Title :
A diffusion mechanism for obstacle detection from size-change information
Author :
Ringach, Dario L. ; Baram, Yoram
Author_Institution :
Dept. of Electr. Eng., Technion-Israel Inst. of Technol., Haifa, Israel
Abstract :
A new immediacy measure, representing the imminence of collision between an object and a moving observer, is defined. A diffusion process on the image domain, whose initial condition is determined by the motion field normal to the object´s boundary, is shown to converge asymptotically to the immediacy measure. Bounds on the convergence time for the diffusion process are described. A network of locally connected neurons, derived from a finite-difference approximation of the diffusion equation, estimates the immediacy measure from normal velocity and boundary information provided by layers of motion measurement and segmentation cells. The network´s performance on real image sequences is demonstrated. The proposed scheme is shown to be consistent with observations on the biological visual system
Keywords :
convergence; image sequences; neural nets; visual perception; biological visual system; convergence time; diffusion process; image sequences; immediacy measure; network of locally connected neurons; obstacle detection; performance; segmentation cells; size-change information; Convergence; Diffusion processes; Equations; Finite difference methods; Image converters; Image segmentation; Motion estimation; Motion measurement; Neurons; Velocity measurement;
Conference_Titel :
Electrical and Electronics Engineers in Israel, 1991. Proceedings., 17th Convention of
Conference_Location :
Tel Aviv
Print_ISBN :
0-87942-678-0
DOI :
10.1109/EEIS.1991.217698