In the marine field, infrared detection technology is of great significance for timely localization and detection of ships in security missions. However, since infrared ship targets are often in the environmental conditions of small pixel occupancy, low contrast and complex background, it poses a great challenge for multi-ship detection, classification and localization tasks. Therefore, to address these problems we propose an edge information-guided infrared ship target detection network (EGISD-YOLO), in which a dense-csp structure is designed to improve the csp module of YOLO to increase the reusability of the backbone feature information, and in addition, to address the noise and interference generated by the image in the complex background, a deconvolutional channel attention module (DCA) is designed to link the contextual language to the image. DCA), which relates the contextual semantics to obtain the local information of the target. Crucially, we propose an edge-guided structure that takes the edge information of low-level features as a cue to fuse with deep-level features to enrich the target contour and thus improve the target localization ability, so that the network still possesses robustness under low-contrast conditions, and finally, we add a small-size prediction head at the end of the network to further increase the detection ability of weak targets. The proposed EGISD-YOLO is experimentally demonstrated to have better detection performance for infrared ship targets.

In this paper, a novel fusion network for infrared and visible images is proposed, named Image Pair Learning Fusion Network (IPLF). At present, most of the released deep learning-based fusion models are trained using unsupervised learning. This learning method lacks ground truth and cannot guide network model learning in a targeted manner. First, we propose the use of supervised learning to guide the training of fusion models (IPLF). The generated image pairs are used as ground truth. Second, we propose a model learning strategy using paired images. This learning strategy enhances the complementary constraints of the network model so that the final fused image possesses the rich features of both infrared and visible images. Third, we designed the structure measurement loss function and the edge preservation loss function to ensure that the generated fusion image has rich edge information and comfortable visual effects. In addition, we have introduced a spatial attention module, which can make the final fusion image highlight the target information. Finally, the size of the convolution kernel we use in the first convolution block is $7\ \times\ 7$ , the main purpose is to increase the receptive field. Experiments on the TNO and CVC-14 datasets prove that our proposed method is superior to the existing state-of-the-art methods in terms of qualitative and quantitative evaluation. The source code can be found in https://github.com/depeng6/IPLF .

When traditional super-resolution reconstruction methods are applied to infrared thermal images, they often ignore the problem of poor image quality caused by the imaging mechanism, which makes it difficult to obtain high-quality reconstruction results even with the training of simulated degraded inverse processes. To address these issues, we proposed a thermal infrared image super-resolution reconstruction method based on multimodal sensor fusion, aiming to enhance the resolution of thermal infrared images and rely on multimodal sensor information to reconstruct high-frequency details in the images, thereby overcoming the limitations of imaging mechanisms. First, we designed a novel super-resolution reconstruction network, which consisted of primary feature encoding, super-resolution reconstruction, and high-frequency detail fusion subnetwork, to enhance the resolution of thermal infrared images and rely on multimodal sensor information to reconstruct high-frequency details in the images, thereby overcoming limitations of imaging mechanisms. We designed hierarchical dilated distillation modules and a cross-attention transformation module to extract and transmit image features, enhancing the network’s ability to express complex patterns. Then, we proposed a hybrid loss function to guide the network in extracting salient features from thermal infrared images and reference images while maintaining accurate thermal information. Finally, we proposed a learning strategy to ensure the high-quality super-resolution reconstruction performance of the network, even in the absence of reference images. Extensive experimental results show that the proposed method exhibits superior reconstruction image quality compared to other contrastive methods, demonstrating its effectiveness.

Image fusion operation is beneficial to many applications and is also one of the most common and critical computer vision challenges. The perfect infrared and visible image fusion results should include the important infrared targets while preserving visible textural detail information as much as possible. A novel infrared and visible image fusion framework is proposed for this purpose. In this paper, the proposed fusion network (MIFFuse) is an end-to-end, multi-level-based fusion network for infrared and visible images. The presented approach makes effective use of the intermediate convolution layer’s output features to preserve the primary image fusion information. We also build a cat_block to swap information between two paths to gain more sufficient information during the convolution steps. To reduce the model’s running time even further, the proposed method that reduces the number of feature channels while maintaining the accuracy of the fusion performance. Extensive experiments on the TNO and CVC-14 image fusion datasets show that our MIFFuse outperforms the other methods in terms of both subjective visual effects and quantitative metrics. Furthermore, MIFFuse is approximately twice as fast as the most recent state-of-the-art methods. Our code and models can be found at https://github.com/depeng6/MIFFuse .