Sea antenna extraction method based on lsd improved visible light image of uuv near sea surface
An extraction method, sea antenna technology, which is applied in the field of sea antenna extraction of UUV near-sea visible light images, can solve the problems of false sea antenna, interference, large error, etc., and achieve real-time and strong adaptability
Active Publication Date: 2020-06-16
HARBIN ENG UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The core idea of most existing sea antenna detection methods is straight line extraction, such as sea antenna extraction methods based on straight line fitting, Hough transform, line mean gradient, line-information entropy, and RANSAC algorithm, most of which are vulnerable to waves, clouds, bridges, etc. , mountains and other high-gradient edges, the error is large or a false sea antenna is formed, causing interference to ship targets in the water boundary area
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
[0031] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings.
[0032] combine figure 1 , the improved LSD-based UUV near-sea surface visible light image sea antenna extraction method of the present invention comprises the following steps:
[0033] 1. Use VS2010 and OPENCV language programming to input and display the visible light image of the UUV offshore surface, record the image as I(x), and the visible light image is as follows figure 2 shown. Then, the original image is converted into a grayscale image and scaled, that is, Gaussian downsampling is performed on the input grayscale image at a scale of s=0.8, the standard deviation of the Gaussian kernel σ=∑ / s, and the parameter ∑=0.6, the purpose is the anti-aliasing effect.
[0034] 2. Gradient calculation, perform pseudo-arrangement according to the gradient magnitude ...
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 provides an improved LSD-based method for extracting sea antennae from UUV near-sea visible light images. Obtain the visible light image of the near sea surface, convert it into a grayscale image and perform scale scaling; perform gradient calculation, perform pseudo-arrangement according to the gradient magnitude and establish a state list, and set the gradient threshold; The feature eliminates points that do not meet the requirements, and generates a straight line support area or the smallest circumscribed rectangle; estimates the rectangle, and merges adjacent rectangles according to the sea antenna length feature and the straight line merging criterion; judges the point density within the class; calculates NFA, and extracts the sea antenna. This method can extract both the horizontal sea antennae and the inclined sea antennae, and is suitable for both sea and sky backgrounds and mountain backgrounds. In addition, the present invention has strong real-time and adaptability, and can extract sea antennae from visible light sequence images.
Description
technical field [0001] The present invention relates to a visible light imaging method, in particular to a sea antenna extraction method of a UUV near-sea visible light image. Background technique [0002] Maritime target recognition technology plays an important role, and has been listed as a key research topic by many countries in recent years. However, due to the interference of strong water ripples on the sea surface, background obstacles, detector noise and other factors, the positioning and identification of ship targets has become a very challenging problem. The visible light image of the sea surface is generally divided into three regions: the sky region, the water boundary region and the sea surface region. Usually, when performing image processing tasks such as target detection and tracking, most of the regions of interest are located in the water boundary region. Sea-antenna detection can effectively suppress noise interference in the complex sea-air background,...
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): G06K9/46
CPCG06V10/457
Inventor 管凤旭周丽萍严浙平张宏瀚周佳加刘怀东车浩
Owner HARBIN ENG UNIV