Air-based rail detection method based on attention enhancement mechanism

A technology for enhancing mechanism and rail detection, applied in the field of aviation surveillance, can solve the problem of small target object and high flying height, and achieve the effect of significant effect, low mitigation efficiency, strong engineering value and practical significance.

Active Publication Date: 2019-02-12
BEIHANG UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the flying altitude of the airborne aircraft is relatively high, so the target object in the collected pictures may be relatively small

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
  • Air-based rail detection method based on attention enhancement mechanism
  • Air-based rail detection method based on attention enhancement mechanism
  • Air-based rail detection method based on attention enhancement mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0037] The invention is a space-based rail detection method based on attention enhancement mechanism, which focuses on solving the problem of rail detection in UAV inspection. judge. In order to improve the detection accuracy, the present invention uses a near-space vehicle equipped with a high-definition array camera as a platform to collect image data on the ground, and obtains more different training samples through image rotation, cropping and splicing, and finally downsamples through the convolutional neural network. The image coding of the image can get a smaller-size...

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 air-based rail detection method based on an attention enhancement mechanism, belonging to the field of aviation surveillance. The method comprises the steps that firstly, the high-definition array camera is mounted on the aerial vehicle, and the original image of the railway track is acquired and pre-processed to obtain training samples; the images of the training samples are inputted into the convolutional neural network for feature extraction, and the 16*16 encoded images are obtained, and the attention enhancement is carried out to increase the ability of featureexpression; then the up sampling is carried out on the image after the attention enhancement by convolution neural network to get the same size decision map as the original image, and the decision mapis classified and judged, and a point in the decision map is a point on the rail; and finally, according to the decision result, the network parameters are updated by back propagation using gradientdescent algorithm. On the basis of precise detection, the method of the invention can monitor the surrounding environment of the rail and the safety condition of the rail, has accurate positioning andremarkable effect, and has strong engineering value and practical significance.

Description

technical field [0001] The invention belongs to the field of aviation surveillance, in particular to an air-based rail detection method based on an attention enhancement mechanism. Background technique [0002] China is a vast country with a vast territory of 9.6 million square kilometers. The huge land area also puts forward high requirements for the construction of transportation in our country. In order to meet the needs of national economic construction and people's daily travel, our country has developed a variety of transportation systems. Among them, the railway is the most important and popular, and plays a key role in China's comprehensive transportation system. Its economical and fast characteristics make it a widely used and popular mode of transportation. As of the end of 2016, China's total operating mileage of railways reached 124,000 kilometers, ranking second in the world; among them, 25,000 kilometers of high-speed railways ranked first in the world. con...

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): G06T3/40G06T7/00G06T7/136G06T9/00
CPCG06T3/4038G06T7/0004G06T7/136G06T9/002G06T2207/20081G06T2207/20084
Inventor 曹先彬甄先通李岩胡宇韬
Owner BEIHANG UNIV
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