The technology of infrared dim- and small-target detection is irreplaceable in many fields, such as those of missile early warning systems and forest fire prevention, among others. However, numerous components interfere with infrared imaging, presenting challenges for achieving successful detection of infrared dim and small targets with a low rate of false alarms. Hence, we propose a new infrared dim- and small-target detection network, Multiscale Feature Extraction U-Net for Infrared Dim- and Small-Target Detection (MFEU-Net), which can accurately detect targets in complex backgrounds. It uses the U-Net structure, and the encoders and decoders consist of ReSidual U-block and Inception, allowing rich multiscale feature information to be extracted. Thus, the effectiveness of algorithms in detecting very small-sized targets can be improved. In addition, through the multidimensional channel and spatial attention mechanism, the model can be adjusted to focus more on the target area in the image, improving its extraction of target information and detection performance in different scenarios. The experimental results show that our proposed algorithm outperforms other advanced algorithms in detection performance. On the MFIRST, SIRST, and IRSTD-1k datasets, we achieved detection rates of 0.864, 0.962, and 0.965; IoU values of 0.514, 0.671, and 0.630; and false alarm rates of 3.08 × ${10}^{-5}$, 2.61 × ${10}^{-6}$, and 1.81 × ${10}^{-5}$, respectively.

Infrared and visible remote sensing image registration is significant for utilizing remote sensing images to obtain scene information. However, it is difficult to establish a large number of correct matches due to the difficulty in obtaining similarity metrics due to the presence of radiation variation between heterogeneous sensors, which is caused by different imaging principles. In addition, the existence of sparse textures in infrared images as well as in some scenes and the small number of relevant trainable datasets also hinder the development of this field. Therefore, we combined data-driven and knowledge-driven methods to propose a Radiation-variation Insensitive, Zero-shot learning-based Registration (RIZER). First, RIZER, as a whole, adopts a detector-free coarse-to-fine registration framework, and the data-driven methods use a Transformer based on zero-shot learning. Next, the knowledge-driven methods are embodied in the coarse-level matches, where we adopt the strategy of seeking reliability by introducing the HNSW algorithm and employing a priori knowledge of local geometric soft constraints. Then, we simulate the matching strategy of the human eye to transform the matching problem into a model-fitting problem and employ a multi-constrained incremental matching approach. Finally, after fine-level coordinate fine tuning, we propose an outlier culling algorithm that only requires very few iterations. Meanwhile, we propose a multi-scene infrared and visible remote sensing image registration dataset. After testing, RIZER achieved a correct matching rate of 99.55% with an RMSE of 1.36 and had an advantage in the number of correct matches, as well as a good generalization ability for other multimodal images, achieving the best results when compared to some traditional and state-of-the-art multimodal registration algorithms.

Infrared target detection has a wide range of application value, but due to the characteristics of infrared images, infrared targets are easily submerged in the complex background. Therefore, in complex scenes, it is difficult to effectively and accurately detect infrared dim small targets. For this reason, we design an infrared dim small target (IDST) detection algorithm containing Large-size Receptive Fields (LRFNet). It uses the Residual network with an Inverted Pyramid Structure (RIPS), which consists of convolutional layers that become progressively smaller, so it can have a larger effective receptive field and can improve the robustness of the model. In addition, through the Attention Mechanisms with Large Receptive Fields and Inverse Bottlenecks (LRIB), it can make the network better localize the region where the target is located and improve the detection effect of the model. The experimental results show that our proposed algorithm outperforms other state-of-the-art algorithms in all evaluation metrics.

Infrared and visible remote sensing image matching is significant for the utilization of remote sensing images to obtain scene information. However, due to the large number of sparse and repetitive texture regions in multimodal remote sensing scenes, feature extraction poses serious difficulties. To address these challenges, this letter proposes attention-based features (AttFeat). First, to solve the problem of coarse feature representation, we propose the parallel channel and spatial attention (PCSA) module, which focuses on important spatial locations and provides richer cross-channel representation. Second, to address the lack of contextual information, we propose the squeezed-axis and window transformer (SAWFormer), which can obtain a dense global receptive field at a lower cost while retaining rich details. Finally, multimodal recoupling loss is utilized to optimize the relationship between the rich feature description and large receptive field. Extensive experiments on aviation and remote sensing multimodal datasets demonstrate the superiority of our algorithm and the effectiveness of the proposed modules. In terms of detection and matching performance, AttFeat outperforms the baseline ReDFeat by 10.81% and 15.48%, respectively. The dataset and code will be released at: https://github.com/Jayden-Li-UCAS/AttFeat