基于時(shí)空標(biāo)記場最大后驗(yàn)概率的多視頻對象分割算法
Multiple Video Object Segmentation Based on Maximization of the A Posteriori Probability of Spatio-Temporal Label Field
-
摘要: 該文提出了一種基于貝葉斯框架的時(shí)空標(biāo)記場最大后驗(yàn)概率的多視頻對象分割算法，根據(jù)視頻序列幀間(時(shí)間域)和幀內(nèi)(空間域)信息的不同特點(diǎn)，建立基于多個(gè)對象分割標(biāo)記場的最大后驗(yàn)概率公式，并導(dǎo)出其最小能量函數(shù)，通過求解最小能量使其分割標(biāo)記的后驗(yàn)概率達(dá)到最大。最小能量的優(yōu)化求解用迭代條件模式(ICM) 方法，初始分割標(biāo)記場用矢量直方圖法得到。實(shí)驗(yàn)結(jié)果表明, 該文提出的算法對存在局部遮擋的多運(yùn)動對象分割是有效的。
-
關(guān)鍵詞:
- 圖像處理;貝葉斯方法;多視頻對象; 時(shí)空分割
Abstract: This paper presents a novel multiple object segmentation algorithm based on a Bayesian framework. According to the characteristic of the intra-frame and inter-frame (spatial and temporal) information, a representation of Maximization of the A posteriori Probability(MAP) of spatio-temporal label field is proposed. So a minimization of energy function is obtained. The optimization of solution is carried out by Iterated Conditional Mode(ICM) method. The initial segmentation label fields is gotten using vector histogram. The experimental results show that the algorithm is effective to multiple object segmentation with partial occlusion. -
計(jì)量
- 文章訪問數(shù): 2740
- HTML全文瀏覽量: 109
- PDF下載量: 1116
- 被引次數(shù): 0
下載:
