期刊
ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2021, PT II
卷 13156, 期 -, 页码 509-516出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-95388-1_33
关键词
Video saliency detection; Mobile edge computing; Deep learning; Refine input frames
资金
- Natural Science Foundation of Fujian Province of China [2020J06023]
- National Natural Science Foundation of China (NSFC) [62172046]
- Special Project of Guangdong Provincial Department of Education in Key Fields of Colleges and Universities [2021ZDZX1063]
- joint project of Production, Teaching and Research of Zhuhai [ZH22017001210133PWC]
Video saliency detection interprets the human visual system by modeling and predicting. The proposed SAFS module selects highly informative frames and has high robustness and extensive application. Combined with TASED-NET, our method achieves significant improvements on various datasets.
Video saliency detection is intended to interpret the human visual system by modeling and predicting while observing a dynamic scene. This method is currently widely used in a variety of devices, including surveillance cameras and Internet-of-Things sensors. Traditionally, each video contains a large amount of redundancies in consecutive frames, while the common practices concentrate on extending the range of input frames to resist the uncertainty of input images. In order to overcome this problem, we propose Self-Adapted Frame Selection (SAFS) module that removes redundant information and selects frames that are highly informative. Furthermore, the module has high robustness and extensive application dealing with complex video contents, such as fast moving scene and images from different scenes. Since predicting the saliency map across multiple scenes is challenging, we establish a set of benchmarking videos for the scene change scenario. Specifically, our method combined with TASED-NET achieves significant improvements on the DHF1K dataset as well as the scene change dataset.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据