Tracking and classifying 3D objects from TV pictures-a neural network approach
作者： A. Dobnikar , A. Likar , B. Jurcic-Zlobec , D. Podbregar
DOI: 10.1109/IJCNN.1991.170421
关键词: Video tracking 、 Object (computer science) 、 Time delay neural network 、 Pattern recognition (psychology) 、 Artificial intelligence 、 Parallel processing (DSP implementation) 、 Tracking (particle physics) 、 Computer vision 、 Kalman filter 、 Computer science 、 Artificial neural network
摘要: The authors introduce two specialized neural networks, one for tracking and another classification of a 3-D moving object from TV pictures. Their structures follow directly the analysis corresponding functions. It is shown that this approach gives equally good results in tasks as optimal Kalman filtering procedure, it even overcomes obtained with Fourier transformations an object's contours. With parallel processing real time applications seem feasible. input images are taken sequentially digitized pictures showing movement along its trajectories. responsibility function to make changes window properly. proposed network same quality can be achieved method. objects performed by also encouraging results. >
sci-hub.se 参考文章(18)
Teuvo Kohonen, Self-organized formation of topologically correct feature maps Biological Cybernetics. ,vol. 43, pp. 509- 521 ,(1988) , 10.1007/BF00337288
Real-time/parallel computing Plenum Publishing Co.,New York, NY, USA. ,(1981) , 10.1007/978-1-4684-3893-2
Morio Onoe, Azriel Rosenfeld, Kendall Preston, Real-Time Parallel Computing: Imaging Analysis New York : Plenum Press. ,(1981)
J. Austin, ADAM: an associative neural architecture for invariant pattern classification international conference on artificial neural networks. pp. 196- 200 ,(1989)
Yoh-Han Pao, Adaptive pattern recognition and neural networks ,(1989)
How patterned neural connections can be set up by self-organization. Proceedings of The Royal Society B: Biological Sciences. ,vol. 194, pp. 431- 445 ,(1976) , 10.1098/RSPB.1976.0087
A. Dobnikar, J. Ficzko, D. Podbregar, U. Rezar, Invariant pattern classification neural network versus FT approach Microprocessing and Microprogramming. ,vol. 33, pp. 161- 168 ,(1992) , 10.1016/0165-6074(92)90018-3
Michael Seibert, Allen M. Waxman, Spreading activation layers, visual saccades, and invariant representations for neural pattern recognition systems Neural Networks. ,vol. 2, pp. 9- 27 ,(1989) , 10.1016/0893-6080(89)90012-9
Kunihiko Fukushima, Analysis of the process of visual pattern recognition by the neocognitron Neural Networks. ,vol. 2, pp. 413- 420 ,(1989) , 10.1016/0893-6080(89)90041-5
A.C.C. Coolen, F.W. Kuijk, A learning mechanism for invariant pattern recognition in neural networks Neural Networks. ,vol. 2, pp. 495- 506 ,(1989) , 10.1016/0893-6080(89)90046-4