Multi visual images fusion approach for metro tunnel defects based on saliency optimization of pixel level defect image features

像素 人工智能 计算机视觉 计算机科学 融合 图像(数学) 图像融合 模式识别(心理学) 哲学 语言学
作者
Dongwei Qiu,Zhengkun Zhu,Xingyu Wang,Keliang Ding,Zhaowei Wang,Yida Shi,Wei Niu,Shanshan Wan
出处
期刊:Measurement Science and Technology [IOP Publishing]
卷期号:35 (4): 045403-045403
标识
DOI:10.1088/1361-6501/ad197d
摘要

Abstract The multi-vision defect sensing system, lining composed primarily of IRT and RGB cameras, allows for automatic identification and extraction of small surface ailments, greatly enhancing detection efficiency. However, the presence of various issues like train vibration, inconsistent lighting, fluctuations in temperature and humidity leads to the images showing inadequate uniformity in illumination, blurriness, and a decrease in the level of detail. The above issues have led to unsatisfactory fusion processing results for multiple visual images and increased missed detection rates. To address the above-mentioned issue, multi visual images fusion approach for subway tunnel defects based on saliency optimization of pixel level defect image features is proposed. The approach initially analyses the train’s motion status and image blurring conditions. It then eliminates the dynamic blurring in the image. Secondly, Image weights are allocated based on the uniformity of visible light image illumination in the tunnel, as well as real-time temperature and humidity. Finally, image feature extraction and fusion are performed by a U-Net network that integrates channel attention mechanisms. The entire experiment was carried out on a dataset consisting of leakage data from the tunnel lining of Shanghai Metro and tunnel defect data from Beijing Metro. The experimental results demonstrate that this approach improves the image pixel value variation rate by 39.7%, enhances the edge quality by 23%, and outperforms similar approach in terms of average gradient, gradient quality, and sum of difference correlation with improvements of 15.9%, 7.3%, and 26.6% respectively.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
长情的乐蕊完成签到,获得积分20
1秒前
danti发布了新的文献求助10
1秒前
1秒前
王耀应助王雅欣采纳,获得10
3秒前
4秒前
CipherSage应助斯文的谷梦采纳,获得10
6秒前
6秒前
康康XY完成签到 ,获得积分10
9秒前
Dr司发布了新的文献求助10
10秒前
沫雨完成签到,获得积分10
11秒前
李健的小迷弟应助苦瓜采纳,获得10
12秒前
赚大钱给赚大钱的求助进行了留言
13秒前
13秒前
星辰大海应助淡水痕采纳,获得10
17秒前
17秒前
打打应助多发paper啊采纳,获得10
18秒前
21秒前
laoli2022发布了新的文献求助10
22秒前
大模型应助ixueyi采纳,获得10
23秒前
SciGPT应助我是聪聪呦采纳,获得10
25秒前
专一的访旋完成签到,获得积分10
26秒前
科研通AI2S应助壮观以松采纳,获得10
26秒前
27秒前
28秒前
wanghe完成签到,获得积分10
28秒前
28秒前
傻傻的香氛完成签到 ,获得积分10
29秒前
29秒前
深情安青应助典雅的静采纳,获得10
30秒前
现代的兔子完成签到,获得积分10
32秒前
要发核心刊的阿爽完成签到,获得积分10
32秒前
DoubleLD完成签到,获得积分0
32秒前
34秒前
英姑应助叫滚滚采纳,获得10
35秒前
35秒前
35秒前
研友_842M4n发布了新的文献求助10
35秒前
张泽崇应助研友_方达采纳,获得10
36秒前
Akim应助要发核心刊的阿爽采纳,获得30
39秒前
40秒前
高分求助中
Thermodynamic data for steelmaking 3000
Counseling With Immigrants, Refugees, and Their Families From Social Justice Perspectives pages 800
Electrochemistry 500
Statistical Procedures for the Medical Device Industry 400
藍からはじまる蛍光性トリプタンスリン研究 400
Cardiology: Board and Certification Review 400
A History of the Global Economy 350
热门求助领域 (近24小时)
化学 材料科学 医学 生物 有机化学 工程类 生物化学 纳米技术 物理 内科学 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 电极 光电子学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 2366015
求助须知:如何正确求助?哪些是违规求助? 2074700
关于积分的说明 5188918
捐赠科研通 1802148
什么是DOI,文献DOI怎么找? 899988
版权声明 557924
科研通“疑难数据库(出版商)”最低求助积分说明 480262