2007 · 11 citations · 8 references
ComputingVision ScienceComputer VisionMachine VisionVisual AttentionCamera MovementFeature DetectionMotion AnalysisMotion EstimationObject DetectionVideo AnalysisGlobal Motion EstimationRegion Of Interest DetectionSaliency DetectionSaliency MappingSaliency-based FeaturesSalient Feature ExtractionSalient Region DetectionVisual Saliency
In this paper, we propose an algorithm for identifying regions of interest (ROIs) in video, particularly for the keyframes extracted from a home video. The camera motion is introduced as a new factor that can influence the visual saliency. The global motion parameters are used to generate location-based importance maps. These maps can be combined with other saliency maps calculated using other visual and high-level features. Here, we employed the contrast-based saliency as an important low level factor along with face detection as a high level feature in our approach.
8
Robert M. Gray · Elsevier eBooks · 1984 · 2.4K citations · Full text
Contrast-based image attention analysis by using fuzzy growing
Yufei Ma · 2003 · 949 citations
Peer group filtering and perceptual color image quantization
Yining Deng, Charles Kenney, Marguerite Moore et al. · 2003 · 205 citations
Automatic image retargeting with fisheye-view warping
Feng Liu, Michael Gleicher · 2005 · 180 citations