SAR Image Target Detection Method Based on Visual Attention Model and Constant False Alarm Rate
A visual attention model and constant false alarm rate technology, applied in the field of radar, can solve the problems such as the easy leakage of ship target pixels into the background window, the reduction of clutter statistical modeling accuracy, and the inability to meet the real-time performance of target detection. The effect of data volume and calculation volume, low false alarm, and high speed
Active Publication Date: 2018-07-17
XIDIAN UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This pixel-level detection method needs to traverse the entire SAR image. Each time the sliding window needs to perform statistical modeling and parameter estimation on the background clutter, the computational complexity is high, and it does not meet the real-time requirements of target detection.
At the same time, if the window size is not set properly, the pixels of the ship target are likely to leak into the background window, resulting in a decrease in the accuracy of clutter statistical modeling, making it easy to miss the detection of the ship target at a close distance.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0029] refer to figure 1 , the specific implementation steps of the present invention are as follows:
[0030] Step 1: Input a SAR image I, and use the spectral residual SR to obtain the saliency map S corresponding to the original image I.
[0031] 1a) For a SAR image I with a size of M×N, use bilinear interpolation method to down-sample the original image I to obtain a down-sampled image D with a size of [M / q]×[N / q], where q is the sampling interval, and [·] represents the rounding operation;
[0032] 1b) Calculate the 2-dimensional Fourier transform F(f)=fft2(D) for the downsampled image D, and obtain the amplitude spectrum X(f)=|F(f)| and the phase spectrum P(f)=angle(F(f) ), and take the logarithm of the amplitude spectrum X(f) to obtain the logarithmic spectrum L(f)=log(X(f)), where f represents the frequency, fft2(·) represents the 2-dimensional Fourier transform, and |·| represents Take the absolute value operation, angle(·) means to take the phase operation, log(·)...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a SAR image target detection method based on a visual attention model and a constant false alarm rate, which mainly solves the problems of slow detection speed and high clutter false alarm in the existing SAR image sea surface ship target detection technology. The implementation steps are: extract the saliency map corresponding to the SAR image according to the Fourier spectrum residual information; calculate the saliency threshold to select the potential target area on the saliency map; adopt the constant false alarm rate method of adaptive sliding window for the potential target area. Detection to obtain the initial detection results; the final detection results are obtained after eliminating false alarms from the initial detection results, and slices of suspected ship targets are extracted to complete the target detection process. The invention has the advantages of fast calculation speed, high target detection rate and low false alarm rate, and has the advantages of simple method and easy realization, and can be used for ship target detection on the sea surface.
Description
technical field [0001] The invention belongs to the technical field of radar, in particular to a synthetic aperture radar SAR image target detection method, which can be used for sea surface ship target detection. Background technique [0002] Ship detection is of great significance to fishery supervision and maritime safety management. Monitoring and identifying marine ships is an important task for every coastal country. Because SAR has the ability of long-distance, all-time and all-weather observation, using SAR images to detect ships at sea has always been one of the hot spots in the field of marine remote sensing. [0003] The main idea of ship target detection is to use the feature difference between the ship target and the surrounding sea area on the SAR image, and set a threshold for the feature for detection. The target features currently used for detection include grayscale features, polarization features, phase features, and multi-resolution features. Due to t...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V2201/07G06F18/29
Inventor 刘峥李焘谢荣冉磊
Owner XIDIAN UNIV