The field of infrared vision systems is moving towards developing innovative solutions for enhanced safety and detection in low-visibility conditions. Researchers are exploring the potential of infrared camera technology to improve driver safety for emergency vehicles operating in challenging environments. Furthermore, there is a growing focus on developing lightweight and high-performance infrared small target detection algorithms, which can effectively detect and track targets in complex backgrounds. Additionally, domain adaptation techniques are being investigated to enable the adaptation of visible-to-thermal domain object detection models, reducing the need for large annotated infrared datasets. Noteworthy papers in this area include: ISTD-YOLO, which proposes a lightweight infrared small target detection algorithm that achieves high-quality detection of small targets. DCFG, which introduces a novel Siamese tracker based on cross-channel fine-grained feature learning and progressive fusion for thermal infrared target tracking. SAGA, which proposes a semantic-aware gray color augmentation strategy for mitigating color bias and bridging the domain gap in visible-to-thermal domain adaptation. Rethinking Generalizable Infrared Small Target Detection, which introduces an ISTD framework enhanced by domain adaptation and proposes a noise-guided representation learning strategy to improve generalization capability across diverse noisy domains.