基于颜色相似和位移一致的运动目标归并算法研究

基于运动学信息的目标检测无须依赖数据训练,但存在被分割为多个离散目标的情况,通过提取各离散目标的色度、饱和度、亮度信息,构建HSI颜色特征向量并定义相似度函数,在当前帧中根据HSI颜色特征相似度实现第一次目标归并。基于前后帧颜色特征向量建立上下文颜色相似矩阵,对于相似度高的目标,基于离散目标质心运动方向和距离进行位移一致性评价,实现第二次归并。实验结果表明,所消耗时间控制在30 ms左右,运动目标的检测正确率较未归并前提高了27个百分点,保证了运动目标检测的完整性。

一种水平位移监测潜在性危害的数据挖掘方法

针对当前水平位移监测依靠变形值和特定方向进行数据分析的局限,本文基于向量工具提出了一种水平位移危害性界定理论与数据挖掘方法,该法首先将水平位移危害性进行分类,然后构造观测向量矩阵,通过矩阵求角运算判定监测体危害类型,实现数据挖掘与分析。实验结果表明,本文提出的方法能有效挖掘出监测体水平位移潜性危害,提供动态可视化分析成果,是一种可靠的水平位移数据挖掘方法,具有较强的普适应用性。

Moving Target Tracking Based on LogGabor Wavelet and Mean-shift Algorithm

Tracking moving target from image or video sequence is a hot research topic in computer vision. An algorithm based on LogGabor wavelet and Mean-shift has been proposed for moving target tracking under fixed camera setting and complicated environment. Phase coherency of LogGabor wavelet facilitates to extract the edge of moving target and check noise. According to the edge detection,the starting location of Mean-shift can be estimated using the target center coordinate. Eventually,a real-time moving target can be extracted by doing iterative matching pursuit,and experimental results proved the effectiveness of the method proposed.