✦ LIBER ✦

Estimating optical flow with cellular neural networks

✍ Scribed by Shi, B. E.; Roska, T.; Chua, L. O.

Publisher: John Wiley and Sons
Year: 1998
Tongue: English
Weight: 412 KB
Volume: 26
Category: Article
ISSN: 0098-9886
DOI: 10.1002/(sici)1097-007x(199807/08)26:4<343::aid-cta20>3.0.co;2-#

No coin nor oath required. For personal study only.

✦ Synopsis

The cellular neural network is a locally interconnected neural network capable of high-speed computation when implemented in analog VLSI. This work describes a CNN algorithm for estimating the optical flow from an image sequence. The algorithm is based on the spatio-temporal filtering approach to image motion analysis and is shown to estimate the optical flow more accurately than a comparable approach proposed previously. Two innovative features of the algorithm are the exploitation of a biological model for hyperacuity and the development of a new class of spatio-temporal filter better suited for image motion analysis than the commonly used space-time Gabor filter.

📜 SIMILAR VOLUMES

Cellular neural networks with opposite-s

Cellular neural networks with opposite-sign templates for image thinning

✍ Wang, Jun-Sheng; Gan, Qiang; Wei, Yu; Xie, Li 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 131 KB 👁 1 views

This paper presents image thinning algorithms using cellular neural networks (CNNs) with one-or two-dimensional opposite-sign templates (OSTs) as well as non-unity gain output functions. Two four-layer CNN systems with one-dimensional (1-D) OSTs are proposed for image thinning with 4-or 8-connectivi

Second-order optical neural network with

Second-order optical neural network with free-space interconnections

✍ Dong-Xue Wang; Wallace L. Anderson; Mohammad A. Karim 📂 Article 📅 1998 🏛 John Wiley and Sons 🌐 English ⚖ 233 KB

configured setup. The variations in mode sizes are studied for varying input polarizations. It is seen that modes corresponding to TM polarization are more confined than that for TE case. The profiling is carried out only along peak power points, and can be extended for other positions too to have a

Estimating correlation energy of diatomi

Estimating correlation energy of diatomic molecules and atoms with neural networks

✍ e Silva, Geraldo Magela; Acioli, Paulo Hora; Pedroza, Antonio Carlos 📂 Article 📅 1997 🏛 John Wiley and Sons 🌐 English ⚖ 179 KB 👁 1 views

The electronic correlation energy of diatomic molecules and heavy atoms is estimated using a back propagation neural network approach. The supervised learning is accomplished using known exact results of the electronic correlation energy. The recall rate, that is, the performance of the net in recog

Convergence of discrete-time cellular ne

Convergence of discrete-time cellular neural networks with interlaced block-sequential dynamics

✍ Perfetti, R. 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 223 KB 👁 2 views

Some interlaced block-sequential modes of operation are introduced for discrete-time cellular neural networks (DTCNN), and the corresponding convergence conditions are investigated. It is proved that DTCNNs, under some block-sequential updating rules, result to be convergent when the feedback templa

On the design of discrete-time cellular

On the design of discrete-time cellular neural networks with circulant matrices

✍ Grassi, Giuseppe 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 98 KB 👁 2 views

Artificial neural network model with par

Artificial neural network model with parameter tuning assisted by genetic algorithm technique: study of critical velocity of slurry flow in pipeline

✍ S. K. Lahiri; K. C. Ghanta 📂 Article 📅 2009 🏛 Wiley (John Wiley & Sons) 🌐 English ⚖ 420 KB