IEEE Trans Image Process. 2017 Nov;26(11):5203-5216. doi: 10.1109/TIP.2017.2736418. Epub 2017 Aug 4.
A novel primary object discovery (POD) algorithm, which uses reliable object proposals while exploiting the recurrence property of a primary object in a video sequence, is proposed in this paper. First, we generate both color-based and motion-based object proposals in each frame, and extract the feature of each proposal using the random walk with restart simulation. Next, we estimate the foreground confidence for each proposal to remove unreliable proposals. By superposing the features of the remaining reliable proposals, we construct the primary object models. To this end, we develop the evolutionary primary object modeling technique, which exploits the recurrence property of the primary object. Then, using the primary object models, we choose the main proposal in each frame and find the location of the primary object by merging the main proposal with candidate proposals selectively. Finally, we refine the discovered bounding boxes by exploiting temporal correlations of the recurring primary object. Extensive experimental results demonstrate that the proposed POD algorithm significantly outperforms conventional algorithms.
本文提出了一种新颖的初级目标发现（POD）算法，该算法利用可靠的目标提议，同时利用视频序列中初级目标的递归特性。首先，我们在每一帧中生成基于颜色和基于运动的目标提议，并使用重新启动随机游走模拟来提取每个提议的特征。接下来，我们估计每个提议的前景置信度，以去除不可靠的提议。通过叠加剩余可靠提议的特征，我们构建了初级对象模型。为此，我们开发了进化的初级对象建模技术，利用了初级对象的递归特性。然后，使用初级对象模型，我们在每一帧中选择主要提议，并通过有选择地合并主要提议和候选提议来找到初级对象的位置。最后，我们通过利用重复出现的初级对象的时间相关性来细化发现的边界框。广泛的实验结果表明，所提出的 POD 算法显著优于传统算法。
