A real-time multitarget tracking system with robust multichannel CNN-UM algorithms

This paper introduces a tightly coupled topographic sensor-processor and digital signal processor (DSP) architecture for real-time visual multitarget tracking (MTT) applications. We define real-time visual MTT as the task of tracking targets contained in an input image flow at a sampling-rate that is higher than the speed of the fastest maneuvers that the targets make. We utilize a sensor-processor based on the cellular neural network universal machine architecture that permits the offloading of the main image processing tasks from the DSP and introduces opportunities for sensor adaptation based on the tracking performance feedback from the DSP. To achieve robustness, the image processing algorithms running on the sensor borrow ideas from biological systems: the input is processed in different parallel channels (spatial, spatio-temporal and temporal) and the interaction of these channels generates the measurements for the digital tracking algorithms. These algorithms (running on the DSP) are responsible for distance calculation, state estimation, data association and track maintenance. The performance of the proposed system is studied using actual hardware for different video flows containing rapidly moving maneuvering targets.     

一种激光散斑法实时测量表面粗糙度的新方法

本文根据激光散斑相干性原理与理论,提出了用双达夫棱镜产生两束间距和夹角连续可调的平面光波同时照射粗糙表面,由1-D CCD采集散射光场的相干度信号,经过计算机对对比度的处理,能实时测量物体表面粗糙度的新方法。结果表明,该方法较现行测试法提高了判读精度,扩大了测量范围。     

基于声光效应的无线光通信光束扫描系统研究

将新型的光束偏转器件--声光器件引入ATP系统中,在建立了声光偏转器的偏转模型的基础上设计了一种快速、非机械的光束跟踪、瞄准系统.此系统与普遍使用的机械光束控制方式相比具有光束偏转速度快、控制方便、功耗小、可重复性好和体积小等诸多优点,显著的提高了光束对目标跟踪的实时性和稳定性.     

一种新型实时快速滚转角测量系统

针对滚转角测量系统中的实时快速图像处理需求,提出一种基于泰伯-莫尔效应的计算量小、快速高效并且精度高的图像处理算法。首先,对干涉图像进行频域滤波和空域中值滤波,去除噪声并平滑保留图像边缘;然后采用自适应二值化进行阈值分割,再进行细化并去除毛刺,剪切图像去除效果差的边缘数据;最后采用一种霍夫变换和最小二乘法求解条纹间隔进而求得滚转角。实验结果表明,测量误差小于2.5 arcsec,在PC机上完成一次运算时间约为400 ms。所采用的算法提高了图像处理速度。全部算法采用ANSI C编程实现,可移植到不同的嵌入式图像处理系统中,提高了算法的通用性和实用性。     

高精度太阳能聚光双轴定时跟踪控制系统设计

为提高太阳能电池光电转换效率,设计了不得一种太阳能双轴全自动聚光跟踪控制系统,使可以放多个太阳能电池模块的框架平台可以跟踪太阳光旋转,并保持框架平台上的太阳能电池与阳光入射角保持垂直,以达到光能的最大获取率。在考虑太阳的运动轨迹模型的基础上,设计出可以同时跟踪太阳轨迹的二轴框架平台结构,方位轴和俯仰轴。在考虑晴天和阴天等复杂天气情况下,设计太阳运行轨迹跟踪方式和光传感器跟踪方式相结合的自适应智能跟踪方法。全自动地准确跟踪太阳的位置,跟踪精度小于0．4°,最大限度的接收太阳能,提高了太阳能光电转换的效率。     

人机交互系统的实时人眼跟踪技术研究

为了解决面向移动设备的眼动跟踪技术存在的计算效率低、跟踪误差大等问题,采用改进眼动跟踪技术的方法,开展人机交互系统的研究。主要内容包含系统总体架构、系统用户登录、系统功能实现等内容设计,并对系统功能实现展开分析。研究结果表明,系统各功能及界面实现均满足用户要求,可用于指导新手用户对重要信息的浏览,提升用户理解效率。     

卫星激光通信中目标跟踪算法的改进

分析了用重心法计算光斑能量中心时图像相对光源强度分布失真引入的误差,建立了强度失真模型,引入修正该失真的修正因子,提出了相应的修正算法,并讨论了该修正算法在卫星激光通信跟踪系统中的应用。计算机模拟结果表明,在适当的情况下,计算出的由于像面上强度分布相对光源失真而导致的跟踪角度偏差可增至109″,从而证明了在激光卫星通信系统中,修正因子的引入提高了定位、跟踪精度和信道的可靠性。     

Real-time algorithm for retinal tracking

Conventional retinal laser photocoagulation is presently performed by an ophthalmologist manually aiming a low-power laser beam at a desired site and firing a high-power laser for a preselected interval of time. To automate this process a retinal tracker must acquire a target, track small saccades, and identify loss of track during a large saccade. The authors successfully implemented a real-time algorithm that used a simple computer, video digitizing card, low light video camera, and fundus camera to perform rudimentary tracking on a photograph of a retina undergoing smooth circular motion. The algorithm tracked speeds up to 5 Hz, or 27°/s, which equated to the retina moving in a 525 μm diameter circle     

Design and implementation of a real-time eye tracking system

Driver fatigue severely affects driver's alertness and ability to drive safely. There are vital problems related to drivers fatigue on driving of trains, vehicles and airplanes. Therefore, the driver fatigue research is important. In this paper, we first study the impact of eye locations on face recognition accuracy, with Haar-like feature and AdaBoost classifier, face and eye area can be detected quickly and accurately. In the part of eye tracking, cam-shift based mean-shift algorithm is used to track the eyes. This method could automatically adjust the size of tracking window according to the different posture of driver. The performance of our eye detection method is validated by using image database with more than 6000 pictures. In addition, our real-time eye tracking system has been tested on railway line segment (China). There are 5 train drivers involved in the experiment. The validation shows that our eye detector has an overall 93% eye detection rate.     

一种相位实时跟踪调整的光伏并网发电模拟系统

本文设计了一种光伏并网发电模拟系统,研究符合国家电网标准的输出电流,减少并网发电系统中的高次谐波分量。本系统以STM32F103ZET6为主控器,采用降压变压器及电压比较器提取电网中高压交流电的零相位时刻作为参考相位,对发电模拟系统的输出与参考相位之间存在的相位差进行比例调节,提高系统跟踪相位的速度和系统的稳定性。测试结果表明,本文设计的光伏并网发电模拟系统可输出50Hz且频率偏差小于0.1Hz的正弦波,符合国家电网要求,验证了方案的可行性与有效性。     

一种新算法的干扰信号侦测、追踪与定位系统

以数学模型为基础,提出了一种基于STC12C5410AD系列单片机的求干扰源各项参数的新算法.在复杂电磁环境下,实现干扰信号侦测、追踪和定位,并在最短时间内消灭干扰源,与现有同类产品相比可节约成本90%以上,该系统已得到应用.     

一种新算法的干扰信号侦测、追踪与定位系统

以数学模型为基础,提出了一种基于STC12C5410AD系列单片机的求干扰源各项参数的新算法。在复杂电磁环境下,实现干扰信号侦测、追踪和定位,并在最短时间内消灭干扰源,与现有同类产品相比可节约成本90％以上,该系统已得到应用。     

基于嵌入式快递包裹实时跟踪系统设计

快递包裹实时跟踪系统主要由包裹传感器模块、车载嵌入式终端以及客户网页查询系统组成。系统以S3C2440作为主控制器,通过若干传感器检查包裹的实时状态。包裹传感器系统与车载嵌入式系统通过无线模块进行通信,用GPS接收器接收经纬度信息,所有包裹相关信息以GPRS无线传输到远程服务器;网页客户端结合Google地图将包裹发生的各种警报标记在地图上,同时在地图上实现包裹运行轨迹的实时显示;最终解决了传统快递所不具备的包裹实时跟踪轨迹和快递运输过程中信息反馈功能的问题。     

红外成像系统中嵌入式实时信号处理技术研究

应用嵌入式信号处理技术,可使红外成像探测系统具备更高性能、更低功耗和更小体积.描述了以Xilinx公司VirtexⅡPro FPGA芯片为核心的红外成像跟踪嵌入式实时信号处理平台,采用了融微处理器、可编程硬件、信号处理算法和软硬件协同设计于一体的设计方法,为红外成像系统的更新发展打下一定的技术基础.     

一种实现图像跟踪的新方法

提出了一种用微机配普通视频采集卡在WinXP操作系统下结合使用DirectDraw和DirectShow编程实现图像跟踪的方法,为高速图像跟踪测量的实现提供了新的思路。     

A new method for eye location tracking

A standard scleral search coil (SSC) system is supplied with a single three-axial transmitter (or with a triad of transmitters) and the direct magnetic coupling between the transmitting coils and the SSC is used for computing the eye location. The SSC's orientation components measured by the SSC system are involved in the location-tracking algorithm as well. The suggested method differs from traditional ones where the eye location is computed indirectly, relative to the measured location and orientation of a transitional three-axial magnetic sensor attached to the subject's head. The new method eliminates systematic errors caused by inaccurate situating the transitional sensor relative to the eye. It also eliminates systematic errors caused by imperfect orthogonality of the transitional sensor. It is found that an accurate location tracking with a single transmitter is possible only if orientation freedom of the eye is limited. To track the eye location with no orientation limitations, a triad of transmitters is employed. The resulting accuracy can be as good as +/- 1 mm (in a 200-Hz bandwidth) over a relatively large (0.5 x 0.5 x 0.5 m) operating region in the center of a 1 x 1 x 1 m SSC system. The analytical results obtained are confirmed with the help of computer simulations.     

机动目标跟踪的新算法

机动目标通常不是做恒定的运动,其运动状态会随时间的变化而变化.这就使描述系统运动的状态方程是非线性的,而且系统参数会不断变化.传统的推广卡尔曼滤波适用于定系统定参数的情况,如果运用到机动目标跟踪上会导致误差增大甚至滤波发散.基于此,将强跟踪滤波运用到机动目标跟踪上.强跟踪滤波在卡尔曼滤波的基础上引入了多重渐消因子,使强跟踪滤波具有极强的跟踪能力和较好地鲁棒性,因此可以很好地解决变系统变参数的问题.通过仿真,将强跟踪滤波与UT-BLUE滤波方法和EKF滤波方法进行比较,结果表明了该滤波方法的有效性和优越性.     

Real-time multimodal retinal image registration for a computer-assisted laser photocoagulation system

An algorithm for the real-time registration of a retinal video sequence captured with a scanning digital ophthalmoscope (SDO) to a retinal composite image is presented. This method is designed for a computer-assisted retinal laser photocoagulation system to compensate for retinal motion and hence enhance the accuracy, speed, and patient safety of retinal laser treatments. The procedure combines intensity and feature-based registration techniques. For the registration of an individual frame, the translational frame-to-frame motion between preceding and current frame is detected by normalized cross correlation. Next, vessel points on the current video frame are identified and an initial transformation estimate is constructed from the calculated translation vector and the quadratic registration matrix of the previous frame. The vessel points are then iteratively matched to the segmented vessel centerline of the composite image to refine the initial transformation and register the video frame to the composite image. Criteria for image quality and algorithm convergence are introduced, which assess the exclusion of single frames from the registration process and enable a loss of tracking signal if necessary. The algorithm was successfully applied to ten different video sequences recorded from patients. It revealed an average accuracy of 2.47 ± 2.0 pixels (～23.2 ± 18.8 μm) for 2764 evaluated video frames and demonstrated that it meets the clinical requirements.