一种基于改进型PN学习的在线长时目标跟踪算法

文中主要讨论针对未知目标的长时跟踪问题。在一帧图像中,目标是由其位置和外观表征的;在连续的视频帧中,需要确定出每一帧中目标的位置和外观特征或者在某一帧中标识出目标是不可见的。因此对PN半监督机器学习算法进行改进,并在此基础上整合模板匹配技术、背景抽离技术和主成分分析技术,提出一种基于检测的在线长时目标跟踪算法。针对该跟踪算法详细阐述了其跟踪架构和算法执行流程,并精心筛选出5个测试视频流。实验结果表明,该跟踪算法具有较强的适应能力和跟踪能力。     

基于面向对象Petri网的知识库模型

根据Petri网能够对知识的细节进行抽象的特点及对知识库系统应用的需求,利用VC 对Petri网进行了类的封装,建立了基于面向对象Petri网的知识库模型,实现了对知识库的动态维护,并增加了单步推理和反向执行的功能,同时也改进了规则维护算法。     

基于RGB-D的在线多示例学习目标跟踪算法

基于2D特征的目标跟踪算法缺少3维信息,因此在目标尺度、姿态变化和平面旋转时会引起跟踪不稳定易丢失目标的问题,为此提出一种基于RGB‐D的在线多示例学习目标跟踪算法。利用深度数据的特性在深度图中和RGB图中构建多尺度空间,提取多尺度的 Haar‐D特征和 Haar特征;利用多实例学习策略将多尺度的 Haar‐D特征和 Haar特征融合。实验结果表明,该算法能很好得处理室内或室外环境下目标姿态变化、平面旋转和部分遮挡的问题。     

A hybrid mobile object tracker based on the modified Cuckoo Search algorithm and the Kalman Filter

Most revolutionary algorithms are inspired from the behavior of natural species. This inspiration can be drawn from their reproductive behavior, flying mode, or even their ways of communication. One of the most efficient metaheuristics in a discrete search space is the Cuckoo Search algorithm, inspired by the Cuckoo?s reproductive behavior and combined with the Lévy flight pattern adopted by many animals and insects. In this paper, we present a new tracking approach, the Hybrid Kalman Cuckoo Search tracker, using a modified version of the Cuckoo Search algorithm combined with the well-known Kalman Filter. The Cuckoo Search algorithm is combined with the prediction step adopted by the Kalman Filter to enhance the initial population?s quality. Using the Hybrid Kalman Cuckoo Search tracker, we can efficiently explore the search space in order to locate an object?s position from one frame to the next. The Lévy flight model is also modified in order to re-adapt the Lévy step size as the algorithm approaches the desired solution. The Hybrid Kalman Cuckoo Search tracker is tested on a variety of datasets including one where we incorporated different situations, as well as some videos from the CAVIAR, SPEVI, and other datasets. The comparative study results show that the proposed algorithm outperforms the Particle Swarm Optimization based tracker, especially in terms of computation time.     

An image caption method based on object detection

Multimedia Tools and Applications - How to represent image information more effectively is the key to the task of image caption. In the existing research, a large number of image caption methods...     

An oscillatory neural model of multiple object tracking

An oscillatory neural network model of multiple object tracking is described. The model works with a set of identical visual objects moving around the screen. At the initial stage, the model selects into the focus of attention a subset of objects initially marked as targets. Other objects are used as distractors. The model aims to preserve the initial separation between targets and distractors while objects are moving. This is achieved by a proper interplay of synchronizing and desynchronizing interactions in a multilayer network, where each layer is responsible for tracking a single target. The results of the model simulation are presented and compared with experimental data. In agreement with experimental evidence, simulations with a larger number of targets have shown higher error rates. Also, the functioning of the model in the case of temporarily overlapping objects is presented.     

基于图像一致性计算的目标识别算法

视觉计算模型集合了人类视觉系统(HVS)的复杂特征,并模拟了视觉输入的分层感知表达。自底向上机制是现代模型中最常见的特征,是指无意识的注意,所提出的一致计算方法模拟自底向上视觉注意,并通过一致区域的计算来达到目标识别的目的。所提模型主要基于对HVS行为的目前的理解,使用对比敏感度函数、感知分解、视觉掩蔽形成一个神经性视觉空间,并在此基础上使用center-surround交互、感知编组和显著图的建立来得到最终的显著图。所提模型的性能通过使用自然图像来进行评估,并将其结果与参照的经典的自底向上模型进行对比,结果表明该模型实效性高。     

基于特征点匹配的自适应目标跟踪算法

由于实际场景复杂多变,目标在运动过程中往往会出现形变、遮挡等问题,增加了跟踪的难度。为了解决上述问题,提出一种基于特征点匹配的自适应目标跟踪算法。算法初始化时在选定的目标区域内提取特征点,跟踪过程中通过对前后两帧的特征点进行匹配,计算出目标的位置、尺度和旋转变化,进而实现对目标的跟踪。同时通过对特征点的不断更新,可以使算法具有一定的抗遮挡能力。实验表明,该方法在实际应用中效果很好。     

基于STM32的逐阳帆控制系统设计

针对传统太阳能跟踪系统现场调试复杂、可靠性不够高的问题,提出一种基于STM32的太阳能跟踪系统设计。该系统为单轴跟踪系统,通过获取太阳能板的地理位置和当前时间信息用一定算法算出太阳的方位角,驱动电机,实现对太阳的跟踪;采用基于Zig Bee技术的无线通讯系统,具有群簇控制能力,简化现场调试过程;通过Mod Bus协议实现控制系统信息上报,便于后台管理;提供多种工作模式,提高系统的抗风、抗雪性能;通过在控制芯片片内Flash写入备份程序,保证系统主程序出现问题后,系统跳转至备份程序继续运行,提高系统的可靠性。在实际现场应用中,该系统具有系统运行稳定、升级维护方便、使用寿命长的特点。     

基于BOPPPS模型的在线混合多元教学模式研究

随着疫情防控的常态化,在线混合多元教学也从应急趋向常态。为解决教学过程中难以把握课堂教学节奏,课堂参与度不高、互动性差、反馈不及时等问题,提出将BOPPPS模型的六大元素融入在线教学全过程,构建基于BOPPPS的在线混合多元教学模式,强化以学生为中心的教学理念,实现师生全方位深度参与的互动教学,有效提高在线课堂的教学质量。     

Visual tracking based on Distribution Fields and online weighted multiple instance learning

This paper presents an improved multiple instance learning (MIL) tracker representing target with Distribution Fields (DFs) and building a weighted-geometric-mean MIL classifier. Firstly, we adopt DF layer as feature instead of traditional Haar-like one to model the target thanks to the DF specificity and the landscape smoothness. Secondly, we integrate sample importance into the weighted-geometric-mean MIL model and derive an online approach to maximize the bag likelihood by AnyBoost gradient framework to select the most discriminative layers. Due to the target model consisting of selected discriminative layers, our tracker is more robust while needing fewer features than the traditional Haar-like one and the original DFs one. The experimental results show higher performances of our tracker than those of five state-of-the-art ones on several challenging video sequences.     

一种基于联合轮廓特征矢量的目标识别方法

针对基于形状特征进行目标识别的方法存在的不足,提出一种联合轮廓不变矩特征和轮廓几何特征的识别方法;针对不同的待识别目标,采集足够数量的训练样本,统计每一个轮廓特征的均值、标准差和变异系数;并据此对这些轮廓特征进行动态筛选和加权,建立起待识别目标的联合轮廓特征矢量模型.在线识别时,提取场景目标的联合轮廓特征矢量,对其进行...     

一种基于ACM程序设计竞赛在线评测系统解决方案

分析了一种基于ACM程序设计竞赛在线评测系统的基本原理及系统的构成,重点阐述了程序性能评判原理及实现方法.对通信安全、资源占用等关键问题给出了相应的解决方案,主要模块给出了相应代码.     

An autowave based methodology for deformable object simulation

This paper presents a new methodology for deformable object simulation by drawing an analogy between autowaves and elastic deformation. The potential energy stored in an elastic body as a result of a deformation caused by an external force is propagated among mass points by non-linear autowaves. The novelty of the methodology is that autowave techniques are established to describe the potential energy distribution of a deformation for extrapolating internal elastic forces, and non-linear material properties are modelled with non-linear autowaves other than geometric non-linearity. A haptic virtual reality system has been developed for deformation simulation with force feedback. The proposed methodology not only deals with large-range deformations, but also accommodates isotropic, anisotropic and inhomogeneous materials by simply modifying diffusion coefficients.     

WISDOM: Web intrapage informative structure mining based on document object model

To increase the commercial value and accessibility of pages, most content sites tend to publish their pages with intrasite redundant information, such as navigation panels, advertisements, and copyright announcements. Such redundant information increases the index size of general search engines and causes page topics to drift. In this paper, we study the problem of mining intrapage informative structure in news Web sites in order to find and eliminate redundant information. Note that intrapage informative structure is a subset of the original Web page and is composed of a set of fine-grained and informative blocks. The intrapage informative structures of pages in a news Web site contain only anchors linking to news pages or bodies of news articles. We propose an intrapage informative structure mining system called WISDOM (Web intrapage informative structure mining based on the document object model) which applies Information Theory to DOM tree knowledge in order to build the structure. WISDOM splits a DOM tree into many small subtrees and applies a top-down informative block searching algorithm to select a set of candidate informative blocks. The structure is built by expanding the set using proposed merging methods. Experiments on several real news Web sites show high precision and recall rates which validates WISDOM'S practical applicability.     

An improved small object detection method based on Yolo V3

Pattern Analysis and Applications - In this paper, an improved algorithm based on Yolo V3 is proposed, which can effectively improve the accuracy of small target detection. First of all, the...     

An approach for moving object recognition based on BPR and CI

A recognition and classification method of multiple moving objects in traffic based on the combination of the Biomimetic Pattern Recognition (BPR) and Choquet Integral (CI) is proposed. The recognition process consists of three stages. At the first stage, vehicles and pedestrians are detected in video images and the area, the shape and the velocity features are obtained by classical methods. At the second stage, BPR is used to classify the Zernike moments extracted at the first stage. At the last stage, CI is then adopted for multi-features fusion based on the output of BPR, and the area and the velocity features obtained at the first stage to improve the recognition accuracy. Experiment results show that this approach is efficient.     

一个基于Web服务的在线优化和监控系统

在流程工业,许多信息集成系统通过CORBA／Agent技术来实现,这些集成方案在实时性,安全性,以及数据通信的稳定性等方面尚待改进。为了研究更加合理的集成方案,实现了一个基于Web服务的在线优化和监控系统,在这个系统中,专业软件Matlab,G2,GAMS被分别封装成Web服务并在UDDI注册中心注册,然后实现了这些Web服务的集成。最后,通过在尼泊丁乙酯合成过程中的应用．证明了该在线优化和监控平台的有效性和适用性。     

改进ALOHA算法在RFID多目标识别中的应用

RFID系统中,由于多标签引起的冲突一直是影响系统性能的大问题。ALOHA算法是运用比较普遍的一种防冲突算法,在标签数目较少的情况下,现有的ALOHA算法也有较高的效率,但是随着标签数目的急剧增加,算法时间也成指数往上增长,本文提出一种改进的ALOHA算法,在标签总数未知的情况下,动态估计标签数目,以选择合适的窗口大小,获得较高的系统效率。仿真结果表明,跟传统ALOHA算法相比,性能有明显改善。