毕业论文---视频图像中运动物体的检测论述.doc

摘 要 运动目标检测处于整个视觉检测系统的最底层，是各种后续高级处理如目标分类、行为理解等的基础。运动目标检测是指从视频流中实时提取目标，一般是确定目标所在区域和颜色特征等。目标检测的结果是一种“静态”目标——前景目标，由一些静态特征所描述。 在论文的第一部分介绍了运动目标检测的基本理论以及实现方法；在论文的第二部分简述了模式识别，数学形态学以及边缘检测的概念，重点介绍了数学形态学中的腐蚀和膨胀以及 canny算子用于边缘检测的方法。通过观察所需检测的图像的性质，笔者首先使用连通性的概念，进行了算法一的尝试；在不成功后，笔者又利用数学形态学和模式识别结合的方法，在canny算子边缘检测的基础上，进行了算法二的初步尝试，得出了检测结果。并通过对比试验，检测了算法的效果。 关键词：运动目标检测，数学形态学，模式识别，边缘检测 Abstract The locomotion target detecting is placed in the understratum of the whole sense of vision detecting system, it is also the base of every kind of follow-up advanced dispose such as the target sorting, behavior comprehending and so on. The locomotion target detecting is pick-uping target in real time from the video stream; it is commonly making sure the region and color characteristic etc. Of the target. The result of the target detecting is a kind of static target —— foreground target, being described by some static characteristic. The basic theoretics and realization method of the locomotion target detecting is introduced in the first part of the thesis; in the second part of the thesis it is simply depicting the conception of pattern identify, mathematical morphology and the edge deetecting,it is mostly introduced the method of the eroding and dilating of mathematical morphology, and the edge detecting using canny operator. Acrossing the character of the observing a kind of picture needing detecting, the author firstly uses the conception of connectedness, and proceed according to the method of connectedness target detecting, but it is unsuccessful, the author according the method of uniting mathematical morphology and pattern identify, on the basis of edge detecting using canny operator, proceed according to the method of difference of two frames threshold value and educe the detecting result. At last , the author according contrast experimentation, detect effect of the arithmetic. Key Words: target detecting, mathematical morphology, pattern identify, edge detecting