STEREOPSIS BY CONSTRAINT LEARNING FEEDFORWARD NEURAL NETWORKS

被引:10
作者
KHOTANZAD, A
BOKIL, A
LEE, YW
机构
[1] Image Processing and Analysis Laboratory, Electrical Engineering Department, Southern Methodist University, Dallas, TX
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1993年 / 4卷 / 02期
关键词
D O I
10.1109/72.207620
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a novel neural network (NN) approach to the problem of stereopsis. The correspondence problem (finding the correct matches between pixels of the epipolar lines of the stereo pair from amongst all the possible matches) is posed as a noniterative many-to-one mapping. Two multilayer feed-forward NN's are utilized to learn and code this nonlinear and complex mapping using the back-propagation learning rule and a training set. The first NN is a conventional fully connected net while the second one is a sparsely connected NN with a fixed number of hidden layer nodes. Three variations of the sparsely connected NN are considered. The important aspect of this technique is that none of the typical constraints such as uniqueness and continuity are explicitly imposed. All the applicable constraints are learned and internally coded by the NN's enabling them to be more flexible and more accurate than the existing methods. The approach is successfully tested on several random-dot stereograms. It is shown that the nets can generalize their learned mappings to cases outside their training sets and to noisy images. Advantages over the Marr-Poggio algorithm are discussed and it is shown that the NN's performances are superior.
引用
收藏
页码:332 / 342
页数:11
相关论文
共 15 条
[1]  
BARNARD ST, 1982, ACM COMPUT SURV, V14, P553
[2]  
DHOND UR, 1989, IEEE T SYST MAN CYBE, V19
[3]  
DRUMHELLER M, 1986, IEEE T ROBOTIC AUTOM, V3, P1439
[4]  
GMITRO AF, 1987, 1ST P IEEE INT C NEU, P599
[5]  
KHOTANZAD A, 1991, ADV NEURAL INFORMATI, V3, P327
[6]  
Lippman R. P., 1987, IEEE ASSP MAGAZI APR, P4
[7]   COOPERATIVE COMPUTATION OF STEREO DISPARITY [J].
MARR, D ;
POGGIO, T .
SCIENCE, 1976, 194 (4262) :283-287
[8]  
NASRABADI NM, 1992, IEEE T NEURAL NETWOR, V3
[9]   STRUCTURE FROM STEREO BY ASSOCIATIVE LEARNING OF THE CONSTRAINTS [J].
OTOOLE, AJ .
PERCEPTION, 1989, 18 (06) :767-782
[10]   GENERALIZATION OF BACK-PROPAGATION TO RECURRENT NEURAL NETWORKS [J].
PINEDA, FJ .
PHYSICAL REVIEW LETTERS, 1987, 59 (19) :2229-2232