Search

In the realm of construction site monitoring, ensuring the proper use of safety helmets is crucial. Addressing the issues of high parameter values and sluggish detection speed in current safety helmet detection algorithms, a feature-enhanced lightweight algorithm, LG-YOLOv8, was introduced. Firstly, we introduce C2f-GhostDynamicConv as a powerful tool. This module enhances feature extraction to represent safety helmet wearing features, aiming to improve the efficiency of computing resource utilization. Secondly, the Bi-directional Feature Pyramid (BiFPN) was employed to further enrich the feature information, integrating feature maps from various levels to achieve more comprehensive semantic information. Finally, to enhance the training speed of the model and achieve a more lightweight outcome, we introduce a novel lightweight asymmetric detection head (LADH-Head) to optimize the original YOLOv8-n's detection head. Evaluations on the SWHD dataset confirm the effectiveness of the LG-YOLOv8 algorithm. Compared to the original YOLOv8-n algorithm, our approach achieves a mean Average Precision (mAP) of 94.1%, a 59.8% reduction in parameters, a 54.3% decrease in FLOPs, a 44.2% increase in FPS, and a 2.7 MB compression of the model size. Therefore, LG-YOLOv8 has high accuracy and fast detection speed for safety helmet detection, which realizes real-time accurate detection of safety helmets and an ideal lightweight effect. [ABSTRACT FROM AUTHOR]

The thermal environment in a geostationary orbit is more complicated than a low orbit. Thermal deformation is a primary factor to deteriorate geometric quality of remote imaging of geostationary optical satellites. The on-orbit geometric quality testing of the SDLT-1 satellite of China shows that the light of sight (LOS) deformation in longitude and latitude are 26 pixels and 14 pixels, respectively, which do not meet the accuracy requirements. Therefore, a novel on-orbit geometric calibration method based on star observation is proposed to improve the geometric deformation. The imager embodied stars are employed as sources to evaluate the developed method and compared with the traditional procedure based upon landmarks. The results show that the geometric accuracy of the new approach is 3.2 pixels which is improved compared to traditional calibration method. [ABSTRACT FROM AUTHOR]

Psoriasis is a chronic autoimmune disease with a long disease course and frequent relapse characteristics. It is now recognised to be associated with epidermal environments of inflammatory cytokines. However, its pathogenesis is still not completely clear. We found the haemorheology of psoriatic patients to be abnormal, and ageing and deformed erythrocytes increased in the blood. The abnormal erythrocytes were more likely to induce psoriasis, which was confirmed in a mouse model induced by different blood components of psoriatic patients/healthy volunteers. Spleen filtration dysfunction, which caused abnormal erythrocytes, was also more likely to induce psoriasis, which was confirmed in a mouse model induced by splenectomy. The mechanism was the weakening of the 'eat me' function of spleen macrophages phagocytizing ageing and deformed erythrocytes, resulting in the dysfunction of spleen filtration and the increase of ageing and deformed erythrocytes in the body. Additionally, the decreased oxygen‐carrying capacity and the declined antioxidant capacity of those erythrocytes led to the hypoxia environment, making psoriasis more likely to be induced. These findings demonstrate that spleen filtration dysfunction contributes to the pathogenesis of psoriasis and suggest that improving it may be an effective therapy for psoriasis and control its relapse. [ABSTRACT FROM AUTHOR]