Search

With the acceleration of urbanization and the growing demand for traffic safety, developing intelligent systems capable of accurately recognizing and tracking pedestrian trajectories at night or under low-light conditions has become a research focus in the field of transportation. This study aims to improve the accuracy and real-time performance of nighttime pedestrian-detection and -tracking. A method that integrates the multi-object detection algorithm YOLOP with the multi-object tracking algorithm DeepSORT is proposed. The improved YOLOP algorithm incorporates the C2f-faster structure in the Backbone and Neck sections, enhancing feature extraction capabilities. Additionally, a BiFormer attention mechanism is introduced to focus on the recognition of small-area features, the CARAFE module is added to improve shallow feature fusion, and the DyHead dynamic target-detection head is employed for comprehensive fusion. In terms of tracking, the ShuffleNetV2 lightweight module is integrated to reduce model parameters and network complexity. Experimental results demonstrate that the proposed FBCD-YOLOP model improves lane detection accuracy by 5.1%, increases the IoU metric by 0.8%, and enhances detection speed by 25 FPS compared to the baseline model. The accuracy of nighttime pedestrian-detection reached 89.6%, representing improvements of 1.3%, 0.9%, and 3.8% over the single-task YOLO v5, multi-task TDL-YOLO, and the original YOLOP models, respectively. These enhancements significantly improve the model's detection performance in complex nighttime environments. The enhanced DeepSORT algorithm achieved an MOTA of 86.3% and an MOTP of 84.9%, with ID switch occurrences reduced to 5. Compared to the ByteTrack and StrongSORT algorithms, MOTA improved by 2.9% and 0.4%, respectively. Additionally, network parameters were reduced by 63.6%, significantly enhancing the real-time performance of nighttime pedestrian-detection and -tracking, making it highly suitable for deployment on intelligent edge computing surveillance platforms. [ABSTRACT FROM AUTHOR]

The Ni60 alloy cladding layer with different La2O3 content was prepared by laser cladding technology on 35CrMoV surface. The phase composition, element distribution, micro-structure and tribological properties of the coating with different addition of La2O3 were characterized by x-ray diffraction (XRD), scanning electron microscopy (SEM), Microscopic Vickers hardness tester, MicroXAM-800 optical surface photometer and friction testing machine. The results show that the main phases of the cladding layer are (Ni, Fe), CrB, CrMn, Cr7C3 and Cr23C6. The diffraction peak shifted to the left in XRD with the addition of La2O3, which indicates that there is a certain lattice distortion in the cladding phase. The microstructure of the cladding layer is refined, the friction coefficient and the depth of wear trace are decreased to varying degrees, and the wear resistance of the cladding layer is greatly improved. The results show that the addition of 1.6%La2O3 can effectively refine grain, inhibit the formation of cracks and pores, and improve the wear performance of the cladding layer. [ABSTRACT FROM AUTHOR]

Ni-WC composite coatings on 35CrMoV alloy surface were successfully prepared by mechanical vibration field-assisted laser cladding technology. Optical microscopy (OM) and scanning electron microscopy (SEM) were used to study the microstructure of the composite coatings without vibration and at different vibration frequencies; the phase composition of the cladding layer was studied by X-ray diffraction (XRD); and an energy dispersive spectrometer (EDS) was used for elemental plane scanning analysis. The grain growth trend under different convection directions was simulated. The wear resistance and mechanical properties of the composite coating were analyzed by friction and wear testing machine, three-dimensional surface profiler, and microhardness tester. The vibration field generated by the self-improved shaking table device is used to assist laser cladding. The effect of mechanical vibration on the quality of the cladding layer was studied. The results show that compared with the coating without mechanical vibration, an appropriate increase in vibration frequency contributes to the refinement of the grains. The original coarse dendrite structure becomes a fine needle-like structure, and the fine grain size gradually decreases. The application of vibration can improve the effect of grain refinement. The vibration makes the grain size distribution more uniform and the microhardness fluctuation of the cladding layer decreases. The experimental results show that mechanical vibration can improve the microstructure uniformity of the coating by selecting suitable vibration parameters. The average friction coefficient and wear width are reduced, and the microhardness is also increased. [ABSTRACT FROM AUTHOR]

Background: Brown adipose tissue (BAT) is involved both in energy production and bone metabolism. The purpose of this study was to analyze the relationship between BAT and microarchitecture at cancellous and cortical bone using Kunming mice and the methods of 7T magnetic resonance imaging (MRI) combined with micro-CT., Methods: Twenty-four female Kunming mice were examined by 7T MRI and measured T2* relaxation time on the deep and superficial interscapular BAT (iBAT) and subcutaneous white adipose tissue (sWAT). Cancellous bone microarchitecture of the distal femur and cortical bone of the middle femur were examined by micro-CT. A paired t-test was used to analyze the differences in T2* values between iBAT and sWAT. The correlation between BAT T2* values and bone microstructure parameters were analyzed using Pearson's correlation., Results: T2* values of the deep and superficial iBAT (6.36±3.31 ms and 6.23±2.61 ms) were significantly shorter than those of sWAT (16.30±3.05 ms, t(deep) iBAT=-10.816), t(superficial) iBAT =-12.276, p<0.01). Deep iBAT T2* values were significantly and negatively correlated with bone volume, cancellous thickness, and bone thickness (Th) and trabecular thickness (Tb.Th) of the cancellous bone of femur. Deep iBAT T2* values were significantly and positively correlated with the structural model index of cancellous bone of femur. Deep iBAT T2* values were significantly and negatively correlated with bone mineral density of the cortical bone of femur., Conclusions: MRI can distinguish the two adipose tissues from each other. T2* values of BAT were lower than WAT on MRI. BAT related bone remodeling was more correlated with the microstructure of cancellous bone than that of cortical bone., (©The Author(s) 2022. Open Access. This article is licensed under a Creative Commons CC-BY International License.)