A method for automatic selection of landmark points in three types of sea areas
A landmark point and sea area technology, applied in the field of aircraft sea scene matching navigation, can solve the problems of close image features, no obvious image features, uneven distribution of landmark points, etc., and achieves improved accuracy, strong operability, and wide engineering applications. effect of value
Active Publication Date: 2022-04-05
NORTHWESTERN POLYTECHNICAL UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The automatic selection method of landmark points in the sea area has the problem that most of the area is ocean and has no obvious image features; the distribution of landmark points (natural islands) is uneven, and the image features such as color and texture are relatively close
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
[0160] Step 1: Prepare sample database
[0161] Calculate the field of view size (real-time image size) R=2Htanθ / 2 (unit: m), ground object resolution q=R 2 / p (unit: m / pixel), according to the real-time map size R and the inertial navigation drift error δ (unit: m), set the image size of the landmark point r (r2 ), and intercept the landmark point sample r×r on the reference map (unit: pixel 2 ).
[0162] Step 2: Feature extraction of landmark points
[0163] Step 1: Unique Features
[0164] For the first and second types of landmark points, the image is grayscaled, and the landmark point and its corresponding reference image are calculated to calculate the sharpness of the highest peak of the gray-scale normalized cross-correlation coefficient, which is used as the unique feature x of the landmark point 11 .
[0165] For the three types of landmark points, construct a triangle matching probability parameter as the unique feature x 12 ,Such as figure 2 As shown, with...
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 a method for automatically selecting three types of landmark points in sea areas, which divides the landmark points in the sea area into three types, extracts the features of the landmark points, and designs a multi-classifier to automatically select the three types of landmark points, and finally obtains the prediction label. The present invention solves the problem of sparse, uneven distribution and missing features by dividing the three types of landmark points in the sea area; by optimizing the kernel functions of different binary classifiers and different features, the classification of the three types of landmark points in the sea area is improved. accuracy rate; provide a convenient and highly operable method for the preparation of the landmark point database for aircraft sea area scene matching navigation, which is of great significance for improving the navigation accuracy of aircraft sea area long-endurance flight, so the present invention has broad development prospects and engineering application value.
Description
technical field [0001] The invention relates to the field of aircraft sea area scene matching navigation, in particular to a method for automatically selecting landmark points, which uses image multi-feature extraction methods, support vector machine multi-core learning methods, error correction output coding multi-classifiers, etc. to realize the automatic selection of three types of sea area landmark points. select. Background technique [0002] The scene matching navigation system has the advantages of small size, low cost, and good autonomy. As an auxiliary means of inertial navigation, it can effectively correct the position error caused by the inertial navigation drift of the aircraft, and meet the long-term and precise navigation requirements of the aircraft. Landmark points are unique, significant, rich and stable, which is an important prerequisite for realizing scene matching navigation based on landmark points. When the aircraft flies to the landmark point, the c...
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): G06V10/764G06K9/62
CPCG06F18/2411
Inventor 白渭津程咏梅顾一凡王强姚顺田朝旭杨速刘楠
Owner NORTHWESTERN POLYTECHNICAL UNIV