2010 IEEE International Conference on Acoustics, Speech and Signal Processing 2010
DOI: 10.1109/icassp.2010.5495239
| View full text |Cite
|
Sign up to set email alerts
|

Abstract: We present a visual saliency detection method and its applications. The proposed method does not require prior knowledge (learning) or any pre-processing step. Local visual descriptors which measure the likeness of a pixel to its surroundings are computed from an input image. Self-resemblance measured between local features results in a scalar map where each pixel indicates the statistical likelihood of saliency. Promising experimental results are illustrated for three applications: automatic target detection,… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0
1

Year Published

2011
2011
2020
2020

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 22 publications
(7 citation statements)
references
References 13 publications
(24 reference statements)
0
6
0
1
Order By: Relevance
“…SUN (saliency using natural statistics) model [9] provides a measure of saliency derived from natural image statistics, instead of being based on a single image [10]. The saliency region obtained from this model is consistent with the neuro-anatomy of the human visual system.…”
Section: Simplified Sun Model For Intensity Based Saliencymentioning
confidence: 90%
“…SUN (saliency using natural statistics) model [9] provides a measure of saliency derived from natural image statistics, instead of being based on a single image [10]. The saliency region obtained from this model is consistent with the neuro-anatomy of the human visual system.…”
Section: Simplified Sun Model For Intensity Based Saliencymentioning
confidence: 90%
“…Notons toutefois ceux de (Munder, 2006) qui s'intéresse à la détection de piétons (36 × 18 pixels) en utilisant des ondelettes de Haar ou des HOG combinés avec un classifieur SVM (Enzweiler, Gavrila, 2009). Les autres travaux utilisent généralement des techniques de saillance ((Rutishauser et al, 2004 ;Seo, Milanfar, 2010)), inexploitables dans notre cas en raison de la complexité des fonds.…”
Section: éTat De L'artunclassified
“…In this case, the objects to be detected are defined as the regions of the image which do not have the same statistics as the background e.g. [19], [20]. Among the rare papers which tried to model small targets explicitly, we can mention the work of [21], which -in addition to introducing a new dataset of 36 × 18 pixels pedestrian images -has shown that good performance can be obtained by combining standard features such as Haar wavelets or HOG features with SVM/boosting classifiers [22].…”
Section: Related Workmentioning
confidence: 99%