基于生物视觉特性的红外与可见光图像融合方法

J4 ›› 2012, Vol. 34 ›› Issue (9): 83-87.

基于生物视觉特性的红外与可见光图像融合方法

李敏,蔡伟

(第二炮兵工程大学,陕西西安 710025)

收稿日期:2011-11-18 修回日期:2012-05-17 出版日期:2012-09-25 发布日期:2012-09-25
基金资助:
国家自然科学基金资助项目（61102170）

Biological Visual Characteristic Based Infrared and Visible Image Fusion Scheme

LI Min，CAI Wei

(The Second Artillery Engineering University,Xi’an 710025,China)

Received:2011-11-18 Revised:2012-05-17 Online:2012-09-25 Published:2012-09-25

摘要/Abstract

摘要：

脉冲耦合神经网络PCNN以其在图像分割、目标识别等领域的独特优势而成为当前的研究热点。本文对其在红外与可见光图像融合领域的应用进行了研究，并针对传统脉冲耦合神经网络参数无法自动设定的难题，提出了基于修正PCNN的参数自动设定方案。针对可见光与红外图像融合的大量实验结果表明，本文方法无论在主观视觉效果还是客观评价参数上均明显优于基于多分辨分析的融合算法，对于拓宽PCNN的应用领域有一定价值。

关键词: 多传感器图像融合, 脉冲耦合神经网络, 参数设定, 客观评价准则

Abstract:

The Pulse Coupled Neural Network (PCNN) model of the cat visual cortex has proven to have interesting properties in image processing,including segmentation,target recognition et al.This paper proposes a multisensor image fusion scheme based on the modified PCNN.Focusing on the famous difficult problem of PCNN and how to determine PCNN parameters adaptively,this paper brings forward an adaptive PCNN parameters determination algorithm based on water area.Experimental results demonstrate that the proposed fusion scheme outperforms the multiscale decomposition based fusion approaches,both in visual effect and objective evaluation criteria.The research fruits have certain value on the theory research and practical application of PCNN.

Key words: multisensor image fusion；pulsecoupled neural network (PCNN)；parameter determination；objective evaluation criteria

李敏,蔡伟. 基于生物视觉特性的红外与可见光图像融合方法[J]. J4, 2012, 34(9): 83-87.

LI Min，CAI Wei. Biological Visual Characteristic Based Infrared and Visible Image Fusion Scheme[J]. J4, 2012, 34(9): 83-87.

参考文献

［1］Broussard R P, Rogers S K, Mark E, et al. Physiologically Motivated Image Fusion for Object Detection Using a Pulse Coupled Neural Network［J］.IEEE Transaction on Neural Networks,1999,10(3):554563.
［2］Eckhorn R, ReitBoeck H J. Feature Linking via Synchronization among Distributed Assemblies: Simulation of Results form Cat Visual Cortex［J］. Neural Computation, 1990, 2(3):293307.
［3］Kuntimad G, Ranganath H S. Perfect Image Segmentation Using Pulse Coupled Neural Networks［J］. IEEE Transaction on Neural Networks, 1999, 10(3):591598.
［4］Hall D L, Llinas J. An Introduction to Multisensor Data Fusion［J］.Proc of IEEE, 1997, 85(1):623.
［5］Piella G. A General Framework for Multiresolution Image Fusion: From Pixels to Regions ［J］. Information Fusion, 2003(4):259280.
［6］Zhang Z, Blum R S. A Categorization of Multiscaledecompositionbased Image Fusion Schemes with a Performance Study for a Digital Camera Application［J］. Proc of IEEE, 1999,87(8):13151326.
［7］黄继武，Shi Y Q，戴宪华. 基于视觉系统特性的图像分割编码算法［J］. 中国图象图形学报, 1999, 4(5):400404.
［8］Xydaes C,Petrovi V.Objective Image Fusion Performance Measure［J］. Electronic Letters, 2000, 36(4):308309.
［9］马义德, 张红娟. PCNN与灰度形态学相结合的图像去噪方法［J］. 北京邮电大学学报, 2008, 31（2）:108112.
［10］刘勍,许录平,马义德,等. 基于PCNN噪声检测的两级脉冲噪声滤波算法［J］. 光电子与激光, 2009, 20(11):14691470.
［11］Gu X D. Feature Extraction Using Unitlinking Pulse Coupled Neural Network and Its Applications［J］. Neural Processing Letters,2008, 27(1):2541.
［12］毕英伟, 邱天爽. 一种基于简化PCNN的自适应图像分割方法［J］. 电子学报, 2005, 33(4):647650.
［13］Karvonen J A. Baltic Sea Ice SAR Segmentation and Classification Using Modified Pulsecoupled Neural Networks［J］. IEEE Transaction on Geoscience and Remote Sensing, 2004, 42(7):15661574.

[1]	邹北骥,胡艺龄,辛国江. 基于小波分解和PCNN的图像融合方法[J]. J4, 2011, 33(2): 102-107.
[2]	毛华章毅. 基于PCNN图像分割与边缘匹配的支票验证方法[J]. J4, 2008, 30(11): 38-41.