Subspace feature extraction method for multi-rotor unmanned aerial vehicle identification
A multi-rotor UAV and subspace feature technology, applied in the field of target recognition, can solve the problem of ineffective use of spatial distribution information, achieve the effect of enhancing spatial distribution structure information and improving recognition rate
Active Publication Date: 2021-08-17
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the conventional subspace composed of the main projection components has the same weight for each projection component. In addition, the spatial distribution information of the samples is not effectively utilized. Therefore, the multi-rotor UAV identification method based on the conventional eigensubspace has been further improved. room for target recognition
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
[0032] The practicability of the present invention will be described below in combination with simulation experiments.
[0033] Four types of UAVs were designed for the simulation experiment, including three-rotor UAVs, four-rotor UAVs, six-rotor UAVs, and eight-rotor UAVs. The blade length is 0.3m, and the distance from the axis to the origin is 0.8m, rotor speed 1200r / m. The simulated radar parameters include: the radar carrier frequency is 24GHz; the pulse repetition frequency is 100KHz; the distance between the target and the radar is 200m; the pitch angle of the UAV relative to the radar is 10°, and the azimuth angle is 30°
[0034] Each type of target records the radar echo signal for 10s, and divides it into segments with a fixed length of 0.05s (including at least one rotation period), the overlap between segments is 50%, and each segment contains 0.05×100000=5000 radar echoes Wave sampling data points, a total of 400 segments for each category. Among the 400 segment...
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 belongs to the technical field of target recognition, and particularly relates to a subspace feature extraction method for multi-rotor unmanned aerial vehicle recognition. The method comprises the following steps: firstly, carrying out clustering processing on a radar echo data set of each type of unmanned aerial vehicles, then forming a clustering distance vector by using mahalanobis distances between sample data and target clustering centers of each type of unmanned aerial vehicles, constructing a singular value weighted subspace by using the clustering distance vector, extracting target features, and completing identification of the multi-rotor unmanned aerial vehicles. Due to the introduction of the clustering distance, the spatial distribution structure information of the sample is enhanced, and meanwhile, when the subspace is constructed, the singular value is used for weighting, so that the effect of the main projection component is more highlighted, and the recognition rate of the target is improved.
Description
technical field [0001] The invention belongs to the technical field of target recognition, and in particular relates to a subspace feature extraction method for multi-rotor UAV recognition. Background technique [0002] With the widespread application of drones in military and civilian fields, it has also brought about great security problems, such as illegal intrusion into private areas, collisions with aircraft, and terrorist attacks. Therefore, accurately identifying the type of UAV has very important practical significance in anti-UAV operations. [0003] At present, the eigensubspace method is an effective method for identifying UAVs. It mainly performs eigendecomposition through the radar echo data set of UAV targets, constructs subspaces from the main projection components, and extracts target features. However, the conventional subspace composed of the main projection components has the same weight for each projection component. In addition, the spatial distribution...
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): G06K9/46G06K9/62G06F30/27G01S7/41
CPCG06F30/27G01S7/415G06V10/40G06F18/23213G06F18/214
Inventor 周代英宋苏杭钱凯
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA