Online Video Object Segmentation via Convolutional Trident Network
Online Video Object Segmentation via Convolutional Trident Network
复制标题
DOI：
10.1109/cvpr.2017.790
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Won-Dong Jang;Chang-Su Kim
中科院分区：
文献类型：
--
作者：
Won-Dong Jang;Chang-Su Kim
本文提出了一种半监督在线视频对象分割算法，该算法在第一帧接受用户对目标对象的注释。我们利用光流矢量将前一帧的分割标签传播到当前帧。然而，这种传播很容易出错。因此，我们开发了卷积三叉戟网络（CTN），它有三个解码分支：分离的、确定的前景解码器和确定的背景解码器。然后，我们基于三个解码器的输出进行马尔可夫随机场优化。我们从第二帧到最后一帧依次执行这些过程，以提取目标物体的段轨迹。实验结果表明，该算法在DAVIS基准数据集上的性能明显优于目前最先进的传统算法。
A semi-supervised online video object segmentation algorithm, which accepts user annotations about a target object at the first frame, is proposed in this work. We propagate the segmentation labels at the previous frame to the current frame using optical flow vectors. However, the propagation is error-prone. Therefore, we develop the convolutional trident network (CTN), which has three decoding branches: separative, definite foreground, and definite background decoders. Then, we perform Markov random field optimization based on outputs of the three decoders. We sequentially carry out these processes from the second to the last frames to extract a segment track of the target object. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on the DAVIS benchmark dataset.