DocumentCode :
3328446
Title :
Computation of optical flow using a neural network
Author :
Zhou, Y.T. ; Chellappa, R.
Author_Institution :
Dept. of Electr. Eng.-Syst., Univ. of Southern California, Los Angeles, CA, USA
fYear :
1988
fDate :
24-27 July 1988
Firstpage :
71
Abstract :
A method for computing optical flow using a neural network is presented. Usually, the measurement primitives used for computing optical flow from successive image frames are the image-intensity values and their spatial and temporal derivatives, and tokens such as edges, corners, and linear features. Conventional methods based on such primitives suffer from edge sparsity, noise distortion, or sensitivity to rotation. The authors first fit a 2-D polynomial to find a smooth continuous image-intensity function in a window and estimate the subpixel intensity values and their principal curvatures. Under the local rigidity assumption and smoothness constraints, a neural network is then used to implement the computing procedure based on the estimated intensity values and their principal curvatures. Owing to the dense measured primitives, a dense optical flow with subpixel accuracy is obtained with only a few iterations. Since intensity values and their principle curvatures are rotation-invariant, this method can detect both rotating and translating objects in the scene. Experimental results using synthetic image sequences demonstrate the efficacy of the method.<>
Keywords :
computerised picture processing; neural nets; 2-D polynomial; computerised picture processing; neural nets; neural network; optical flow; smooth continuous image-intensity function; synthetic image sequences; Image processing; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
Type :
conf
DOI :
10.1109/ICNN.1988.23914
Filename :
23914
Link To Document :
بازگشت