Deep dual recurrence optical flow learning for time-resolved particle image velocimetry

Abstract

Motion fields estimated from image data has been widely used in physics and engineering. Time-resolved particle image velocimetry (TR-PIV) is considered as an advanced flow visualization technique that measures multi-frame velocity fields from successive images. Contrary to conventional PIV, TR-PIV essentially estimates a velocity field video that provides both temporal and spatial information. However, performing TR-PIV with high computational efficiency and high computational accuracy is still a challenge for current algorithms. To solve these problems, we put forward a novel deep learning network named Deep-TRPIV in this study, to effectively estimate fluid motions from multi-frame particle images in an end-to-end manner. First, based on particle image data, we modify the optical flow model known as recurrent all-pairs field transforms (RAFT) that iteratively updates flow fields through a Conv-GRU recurrent unit. Second, we specifically design a temporal recurrent network architecture based on this optical flow model by conveying features and flow information from previous frame. When fed N successive images, the network can efficiently estimate N-1 motion fields. Moreover, we generate a dataset containing multi-frame particle images and true fluid motions to supervised train the network. Eventually, we conduct extensive experiments on synthetic and experimental data to evaluate the performance of the proposed model. Experimental evaluation results demonstrate that our proposed approach achieves high accuracy and computational efficiency, compared with classical approaches and related deep learning models.

Real-time and On-site Aerodynamics using Stereoscopic PIV and Deep Optical Flow Learning

“…Drawing inspiration from the recent optical flow architecture known as recurrent all-pairs field transforms (RAFT) Teed and Deng (2020), numerous studies have built upon this network Lagemann et al (2021b), Yu et al (2021), Lagemann et al (2022, Yu et al (2023), and Han and Wang (2023). They achieved remarkable results in the field of PIV for fluid dynamics, thereby highlighting its significant impact and widespread adoption within the research community.…”

“…More recently, PIV processing has been approached using deep learning techniques Rabault et al (2017), Lee et al (2017), Cai et al (2019), Cai et al (2020), Zhang and Piggott (2020), Lagemann et al (2021a), Lagemann et al (2021b), Yu et al (2021), Gao et al (2021), Lagemann et al (2022, Yu et al (2023), and Han and Wang (2023) demonstrating remarkable success in planar PIV evaluation. However, the complexity of real-world PIV measurements, such as those encountered in industrial applications, demands a more sophisticated approach than planar PIV can provide.…”

Experimental dataset investigation of deep recurrent optical flow learning for particle image velocimetry: flow past a circular cylinder

“…Furthermore, Zhang et al [19] introduced UnPWCNet-PIV, which builds upon PIV-PWCNet [20]. Other notable deep learning-based algorithms for flow estimation in PIV include CC-FCN by Gao et al [21], which synergistically combines cross-correlation and fully convolutional network approaches; CascLiteFlowNet-R-en by Guo et al [22], a novel cascaded CNN tailored for time-resolved PIV (TR-PIV) inspired by LiteFlowNet; Yu et al developed Deep-TRPIV [23], a multi-frame architecture for optical flow prediction from successive particle images, drawing inspiration from RAFT architecture; ARaft-FlowNet by Han and Wang [24] and DeepST-CC by Yu et al [25] leverage the RAFT optical flow model, employing attention-based architectures to improve tracer particle motion recognition.…”