The intersecting cortical model in image processing

被引：62

作者：

Ekblad, U ^{[1
]}

Kinser, JM

Atmer, J

Zetterlund, N

机构：

[1] Royal Inst Technol, Dept Phys, S-10044 Stockholm, Sweden

[2] George Mason Univ, Ctr Biomed Genom & Informat, Manassas, VA USA

[3] Linkoping Univ, Linkoping, Sweden

[4] Univ Uppsala, Sch Engn, Uppsala, Sweden

来源：

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT | 2004年 / 525卷 / 1-2期

关键词：

intersecting cortical model; pulse-coupled neural network; motion detection; change detection; aircraft detection; car detection;

D O I：

10.1016/j.nima.2004.03.102

中图分类号：

TH7 [仪器、仪表];

学科分类号：

0804 ; 080401 ; 081102 ;

摘要：

The Intersecting Cortical Model (ICM), or ICM algorithm, is presented. It is a reduced set of equations of the Pulse-Coupled Neural Network (PCNN) model. The ICM algorithm is especially designed for enhancing features without sharp edges or straight lines in images. The ICM is tested on a series of images of an aircraft moving in the sky in order to detect its motion. The ICM algorithm is shown to be useful even when there is a deficiency in reference points. In another test, the ICM is applied to two images taken from a helicopter over a town area. (C) 2004 Elsevier B.V. All rights reserved.

引用

页码：392 / 396

页数：5

共 4 条

[1] Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex [J].

Eckhorn, R. ;

Reitboeck, H. J. ;

Arndt, M. ;

Dicke, P. .

NEURAL COMPUTATION, 1990, 2 (03) :293-307

[2] SEGMENTATION THROUGH THE DETECTION OF CHANGES DUE TO MOTION [J].

JAIN, R ;

MARTIN, WN ;

AGGARWAL, JK .

COMPUTER GRAPHICS AND IMAGE PROCESSING, 1979, 11 (01) :13-34

[3] A simplified pulse-coupled neural network [J].

Kinser, JM .

APPLICATIONS AND SCIENCE OF ARTIFICIAL NEURAL NETWORKS II, 1996, 2760 :563-567

[4]

REICHARDT W, 1957, Z NATURFORSCH 2B, V12, P447, DOI DOI 10.1515/ZNB-1957-0707

← 1 →