摘要：When the traditional method is used to detect the target image of the marine environment,the contrast of the target wake cannot be improved.That is, the definition of the target image is low and the detection error is large.In order to overcome this shortcoming,in this paper,we propose a target image detection method for marine environment based on Radon transform and feature space decision.This method uses the average gray value of the image to replace the target part,and improves the contrast of the target trail by segmenting the target image and normalizing the grayscale Hough transform of each sub-image.The Radon transform coefficients in the image are processed by thresholding,and the peak points in the image are extracted and matched with the wavelet transform peaks.We input the extracted parameters in the feature space to make decisions,so as to realize the detection of the target image of the marine environment.The experimental results show that the detection image of the proposed method has high definition and small detection error,and the detail retention rate of the target wake image is higher, which provides a reliable basis for related fields.
关键词：Marine environment target;Radon transform;Feature space decision;Wake contrast;Image detection
