Top-down spatiotemporal saliency detection using spectral filtering
Li, Wanyi; Wang, Peng; Qiao, Hong; Li, WY
2013
Conference Name5th International Conference on Digital Image Processing (ICDIP)
Source PublicationFIFTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2013)
Conference DateAPR 21-22, 2013
Conference PlaceBeijing, PEOPLES R CHINA
AbstractA spectral filtering based method for top-down spatiotemporal saliency detection is proposed. The proposed method enables to favor the salient features of the target object needed to pop out. Here a feature vector representing the salient features of the target object is learned online within the first image in which it is detected or initialized manually. The proper scale of the Gaussian kernel forspectral filtering is selected automatically according to the size ratio of the whole image to the target object. Guided by the top-down information, a top-down, target-related saliency map can be built in subsequent images. This enables to focus on the most relevant salient region and can be extended to complicated computer vision tasks. Experiment results demonstrate the effectiveness of the proposed method.
KeywordVisual Attention Top-down Spatiotemporal Saliency Spectral Filtering
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12871
Collection复杂系统管理与控制国家重点实验室_机器人理论与应用
Corresponding AuthorLi, WY
Recommended Citation
GB/T 7714
Li, Wanyi,Wang, Peng,Qiao, Hong,et al. Top-down spatiotemporal saliency detection using spectral filtering[C],2013.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Wanyi]'s Articles
[Wang, Peng]'s Articles
[Qiao, Hong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Wanyi]'s Articles
[Wang, Peng]'s Articles
[Qiao, Hong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Wanyi]'s Articles
[Wang, Peng]'s Articles
[Qiao, Hong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.