研究目的
To propose a wrapping-based curvelet transform method for fusion of infrared and visible images to improve situation awareness of an observer during surveillance in poor ambient lighting conditions.
研究成果
The proposed wrapping-based curvelet approach for fusing infrared and visible images outperforms other fusion methods in terms of visual and statistical analysis. It effectively combines hot target information with crisp background details, enhancing the observer's situation awareness during poor ambient lighting conditions by improving perception, the first step to achieving optimal situation awareness.
研究不足
The proposed fusion approach results in a darker shade halo surrounding the hot target region, indicating a potential area for improvement to prevent minimal loss of information.
1：Experimental Design and Method Selection:
A wrapping-based curvelet transform method is proposed for fusion of infrared and visible images. Curvelet transform is chosen for its advantages over wavelet transform, such as better directionality and reconstruction.
2：Sample Selection and Data Sources:
Registered infrared and visible images from the TNO Image Fusion dataset are used.
3：List of Experimental Equipment and Materials:
The study utilizes digital images from the TNO dataset without specifying hardware equipment.
4：Experimental Procedures and Operational Workflow:
The images are decomposed using curvelet transform, with approximation coefficients fused using PCA and detailed coefficients fused using the absolute maximum rule. The fused image is then reconstructed using inverse curvelet transform.
5：Data Analysis Methods:
The performance of the proposed method is compared with other fusion approaches through qualitative (visual analysis) and quantitative (statistical analysis) methods, including standard deviation, entropy, PSNR, and correlation metrics.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
