Unlock instant, AI-driven research and patent intelligence for your innovation.

Airport runway foreign matter detection method based on global context information

A technology for airport runway and foreign object detection, applied in neural learning methods, computer components, biological neural network models, etc., can solve problems such as low detection accuracy, improve accuracy, improve generalization ability, and facilitate training.

Pending Publication Date: 2020-07-03
BEIJING UNIV OF TECH
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the problem of foreign object detection on the airport runway, the detection accuracy is relatively low by directly using the existing target detection algorithm

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 runway foreign matter detection method based on global context information
  • Airport runway foreign matter detection method based on global context information
  • Airport runway foreign matter detection method based on global context information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The algorithm of the present invention is described in detail below in conjunction with the accompanying drawings:

[0028] The invention is a target detection algorithm based on global context information. Such as Figure 5 As shown, the algorithm detection process is as follows: input the picture into the designed convolutional network, the backbone network is ResNeXt, and extract the target feature map through a series of convolution operations of the backbone network; in this process, add the global context module (GC block), capture the global context information of the image through the self-attention mechanism; then set three different IoU thresholds for training through the cascaded network structure, score the candidate frames, determine positive and negative samples, and detect the target; finally Output classification results and prediction accuracy.

[0029] The specific algorithm is introduced as follows:

[0030] (1) Backbone network based on ResNeXt

...

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 runway foreign matter detection method based on global context information, and the method comprises the steps: inputting a picture into a designed convolution network, employing ResNeXt for a backbone network, increasing the width of a residual block through a plurality of parallel paths, and improving the detection accuracy of the network for a small target; inthe process, a global context module (GC block) is added, and global context information of the image is captured through a self-attention mechanism; a cascade network structure is adopted, and threedifferent IOU thresholds are set for training, so that the generalization ability of the network is improved, and the detection accuracy is further improved; finally, a result of the detection is output. An experimental result on a Foreign object debris (FOD) set shows that the detection performance of the method disclosed by the invention is superior to that of other algorithms.

Description

technical field [0001] The invention belongs to the field of target detection in computer vision, and relates to the problem of detection of foreign objects on airport runways. The network structure is designed according to the characteristics of foreign objects on airport runways. It is a target detection method based on global context information. Compared with the current mainstream target detection methods, The accuracy rate has been improved to a certain extent. Background technique [0002] The foreign matter on the airport runway has brought a huge impact on the take-off and landing of the aircraft. Many cases have proved that the foreign matter on the airport runway can be easily sucked into the aircraft engine, causing the engine to fail, and debris will also accumulate in the mechanical device, affecting the landing gear, The normal operation of the wing and other equipment. Among the foreign objects on the airport runway, some targets are small and difficult to d...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/00G06V10/464G06V2201/07G06N3/048G06N3/045G06F18/241Y02T10/40
Inventor 王素玉冯明宽王萌萌
Owner BEIJING UNIV OF TECH