OBJECT RECOGNITION IN IMAGE SEQUENCES WITH HOPFIELD NEURAL-NETWORK

被引:0
|
作者
NISHIMURA, K
IZUMI, M
FUKUNAGA, K
机构
[1] Univ of Osaka Prefecture, Sakai-shi, Japan
关键词
ROBOT VISION; OBJECT RECOGNITION; CAMERA MOVING; THE MULTIPLE REGRESSION ANALYSIS; HOPFIELD NEURAL NETWORK;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In case of object recognition using 3-D configuration data, the scale and poses of the object are important factors. If they are not known, we can not compare the object with the models in the database. Hence we propose a strategy for object recognition independently of its scale and poses, which is based on Hopfield neural network. And we also propose a strategy for estimation of the camera motion to reconstruct 3-D configuration of the object. In this strategy, the camera motion is estimated only with the sequential images taken by a moving camera. Consequently, the 3-D configuration of the object is reconstructed only with the sequential images. And we adopt the multiple regression analysis for estimation of the camera motion parameters so as to reduce the errors of them.
引用
收藏
页码:1058 / 1064
页数:7
相关论文
共 50 条
  • [11] A quantum Hopfield neural network model and image recognition
    Liu, Ge
    Ma, Wen-Ping
    Cao, Hao
    Lyu, Liang-Dong
    LASER PHYSICS LETTERS, 2020, 17 (04)
  • [12] LANDMARK-BASED SHAPE-RECOGNITION BY A MODIFIED HOPFIELD NEURAL-NETWORK
    ANSARI, N
    LI, K
    PATTERN RECOGNITION, 1993, 26 (04) : 531 - 542
  • [13] Object recognition in image sequences with cellular neural networks
    Milanova, M
    Büker, U
    NEUROCOMPUTING, 2000, 31 (1-4) : 125 - 141
  • [14] GENERALIZED HOPFIELD NEURAL-NETWORK FOR CONCURRENT TESTING
    ORTEGA, J
    PRIETO, A
    LLORIS, A
    PELAYO, FJ
    IEEE TRANSACTIONS ON COMPUTERS, 1993, 42 (08) : 898 - 912
  • [15] A HOPFIELD NEURAL-NETWORK MODEL IN A TRANSVERSE FIELD
    MA, YQ
    ZHANG, YM
    GONG, CD
    COMMUNICATIONS IN THEORETICAL PHYSICS, 1994, 21 (02) : 253 - 256
  • [16] AUTOMATIC FAULT RECOGNITION BY IMAGE CORRELATION NEURAL-NETWORK TECHNIQUES
    SZU, HH
    IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 1993, 40 (02) : 197 - 208
  • [17] THE HOPFIELD NEURAL-NETWORK APPLIED TO THE QUADRATIC ASSIGNMENT PROBLEM
    BOUSONOCALZON, C
    MANNING, MRW
    NEURAL COMPUTING & APPLICATIONS, 1995, 3 (02): : 64 - 72
  • [18] OPTIMAL PATH DETERMINATION IN A GRAPH BY HOPFIELD NEURAL-NETWORK
    CAVALIERI, S
    DISTEFANO, A
    MIRABELLA, O
    NEURAL NETWORKS, 1994, 7 (02) : 397 - 404
  • [19] A GENETIC APPROACH TO THE HOPFIELD NEURAL-NETWORK IN THE OPTIMIZATION PROBLEMS
    ARABAS, J
    BULLETIN OF THE POLISH ACADEMY OF SCIENCES-CHEMISTRY, 1994, 42 (01): : 59 - 66
  • [20] EDGE-DETECTION USING A HOPFIELD NEURAL-NETWORK
    CHAO, CH
    DHAWAN, AP
    OPTICAL ENGINEERING, 1994, 33 (11) : 3739 - 3747