TY - JOUR

T1 - Sensor noise effects on signal-level image fusion performance.

AU - Petrovic, Vladimir S.

AU - Xydeas, Costas

N1 - The novel and leading, both chronologically and technically, concepts of this paper on objective image fusion metrics as applied to practical noisy input modalities provided for the first time researchers with the means i) to carry out subjectively meaningful comparative assessments of different image fusion algorithms and ii) to accurately and efficiently optimise fusion algorithms. This work has been identified and supported by BAES, Warton ( Dr. D. Parker) for aerospace applications. RAE_import_type : Journal article RAE_uoa_type : Electrical and Electronic Engineering

PY - 2003/9/1

Y1 - 2003/9/1

N2 - The aim of this paper is twofold: (i) to define appropriate metrics which measure the effects of input sensor noise on the performance of signal-level image fusion systems and (ii) to employ these metrics in a comparative study of the robustness of typical image fusion schemes whose inputs are corrupted with noise. Thus system performance metrics for measuring both absolute and relative degradation in fused image quality are proposed when fusing noisy input modalities. A third metric, which considers fusion of noise patterns, is also developed and used to evaluate the perceptual effect of noise corrupting homogenous image regions (i.e. areas with no salient features). These metrics are employed to compare the performance of different image fusion methodologies and feature selection/information fusion strategies operating under noisy input conditions. Altogether, the performance of seventeen fusion schemes is examined and their robustness to noise considered at various input signal-to-noise ratio values for three types of sensor noise characteristics.

AB - The aim of this paper is twofold: (i) to define appropriate metrics which measure the effects of input sensor noise on the performance of signal-level image fusion systems and (ii) to employ these metrics in a comparative study of the robustness of typical image fusion schemes whose inputs are corrupted with noise. Thus system performance metrics for measuring both absolute and relative degradation in fused image quality are proposed when fusing noisy input modalities. A third metric, which considers fusion of noise patterns, is also developed and used to evaluate the perceptual effect of noise corrupting homogenous image regions (i.e. areas with no salient features). These metrics are employed to compare the performance of different image fusion methodologies and feature selection/information fusion strategies operating under noisy input conditions. Altogether, the performance of seventeen fusion schemes is examined and their robustness to noise considered at various input signal-to-noise ratio values for three types of sensor noise characteristics.

KW - Image fusion

KW - Fusion performance evaluation

KW - Sensor noise effect

KW - DCS-publications-id

KW - art-802

KW - DCS-publications-credits

KW - dsp

KW - DCS-publications-personnel-id

KW - 24

U2 - 10.1016/S1566-2535(03)00035-6

DO - 10.1016/S1566-2535(03)00035-6

M3 - Journal article

VL - 4

SP - 167

EP - 183

JO - Information Fusion

JF - Information Fusion

SN - 1566-2535

IS - 3

ER -