A New Method of Rainfall Detection from the Collected X-Band Marine Radar Images

To control the quality of X-band marine radar images for retrieving information and improve inversion accuracy, research on rainfall detection from is investigated in this paper. Currently, difference correlation characteristic between rain-contaminated image rain-free utilized to detect rainfall. However, only coefficient at a position lagged azimuth utilized, statistical hard threshold adopted. By deeply investigating calculated images, can be used constitute feature vector (CCFV). Then, an unsupervised K-means clustering learning method obtain centers. Based constituted CCFV algorithm, new collected proposed. The acquired are verify effectiveness proposed method. Compared with zero-pixel percentage (ZPP) method, (CCD) support machine (SVM) wave texture (WTD) experimental results demonstrate that could finish task detection, accuracy increases by 10.0%, 6.3%, 2.0% 0.6%, respectively, proportion 25% training dataset.