Knowledge Commons of Institute of Automation,CAS
IoT-based 3D convolution for video salient object detection | |
Dong, Shizhou1,2; Gao, Zhifan3; Pirbhulal, Sandeep1; Bian, Gui-Bin4![]() | |
发表期刊 | NEURAL COMPUTING & APPLICATIONS
![]() |
ISSN | 0941-0643 |
2020-02-01 | |
卷号 | 32期号:3页码:735-746 |
通讯作者 | Bian, Gui-Bin(guibin.bian@ia.ac.cn) |
摘要 | The video salient object detection (SOD) is the first step for the devices in the Internet of Things (IoT) to understand the environment around them. The video SOD needs the objects' motion information in contiguous video frames as well as spatial contrast information from a single video frame. A large number of IoT devices' computing power is not sufficient to support the existing SOD methods' expensive computational complexity in emotion estimation, because they might have low hardware configurations (e.g., surveillance camera, and smartphone). In order to model the objects' motion information efficiently for SOD, we propose an end-to-end video SOD algorithm with an efficient representation of the objects' motion information. This algorithm contains two major parts: a 3D convolution-based X-shape structure that directly represents the motion information in successive video frames efficiently, and 2D densely connected convolutional neural networks (DenseNet) with pyramid structure to extract the rich spatial contrast information in a single video frame. Our method not only can maintain a small number of parameters as the 2D convolutional neural network but also represents spatiotemporal information uniformly that enables it can be trained end-to-end. We evaluate our proposed method on four benchmark datasets. The results show that our method achieves state-of-the-art performance compared with the other five methods. |
关键词 | Internet of Things Salient object detection Video processing Deep learning |
DOI | 10.1007/s00521-018-03971-3 |
关键词[WOS] | SEGMENTATION |
收录类别 | SCI |
语种 | 英语 |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000512022900010 |
出版者 | SPRINGER LONDON LTD |
七大方向——子方向分类 | 多模态智能 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38338 |
专题 | 复杂系统认知与决策实验室_先进机器人 |
通讯作者 | Bian, Gui-Bin |
作者单位 | 1.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen, Peoples R China 2.Univ Chinese Acad Sci Shenzhen, Shenzhen Coll Adv Technol, Shenzhen, Peoples R China 3.Western Univ, London, ON, Canada 4.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing, Peoples R China 5.Sun Yat Sen Univ, Guangzhou, Guangdong, Peoples R China |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Dong, Shizhou,Gao, Zhifan,Pirbhulal, Sandeep,et al. IoT-based 3D convolution for video salient object detection[J]. NEURAL COMPUTING & APPLICATIONS,2020,32(3):735-746. |
APA | Dong, Shizhou.,Gao, Zhifan.,Pirbhulal, Sandeep.,Bian, Gui-Bin.,Zhang, Heye.,...&Li, Shuo.(2020).IoT-based 3D convolution for video salient object detection.NEURAL COMPUTING & APPLICATIONS,32(3),735-746. |
MLA | Dong, Shizhou,et al."IoT-based 3D convolution for video salient object detection".NEURAL COMPUTING & APPLICATIONS 32.3(2020):735-746. |
条目包含的文件 | 条目无相关文件。 |
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。
修改评论