Videos and Presentations

Proto-object based dynamic visual saliency model

Research Summary:

Many current models are feature-based and do not consider motion/temporal change when computing a saliency map. This model is purely bottom-up, object-based saliency model that considers temporal change for computing a dynamic visual saliency map given any video sequence. Current work consists of optimizing the motion-sensitive channel in a biologically-plausible manner. Continuing work involves implementing this model on FPGA hardware.


Project Code and Paper

Related Publication:

  • Russell, A. F., Mihalas, S., von der Heydt, R., Niebur, E., & Etienne-Cummings, R., A model of proto-object based saliency, Vision research, 94, 1-15.
  • Molin, J. L., Russell, A. F., Mihalas, S., Niebur, E., & Etienne-Cummings, R. Proto-object based visual saliency model with a motion-sensitive channel, Proc. BioCAS 2013 (pp. 25-28)
  • T. Figliolia, Mendat, D. R., Russell, A. F., Murray, T. A., Niebur, E., Etienne-Cummings, R., & Andreou, A. G., Auditory Modulation Of Visual Proto-Object Formation In A Hierarchical Auditory-Visual Saliency Map, Proc. CISS 2013, Baltimore, MD, March 2013