A Contour Co-Tracking Method for Image Pairs
A Contour Co-Tracking Method for Image Pairs
复制标题
DOI：
10.1109/tip.2021.3079798
复制
发表时间：
2021-01-01
影响因子：
10.6
通讯作者：
Gao, Xinbo
中科院分区：
文献类型：
--
作者：
Wang, Bin;Tao, Dapeng;Gao, Xinbo
提出了一种基于活动轮廓模型的轮廓共跟踪图像对共分割方法。该方法对水平集函数表示的目标和背景进行全面的重建，并利用Hellinger距离来度量图像区域之间的相似度。主要贡献如下。1)新的能量泛函结合了奖罚项，放宽了共分割方法的假设条件。2)满足三角不等式的Hellinger距离保证了度量空间中概率分布之间的一致性度量，并有助于找到能量泛函的唯一解。在图像对数据集(105对)、MSRC数据集(30对)、iCOSEG数据集(66对)和COSEG-REP数据集(25对)上对所提出的轮廓共同跟踪方法进行了仔细的验证。对比实验表明，我们的方法取得了与目前最先进的共分割方法相当甚至更好的性能。
We proposed a contour co-tracking method for co-segmentation of image pairs based on active contour model. Our method comprehensively re-models objects and backgrounds signified by level set functions, and leverages Hellinger distance to measure the similarity between image regions encoded by probability distributions. The main contribution are as follows. 1) The new energy functional, combining a rewarding and a penalty term, relaxes the assumptions of co-segmentation methods. 2) Hellinger distance, fulfilling the triangle inequality, ensures a coherence measurement between probability distributions in metric space, and contributes to finding a unique solution to the energy functional. The proposed contour co-tracking method was carefully verified against five representative methods on four popular datasets, i.e., the images pair dataset (105 pairs), MSRC dataset (30 pairs), iCoseg dataset (66 pairs) and Coseg-rep dataset (25 pairs). The comparison experiments suggest that our method achieves the competitive and even better performance compared to the state-of-the-art co-segmentation methods.