基于B-样条Snake模型的人体运动跟踪方法研究  

Human motion tracking based on B-spline Snake algorithm

作　　者：曹晓叶[1] 王知衍[1] 

机构地区：[1]华南理工大学计算机科学与工程学院,广州510640

出　　处：《计算机应用研究》2008年第2期504-506,共3页Application Research of Computers

基　　金：科技部科技型中小型企业技术创新基金无偿资助项目(02C26214400224);广东省科技计划资助项目(2002A1020104)

摘　　要：提出了一种基于B-样条曲线Snake模型的新的人体运动跟踪方法。Snake算法是通过最小能量来逼近物体的轮廓。采用改进的B-样条曲线Snake模型,每一帧图像中的目标轮廓用三次样条曲线准确地表示,使Snake模型更加稳定和具有较快的收敛速度。计算相邻帧之间的差分图像,通过利用一种基于统计关系双阈值分割方法,有效地检测出图像中运动人体,初步确定目标在每帧图像中的粗略位置。把从上一帧图像中得到的目标轮廓置于该位置,作为B-样条曲线Snake算法中轮廓提取的初始值,经运算后可得到对人体目标的准确分割与跟踪。A new method for tracking of moving human objects was presented. The developed algorithm was based on B-spline Snake model, The Snake algorithm access the object contour through minimizing the energy, the object contour in each frame was presented through three B-spline curve, This approach got the change image with double thresholds image segmentation between the neighboring frames, it could detect moving human objects with high quality and locate objects approximately. The contour extracted from the last frame was put at the approximate position as the B-spline Snake model initialization. It accomplished the tracking of moving human objects.

关 键 词：SNAKE算法 B-样条曲线 目标提取 人体跟踪 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]