In many actual applications, fused image is essential to contain high-quality details for achieving a comprehensive representation of the real scene. However, existing image fusion methods suffer from loss of details because of the error accumulations of sequential tasks. This paper proposes a novel fusion method to preserve details of infrared and visible images by combining new decomposition, feature extraction, and fusion scheme. For decomposition, different from the most decomposition methods by guided filter, the guidance image contains only the strong edge of the source image but no other interference information so that rich tiny details can be decomposed into the detailed part. Then, according to the different characteristics of infrared and visible detail parts, a rough convolutional neural network (CNN) and a sophisticated CNN are designed so that various features can be fully extracted. To integrate the extracted features, we also present a multi-layer features fusion strategy through discrete cosine transform (DCT), which not only highlights significant features but also enhances details. Moreover, the base parts are fused by weighting method. Finally, the fused image is obtained by adding the fused detail and base part. Different from the general image fusion methods, our method not only retains the target region of source image but also enhances background in the fused image. In addition, compared with state-of-the-art fusion methods, our proposed fusion method has many advantages, including (i) better visual quality of fused-image subjective evaluation, and (ii) better objective assessment for those images.

No abstract

No abstract

To improve navigation safety in maritime environments, a key step is to reduce the influence of human factors on the risk assessment of ship collisions by automating the decision-making process as much as possible. This paper optimizes a dynamic elliptical ship domain based on Automatic Identification System (AIS) data, combines the relative motion between ships in different encounter situations and the level of ship intrusion in the domain, and proposes a ship intrusion collision risk (SICR) model. The simulation results show that the optimized ship domain meets the visualization requirements, and the intrusion model has good collision risk perception ability, which can be used as the evaluation standard of ship collision risk: when the SICR is 0.5–0.6, the ship can establish a collaborative collision avoidance decision-making relationship with other ships, and the action ship can take effective collision avoidance action at the best time when the SICR is between 0.3 and 0.5. The SICR model can give navigators a more accurate and rapid perception of navigation risks, enabling timely maneuvering decisions, and improving navigation safety.