摘要
针对固定监控场景提出了一种基于色彩分割与局部模型匹配的目标跟踪方案.利用自适应混合高斯背景模型提取前景运动目标,通过基于区域生长的色彩分割算法建立目标局部模型并实时更新,结合区域约束条件和模型特征匹配实现目标跟踪.实验结果证明,本算法能有效地实现多运动目标的跟踪,对跟踪过程目标部分遮挡与形变问题具有良好的适应性和鲁棒性.
A tracking method was presented to enhance the performance of object tracking in stationary scene, in which the background was modeled by an effective adaptive background updating method with Gaussian mixture model（GMM）, and the foreground blobs were obtained by background subtract. Object parts in the part model, were generated online by the color segmentation based on region-growth. The constraints between parts and region features were taken into account and used to perform objects tracking effectively in real time even under partial occlusion and object deformation. Experimental results with different real-world scenarios demonstrate the validity and robust of the solution.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2008年第12期67-70,共4页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
关键词
目标跟踪
背景建模
区域分割
特征提取
模型匹配
色彩分割
object tracking
background modeling
region segmentation
feature extraction
model matching
color segmentation
