Image Analysis for Wave Swash Using Color Feature Extraction

To improve nearshore video observation, a novel and efficient method for wave swash measurement based on color feature extraction has been proposed in this paper. Firstly, the original images are transformed from RGB color space to HSV color space. Then, the color features are extracted using computation of statistical measures of texture in an image from H, S and V plane. Further decision is made to choose which plane is better for distinguish water and land area. After waterline detection with a threshold using Otsu´s method from the selected color plane, a timestack image is used to track swash movement. Moreover, several wave parameters are computed using spectral texture of a timestack. The experiment results show that the proposed method provides an effective way for waterline extraction and wave swash movement estimation. The preliminary results are encouraging and suggest that the new algorithm could be useful image analysis for wave swash movement.