An improved vision-based wastewater velocity measurement system using discontinuity-preserving smoothing and GPU acceleration

摘要: Automatic long-term measuring wastewater velocity is an important and challenging task in hydraulic systems. This paper proposed a vision-based measurement method using Bilateral filter that discontinuity-preserving smoothing as prior-processing step. Experimental results showed can improve estimation accuracy over existing methods. An effective background creation algorithm simple floating waste tracking based on binary blob properties are also discussed this paper. Furthermore, by implementing the massively parallel GPU (graphics processing units) CUDA (compute unified device architecture) programming model, we achieve satisfactory acceleration to apply real-time applications. Memory usage optimization methods analyzed for implementation graphics hardware.