Title :
Saliency pattern detection via simulated saccade in naturally complex scenes
Author_Institution :
Fac. of Inf. Sci. & Technol., Osaka Inst. of Technol., Osaka, Japan
Abstract :
Joint stochastic-computational dynamics is introduced in image-color spaces for associative detection of saliency patterns from complex scene images. By regenerating the chromatic diversity by fractal attractor controlled by as-is primaries, saliency patterns are separated from noisy background. Resulted saliency patterns are efficiently detected via saccadic dynamics nondeterministically spanning boundary objects.
Keywords :
computer vision; fractals; image colour analysis; natural scenes; object detection; stochastic processes; as-is primaries; chromatic diversity; fractal attractor; image color spaces; naturally complex scenes; saliency pattern detection; simulated saccade; spanning boundary objects; stochastic computational dynamics; Complexity theory; Fractals; Image color analysis; Indexes; Trajectory; Vehicles; Visualization; As-is Primary; Naturally Complex Scene; Saliency Pattern Detection; Simulated Saccade;
Conference_Titel :
SICE Annual Conference (SICE), 2011 Proceedings of
Conference_Location :
Tokyo
Print_ISBN :
978-1-4577-0714-8
