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

Railway detection picture matching method based on SIFT characteristics

A matching method and picture technology, applied in the field of image processing, can solve problems such as high labor intensity, and achieve the effect of ensuring accuracy and reducing labor intensity.

Inactive Publication Date: 2016-11-23
ZHEJIANG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For manual inspection, it undoubtedly requires extremely high labor intensity

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
  • Railway detection picture matching method based on SIFT characteristics
  • Railway detection picture matching method based on SIFT characteristics
  • Railway detection picture matching method based on SIFT characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0023] Between Hangzhou and Deqing Railway Station, the railway detection picture matching is carried out according to the method of the present invention.

[0024] Such as figure 1 Shown is the matching result ROAD of matching 992 pictures to be matched (namely Match) to 50 target position pictures (namely Aim) under sunny conditions. It can be seen that for these 50 pictures, each picture corresponds to multiple pictures to be matched. Such as figure 2 Shown is the matching result ROAD of matching 725 pictures to be matched (namely Match) to 50 target position pictures (namely Aim) under rainy conditions. It can be seen that for these 50 pictures, each picture corresponds to multiple pictures to be matched. Such as image 3 As shown, it is the 39th picture among the 50 target position pictures, and the pole label is '1232'. Such as Figure 4 As shown, when the weather is sunny, the figure 1 The matching result ROAD of the obtained matching image matches the target po...

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 a railway detection picture matching method based on SIFT characteristics. The method comprises steps of target position image selection, to-be-detected image input, SIFT characteristic detection and matching, DTW optimal path planning and matching image output, specifically, target position images are selected, wire poles needing detection are marked manually, to-be-detected images are a set of images with redundancy, the quantity of matching characteristic points of the redundancy images and the target position images are acquired through SIFT characteristic detection and matching, a global optimal matching result is acquired through DTW optimal path planning, and an image with the highest matching degree is acquired from a matching result and is outputted for railway detection. The method is advantaged in that the matching result is not dependent on the weather environments and a shooting angle, thousands of images with redundancy are compressed to be hundreds of images for detection, so labor intensity of workers can be greatly reduced, and matching accuracy is further guaranteed.

Description

technical field [0001] The invention relates to image processing technology, in particular to a method for matching pictures of railway detection based on SIFT features. Background technique [0002] With the development of China's railway technology, higher requirements are put forward for the safety of railways. To this end, the relevant departments installed high-frame-rate cameras on the trains, and manually inspected the obtained pictures to find out whether there were abnormal changes in the railway and its surrounding environment (such as the wire poles on both sides). However, due to the long distance and high frame rate, the number of pictures acquired by each train only between two stations reaches tens of thousands or even hundreds of thousands. For manual detection, it undoubtedly requires extremely high labor intensity. But the fact is that due to the high similarity and continuity between the pictures, for each pole, there will be multiple redundant pictures ...

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): G06K9/00G06K9/62
CPCG06V20/52G06V10/751
Inventor 马彦昭胡浩基王曰海
Owner ZHEJIANG UNIV