Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 2021

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

A single upper limb pose estimation method based on the improved stacked hourglass network

Peng Gang, Zheng Yuezhi, Li Jianfeng, Yang Jin

International Journal of Applied Mathematics and Computer Science

2021

Vol. 31, no. 1

123--133

At present, most high-accuracy single-person pose estimation methods have high computational complexity and insufficient real-time performance due to the complex structure of the network model. However, a single-person pose estimation method with high real-time performance also needs to improve its accuracy due to the simple structure of the network model. It is currently difficult to achieve both high accuracy and real-time performance in single-person pose estimation. For use in human–machine cooperative operations, this paper proposes a single-person upper limb pose estimation method based on an end-to-end approach for accurate and real-time limb pose estimation. Using the stacked hourglass network model, a single-person upper limb skeleton key point detection model is designed. A deconvolution layer is employed to replace the up-sampling operation of the hourglass module in the original model, solving the problem of rough feature maps. Integral regression is used to calculate the position coordinates of key points of the skeleton, reducing quantization errors and calculations. Experiments show that the developed single-person upper limb skeleton key point detection model achieves high accuracy and that the pose estimation method based on the end-to-end approach provides high accuracy and real-time performance.

Dynamic splitting tensile behaviour and statistical scaling law of hybrid basalt-polypropylene fibre-reinforced concrete

Fu Qiang, Zhao Xu, Zhang Zhaorui, Peng Gang, Zeng Xiaohui, Niu Ditao

Archives of Civil and Mechanical Engineering

2021

Vol. 21, no. 4

123--144

The dynamic splitting tensile behaviour of hybrid basalt‒polypropylene fibre-reinforced concrete (HBPRC) was investigated, and the reinforcing mechanism of the fibres was explored. The results indicate that the dynamic splitting tensile strength and dynamic energy dissipation capacity of HBPRC increased with strain rate. The effects of fibre type and content on the strain rate sensitivity of dynamic splitting tensile strength were consistent with that of dynamic dissipation energy. Furthermore, the dynamic splitting tensile strength of concrete was improved by adding appropriate content of basalt fibre (BF) and polypropylene fibre (PF), and the improving effect of hybrid BF and PF was the most significant. Excess fibres reduced the dynamic splitting tensile strength at low strain rates but improved it at high strain rates. The addition of fibres improved the dynamic dissipation energy and the impact resistance of concrete. With an increase in the strain rate, the pull-out lengths of BF and PF decreased gradually. When using hybrid BF and PF, the failure morphology of BF did not change considerably, although PF underwent more severe damage. Based on the weakest-link theory, a calculation model for the statistical scaling law of dynamic splitting tensile strength considering the strain rate effect was established.