融合外观和运动特征的在线目标分割  

Online object segmentation via fusing appearance and motion features

作　　者：张雷[1] 李成龙[1] 汤进[1,2] 高思晗 

机构地区：[1]安徽大学计算机科学与技术学院,合肥230601 [2]安徽省工业图像处理与分析重点实验室,合肥230039

出　　处：《中国图象图形学报》2015年第10期1358-1365,共8页Journal of Image and Graphics

基　　金：安徽省科技攻关项目(1301b042002);安徽省电力公司科技项目(521200130M0U)~~

摘　　要：目的视频中的目标分割是计算机视觉领域的一个重要课题,有着极大的研究和应用价值。为此提出一种融合外观和运动特征的在线自动式目标分割方法。方法首先,融合外观和运动特征进行目标点估计,结合上一帧的外观模型估计出当前帧的外观模型。其次,以超像素为节点构建马尔可夫随机场模型,结合外观模型和位置先验把分割问题转化为能量最小化问题,并通过Graph Cut进行优化求解。结果最后,在两个数据集上与5种标准方法进行了对比分析,同时评估了本文方法的组成成分。本文算法在精度上至少比其他的目标分割算法提升了44.8%,且具有较高的分割效率。结论本文通过融合外观与运动特征实现在线的目标分割,取得较好的分割结果,且该方法在复杂场景中也具有较好的鲁棒性。Objective Object segmentation in video is an important subject in computer vision and has gained various researeh and application values. The online automatic object segmentation method is proposed in this paper; this method fuses appearance and motion features. Method First, the object points were roughly estimated by employing appearance and motion boundaries. Then, we utilized these estimated object points to refine the appearance model （ GMM ） of the previous frame as current appearance model. Second, a Markov random field （MRF） model was constructed by taking the superpixels as nodes, and integrating the appearance model and the location prior. Therefore, the object segmentation can be converted to an energy minimization problem, which is optimized by graph cut in this paper. Result After extensive experiments which included comparison analysis of five approaches and component analysis of the proposed approach on two datasets, the proposed approach improved accuracy of segmentation by at least 44. 8% than other approaches, and achieved higher efficiency of segmentation. Conclusion The proposed algorithm achieved online automatic object segmentation by fusing appearance and motion features, and obtained good segmentation performance. Furthermore, this algorithm was also robust in several complicated scenes.

关 键 词：特征融合 MRF模型 在线分割 自动分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]