The detection and recognition of dim and small infrared (IR) targets across domains pose two formidable challenges: distributional discrepancies in samples and scarcity or absence of annotated instances in the target domain. While current unsupervised domain adaptive object detection methods can somewhat alleviate the performance degradation caused by these issues, they fail to address the differences in semantic content between the background environments in different application scenarios. This results in a semantic gap that impedes the algorithm’s adaptability. We propose a content-decoupled unsupervised domain adaptive method to mitigate the adverse impact of the semantic gap on domain adaptation. Specifically, we introduce an unsupervised task-guided branch in the one-stage detector that executes style transfer in real-time during training, directing the feature representation via shared parameters. A novel content-decoupled feature alignment module aligns semantically unrelated features in the source and target domains while preserving the intrinsic semantics of dim and small IR targets. The experiments on a cross-band IR dataset reveal that the proposed method enhances the mean average precision by 18.3% compared to the baseline detector without increasing computational burden.

We propose a polarized image defogging algorithm according to the sky segmentation results and transmission map optimization. Firstly, we propose a joint sky segmentation method based on scene polarization information, gradient information and light intensity information. This method can effectively segment the sky region and accurately estimate the global parameters such as atmospheric polarization degree and atmospheric light intensity at infinite distance. Then, the Gaussian filter is used to solve the light intensity map of the target, and the information of the polarization degree of the target is solved. Finally, based on the segmented sky region, a three-step transmission optimization method is proposed, which can effectively suppress the halo effect in the reconstructed image of large area sky region. Experimental results shows that defogging has a big improvement in the average gradient of the image and the grayscale standard deviation. Therefore, the proposed algorithm provides strong defogging and can improve the optical imaging quality in foggy scenes by restoring fog-free images.

Specific to the problem of infrared small-target detection in complex backgrounds, a multimechanism deep feature enhancement network model (MDFENet) was proposed. A lightweight multimechanism attention collaborative fusion module was proposed to efficiently fuse low-level features and high-level features to solve the problem that small infrared targets are easy to annihilate in the deep layer of the network. Based on the analysis of the background and target data, a normalized loss function was proposed, which integrates the segmentation threshold selection into the network and normalizes the probability of the network output to simulate a step function and reflect relative differences. Aiming at the sparseness of infrared target features, we used the subpixel convolution method to upsample the features to obtain high-resolution feature images while expanding the size of the feature map. We conducted detailed comparison and ablation experiments, comparing MDFENet with ALCNet, APGCNet, and other state-of-the-art networks to verify the effectiveness and efficiency of the network. Results show that the MDFENet algorithm achieves the optimal result in the balance of detection efficiency and lightweightedness on two datasets.