Video Saliency Incorporating Spatiotemporal Cues and Uncertainty Weighting

• Published in: IEEE transactions on image processing Vol. 23; no. 9; pp. 3910 - 3921
• Main Authors: Fang, Yuming, Wang, Zhou, Lin, Weisi, Fang, Zhijun
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial Intelligence; Biological system modeling; Biomimetics - methods; Computational modeling; Computer Simulation; Feature extraction; Humans; Image color analysis; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Mathematical models; Models, Statistical; Pattern Recognition, Automated - methods; Perception; Photography - methods; Reproducibility of Results; Sensitivity and Specificity; Spatio-Temporal Analysis; Spatiotemporal phenomena; Subtraction Technique; Temporal logic; Uncertainty; Video Recording - methods; Visual; Visual Perception - physiology; Visualization; Weighting; video saliency; Visual attention; spatiotemporal saliency detection; uncertainty weighting

We propose a novel algorithm to detect visual saliency from video signals by combining both spatial and temporal information and statistical uncertainty measures. The main novelty of the proposed method is twofold. First, separate spatial and temporal saliency maps are generated, where the computati...