基于模糊熵聚类和Kalman滤波的区域跟踪  

Region Tracking Based on Fuzzy Entropy Clustering and Kalman Filter

作　　者：周志宇[1] 汪亚明[1] 

机构地区：[1]浙江工程学院计算机视觉与模式识别研究中心,浙江杭州310033

出　　处：《测控技术》2003年第11期60-62,共3页Measurement & Control Technology

摘　　要：目前 ,运动目标跟踪是计算机视觉领域中最活跃的研究课题之一。本研究提出了基于模糊熵聚类和Kalman滤波预测的区域跟踪方法 ,用Kalman滤波的预测值作为下一帧图像运动区域的聚类中心 ,从而减少了迭代次数 ,加强了跟踪的实时性。算法有效地利用了计算机视觉技术从图像序列中检测出运动区域 ,并获得了运动目标的轨迹 ,统计了运动目标的数目。Moving targets tracking is currently one of the most active research topics in the domain of computer vision.A method of moving targets tracking based on fuzzy entropy clustering and Kalman filter forecasting is advanced,and the forecasting value of Kalman filter as the center of next frame cluster is used.This method reduces the iterative numbers and increases the real-time tracking.The method effectively applies the teachnology of the computer vision detecting the motion region in image sequences.It acquires with the trajectories of moving targets and counts the number of moving targets.

关 键 词：模糊熵 KALMAN滤波 区域跟踪 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]