摘要
针对医学步态分析中的运动目标检测问题,提出了基于最小错误率的贝叶斯决策规则的方法。该方法由变化检测、变化分类、前景目标提取和背景更新四部分组成。变化检测采用自适应阈值法检测二值化变化点和非变化点。变化分类基于颜色共生特征向量,采用贝叶斯规则进行决策,前景对象的提取融合了时间差分法和减背景法。针对复杂场景中背景的"渐变"和"突变"情况,提出了不同的背景更新策略。实验表明,该方法能将包含有摇动的树枝或者灯的开关等复杂背景中运动目标准确地提取,可用在医学步态分析的研究中。
This paper proposes a novel method for moving object detection from a video in medical gait analysis.It consists of four parts：change detection, change classification, foreground object abstraction and background updating.We used the Bayes decision rule for classification of background and foreground changes based on color co-occurrence feature.Foreground object abstraction fuse the classification results from both stationary and moving pixels.Learning strategies for the gradual and ＂once-off＂ background changes were proposed to adapt to various changes in background through the video.Extensive experiments on detecting foreground objects from a video containing wavering tree branches or light open/close demonstrated that the proposed method was effective and could be used in medical gait analysis.
出处
《中国医疗设备》
2010年第9期16-19,共4页
China Medical Devices
基金
吉林省科技重点项目(20070323)资助
关键词
医学步态分析
贝叶斯决策规则
目标检测
medical gait analysis
the Bayes decision rule
object detection
