DMCA
Salient object detection by composition (2011)
| Venue: | in International Conference on Computer Vision |
| Citations: | 29 - 4 self |
BibTeX
@INPROCEEDINGS{Feng11salientobject,
author = {Jie Feng and Yichen Wei and Litian Tao and Chao Zhang and Jian Sun},
title = {Salient object detection by composition},
booktitle = {in International Conference on Computer Vision},
year = {2011},
pages = {1028--1035}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Conventional saliency analysis methods measure the saliency of individual pixels. The resulting saliency map inevitably loses information in the original image and finding salient objects in it is difficult. We propose to detect salient objects by directly measuring the saliency of an image window in the original image and adopt the well established sliding window based object detection paradigm. We present a simple definition for window saliency, i.e., the cost of composing the window using the remaining parts of the image. The definition uses the entire image as the context and agrees with human intuition. It no longer relies on idealistic assumptions usually used before (e.g., “background is homogenous”) and generalizes well to complex objects and backgrounds in real world images. To realize the definition, we illustrate how to incorporate different cues such as appearance, position, and size. Based on a segment-based representation, the window composition cost function can be efficiently evaluated by a greedy optimization algorithm. Extensive evaluation on challenging object detection datasets verifies better efficacy and efficiency of the proposed method comparing to the state-of-the-art, making it a good pre-processing tool for subsequent applications. Moreover, we hope to stimulate further work towards the challenging yet important problem of generic salient object detection. 1.
Keyphrases
salient object detection original image salient object individual pixel resulting saliency map simple definition window composition cost function human intuition object detection paradigm idealistic assumption object detection datasets verifies generic salient object detection extensive evaluation important problem segment-based representation greedy optimization algorithm conventional saliency analysis method complex object entire image real world image image window subsequent application good pre-processing tool different cue window saliency
