Ship wake detection method based on top hat transformation and Radon transformation
A technology of top-hat transformation and detection method, which is applied in the field of image processing, can solve the problems that trails are difficult to be detected, and achieve the effect of facilitating automatic detection, improving contrast, and improving detection performance
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2020-02-28
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the field of image processing, in particular to a ship wake detection method based on top hat transformation and Radon transformation. Background technique
[0002] Tiangong-2 interferometric imaging radaraltimeter (InIRA) is the first microwave altimeter in the world that can simultaneously measure sea surface height with wide swath and perform 3D imaging and 2D imaging, which is different from ordinary synthetic aperture radar ( Aperture Radar, SAR) is characterized by a large incident angle, whose incident angle ranges from 1° to 8° (Reference [1]: Y. Zhang et al., “Demonstration of ocean target detection by Tiangong-2 interferometric imaging radaraltimeter,” MIKON 2018-22nd Int.Microw.Radar Conf., no. 2, pp. 261–264, 2018.). In the InIRA image, a large number of ship wakes can be observed, and the detection of ship wakes can locate the ship's position, obtain the heading, and estimate the speed, which plays an important ro...
Examples
Embodiment Construction
[0063] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings.
[0064] like figure 1 As shown, the present invention proposes a kind of ship wake detection method based on top-hat transform and Radon transform, comprises the following steps:
[0065] Step 1) Obtain the original image, and perform median filtering on the original image: from the (4,4)th pixel of the image that has undergone median filtering as the operation object point;
[0066] Step 2) Take the 7×7 neighborhood of the operation object point as the neighborhood window, divide the neighborhood window into nine 3×3 overlapping windows, calculate the average value of the nine overlapping windows respectively, and form them according to the corresponding positions 3×3 mean matrix;
[0067] Step 3) correlate the four edge detection operators with the average value matrix respectively to obtain four values;
[0068] Step 4) According to the...