Varies of segmentation methods can be used according to different situations of moving objects with their different background . this paper proposed a method based on spatio - temporal information : first construct a stationary panoramic background , and then detect the moving areas in every frame 算法的思路是:首先构建不包含运动目标的背景全景图,然后用经过配准的各帧图像与背景相应部分做差分提取出运动模板,最后引入空间分割的信息对模板进行优化,得到精确的分割结果。
In temporal segmentation a statistical model is used to automatically separate the moving areas from the background in a general video sequence . the spatial segmentation bases on the results of temporal segmentation and using region - growing algorithm in rgb space can locate precise boundary of moving object . lastly , using segment moving object as the initial model , moving object can be tracked by matching an image to a model based on hausdorff distance on a sequence of video , and the model is updated every frame to accommodate for changes in shape 时间分割中采用连续帧间差的统计假设检验，确定运动对象的位置，自动地分离出运动区域与背景区域；空间分割中则采用基于颜色的区域增长算法来精确地提取运动对象的轮廓；最后，将提取到的运动对象作为模板，对后续的视频序列，用基于hausdorff距离度量匹配，来跟踪并提取后续帧中运动对象。
The performance of usscd is compared with the well known algorithm , icollide , through a series of experiments . the results show that , when the objects are evenly distributed , and the number of objects is large , the performance of usscd is better than that of icollide . in this paper , a class of non - uniform spacial subdivision method is proposed , which is composed of two steps : first , the space is coarsely subdivided non - uniformly , based on the distribution density of the objects , then , every subspace is uniformly subdivided 提出了一种基于均匀空间分割的快速碰撞检测算法usscd ，与经典的icollide算法进行了对比试验，试验结果表明，在物体均匀分布的情况下，随物体数量的增多， usscd表现出明显的优势；提出了一类非均匀空间分割方法，在该方法中，空间分割由基于密度的非均匀空间分割和对每个子空间进行均匀分割两个步骤实现；提出了一种基于投影的非均匀空间分割方法。
