Automatic Visual Leakage Detection and Localization from Pipelines in Chemical Process Plants Using Machine Vision Techniques

Fahimipirehgalin, Mina; Trunzer, Emanuel; Odenweller, Matthias; Vogel‐Heuser, Birgit

doi:10.1016/j.eng.2020.08.026

Cited by 23 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is used in the environments where manual operation cannot meet the requirements. It can monitor the product's quality and greatly improves the production efficiency in large-scale mechanical production [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning to Badminton Action Decomposition Teaching

Long

Rong

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The study was aimed at realizing the identification of athletes’ actions in badminton teaching. The teaching process is segmented into many independent actions to help learners standardize their movements in badminton play, improving the national physical quality. First, the principle and advantages of machine vision sensing are introduced. Second, the images and videos about the action decomposition of badminton teaching are collected, and the image data are extracted by Haar-like. Subsequently, badminton players’ actions are recognized and preprocessed, and a dataset is constructed. Furthermore, a new algorithm model is implemented and trained by using Haar-like and Adaptive Boosting (AdaBoost). Finally, the badminton players’ action recognition algorithm is tested and compared with the traditional hidden Markov model (HMM) and support vector machine (SVM). The results show that action images improved by machine vision can process the captured actions effectively, making the computer better identify different badminton teaching actions. The proposed method has a recognition rate of more than 90% for each action, the average recognition accuracy of actions reaches 95%, the average recognition rate of the same person’s actions is 96.5%, and the average recognition rate of different people’s actions is 94.8%. The badminton teaching action recognition model based on Haar-like and AdaBoost can recognize and classify badminton actions and improve the quality of badminton teaching. This study shows that the image processing technology can effectively process the players’ static images, which gives the direction for physical education (PE) under artificial intelligence (AI).

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning to Badminton Action Decomposition Teaching

Long

Rong

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Machine vision systems offer a rich source of information regarding the objects they measure, including their position, orientation, texture, and other features [1,2]. Due to their flexibility, non-contact nature, and high precision, machine vision systems find widespread application in industrial activities such as inspection [3,4], recognition [5,6], localization [7,8], and measurement [9,10]. These systems can generally be categorized into three groups: monocular, binocular, and multi-camera vision systems.…”

Section: Introductionmentioning

confidence: 99%

“…By substituting equation (24) into equation (7), we can derive the transformation matrix between the pixel points and the physical points on the actual calibration plane as follows: Where:…”

mentioning

confidence: 99%

Error analysis of precision measurement with monocular vision

Wang,

Li,

Zhang

et al. 2023

Eng. Res. Express

View full text Add to dashboard Cite

To systematically study the measurement error of the calibration coefficient method when the camera’s optical axis is not perpendicular to the measurement plane, this paper first discusses the principle of error measurement with 2D imaging model, and then derives the distribution relationship of physical points corresponding to evenly distributed pixels in the pixel coordinate system based on the projection transformation matrix of the vision system. Theoretical analysis reveals an equivariance series in the expression of physical point intervals. Considering rotational symmetry of the coordinate axis, this paper analyzes the geometric relationship when the calibration plane rotates around the X axis and derives the mathematical expression for dimensional measurement. Finally, an experimental platform with both industrial and telecentric lenses is proposed and designed. Experimental results demonstrate that the measurement results of the expression derived in this paper are consistent with the traditional coordinate transformation method and the maximum deviation of the measurement is less than 0.06 mm, validating the theoretical analysis presented in this paper and providing theoretical guidance for subsequent practical application.

show abstract

“…Use of image processing methods for gas leakage monitoring via infrared cameras have been suggested. This can detect methane molecules on the infrared spectrum (Fahimipirehgalin et al, 2021;Vollmer and Möllmann, 2017).…”

Section: Introductionmentioning

confidence: 99%