Visual saliency for automatic target detection, boundary detection, and image quality assessment

Seo, Hae Jong; Milanfar, Peyman

doi:10.1109/icassp.2010.5495239

Cited by 23 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

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%

Motion-decision based spatiotemporal saliency for video sequences

Zhu

Jacobson

Hong

et al. 2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

An adaptive spatiotemporal saliency algorithm for video attention detection using motion vector decision is proposed, motivated by the importance of motion information in video sequences for human visual system. This novel system can detect the saliency regions quickly by using only part of the classic saliency features in each iteration. Motion vectors calculated by block matching and optical flow are used to determine the decision condition. When significant motion contrast occurs (decision condition is satisfied), the saliency area is detected by motion and intensity features. Otherwise, when motion contrast is low, color and orientation features are added to form a more detailed saliency map. Experimental results show that the proposed algorithm can detect salient objects and actions in video sequences robustly and efficiently.

show abstract

Section: Simplified Sun Model For Intensity Based Saliencymentioning

confidence: 90%

Motion-decision based spatiotemporal saliency for video sequences

Zhu

Jacobson

Hong

et al. 2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…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

Autoencodeurs discriminants pour la détection et la reconnaissance de véhicules en imagerie aérienne

Razakarivony¹,

Jurie²

2015

Traitement du signal

View full text Add to dashboard Cite

Les autoencodeurs, qui permettent de modéliser des données au moyen de variétés, peuvent être utilisés dans un contexte de détection d'objets pour modéliser l'apparence des classes d'objets à détecter. La distance entre un vecteur à classer et la variété peut alors être utilisée comme une mesure de probabilité d'appartenance du vecteur à la classe. Cependant, en construisant la variété de manière à ce que les vecteurs de la classe appartiennent à la variété, rien ne garantit que des vecteurs d'autres classes ne lui appartiennent pas également. Nous cherchons à lever cette limitation en proposant un nouveau type d'autoencodeurs, les autoencodeurs discriminants, qui ont la propriété de construire des variétés éloignant les formes n'appartenant pas à la classe d'objets à détecter de la variété. Une validation expérimentale dans un contexte de détection et reconnaissance de véhicules en imagerie aérienne permet de conclure sur la pertinence de la méthode proposée. ABSTRACT. The autoencoders allow to model data with manifolds. In an object detection task, they model the appearance of objects to detect. The distance between a vector to classify and the manifold can then be used as a measure of the probability that the vector belong to it. However, if the learnt manifold is such that all vectors of the class belong to it, nothing garanties that the vectors of other classes will not. We propose to remove this limitation with a new kind of encoders, the discriminative autoencoders, which have the property to build manifolds that move away the negative examples from the positive ones. An experimental validation on the context of detection and recognition of vehicles allows to conclude on the method.

show abstract

“…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%