近年来随着多媒体技术的迅速发展和计算机性能的不断提高，数字式视频监控系统已逐渐取代传统的模拟式监控系统而广泛应用于机场、车站、银行、宾馆等公共场所，在公共安全领域当中发挥着日益重要的作用，智能化监控系统在未来必将有广阔的应用前景并能为社会带来巨大的经济效益。 智能化监控系统的核心技术是运动目标的检测、识别和跟踪。本文在熟悉相关资料的基础上实现了一种基于PC机的智能化数字视频监控系统，研究了包括视频图像采集、云台系统控制和运动目标检测、跟踪的软件编程和硬件系统集成等方面问题。硬件系统集成部分，本系统选用专业CCD摄像机和视频图像采集卡以实现视频图像的高速高质采集；电动云台控制则采用基于RS-485总线接口的解码器进行控制调节。软件编程部分采用Visual C++ 6.0在视频采集卡二次开发包的基础上构建了整个智能视频监控程序，其中包括视频图像采集、串口通信和运动目标检测跟踪等方面的编程。 运动目标的检测部分，首先用中值滤波的方法对视频图像进行消噪处理，然后采用基于两帧差分法和背景差分法相结合的运动目标检测方法，检测出运动目标，最后用投影法对目标定位，从而得到目标的运动状态。 运动目标的跟踪部分，采用以灰度直方图为模式特征的模板匹配方法并与卡尔曼滤波器预测运动目标轨迹相结合，实现对运动目标的自动跟踪。实验结果表明：该方法能快速、准确地检测和分离出运动目标，并能有效地对目标进行自动跟踪。

In recent years, with the rapid development of multimedia technical and the unceasing enhancement of computer performance, the digital video monitoring system has gradually substituted for traditional analog video monitoring system, which is widely applied to the public places such as airport, station, bank and guesthouse and plays an important role in the public security domain. The intelligent video monitoring system will certainly have a broad application prospect in the future and will bring huge economic efficiency for the society. The critical technology of intelligent video monitoring system is the moving-target detection, recognition and tracking. In the foundation of familiar with correlation data, the paper has realized one type of intelligent digital video monitoring system based on the ordinary PC, and has studied several problems including video frequency picture gathering, cradle head control, software programming of the moving-target detection and track and system integration. In the hardware system integration part, this system adopts specialized CCD camera and the video data acquisition card so as to realizes high speed and high-grade gathering of video frequency picture; The electric cradle head control uses decoder based on the RS-485 main line connection to realize the control adjustment. In the software programming part, Visual C++6.0 is used to construct the entire intelligent video frequency monitor system on the basis of the second development packages of the video frequency gathering, including the programming of video frequency picture gathering, serial port communication and the detection track of mobile. In the moving-target detection, first use the value filter method to remove the noise, then use the moving-target detection method, which combines the two frame difference methods and the background difference method, together with the projection method to detect the moving state of the mobile. In the moving-target track, uses template match method with the pattern characteristic of gradation histogram and Kalman filter forecast track of the target to realize track of the moving-target. The experimental result indicates that, this method can fast and precisely examine and separates the moving-target and can effectively realize the automatic tracking of target.