为识别;结果 在Weizmann数据库和KTH数据库中进行实验,Weizmann数据库中的平均识别率高达96.04%,KTH数据库中的平均识别率也高达96.93%。结论 与其他行为识别方法相比可以明显提高行为平均识别率。     

Teaching Turkish-Dutch kindergartners Dutch vocabulary with a social robot: Does the robot's use of Turkish translations benefit children's Dutch vocabulary learning?

Providing first language (L1) translations in L2 vocabulary interventions may be beneficial for L2 vocabulary learning. However, in linguistically diverse L2 classrooms, teachers cannot provide L1 translations to all children. Social robots do offer such opportunities, as they can be programmed to speak any combination of languages. This study investigates whether providing L1 translations in a robot-assisted L2 vocabulary training facilitates children's learning. Participants were Turkish-Dutch kindergartners (n = 67) who were taught six Dutch (L2) words for which they knew the L1 (Turkish), but not the L2 Dutch form. Half of these words were taught by a Turkish-Dutch bilingual robot, alongside their Turkish translations; the other half by a monolingual Dutch robot. Children also completed Dutch and Turkish receptive vocabulary tests. Results of generalized linear regression models indicated better performance in the Dutch-only condition than in the Turkish-Dutch condition. Children with well-developed Turkish and Dutch vocabulary knowledge outperformed children with less well-developed vocabulary knowledge. The majority of children preferred working with the bilingual robot, but children's preference did not affect word learning. Thus, contrary to our prediction, we found no evidence for a facilitating effect of providing L1 translations through a robot on bilingual children's L2 word learning.     

Artificial potential functions based camera movements and visual behaviors in attentive robots

An attentive robot needs to exhibit a plethora of different visual behaviors including free viewing, detecting visual onsets, search, remaining fixated and tracking depending on the vision task at hand. The robot’s associated camera movements—ranging from saccades to smooth pursuit—direct its optical axis in a manner that is dependent on the current visual behavior. This paper proposes a closed-loop dynamical systems approach to the generation of camera movements based on a family of artificial potential functions. Each movement from the current fixation point to the next is associated with an artificial potential function that encodes saliency and possibly inhibition depending on the visual behavior that the robot is engaged in. The novelty of this approach is that since the nature of resulting motion can vary from being saccadic to smooth pursuit, the full repertoire of visual behaviors all become possible within the same framework. The robot can switch its visual behavior simply by changing the parameters of the constructed artificial potential functions appropriately. Furthermore, automated reflexive changes among the different visual behaviors can be achieved via a simple switching automaton. Experimental results with APES robot serve to show the performance properties of a robot engaged in each different visual behavior.     

Simulation systems for the design of robot mechanisms

Building environmental models by a vision-guided mobile robot is a key problem in robotics. This paper presents a new strategy of the vision-guided mobile robot for building models of an unknown environment by panoramic sensing. The mobile robot perceives with two types of panoramic sensing: one is for acquiring omnidirectional visual information at an observation point to find the outline structure of the local environment and the other is for acquiring visual information along a route to build local environmental models. Before exploring the environment, the robot looks around and finds the outline structure of the local environment as a reference frame for acquiring the local models. Then the robot builds the local models while moving along the directions of the outline structure (the outline structure is represented by a simple convex polygon, each side of which has a direction). We have implemented the above-mentioned robot behaviors into a mobile robot which has multiple vision agents. The multiple vision agents can simultaneously execute different vision tasks needed for panoramic sensing.     

基于图象分割的机器人视觉系统的设计与实现

机器人视觉系统是自主机器人的重要组成部分，而如何精确高效的处理视觉信息是视觉系统的关键问题．本文介绍了一个包括离线颜色分析器和实时视觉信息处理器两大部分的机器人视觉系统。离线颜色分析器用于提取各种颜色的阈值，实时视觉信息处理器则利用阈值进行图象分割，从而使机器人准确认知当前环境。     

Agent任务可视编程和单元组合重构

文中将机器人装配单元的各类设备定义为独立的Ａｇｅｎｔ,采用Ｐｅｔｒｉ Ｎｅｔ模型,为各Ａｇｅｎｔ的作业定义了有关操作的基本模型结构,作为基于多Ａｇｅｎｔ的模型库。通过对Ａｇｅｎｔ模型库元素的可视化组合重构,不仅可以实现机器人作业单元几何元素的重组,而且可以方便地实现作业任务的重组。