TY - GEN
T1 - Salient object detection in image sequences via spatial-temporal cue
AU - Gan, Chuang
AU - Qin, Zengchang
AU - Xu, Jia
AU - Wan, Tao
PY - 2013
Y1 - 2013
N2 - Contemporary video search and categorization are non-trivial tasks due to the massively increasing amount and content variety of videos. We put forward the study of visual saliency models in video. Such a model is employed to identify salient objects from the image background. Starting from the observation that motion information in video often attracts more human attention compared to static images, we devise a region contrast based saliency detection model using spatial-temporal cues (RCST). We introduce and study four saliency principles to realize the RCST. This generalizes the previous static image for saliency computational model to video. We conduct experiments on a publicly available video segmentation database where our method significantly outperforms seven state-of-the-art methods with respect to PR curve, ROC curve and visual comparison.
AB - Contemporary video search and categorization are non-trivial tasks due to the massively increasing amount and content variety of videos. We put forward the study of visual saliency models in video. Such a model is employed to identify salient objects from the image background. Starting from the observation that motion information in video often attracts more human attention compared to static images, we devise a region contrast based saliency detection model using spatial-temporal cues (RCST). We introduce and study four saliency principles to realize the RCST. This generalizes the previous static image for saliency computational model to video. We conduct experiments on a publicly available video segmentation database where our method significantly outperforms seven state-of-the-art methods with respect to PR curve, ROC curve and visual comparison.
KW - object detection
KW - saliency
KW - spatial-temporal cue
UR - http://www.scopus.com/inward/record.url?scp=84893678422&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84893678422&partnerID=8YFLogxK
U2 - 10.1109/VCIP.2013.6706438
DO - 10.1109/VCIP.2013.6706438
M3 - Conference contribution
AN - SCOPUS:84893678422
SN - 9781479902903
T3 - IEEE VCIP 2013 - 2013 IEEE International Conference on Visual Communications and Image Processing
BT - IEEE VCIP 2013 - 2013 IEEE International Conference on Visual Communications and Image Processing
T2 - 2013 IEEE International Conference on Visual Communications and Image Processing, IEEE VCIP 2013
Y2 - 17 November 2013 through 20 November 2013
ER -