Advances in Infrared Image Fusion and Detection

The field of infrared image processing is rapidly advancing, with a focus on developing innovative methods for image fusion and target detection. Recent research has emphasized the importance of integrating global and local information, as well as leveraging multi-scale features and evolutionary learning techniques. Notably, the use of deep learning architectures and wavelet transforms has shown significant potential in improving image quality and detection accuracy. Furthermore, the incorporation of contrastive learning and object-aware approaches has enabled more effective fusion of infrared and visible images. Overall, these advancements are paving the way for enhanced performance in various applications, including surveillance and object detection. Noteworthy papers include: MSCA-Net, which proposes a novel network architecture for infrared small target detection, achieving outstanding performance on several benchmark datasets. DCEvo, which introduces a discriminative cross-dimensional evolutionary learning framework for infrared and visible image fusion, demonstrating significant improvements in visual quality and perception accuracy.

Sources

MSCA-Net:Multi-Scale Context Aggregation Network for Infrared Small Target Detection

DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion

Exploring State Space Model in Wavelet Domain: An Infrared and Visible Image Fusion Network via Wavelet Transform and State Space Model

OCCO: LVM-guided Infrared and Visible Image Fusion Framework based on Object-aware and Contextual COntrastive Learning

Residual Learning Inspired Crossover Operator and Strategy Enhancements for Evolutionary Multitasking

Built with on top of