Coupled region-edge shape priors for simultaneous localization and figure-ground segmentation

We propose a new algorithm for simultaneous localization and figure-ground segmentation where coupled region-edge shape priors are involved with two different but complementary roles. We resort to a segmentation-based hypothesis-and-test paradigm in this research, where the region prior is used to form a segmentation and the edge prior is used to evaluate the validity of the formed segmentation. Our fundamental assumption is that the optimal shape-constrained segmentation that maximizes the agreement with the edge prior occurs at the correctly hypothesized location. Essentially, the proposed algorithm addresses a mid-level vision issue that aims at producing a map image for part detection useful for high-level vision tasks. Our experiments demonstrated that this algorithm offers promising results in terms of both localization and segmentation.     

Moderating effects of localization differences on ERP use: A socio-technical systems perspective

Despite the promised benefits of Enterprise Resource Planning (ERP) systems, more than two thirds of ERP system projects result in failure. In this study, we investigate some plausible reasons for their failure from the user’s perspective. Particularly, we propose the socio-technical factors that affect ERP system use. This study has two research objectives. First, it introduces and tests a theoretical model that views ERP systems as both an organizational change driver and a sophisticated information system to explain the phenomenon of ERP system use. For this purpose, the proposed model includes attitude toward change and computer self-efficacy; this may affect ERP system use behavior through perceived usefulness for the systems. Second, this paper attempts to shed some light on how the localization differences of ERP systems may affect users’ intention to use the ERP systems. The results based on survey data using subjects from two different ERP systems support the proposed research model. It identifies the moderating effect of the localization differences. Theoretical and practical implications of the study are discussed along with its limitations.     

基于Monte Carlo的多能量级移动节点定位算法研究

提出了一种基于Monte Carlo的移动无线传感器网络节点定位算法,即移动导标周期性发射不同能量级的广播信号,未知节点接收感知范围内的导标定位信息,以确定自己所处的限定区域。利用改进的Montc Carl。方法,采用较少样本实现了节点的位置估计。为避免导标共线时出现节点定位失效的情况,引入共线度限制因子,提出了一种导标共线度约束策略。仿真实验结果表明,提出的算法具有较低的定位误差,算法在导标节点密度、运动速度、测距误差等影响因子下表现出了良好的适应性。     

WSN节点定位中移动信标路径规划的研究

在无线传感器网络的节点定位技术中,通过移动锚节点定位是比较实用的定位方法,移动锚节点定位需要考虑移动路径问题,路径规划合理有效,可以获得较高的定位精度。若将传感器节点看作图的顶点,利用解决TSP的思想结合蚁群算法来寻找一条最佳路径,通过理论分析及仿真实验可知,该方法形成的路径可以很好地覆盖整个网络,很好地适应无线传感器网络节点随机分布时的节点定位。     

近场声源定位算法研究

麦克风阵列声源定位可为在复杂环境下的说话人的空间位置估计提供有效的解决方案。而传统的应用于雷达,声呐系统领域的阵列信号处理理论已趋于完美,很多应用于阵列信号处理的算法加以修改就可以用来进行麦克风阵列的声源定位。以阵列信号处理中的经典算法MUSIC（Multiple Signal Classification）算法为原型,同时根据语音信号在应用中的特点,介绍了一种基于近场的信号模型,并以此为依据对算法进行改进,使声源定位更加精确。对此算法进行了仿真实验,仿真结果表明,此算法具有良好的定位性能,并随着信号信噪比的上升,性能有所提高。     

GNSS accuracy enhancement based on pseudo range error estimation in an urban propagation environment

For new ITS applications, positioning solutions will require to be more accurate and available. The most common technique used today is composed of a GPS receiver, sometimes aided by other sensors. GPS, and GNSS in general, suffer from masking effects and propagation disturbances in urban areas that cause biases on pseudo range measurements. Mitigation solutions sometimes propose to detect and exclude outliers but in land transportation applications, such a decision reduces dramatically the service availability and thus, the interest of satellite-based solutions. In order to optimize the use the satellites received, we propose a new positioning algorithm based on signals only with pseudo range error modeling in association with an adapted filtering process. The model and the filter have been validated with simulation data performed along an urban bus line and have shown that both positioning error and availability can be improved. Along the trajectory tested, the mean accuracy has been reduced from 5.3 m with a classical filter to 2.6 m with our algorithm with 89% of the points more accurate than 5 m instead of 64% before.     

基于人工蜂群算法的DV-Hop定位改进

针对无线传感器网络无需测距依赖的DV-Hop定位算法节点定位精度不高的问题,将鲁棒性强、收敛速度快且全局寻优性能优异的人工蜂群算法引入到DV-Hop算法的设计中,提出了一种ABDV-Hop(Artificial Bee ColonyDV-Hop)算法。该算法在传统DV-Hop算法的基础上,利用节点间的距离和锚节点的位置信息,在DV-Hop算法的最后阶段,通过建立目标优化函数,实现对未知节点坐标的估计。仿真结果表明,与传统DV-Hop算法相比,在不增加传感器节点的硬件开销的基础上,改进算法能有效降低定位误差。     

动态环境下基于深度学习的语义SLAM算法

针对应用场景中存在的运动物体会降低视觉同步定位与地图构建（SLAM）系统的定位精度和鲁棒性的问题,提出一种基于语义信息的动态环境下的视觉SLAM算法。首先,将传统视觉SLAM前端与YOLOv4目标检测算法相结合,在对输入图像进行ORB特征提取的同时,对该图像进行语义分割;然后,判断目标类型以获得动态目标在图像中的区域,剔除分布在动态物体上的特征点;最后,使用处理后的特征点与相邻帧进行帧间匹配来求解相机位姿。实验采用TUM数据集进行测试,测试结果表明,所提算法相较于ORB-SLAM2在高动态环境下在位姿估计精度上提升了96.78%,同时该算法的跟踪线程处理一帧的平均耗时为0.065 5 s,相较于其他应用在动态环境下的SLAM算法耗时最短。实验结果表明,所提算法能够实现在动态环境中的实时精确定位与建图。     

动态场景下基于语义和光流约束的视觉同步定位与地图构建

针对动态场景下的定位与静态语义地图构建问题,提出了一种基于语义和光流约束的动态环境下的同步定位与地图构建（SLAM）算法,以降低动态物体对定位与建图的影响。首先,对于输入的每一帧,通过语义分割获得图像中物体的掩模,再通过几何方法过滤不符合极线约束的特征点;接着,结合物体掩模与光流计算出每个物体的动态概率,根据动态概率过滤特征点以得到静态特征点,再利用静态特征点进行后续的相机位姿估计;然后,基于RGB-D图片和物体动态概率建立静态点云,并结合语义分割建立语义八叉树地图。最后,基于静态点云与语义分割创建稀疏语义地图。公共TUM数据集上的测试结果表明,高动态场景下,所提算法与ORB-SLAM2相比,在绝对轨迹误差和相对位姿误差上能取得95%以上的性能提升,与DS-SLAM、DynaSLAM相比分别减小了41%和11%的绝对轨迹误差,验证了该算法在高动态场景中具有较好的定位精度和鲁棒性。地图构建的实验结果表明,所提算法创建了静态语义地图,与点云地图相比,稀疏语义地图的存储空间需求量降低了99%。     

面向半稠密三维重建的改进单目ORB-SLAM

构建更详细的地图以及估计更精准的相机位姿一直都是同时定位与地图构建（Simultaneous Localization And Mapping,SLAM）技术所追求的目标,但是以上目标与实时性要求、较低的计算代价和受限的计算资源条件是相矛盾的。提出一种在单目ORB-SLAM（Oriented FAST and Rotated BRIEF-SLAM）方法的基础上利用关键帧中提取到的直线特征进行半稠密三维重建的方法。由ORB-SLAM实时提供一组关键帧及其对应的相机位姿信息和一系列地图点,提出一种关键帧再剔除算法进一步减少冗余帧数目,使用直线段提取方法提取各帧中的直线段,使用纯几何约束方法对以上检测得到的直线段进行匹配,生成一个由直线段构成的半稠密三维场景模型。实验结果表明新方法持续稳定的运行,能在低计算代价条件下快速地在线三维重建。