Target automatic recognition method and automatic recognition system of synthetic aperture sonar image
A synthetic aperture sonar and automatic recognition technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of no feature optimization steps and difficult recognition
Inactive Publication Date: 2016-12-21
INST OF ACOUSTICS CHINESE ACAD OF SCI
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the variability and complexity of the underwater acoustic channel and the transmittance of the sound wave itself, SAS images are different from optical images, and there are fewer details that can be extracted. Most of the existing sonar target recognition methods extract the information of the target and ignore Shadow information, and there is no feature optimization step, which makes recognition difficult
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
[0043] The present invention will be described in detail below in conjunction with specific drawings and embodiments.
[0044] figure 1 It shows the structure of the traditional underwater sonar recognition system. It can be seen that it is mainly divided into image preprocessing, feature extraction, and classification and judgment.
[0045] Figure 6 It is a schematic diagram of an automatic identification system for a synthetic aperture sonar image target according to an embodiment of the present invention. The recognition system includes an image preprocessing and segmentation module 1, a feature extraction and optimization module 2, and a classification and judgment module 3, wherein the image preprocessing and segmentation module includes an image preprocessing unit and a segmentation unit; the feature extraction and optimization module is used to extract the target feature and optimize the feature; the classification judgment module includes a classifier using a suppor...
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 discloses a method and system for automatic recognition of synthetic aperture sonar images. The method includes the following steps: image preprocessing and segmentation steps, feature extraction steps, and classification and judgment steps, wherein the feature extraction step includes: shadow geometric features The extraction step of the target normalized central moment and the extraction step of the target normalized central moment are also provided between the feature extraction step and the classification decision step: a feature optimization step. The automatic recognition system provided by the present invention is provided with a feature extraction and optimization module on the basis of the existing recognition system, and the feature extraction and optimization module includes: a feature extraction unit, a feature optimization unit, and the feature extraction unit is used to extract the geometric features of shadows and The normalized central moment feature of the target; the feature optimization unit is used to optimize the geometric feature of the shadow and the normalized central moment feature of the target. The method and the system provided by the invention are easy to recognize the target in the synthetic aperture sonar image, and also improve the recognition accuracy.
Description
technical field [0001] The present invention relates to the field of image processing and pattern recognition, in particular, the present invention relates to an automatic target recognition method and automatic recognition system of a SAS (synthetic aperture sonar, synthetic aperture sonar) image. Background technique [0002] Synthetic aperture sonar is a high-resolution underwater imaging sonar that can obtain high-quality underwater image data. Synthetic aperture technology uses the coherent superposition of multiple echoes to obtain an aperture. Because Synthetic Aperture Sonar (SAS: Synthetic Aperture Sonar) can obtain images with high precision in azimuth and range, it has become a current research hotspot. With the development of synthetic aperture sonar imaging technology, target recognition based on synthetic aperture sonar images has become an important research topic at home and abroad. Due to the variability and complexity of the underwater acoustic channel an...
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): G06K9/46G06K9/62
Inventor 丁雪洁解恺刘维刘纪元
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI