Check patentability & draft patents in minutes with Patsnap Eureka AI!

Train linear array image distortion correction method and electronic equipment

An image distortion correction and train line technology, applied in the field of rail train images, can solve problems such as train line array image distortion, achieve the effect of avoiding the extraction of feature points and improving stability

Pending Publication Date: 2021-12-17
CHENGDU HUOAN MEASURE TECHN CENT
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the problem of distortion in the collected train line array image existing in the prior art, and provide a method for correcting the distortion of the train line array image and electronic equipment

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
  • Train linear array image distortion correction method and electronic equipment
  • Train linear array image distortion correction method and electronic equipment
  • Train linear array image distortion correction method and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 As shown, a train line array image distortion correction method includes the following steps:

[0049] S1: Collect train linear array images and perform preprocessing; the preprocessing includes labeling, data enhancement, and multi-scale transformation; and complete the training of the car body detection model and the column detection model through the RetinaNet network.

[0050] Among them, RetinaNet is a unified target detection network composed of a backbone network and two sub-networks. The main function of the backbone network is to obtain the feature map of the entire input image through a series of convolution operations. The two subnetworks perform object classification and location regression based on the output feature maps, respectively.

[0051] The car body detection model and the pillar detection model use ResNet-101+FPN as the backbone network to generate multi-scale feature pyramids. Focal Loss is used as the loss function, and its e...

Embodiment 2

[0070] This embodiment is a specific application example of the method described in Embodiment 1, which specifically includes the following steps:

[0071] 1. Using the collected train image data, after labeling the car body and pillars and performing data enhancement and multi-scale transformation, the models for detecting the car body and pillars are respectively trained through the RetinaNet network;

[0072] 2. Screen out the template images of different vehicle models and the images to be corrected from the collected images, see image 3 up and down;

[0073] 3. Use the trained model to detect the car body and cylinder on the normal and to-be-corrected images. Within the range of the detected vehicle body, the adjacent cylinders and the two sides of the cylinder and the side of the vehicle are divided into an area. Finally, each An image is divided into 7 tiles, see the division method Figure 4 ;

[0074] 4. Select the initial truncation step as 10, intercept the bloc...

Embodiment 3

[0080] Such as Figure 9 As shown, an electronic device includes at least one processor, and a memory communicated with the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor. Execution by at least one processor, so that the at least one processor can execute the method for correcting distortion of train line array images described in the foregoing embodiments. The input and output interfaces may include a display, a keyboard, a mouse, and a USB interface for inputting and outputting data; the power supply is used for providing electric energy for electronic equipment.

[0081] Those skilled in the art can understand that all or part of the steps for implementing the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned programs can be stored in computer-readable storage media. The steps of the method e...

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 relates to the technical field of rail train images, in particular to a train linear array image distortion correction method and electronic equipment. The method comprises the following steps: detecting an acquired train linear array image, and segmenting a train into a plurality of image areas by using a detection result; screening and determining a template image, and simultaneously segmenting the to-be-corrected image and the template image which are obviously distorted by using a model; cutting off and changing each segmented to-be-corrected image according to a set step length, then calculating the similarity between the changed image and the same cut-off area of the template image, wherein the conversion area with the maximum similarity is the corrected image of the corresponding cut-off area, and distortion correction of the linear array image can be finally achieved after image block splicing. According to the method, the extraction of feature points in the distortion correction process is avoided, the influence of environment change on the image quality is reduced, the distortion correction of the image is adaptively realized according to the similarity index, and the stability of the image correction is improved.

Description

technical field [0001] The invention relates to the technical field of rail train images, in particular to a method for correcting distortion of train linear array images and electronic equipment. Background technique [0002] In recent years, with the rapid development of my country's rail transit industry, more and more attention has been paid to the safety of train operation, and the main focus of attention is the condition monitoring of vehicle appearance and running components. Since the body length of the freight train is much longer than its height, in order to achieve fine appearance imaging, the current common method is to install a line array camera on the trackside to collect images and videos during the train operation, and then arrange professional personnel to check them one by one through visual inspection. Whether there is an abnormality in the vehicle, this method is inefficient, has high labor costs, and is prone to missed inspections, which may cause train...

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
IPC IPC(8): G06T5/00G06K9/62G06N3/04G06N3/08G06T3/40
CPCG06T3/4038G06N3/08G06T2207/20081G06T2207/20084G06T2200/32G06N3/045G06F18/22G06T5/80Y02T10/40
Inventor 王炜马保成王坤滕昭军范俩彬杨雷王燕兵李晖邓雪郭海涛王筱野彭恢全赵旺刘向东吴梦迪邓佳林陈威聂东林
Owner CHENGDU HUOAN MEASURE TECHN CENT
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com