Title :
Eye movement computation model based on short-term memory optical flow image
Author_Institution :
Fac. of Eng., Yamaguchi Univ., Ube, Japan
fDate :
30 July-1 Aug. 2003
Abstract :
In this paper, we introduced a computation model of eye movement using the short-term memory optical flow image. We also applied this model into the simulation of driver´s eye movements in an open road. The computation model of the eye movement is based on the parallel tasks and the short-term memory. It is especially important to realize certain driving tasks, which involve tracking the moving vehicles, identifying road sign, and estimating the road shape. The short-term memories corresponding to tasks are used due to change the attention region. We show that the viewpoint moves smoothly in the wide region by using the short-term memory image generated by the low-level features of the optical flow. We simulate the driver´s eye movement and show the efficiency of this model.
Keywords :
driver information systems; image processing; image sequences; object detection; optical computing; sensor fusion; computation model; eye movement; optical flow; road shape estimation; road sign identification; short-term memory image; vehicle tracking; Computational modeling; Equations; Humans; Image motion analysis; Optical arrays; Optical computing; Optical sensors; Psychology; Retina; Roads;
Conference_Titel :
Multisensor Fusion and Integration for Intelligent Systems, MFI2003. Proceedings of IEEE International Conference on
Print_ISBN :
0-7803-7987-X
DOI :
10.1109/MFI-2003.2003.1232569