Image Quality Evaluation in Security Imaging Systems

The subjective image quality of image or video information is a crucial item in security imaging systems. During the last five years our lab has tested and verified various approaches to the image compression for security purposes and the evaluation of subjective image quality. In the paper we discuss selected important facts related to the subjective image quality evaluation and we present some anomalous experimental behavior of image compression techniques. An object-defined approach is investigated and advantageous characteristics of chosen methods are deployed to achieve the optimal performance of the surveillance video coder. Among others, we propose to use the artificial neural network (ANN) to predict resulting image quality rating scores. The proposed quality assessment model has been trained and tested using a set of grayscale images distorted by selected image compression algorithms     

基于ASM实现视频中物体的定位

对目标进行有效跟踪是目前许多国家获取信息的重要手段,主动形状模型(ASM)主要应用于灰度图像中物体的跟踪与定位,本文针对Koschan等提出的结合金字塔模型的ASM方法作进一步改进,使之应用于视频(本文视频采用MPEG数字视频压缩编码标准)中物体的定位:首先将视频解码还原成图像序列,从人眼视觉特征出发,将RGB颜色模型转换为HSV颜色模型,用色调信息取代灰度信息进行物体定位;并研究图像序列帧之间物体的重合度对提高定位效率的作用.实验结果说明在ASM中使用色调信息能有效地实现视频中的物体定位.     

Compression standards and alternative methods for video telecom

The complex video compression methods in the process of being standardized, which are designed to reduce transmission needs by detecting and coding image redundancy temporally and spatially between frames, are examined. Methods involving fractals, and wavelets may achieve more efficient coding by defining spatial formats and equations more applicable to the specific image than the more general-purpose transforms of the standards. A newer method involves the capture of an entire database of image characteristics and identifies and stores the 3-D motion in the image field. The image can be reproduced at high compression rates at remote locations. Telecommunication products that facilitate the operation and use of video compression systems are presented     

无人机地面站图像压缩传输系统设计与应用

针对无人机地面指挥控制系统要实现互连、互通、互操作的网络化要求,设计了视频信号实时网络传输和显示系统。系统由基于DSP的服务器端和通用客户端播放器组成,服务器端通过设置并行任务完成视频信号的实时采集、编码和发送,客户端完成视频信号的实时接收、解码和播放,从而使系统实现了图像信息在地面站所有显示终端上的实时显示。实验结果表明,系统完全满足无人机地面站系统功能及指标要求,并且通过网络化技术节省了地面站宝贵空间资源,系统设计方法对同类型系统具有一定借鉴意义。     

Spatio-temporal pattern recognition using hidden Markov models

A spatio-temporal method for identifying objects contained in an image sequence is presented. The Hidden Markov Model (HMM) technique is used as the classification algorithm, making classification decisions based on a spatio-temporal sequence of observed object features. A five class problem is considered. Classification accuracies of 100% and 99.7%, are obtained for sequences of images generated over two separate regions of viewing positions. HMMs trained on image sequences of the objects moving in opposite directions showed a 98.1% successful classification rate by class and direction of movement. The HMM technique proved robust to image corruption with additive correlated noise and had a higher accuracy than a single-look nearest neighbor method. A real image sequence of one of the objects used was successfully recognized with the HMMs trained on synthetic data. This study shows the temporal changes that observed feature vectors undergo due to object motion hold information that can yield superior classification accuracy when compared with single-frame techniques     

Recognition and Self-Organization of Nodes into DTDMA Nets

An effective relay management solution applicable to multiple terminal ground-to-ground or ground-to-air line-of-sight communication environments is described. Algorithms are developed which enable terminals first to recognize the existence or availability of other terminals, and second, to self-organize a community of terminals rapidly into local nets without the need for a master control terminal. Computer simulation results show how a static or dynamically changing user geometry can be managed. Network connectivity is provided automatically and the system protects itself against the loss of a master user by not requiring one.     

基于概率模型运动检测技术的视频对象分割技术研究

MPEG-4最重要的特点是用音频-视频对象来描述内容和进行编码。这就需要按照视频对象进行视频图像分割,而视频对象具有时域和空域这两大特点,而时域分割又占主要的地位。研究了一种时域分割算法,即研究了一种运动检测技术方案,采用Til Aach,Andre Kaup提出的基于概率模型的运动检测技术,用Gauss模型描述噪声引起的像素值变化,将运动目标和有噪声的背景区别开来。最后,采用二值开闭重建滤波器来去除前景和背景中的“小洞”,从而获取了最终的运动检测掩码。     

MAP-CA在视频压缩中的应用

信息时代的重要特征是信息的数字化,但数字化的视频数据量是非常巨大的。为了使数字化的视频信号更有效地传输,对其进行压缩势在必行。应用MAP-CA这个DSP芯片可以对视频图像进行MPEG-4标准的压缩,压缩比可以达到1000:1。在公用电话线上就可以连续传输视频,并能保持图像的质量,最高图像清晰度为768×576,可以达到接近DVD的画面效果。     

Multi-view space object recognition and pose estimation based on kernel regression

The application of high-performance imaging sensors in space-based space surveillance systems makes it possible to recognize space objects and estimate their poses using vision-based methods. In this paper, we proposed a kernel regression-based method for joint multi-view space object recognition and pose estimation. We built a new simulated satellite image dataset named BUAA-SID 1.5 to test our method using different image representations. We evaluated our method for recognition-only tasks, pose estimation-only tasks, and joint recognition and pose estimation tasks. Experimental results show that our method outperforms the state-of-the-arts in space object recognition, and can recognize space objects and estimate their poses effectively and robustly against noise and lighting conditions.     

基于运动形态学的掠地飞行器视频检测方法

 结合数学形态学、视频图像运动分析以及数学统计分析方法,提出了一种用于空中预警控制系统(AWACS)的小型掠地飞行器运动形态学视频检测方法。该方法首先应用形态学tophat滤波提取出视频图像中的可疑目标(SO),并求取SO的运动参数,利用真实目标和类目标干扰的不同运动特性,应用数学统计的方法对各运动参数进行分析以剔除部分类目标干扰,从而获得潜在目标(PT)的灰度分布和运动参数。在应用形态学tophat滤波器进行可疑目标提取中,一种新的金字塔型结构元的引入有效减少了虚警数量。外场试验表明,该检测方法能够有效抑制航拍掠地飞行器视频图像中的地物干扰,降低虚警目标的数量。     

面向企业管理系统的动态表单技术研究

企业管理系统中录入表单的重复设计和开发是制约系统开发效率和质量的重要问题.本文通过将录入表单划分为模板、页、网格和列四种对象建立对表单的完备表达.页是模板的实例化,模板包含网格、网格包含列.针对四种对象设计了通用数据库表结构,用以描述表单中四种对象的组成关系和建立企业业务数据存储空间.最后构建面向对象的类库,管理系统开发只需要通过调用类库就可以实现动态表单的构建和录入信息存储而无需重复设计和开发数据库.     

基于DSP和FPGA的视频编码器协同设计与算法优化实现

采用DSP和FPGA协同技术设计实现了一个高性能的MPEG-4视频编码器。FPGA模块完成视频采集、YUV分离、数据I/O等功能,而使用DSP专一进行视频压缩编码。针对DSP片内资源特点设计了片内存储器数据分配方案,并根据该方案优化了MPEG-4视频压缩的数据流模式。提出了基于宏块空间复杂度的宏块类型判断算法,有效地降低了视频压缩算法的计算复杂度。测试结果表明,采用MPEG-4视频标准该视频编码器每秒能够压缩39.2帧CIF图像。     

A shortcut to marking 3D target curves on curved surface via a galvanometric laser scanner

Marking arbitrary three-dimensional(3D) target curves on given objects with curved surface is required in many industrial fields, such as fabric prepreg placement in composite material part fabrication, product assembly, surface painting for decoration, etc. A shortcut to the solution of this intractable problem is proposed by utilizing a galvanometric laser scanner(GLS) with the aid of a camera. Without using the existing tedious GLS calibration procedures,the proposed method directly establishes a mapping between the 3D coordinates of the laser spots on the object surface and the control voltages of the scanner. A single-hidden layer feedforward neural network(SLFN) is employed to model the mapping. By projecting a dense grid of laser spots on the object to be marked and simultaneously taking only one image, the SLFN model is trained in minutes via a linear solving mechanism. Experiments demonstrate that the trained SLFN model has a good generalization performance for marking 3D target curves. The 3D laser marking errors on experimental objects are less than 0.5 mm. The proposed method is especially suitable for on-site use and can be conveniently extended to multiple GLSs for marking large complex objects.     

一种三维物体的视觉识别方法研究

研究了一种利用二维图像识别三维物体的方法。通过颜色特征提取物体的有效区域．使用链码描述了区域中三维物体的形状特征，并形成物体的形状特征向量。将该特征向量作为所设计的BP神经网络的输入进行物体匹配识别，网络输出为属于某种物体的隶属度。通过在各种光照环境下不同三维物体的二维彩色图像进行实验，证明了所提出方法的有效性。     

单目相机物体位姿估计方法研究

现有的机器视觉通常以边缘轮廓和角点作为特征,因此要求背景单一,对环境结构化依赖程度高。为了拓展机器人的应用范围,使其脱离结构化的环境,提出了一种基于SIFT特征点和PNP技术的单目相机估计目标物体位姿的方法。以BumbleBee双目相机为硬件基础,以C++为开发平台,结合了Eigen计算库、OpenCV图像处理库和Triclops库,开发了单目视觉位姿估计算法,实现在复杂背景下对表面纹理较为丰富的物体的位姿估计。利用试验对所提方法进行了验证,试验结果表明,该算法具有较高的估计精度,可以作为机器抓取的依据。     

基于ADV202的视频压缩在航空领域中的应用研究

主要介绍了基于JPEG2000压缩标准,采用ADV202芯片视频图像压缩的设计方法,在航空领域可用于视频监控记录。给出了基本的硬件电路框图和软件流程框图,并介绍了基于FPGA实现ADV7402的I2C编程、ADV202的初始化、USB的操作及ADV202的级联使用方法。     

基于加权的可见光与红外光图像融合算法

红外图像所含边缘等细节偏少、可见光又容易受外部环境干扰,融合图像可以提供更全面的信息,符合人或机器的视觉特性,为图像进一步分析、识别等提供基础。提出一种比值与梯度加权的可见光与红外光图像融合算法,结合小波变换在图像分解中的特性及信号集中的特点,将小波变换应用于红外光和可见光图像融合中可以提高融合信息的理解能力。针对分解获得的低频系数主要反映图像细节信息的特点,对低频系数采用比值加权分析融合规则;针对分解获得的高频系数主要反映图像边缘信息特征的特点,对高频系数采用改进边缘检测算子梯度加权的融合规则。选取多组图像进行了不同融合规则实验对比分析,通过客观评价指标进行评价,改进的融合算法可以获得较清晰的融合图像,可以增加图像的互补信息,并能较好地提高融合图像的清晰度。     

Video surveillance applications using multiple views of a scene

Automatic video surveillance techniques are used to detect intruders within a scene. This task is mostly reduced to the problem of detecting moving objects evaluating image sequences of a monocular camera. An essential problem of this monocular approach is its inability to measure the 3D-size and 3D-position of objects reliably, as object size and velocity are estimated within the 2D-image plane. To include 3D-information about the scene an approach using a second camera is proposed in this paper which combines the evaluation of the measurement data of the two cameras using an efficient 3D-scene model. Here, two cameras are used with an overlapping field of view, which represents an installation often used in existing video surveillance applications. It is shown that using the combined evaluation of the two cameras, the false detection rate in the case of moving shadows, leaves, birds and insects or blindings can be further reduced compared to a pure monocular evaluation     

靶场试验实况信息监测及质量检测分析

为解决试验测控实况信息的可视化作用与全链路实况信息缺乏质量监测功能的矛盾日益突出的问题,就实况信息监测及质量检测分析开展研究。具体采用模块化的监测和质量分析方法,针对整个实况信息运行系统中的有效节点展开监测,主要帮助系统判定视音频流、IP码流的信息故障点,实时分析流信息指标,诊断网络实况信息的传输质量,通过对原始视频图像文件压缩前后逐帧度量及损伤映射分析,检测图像信号模糊不清,拖尾或边缘锐化等问题,为快速排查和判断实况信号故障信息提供了验证结果。最终,为实况信息的高质量运行提供监测手段和检测依据。