Title :
Dual Analog Focal Plane Sensors for Depth Perception
Author :
Karri, Sirisha S. ; Titus, Albert H.
Abstract :
In this work we propose a neuromorphic algorithm, depth through motion parallax (DTMP) to compute the depth of objects based on the principles of motion parallax. The proposed DTMP algorithm can unambiguously provide the depth information of both stationary and moving objects (moving with constant or time varying velocity). We also describe the possible hardware implementation of the algorithm using dual focal plane analog VLSI sensors that compute the apparent velocity of the object to be used for depth perception.
Keywords :
VLSI; sensors; spatial variables measurement; velocity measurement; apparent velocity computation; depth computation; depth perception; depth through motion parallax; dual focal plane analog VLSI sensors; neuromorphic algorithm; Hardware; Head; Image processing; Neuromorphics; Real time systems; Retina; Sensor phenomena and characterization; Sensor systems; Very large scale integration; Visual system;
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
DOI :
10.1109/IJCNN.2006.247080