Automatic Edge Detection Applied to Cavitating Flow Analysis: Cavitation Cloud Dynamics and Properties Measured through Detected Image Regions

In a cavitating water jet, cavity clouds emerge and collapse with an unsteady, but periodic tendency where the frequencies depend on the working conditions. The presented work aims at examining and analyze the dynamic behavior and properties of the clouds under different circumstances. Computer vision and image processing were introduced as tools to define the cavitation clouds based on the Contour Recognition technique. A Canny operator and Otsu threshold fragmenting methods were used. The use of these methods allows for a better understanding of the cavitating jet clouds' behavior based on the pixel intensities and shows that for an arbitrary cloud the surface itself has a dynamic feature and depends on the cavity composition. The clouds' properties could be measured and correlated to the applied working conditions. Also, the oscillation frequencies of the area of the clouds could be determined. The analysis shows that the quality of the obtained results depends mainly on the input threshold values separating the foreground and background pixels. The difficulty of defining the threshold value is discussed in the paper, as well as the validity of using the Contour Recognition technique in this field.