Multi-sensor image fusion focuses on processing images of the same object or scene acquired by multiple sensors, in which various sensors with multi-level and multi-spatial information are complemented and combined to ultimately yield a consistent interpretation of the observed environment. In recent years, multi-sensor image fusion has become a highly active topic, and various fusion methods have been proposed. Many effective processing methods, including multi-scale transformation, fuzzy inference, and deep learning, have been introduced to design fusion algorithms. Despite the great progress, there are still some noteworthy challenges in the field, such as the lack of unified fusion theories and methods for effective generalized fusion, the lack of fault tolerance and robustness, the lack of benchmarks for performance evaluation, the lack of work on specific applications of multi-sensor image fusion, and so on.
This research topic focuses on reporting advanced studies related to multi-sensor image fusion, including methods, evaluations, and applications, aiming to promote the development of multi-sensor image fusion techniques and applied it to medical image segmentation, biology analysis and astronomy imaging. More specifically, this research topic expects high-quality work such as unified fusion theories and effective generalized fusion methods, effective performance evaluation methods for multi-sensor image fusion, and practical applications of multi-sensor image fusion in classification, detection and segmentation tasks. Multi-sensor fusion methods can be developed based on traditional processing methods or deep learning methods. For performance evaluations, benchmarks involving datasets, objective metrics, and baseline creation methods are welcome to be investigated. In addition, specific applications are also welcome to be studied, such as the fusion of images from different modalities using multi-sensor fusion techniques.
• Multi-sensor image registration
• Multi-sensor image fusion
• High dynamic range imaging
• Machine learning/deep learning for multi-sensor image fusion and segmentation
• Multi-sensor image fusion datasets and benchmarks
• Objective evaluation of multi-sensor image fusion
• Multi-sensor image fusion in different fields
• Multi-sensor image monitoring and detection
Multi-sensor image fusion focuses on processing images of the same object or scene acquired by multiple sensors, in which various sensors with multi-level and multi-spatial information are complemented and combined to ultimately yield a consistent interpretation of the observed environment. In recent years, multi-sensor image fusion has become a highly active topic, and various fusion methods have been proposed. Many effective processing methods, including multi-scale transformation, fuzzy inference, and deep learning, have been introduced to design fusion algorithms. Despite the great progress, there are still some noteworthy challenges in the field, such as the lack of unified fusion theories and methods for effective generalized fusion, the lack of fault tolerance and robustness, the lack of benchmarks for performance evaluation, the lack of work on specific applications of multi-sensor image fusion, and so on.
This research topic focuses on reporting advanced studies related to multi-sensor image fusion, including methods, evaluations, and applications, aiming to promote the development of multi-sensor image fusion techniques and applied it to medical image segmentation, biology analysis and astronomy imaging. More specifically, this research topic expects high-quality work such as unified fusion theories and effective generalized fusion methods, effective performance evaluation methods for multi-sensor image fusion, and practical applications of multi-sensor image fusion in classification, detection and segmentation tasks. Multi-sensor fusion methods can be developed based on traditional processing methods or deep learning methods. For performance evaluations, benchmarks involving datasets, objective metrics, and baseline creation methods are welcome to be investigated. In addition, specific applications are also welcome to be studied, such as the fusion of images from different modalities using multi-sensor fusion techniques.
• Multi-sensor image registration
• Multi-sensor image fusion
• High dynamic range imaging
• Machine learning/deep learning for multi-sensor image fusion and segmentation
• Multi-sensor image fusion datasets and benchmarks
• Objective evaluation of multi-sensor image fusion
• Multi-sensor image fusion in different fields
• Multi-sensor image monitoring and detection
