Abstract
Abstract
Particle tracking velocity has reached a high level of maturity in time-resolved measurements since the introduction and development of the Shake-The-Box algorithm. The effectiveness of this approach lies, in part, in its ability to exploit the temporal coherence of particle trajectories to reject the ghost particles while increasing the density of true particles. However, certain situations may prevent time-resolved measurements. In those cases, a Two-Pulse configuration is often the only option. This raises a challenge with regard to the capacity in separating the ghost from the true particles due to the lack of long-term trajectories. This article proposes a new approach to solve this problem using the coherent point drift (CPD) method. This method identifies a spatially coherent deformation field that models the transformation between two correlated sets of points. In the context of particle tracking velocimetry, the imposed spatial coherence of this calculation is believed to act in the same way as the temporal coherence that made Shake-The-Box successful. The CPD is governed by three parameters whose optimal values have been evaluated in the present contribution. These values were found to be weakly sensitive to the characteristics of the flow under study, ensuring that this method is robust without further tuning of the parameters. The method is then compared with the Two-Pulse implementation of Shake-The-Box (2P-STB) available in Davis 10.2. For this purpose, sets of realistic images were generated at two successive times for different configurations based of synthetically generated turbulent flows. The Iterative-Particle-Reconstruction in Davis 10.2 was then used to extract the list of particles to be processed by CPD. The comparison shows a better recall with 2P-STB than CPD, especially for large time intervals between frames, but an overall better rejection of ghost particles by CPD than 2P-STB, which was the expected benefit of this method.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献