Method and device for identifying ultra wideband target based on combination characteristic vector
A technology of combining features and target recognition, applied in the field of target recognition, can solve problems such as difficult target recognition and instability, and achieve the effect of improving target recognition probability.
Inactive Publication Date: 2017-10-31
INST OF ACOUSTICS CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] In the target recognition application of the underwater target to be measured, the single-frequency target recognition method is often used, and some features extracted are often affected by the frequency of the transmitted signal, which is unstable. It is very difficult to use only one frequency or frequency band of target information. difficult to identify target
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
[0023] The technical solutions of the present invention will be described in further detail below with reference to the drawings and embodiments.
[0024] figure 1 It is a flow chart of an ultra-wideband target recognition method based on combined feature vectors provided by an embodiment of the present invention. Such as figure 1 As shown, the method includes steps 101-106:
[0025] Step 101, acquiring target echo signals of an underwater target to be tested at different frequency points.
[0026] Transmit single-frequency pulse signals of different frequencies to the underwater target to be tested, and use the hydrophone to obtain target echo signals of the underwater target to be tested at different frequency points.
[0027] Step 102, preprocessing the target echo signal.
[0028] The methods for preprocessing the target echo signal include the band-pass filtering method and the method of intercepting the target echo signal in the prior art.
[0029] Step 103, extract...
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 relates to a method and a device for identifying an ultra wideband target based on a combination characteristic vector. The method comprises the steps of acquiring a target echo signal of a to-be-detected underwater target on different frequency points; preprocessing the target echo signal; extracting time domain centroid characteristics of the target echo signal; combining the time domain centroid characteristics on different frequency points into the combination characteristic vector; selecting characteristics and reducing dimensions; and carrying out data normalization on the characteristic vector, and identifying the target by use of a BP (Back-Propagation) neural network classifier. The device comprises a collection module, a first processing module, an extraction module, a second processing module, a third processing module and an identification module. The method for identifying the ultra wideband target based on the combination characteristic vector is applied to identification of the to-be-detected underwater target, classification is performed by use of the time domain centroid characteristics of the target on different frequencies; compared with the target identification in a single frequency band, the target identification probability is improved.
Description
technical field [0001] The invention relates to the field of target recognition, in particular to a method and device for ultra-wideband target recognition based on combined feature vectors. Background technique [0002] In the target recognition application of the underwater target to be measured, the single-frequency target recognition method is often used, and some features extracted are often affected by the frequency of the transmitted signal, which is unstable. It is very difficult to use only one frequency or frequency band of target information. It is difficult to identify the target. The system using ultra-wideband can obtain target information on different frequencies at the same time, can obtain more new available target information in a single frame, and shorten the identification time of targets. [0003] Feature extraction is a key link in object recognition and classification, and the effectiveness of object feature extraction and selection is directly relate...
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 IPC IPC(8): G06K9/00G06K9/62G06N3/02
CPCG06N3/02G06F2218/08G06F2218/12G06F18/253
Inventor 许枫温涛安旭东王梦宾
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI