Data Fusion for Improved Image Processing using Signal Models
PDF

Keywords

Data fusion
image processing
signal models
multi-sensor integration
sparse representation
feature extraction

Abstract

Data fusion techniques have become a cornerstone in advancing image processing capabilities by integrating complementary information from multiple sources. This paper explores the application of signal models in data fusion to enhance image quality, feature extraction, and interpretation accuracy. The study reviews common signal models utilized in image fusion, including linear, Bayesian, and sparse representation models, highlighting their advantages in diverse imaging scenarios. A comparative analysis using multi-sensor datasets demonstrates improved denoising, resolution enhancement, and robustness to noise when applying fusion based on these signal models. Experimental results underscore the effectiveness of data fusion in complex environments, with a case study involving infrared and visible spectrum images. The paper concludes with a discussion on challenges and future trends in signal-model-based data fusion for image processing.

PDF
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright (c) 2022 Dr. Elena Martinez (Author)