An Algorithm for Detecting Precipitation in Computer Processing of Video Images

The importance of detecting and reducing the visibility of precipitation in video images obtained by fixed cameras is shown. A statistical analysis of the geometric (area, shape factor, and orientation deviation from the frame average), and color–brightness (intensity and color saturation) characteristics of rain and snow particles is performed in order to substantiate decision rules for detecting pixels corresponding to precipitation particles. This analysis consists in obtaining distributions of the particle parameters and approximating them by known distribution laws using the family of Pearson’s curves, the Kolmogorov criterion, and the Nelder–Mead simplex algorithm. An algorithm for detecting raindrops and snowflakes in video sequences is developed, which is supposed to be used as part of an algorithm for reducing the visibility of precipitation. The proposed approach is presented in the form of a multistage classification of frame pixels into zones with moving objects and regions of a stationary background distorted and undistorted by precipitation particles in accumulated frames. Depending on the region to which the processed pixel belongs, the final decision to assign it to the class of precipitation is made using the proposed decision rules or the developed thresholding procedure with automatic determination of local threshold values. The proposed algorithm is experimentally investigated and, using a two-criteria approach, the optimal values for the number of accumulated frames for the correct operation of the algorithm are determined—100 frames for video images with rain and 140 frames for video with snow. The gain of the developed approach in comparison with the known estimates of the probabilities of false positives and false negatives is up to 1.7% and 9.1%, respectively.