Optical Flow Estimation with Foreground Attention Guided Network
文献类型：会议论文
| 作者 | Hou DD(侯冬冬) ; Sun G(孙干)
|
| 出版日期 | 2021 |
| 会议日期 | March 5-8, 2021 |
| 会议地点 | Xiamen, China |
| 关键词 | optical flow attention foreground guided |
| 页码 | 42-48 |
| 英文摘要 | Optical flow is used to describe the variations between adjacent images of a sequence. Although the pixels belonging to a same object have similar displacements, most existing optical flow estimation methods focus on processing each pixel indiscriminately, while neglecting the semantic information of pixels. Consider the foreground objects usually have large displacement and outstanding to viewer, we in this paper propose a foreground attention guided network to strengthen the foreground target feature for optical flow estimation. Specifically, we first adopt a foreground attention network to obtain a map of foreground objects. Then the attention map of foreground is utilized to strengthen the features in multiple scales via 3D convolution for optical flow estimation progression. Finally, the strengthening features are concatenated with the original feature maps in multi-scale deconvolution operation to achieve the final optical flow. To the end, we pretrain our proposed framework on Flying Chairs dataset, and then execute comparison experiments on MPI Sintel and KITTI benchmark datasets. The experimental results verify that our proposed framework is comparable with state-of-the-art methods with a miniature network. |
| 产权排序 | 1 |
| 会议录 | ICIAI 2021- 5th International Conference on Innovation in Artificial Intelligence
 |
| 会议录出版者 | ACM |
| 会议录出版地 | New York |
| 语种 | 英语 |
| ISBN号 | 978-1-4503-8863-4 |
| WOS记录号 | WOS:000777584200008 |
| 源URL | [http://ir.sia.cn/handle/173321/29558]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 通讯作者 | Hou DD(侯冬冬) |
| 作者单位 | State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, China |
| 推荐引用方式 GB/T 7714 | Hou DD,Sun G. Optical Flow Estimation with Foreground Attention Guided Network[C]. 见:. Xiamen, China. March 5-8, 2021. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。