One-dimensional range profile fusion recognition method based on multi-scale sparsity preserving projection
A technology that maintains projection and fusion recognition. It is used in character and pattern recognition, instruments, computer parts, etc., and can solve the problems of difficult to break through the bottleneck of recognition, limited effect, and insufficient information utilization.
Active Publication Date: 2017-07-14
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF7 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, although a single principal component extraction can reduce the feature dimension to a certain extent and reduce the influence of noise, the effect is limited, and the utilization of information is not sufficient, so it is difficult to break through its identification bottleneck.
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
[0068] The present invention will be further described below in conjunction with the accompanying drawings.
[0069] The present invention provides a one-dimensional distance image fusion recognition method based on multi-scale sparsity-preserving projection. The general flow chart is as follows figure 1 shown. The existing one-dimensional range image echo data of an aircraft are as follows: figure 2 As shown, in the actual situation, the echoes of different types of aircraft are different, and the echo signals of the same type of aircraft at different angles are also different. The main purpose of the present invention is to complete the category judgment of such echo signals. In order to solve the recognition and classification problem of this kind of one-dimensional echo signal. The present invention comprises the following steps:
[0070] Training phase:
[0071] Step 1: For the training sample set X=[x 1 ,x 2 ,...,x n ], extracting its normalized spectrum magnitud...
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 one-dimensional range profile fusion recognition method based on multi-scale sparsity preserving projection. First, the normalized amplitude features of a measured one-dimensional range profile signal sample are extracted, and translational alignment pretreatment is carried out; then, multi-scale spatial mapping is carried out using a one-dimensional Gauss Laplasse operator; next, a multi-scale spatial signal is sparsely represented through a sparsity preserving projection method, and a multi-scale spatial sparse feature vector is obtained; and finally, a target sparse feature vector is classified and recognized using a multi-scale decision fusion classifier, and the classification result is output. Based on multi-scale spatial analysis, sparsity preserving projection and the decision fusion classifier, multi-scale effective sparse features of a one-dimensional range profile are extracted, and fusion recognition is carried out on the result through the decision fusion classifier. The recognition efficiency of one-dimensional range profile signals is increased to a certain extent. The anti-jamming performance is enhanced obviously.
Description
technical field [0001] The invention relates to a method for identifying a radar one-dimensional signal, in particular to a technology for accurately identifying a target radar one-dimensional range image in an interference environment. Background technique [0002] Radar Automatic Target Recognition (RATR) is based on the echo signal of the target and the environment, and the radar extracts the target feature information based on the electromagnetic scattering mechanism to realize the automatic determination of the target attribute category. Radar high-resolution one-dimensional range profile (HRRP) reflects the distribution of target scattering points along the radar line-of-sight direction, which contains rich target structural features, and its inherent advantages are easy acquisition and small data volume. Therefore, HRRP-based target recognition has always been a research hotspot in the field of radar automatic target recognition, and it is also the radar target recogn...
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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06F2218/12G06F18/2136G06F18/2411G06F18/256
Inventor 戴为龙刘文波张弓
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS