Method and device for verification of ship recognition model based on radar image
A radar image and recognition model technology, applied in the field of computer vision, can solve the problems of low accuracy of ship recognition model, difficulty in verification of recognition accuracy of radar images of different scales, etc.
Active Publication Date: 2021-10-15
ZHUHAI DAHENGQIN TECH DEV CO LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of this, the embodiment of the present invention provides a radar image-based ship recognition method, device and electronic equipment to solve the problem that it is often difficult for ship recognition models in the prior art to verify the recognition accuracy of radar images of different scales. The problem that caused the accuracy of the ship recognition model to be relatively low
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
[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.
[0029] According to the first aspect, an embodiment of the present invention provides an embodiment of a method for verifying a ship identification model based on radar images. It should be noted that the steps shown in the flow chart of the accompanying drawings can be implemented in a set of computer-executable instructions such as computer system, and alth...
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 the technical field of computer vision, in particular to a method and device for verifying a ship recognition model based on radar images. Wherein, the method includes: acquiring a radar image with annotation information; wherein, the annotation information includes the category of the ship in the radar image and the first bounding box; using the pre-trained ship recognition model to extract the multi-scale of the radar image feature map; each scale feature map is detected by using the ship recognition model to obtain a second bounding box corresponding to each scale feature map; using the first bounding box, each of the second The bounding box is corrected to obtain the correction amount at different scales, and the recognition accuracy rate of the ship recognition model is determined through the correction amount, so as to solve the problem that the ship recognition model in the prior art is often difficult to recognize radar images of different scales The accuracy rate is verified, which leads to the problem that the accuracy rate of the ship recognition model is relatively low.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to a method and device for verifying a ship recognition model based on radar images. Background technique [0002] Vessel identification plays a very important role in maritime traffic management, oil spill pollution control, maritime safety management, and maintenance of marine rights and interests. Remote sensing images currently used for ship identification at sea include optical remote sensing images, reflective infrared remote sensing images, hyperspectral remote sensing images, thermal infrared remote sensing images, and radar images. Radio waves, receiving images formed by scattered echoes, have the characteristics of all-day and all-weather. Among them, synthetic aperture radar (SAR) is the most suitable radar for ship detection. With the successful launch of China's Gaofen-3, Japan's ALOS-2, and the European Space Agency's Sentinel-1, a large number of radar image...
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): G06K9/00G06K9/46G06K9/62
CPCG06V20/13G06V10/40G06F18/253G06F18/214
Inventor 邓练兵李皓高妍
Owner ZHUHAI DAHENGQIN TECH DEV CO LTD