This paper tackles the challenges of infrared small target detection, aiming to improve detection accuracy and robustness in complex, low-contrast infrared environments. We propose several novel enhancements to YOLO-based models, commonly employed in real-time target detection tasks. First, we introduce a Multi-Scale Dilated Separable Fusion (MDSF) block, a flexible plug-in that can replace traditional convolution layers and be inserted at various stages of the network. This module enhances the network’s sensitivity to small targets by leveraging large convolution kernels in conjunction with multi-scale decomposition. Next, we design a Deep Feature Fusion (DFF) module and a Multi-Scale Dilated Separable Fusion Head (MDSF-Head) based on the MDSF block, and integrate them into YOLO models (v5-v11), resulting in significant performance gains, with mAP@50 values improving by 5.4% to 9.6%. Furthermore, we propose the coarse-to-fine Spatial and Channel Reconstruction Convolution (C2f_SCConv) module, which effectively fuses shallow spatial features with deep semantic features, boosting detection performance, particularly for occluded and small targets. Additionally, we incorporate the Spatial-to-Depth Convolution (SPD) module and replace the traditional Complete IoU (CIoU) with Efficient-IoU (EIoU) to further optimize the model. Experimental results on the Forward Looking Infrared ADAS (FLIR) dataset demonstrate that our approach outperforms the baseline YOLOv8n, with improvements of 10.9% in mAP@50 and 10.3% in mAP@50-95. On the High-altitude Infrared Thermal dataset for Unmanned Aerial Vehicle-based object detection (HIT-UAV) dataset, we observe similar improvements, with mAP@50 increasing by 8.1% and mAP@50-95 by 9.7%. These results validate the effectiveness of our proposed method, substantially enhancing detection accuracy, robustness, and adaptability in challenging infrared environments.

A parallel high-resolution underwater target detection network is proposed to address the problems of complex underwater scenes and limited target feature extraction capability. First, a high-resolution network (HRNet), a lighter high-resolution human posture estimation network, is used to improve the target feature representation and effectively reduce the semantic information lost in the image during sampling. Then, the attention module (A-CBAM) is improved to capture complex feature distributions by modeling the two-dimensional space in the activation function stage through the introduction of the flexible rectified linear units (FReLU) activation function to achieve pixel-level spatial information modeling capability. Feature enhancement in the spatial and channel dimensions is performed to improve understanding of fuzzy targets and small target objects and to better capture irregular and detailed object layouts. Finally, a receptive field augmentation module (RFAM) is constructed to obtain sufficient semantic information and rich detail information to further enhance the robustness and discrimination of features and improve the detection capability of the model for multi-scale underwater targets. Experimental results show that the method achieves 81.17%, 77.02%, and 82.9% mean average precision (mAP) on three publicly available datasets, specifically underwater robot professional contest (URPC2020, URPC2018) and pattern analysis, statistical modeling, and computational learning visual object classes (PASCAL VOC2007), respectively, demonstrating the effectiveness of the proposed network.

Detailed density functional theory (DFT) calculations of the structural, mechanical, thermodynamic, and electronic properties of crystalline CaF₂ with five different structures in the pressure range of 0 GPa–150 GPa are performed by both GGA (generalized gradient approximation)-PBE (Perdew–Burke–Ernzerhof) and LDA (local density approximation)-CAPZ (Cambridge Serial Total Energy Package). It is found that the enthalpy differences imply that the fluorite phase → PbCl₂-type phase → Ni₂In-type phase transition in CaF₂ occurs at P _GGA1 = 8.0 GPa, P _GGA2 = 111.4 GPa by using the XC of GGA, and P _LDA1 = 4.5 GPa, P _LDA2 = 101.7 GPa by LDA, respectively, which is consistent with previous experiments and theoretical conclusions. Moreover, the enthalpy differences between PbCl₂-type and Ni₂In-type phases in one molecular formula become very small at the pressure of about 100 GPa, indicating the possibility of coexistence of two-phase at high pressures. This may be the reason why the transition pressure of the second phase transition in other reports is so huge (68 GPa–278 GPa). The volume changed in the second phase transition are also consistent with the enthalpy difference result. Besides, the pressure dependence of mechanical and thermodynamic properties of CaF₂ is studied. It is found that the high-pressure phase of Ni₂In-type structure has better stiffness in CaF₂ crystal, and the hardness of the material has hardly changed in the second phase transition. Finally, the electronic structure of CaF₂ is also analyzed with the change of pressure. By analyzing the band gap and density of states, the large band gap indicates the CaF₂ crystal is always an insulator at 0 GPa–150 GPa.