一种构建于DSM的移动对象的全时态索引方法

移动对象索引技术是移动对象数据库这个新兴的热点领域中的关键技术之一.针对该技术处理数据的繁琐复杂特性,提出构建于DSM的移动对象索引方法 DSM_MSMON,在分布式系统中并行的管理移动对象的信息,支持更新和查询操作.DSM_MSMON统一了单机和多机的内存管理策略,解决了DSM系统中的数据定位、一致性维护、负载平衡和可扩充性等主要问题,有效地提高了移动对象索引的效率.文中给出DSM_MSMON的设计思想和模型,并分析了DSM_MSMON的关键技术和程序流程.实验结果表明,该方法要优于MSMON结构.     

Dynamic integration of height maps into a 3D world representation from range image sequences

Integration of 21/2D sketches obtained at different observation stations into a consistent world (or object) representation is one of the central issues in computer vision and robotics. The resolution and accuracy of 21/2D sketches may be different from one view point to another, and inconsistent data between different observations may occur. This article presents an approach to building a spatiotemporal representation of dynamic scenes including moving objects from a sequence of range images taken by a moving observer. A range image is transformed into a height-map representation, which is segmented into the ground plane and objects on it. In order to capture the resolution and accuracy of the range information and the consistency of the height information between different height maps, we define a reliability measure of the height information for each bucket on the height map. Using this reliability, the system finds the correspondences of both static and moving objects between different observations, and successively refines the height information and its reliability with newly acquired data, dealing with inconsistent data. Final representation of the integrated height map consists of the time stamp of the last observation, region labels of static and moving objects and their spatiotemporal properties such as height information, its reliability, and the velocities of both the observer and independently moving objects. We applied the method to road scenes physically simulated by landscape toy models and show the experimental results.     

时空相点移动对象数据索引PM-Tree

随着移动定位技术和无线通讯技术发展,移动对象的应用领域越来越广阔.位置随时间而变化的移动对象产生的时空数据具有规模大、多维性、结构复杂和关系复杂等特点.由于移动对象的运动轨迹大多被限定在特定的交通网络中,因此基于路网的移动对象索引成为时空数据索引研究的一个重要应用分支.目前,针对移动对象历史数据的区域查询优化的研究重点...     

Robust high-quality interpolation of regions to moving regions

With the rise of moving object databases it is possible to store and process spatial and temporal data, for example geometrical structures together with the information about how these behave over intervals of time. For simple objects like moving points the spatiotemporal development is derived from the start and end position in space and time, which is then linearly interpolated. For moving regions, especially with changing shapes, it is more challenging to obtain the necessary data to represent them. An elegant and intuitive solution is to create an algorithm, which automatically interpolates the moving region from the start and end shape over a specified time interval. Two papers on this topic have been published in the past, each focussing on different aspects of this so-called Region Interpolation Problem. This paper tries to combine the advantages and improve these approaches to provide high-quality interpolations while maintaining robustness even in border cases. This results in the implementation of a library, which can be easily integrated into existing moving objects database systems, as for example the DBMS Secondo developed at the FernUniversität in Hagen.     

A framework for unsupervised mesh based segmentation of moving objects

Multimedia analysis usually deals with a large amount of video data with a significant number of moving objects. Often it is necessary to reduce the amount of data and to represent the video in terms of moving objects and events. Event analysis can be built on the detection of moving objects. In order to automatically process a variety of video content in different domain, largely unsupervised moving object segmentation algorithms are needed. We propose a fully unsupervised system for moving object segmentation that does not require any restriction on the video content. Our approach to extract moving objects relies on a mesh-based combination of results from colour segmentation (Mean Shift) and motion segmentation by feature point tracking (KLT tracker). The proposed algorithm has been evaluated using precision and recall measures for comparing moving objects and their colour segmented regions with manually labelled ground truth data. Results show that the algorithm is comparable to other state-of-the-art algorithms. The extracted information is used in a search and retrieval tool. For that purpose a moving object representation in MPEG-7 is implemented. It facilitates high performance indexing and retrieval of moving objects and events in large video databases, such as the search for similar moving objects occurring in a certain period.     

Composition and Retrieval of Visual Information for Video Databases

This paper presents a new visual aggregation model for representing visual information about moving objects in video data. Based on available automatic scene segmentation and object tracking algorithms, the proposed model provides eight operations to calculate object motions at various levels of semantic granularity. It represents trajectory, color and dimensions of a single moving object and the directional and topological relations among multiple objects over a time interval. Each representation of a motion can be normalized to improve computational cost and storage utilization. To facilitate query processing, there are two optimal approximate matching algorithms designed to match time-series visual features of moving objects. Experimental results indicate that the proposed algorithms outperform the conventional subsequence matching methods substantially in the similarity between the two trajectories. Finally, the visual aggregation model is integrated into a relational database system and a prototype content-based video retrieval system has been implemented as well.     

基于公路网的移动对象数据库数据模型

移动对象数据库对大量移动对象的位置信息进行管理,能够支持传统数据库不能进行的时空查询,考虑到大多数移动对象的运动都固定在已知的路线中,基于公路网的移动对象数据模型、通过对公路网拓扑图的数字化转换,能够对移动对象进行有效的管理,该文采用实时平均法来反映每条线路的动态运行情况,对移动对象未来位置进行了精确预测。     

GPU环境下加速移动对象可视化更新的方法研究

移动对象数据具有规模大、更新频繁的特点,对数据可视化具有较高的性能要求。当数据规模增大时,实时加载数据进行可视化的性能效率会随之降低。为了提高移动对象可视化的效率,提出了GPU环境下的移动对象更新方法,并结合移动对象特征设计出并行查询方案。同时,优化了移动对象的更新函数,通过比较临近的两次可视化查询的时间区间,找出需要更新的时间片,对其进行相应的更新,从而避免了整个时间区间的更新。实验使用了数据规模为400万到1 000万的合成数据集,和包含约960万个采样点的真实出租车数据集。实验结果表明,与CPU上的R-Tree查询、GPU上的R-Tree查询和CPU上更新函数中的串行索引查询方法相比,所提方法具有较好的查询性能,加速比最高可达18.48。移动对象更新函数优化后,当临近的两次可视化查询时间区间完全重叠时,加速效率接近100%。     

基于大数据分析的移动对象轨迹预测方法

对移动对象的轨迹预测将在移动目标跟踪识别中具有较好的应用价值。移动对象轨迹预测的基础是移动目标运动参量的采集和估计,移动目标的运动参量信息特征规模较大,传统的单分量时间序列分析方法难以实现准确的参量估计和轨迹预测。提出一种基于大数据多传感信息融合跟踪的移动对象轨迹预测算法。首先进行移动目标对象进行轨迹跟踪的控制对象描述和约束参量分析,对轨迹预测的大规模运动参量信息进行信息融合和自正整定性控制,通过大数据分析方法实现对移动对象运动参量的准确估计和检测,由此指导移动对象轨迹的准确预测,提高预测精度。仿真结果表明,采用该算法进行移动对象的运动参量估计和轨迹预测的精度较高,自适应性能较强,稳健性较好,相关的指标性能优于传统方法。     

A Kalman filter updating method for the indoor moving object database

A moving object database (MODB), a database representing information on moving objects, has many uses in a wide range of applications, such as the digital battlefield and transportation systems. In the transportation system, an MODB processes queries such as “How long should I wait until the next bus arrives here?” Therefore, location information on moving objects reflects the most important data the MODB has to manipulate. Most moving objects are equipped with a GPS (Global Positioning System) unit that sends location information to the MODB. However, GPS signals are usually very weak inside enclosed structures; thus, locating indoor moving objects requires more than the GPS. In this regard, indoor positioning for location-based services (LBSs) has been an important research topic for the last decade. There are many other differences between indoor and outdoor MODBs. For examples, the area where the indoor moving objects are moving around is much smaller than where the outdoor moving objects are moving around, and the speed of indoor moving objects is much slower than that of outdoor ones. Therefore, the indoor moving object database (IMODB) should be studied separately from the outdoor MODB or the MODB.One of the most important problems that the MODB has to solve is the updating problem. In this regard, this paper proposes an updating method of IMODBs for location-based services. Our method applies the Kalman filter to the most recently collected series of measured positions to estimate the moving object’s position and velocity at the last moment of the series of the measurements and extrapolates the current position with the estimated position and velocity. If the difference between the extrapolated current position and the measured current position is less than the threshold, that is, if the two positions are close, we skip updating the IMODB.When the IMODB requires information on the moving object’s position at a certain moment T, it applies the Kalman filter to the series of the recorded measurements at the moments before T and extrapolates the position at T with the Kalman filter in the same manner as the updating process described earlier. To verify the efficiency of our updating method, we applied our method to a series of measured positions obtained by employing the fingerprinting indoor positioning method while we walked through the test bed. We then analyzed the test results to calculate savings of communication cost and error.     

粒子滤波的视频目标跟踪算法研究

目标跟踪是计算机视觉和图像处理的一个重点课题,在视频监控、机器人视觉导航以及智能交通控制中具有广泛的应用前景.通过粒子滤波技术,研究了如何整合颜色特征、前景信息和积分图运算等技术实现视频目标跟踪的粒子滤波算法.在对目标进行分割中采用了混合高斯背景建模方法;同时结合积分直方图的计算方法对颜色特征进行分段统计及相互遮挡的判断,实现基于粒子滤波的目标跟踪算法的优化,解决跟踪中诸如遮挡、光照变化、背景干扰、尺寸变化等难以解决的问题.实验结果表明提出的方法达到了预期目标.     

一种高效的移动对象伴随模式挖掘算法

从时空维度中寻找轨迹相似、时间相近的对象集合,即挖掘移动对象的伴随模式,在基于地理位置的用户行为分析中被广泛使用.然而现有移动对象相似性挖掘算法难以处理时间连续、空间离散、时空相关并且数据量大的时空数据.针对此类数据,设计基于滑动窗口、Apriori性质和贪心选择策略的宽度优先搜索算法,对移动对象伴随模式挖掘问题进行求解.同时结合基于哈希的迭代剪枝算法和基于摘要信息的剪枝算法,设计两层剪枝算法以去除冗余的中间结果.在真实数据上的实验结果表明,与仅使用哈希迭代或摘要信息的剪枝算法相比,该算法的剪枝效率较高,并且能够稳定去除99%以上的冗余数据.     

Modeling and Retrieval of Moving Objects

This paper presents a symbolic formalism for modeling and retrieving video data via the moving objects contained in the video images. The model integrates the representations of individual moving objects in a scene with the time-varying relationships between them by incorporating both the notions of object tracks and temporal sequences of PIRs (projection interval relationships). The model is supported by a set of operations which form the basis of a moving object algebra. This algebra allows one to retrieve scenes and information from scenes by specifying both spatial and temporal properties of the objects involved. It also provides operations to create new scenes from existing ones. A prototype implementation is described which allows queries to be specified either via an animation sketch or using the moving object algebra.     

采用时空信息的运动对象检测

针对复杂背景下的运动检测困难,提出了一种结合时域差分与尺度空间信息的运动对象检测算法。该方法首先以视频序列的第一帧作为初始背景,以相邻帧金字塔差分信息作为背景更新掩膜,并采用自适用的背景更新因子实现背景更新。在运动对象检测阶段,结合背景差信息与当前帧和背景帧金字塔差分信息,提取出运动对象。实验结果表明,该方法具有较好的实时性和自适应性,对噪声不敏感,有效提取运动对象。     

基于抑制光线强度变化影响的运动目标检测

在运动目标检测过程中,若两帧图像拍摄条件下光线强度不同,则运动目标检测的结果将会受到影响。据此,该文提出了抑制光线强度变化影响的运动目标检测方法。首先,对两帧图像通过自适应高斯核平滑滤波器处理,以降低图像的随机噪声对处理结果的影响;然后,根据两帧图像对应像素的灰度变化量信息,判断该两帧图像的光强变化程度;最后,根据本文所研究的抑制光线强度变化影响的方法,将运动目标从背景中检测出来。实验证明,取得了良好的效果。     

基于时空背景差的运动目标检测算法

假定图像序列的背景图像已经获得,提出一种基于时空背景差的运动目标检测算法.该算法融合背景差分、基于时间信息的帧间差分及基于空间信息的背景差分信息,得到真实运动物体的运动种子点,认为背景差分图像中包含运动种子点的连通区域为真实的前景目标,从而可以检测出正确而完整的前景目标.仿真实验表明,该算法可以避免背景模型对场景的表征不足及背景更新阶段造成的错误检测,即使在场景中存在微小运动的复杂环境下,仍能实现准确的运动分割.     

Boundary Extraction of Discrete Objects

One of the aims in the field of computer vision is to acquire information about the geometric and topological properties of objects in a three-dimensional world. First, we measure the objects and then we convert the measured data into geometric and topological properties of the objects. As an intermediate between the measured data and the geometric and topological properties, a representation of the objects for computers is desired. In this paper, we propose a representation of objects and their boundaries, which is based on combinatorial topology, and develop a method of extracting boundaries of objects from measured data. It is sufficient to extract boundaries, because they include information about the shape of the objects; the internal structure of the objects is not necessary for information about the shape. In addition, we prove that boundaries are uniquely obtained using our algorithm.     

一种自然环境下运动物体监测算法

提出了一种自然环境下运动物体的监测算法,该算法基于时空信息融合与特征识别,主要包括背景分析、前景提取、去除阴影、背景更新。其思想是将图像序列均转换为HSV颜色模型,并分析比较各像素点参数在某一时间段内的变化规律,通过判定公式的判定,便可区分出各像素点在某一帧中是属于背景点、运动物体点还是阴影点。该算法针对风、阳光、闪电等自然条件可能带来的影响进行了改进,并能够在光照突变、运动物体静止后融入背景、背景物体转为运动等情况下智能更新背景,适用于自然环境下运动物体的监测。     

移动对象数据库的查询方法研究

最近,移动对象数据库(Moving ObjectsDatabases,简称MOD)技术受到大量的关注.在现有的方法中,很多是针对管理移动对象动态改变的信息的应用.这些技术的缺点是它们只注意当前时刻的信息,而经常忽略了对过去和将来信息的管理.为了解决这个问题,本文提出一种新的基于推理技术的移动对象管理系统,将人工智能中的推理技术应用到现有的时空网格(ST-Grid)移动对象数据库中,用它来管理移动对象的相关信息.