Airport scene target segmentation method and system

An airport scene and object segmentation technology, applied in the field of deep learning, can solve the problems of slow airport scene design, achieve the effect of improving accuracy, efficient extraction, and improving efficiency

Active Publication Date: 2021-10-08
YANGTZE DELTA REGION INST (QUZHOU) UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF17 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The object of the present invention is to provide a method and system for segmenting an airport scene object, so as to solve the relatively slow problem of existing airport scene design

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Airport scene target segmentation method and system
  • Airport scene target segmentation method and system
  • Airport scene target segmentation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] The technical scheme that the present invention solves the problems of the technologies described above is as follows:

[0050] The present invention provides a method for segmenting an airport scene target, referring to figure 1 Shown, described airport scene object segmentation method comprises:

[0051] S1: Multi-scale feature extraction for airport scene surveillance images;

[0052] S2: According to the multi-scale features, obtain a location-spatial attention model diagram;

[0053] S3: Decoding the spatial attention model diagram to obtain the airport scene monitoring image segmentation result;

[0054] S4: Comparing the segmentation result of the airport scene monitoring image with the airport scene monitoring image to obtain a comparison result;

[0055] S5: Perform loss calculation according to the comparison results, and select an optimal result from the loss calculation results;

[0056] S6: Carry out airport scene object segmentation according to the op...

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

No PUM Login to view more

Abstract

The invention discloses an airport scene target segmentation method and system. The airport scene target segmentation method comprises the steps of S1, performing multi-scale feature extraction on an airport scene monitoring image; S2, obtaining a position space attention model graph according to the multi-scale features and a convolutional layer; s3, carrying out decoding operation on the space attention model graph, and obtaining an airport scene monitoring image segmentation result; s4, comparing the airport scene monitoring image segmentation result with the airport scene monitoring image to obtain a comparison result; s5, carrying out loss calculation according to the comparison result, and selecting an optimal result from loss calculation results; and S6, carrying out airport scene target segmentation according to the optimal result. According to the airport scene target segmentation method and system provided by the invention, the problem that the existing airport scene design is relatively slow can be solved.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a method and system for segmenting an airport scene object. Background technique [0002] At the 2008 National Civil Aviation Work Conference, the Civil Aviation Administration of China put forward the strategy of strengthening the civil aviation industry. With the rapid development of the civil aviation industry, the number of certified transport airports in the country has increased to 241, and more and more people choose to travel by plane. Airport scene activities are becoming more and more complex, which is likely to cause safety problems and affect the efficiency of airport operations. Therefore, airport scene intelligence is becoming more and more important, and one of the most important points is airport scene intelligent monitoring. At present, airport scene intelligent monitoring generally adopts Use images collected by radar or surveillance camera modules for ide...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/46G06N3/04G06N3/08
CPCG06N3/04G06N3/08
Inventor 张翔李晶张健星汤应祺田橪李文静张志卓
Owner YANGTZE DELTA REGION INST (QUZHOU) UNIV OF ELECTRONIC SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products