Top-down spatiotemporal saliency detection using spectral filtering

Wanyi Li; Peng Wang; Hong Qiao

doi:10.1117/12.2030535

19 July 2013 Top-down spatiotemporal saliency detection using spectral filtering

Wanyi Li, Peng Wang, Hong Qiao

Proceedings Volume 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013); 88782G (2013) https://doi.org/10.1117/12.2030535
Event: Fifth International Conference on Digital Image Processing, 2013, Beijing, China

Abstract

A 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 for spectral 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.

Citation Download Citation

Wanyi Li, Peng Wang, and Hong Qiao "Top-down spatiotemporal saliency detection using spectral filtering", Proc. SPIE 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013), 88782G (19 July 2013); https://doi.org/10.1117/12.2030535

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available