An Implementation of Environment Recognition for Enhancement of Advanced Video Based Railway Inspection Car Detection Modules

Cho, Chul Jin; Park, Young; Ku, Bonhwa; Ko, Hanseok

doi:10.1166/sam.2018.3050

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model of the feature vector for classification by SVM is shown in Eq. (1) [13]. Each of the k considered images is converted into a feature vector, xi, which is defined by multiple area features and its label yi that represents the class index indicating one of the classes.…”

Section: Image Processing Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Implementation of Image Processing in Studying Contact Conditions of Overhead Contact Line-Pantograph at 400 km/h

Lee

Kim

et al. 2020

J. Electr. Eng. Technol.

Self Cite

View full text Add to dashboard Cite

As an overhead contact line contacts the pantograph of an electric railway to supply electricity, it is operated after its electrical and mechanical safety features are examined. This study investigates a technology for examining the contact condition between the pantograph and the overhead contact line by using image processing. Contact condition images between the pantograph and the overhead contact line were obtained using a video device installed on the roof of a train, and the contact condition was tested between Iksan Station and Jeongeup Station of the Honam high-speed railway in the velocity range of 100-400 km/h. Images between the pantograph and the overhead contact line were used to recognize the feature points of the pantograph, and the moving displacement of the contact strip was detected using a Hough transform. The detected displacement was represented as a frequency through the zero crossing and a Fourier transform, and then its relationship with the arcing between the overhead contact line and the pantograph was analyzed.

show abstract

Section: Image Processing Methodsmentioning

confidence: 99%

“…6 Method for detecting displacement using tilt of contact strip on pantograph [12,14] Fig. 4 Example of feature vector quantified from image [13] the pixel information of the reference image of the pantograph recognized through the first template matching, the position of the pantograph is found in the detected image.…”

Section: Image Processing Methodsmentioning

confidence: 99%

Implementation of Image Processing in Studying Contact Conditions of Overhead Contact Line-Pantograph at 400 km/h

Lee

Kim

et al. 2020

J. Electr. Eng. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The increase in speed and tension of the overhead line can lead to a rise in the uplift amount, strain, and contact loss, which necessitates the development of components with high mechanical strength and electrical conductivity [3]. The overhead line system is installed at a height of 5 m or higher and consists of diverse components [4][5][6]. Especially, as the speed of railway increases, the demand for precision also keeps rising [1].…”

Section: Introductionmentioning

confidence: 99%

An improvement of manufacturing process using 3D printing technology for overhead line components on railway electrification

Lee

Jung

2022

J. Electr. Eng. Technol.

View full text Add to dashboard Cite

In an electric railway, an overhead contact system (OCS) is assembled with many components, and it maintains a voltage of 25 kV to supply electricity to the electric trains. As electric trains grow faster, the overhead line comes to employ a diverse range of materials to deliver electricity and maintain high tension. Overhead lines supply electricity to electric trains through mechanical contact with a pantograph, and since they are not fault-tolerant, they require high reliability. That makes it take a long time to develop and supply components and also makes it difficult and time consuming to apply new materials or new designs to components. This study proposes a manufacturing process for overhead line components using 3D printing technology. For this, a clevis terminal clamp for high-speed railway was chosen and a design drawing was created with 3D scanning. For molding, additive manufacturing technology was used. The study castings were obtained by applying precision casting and sand mold casting methods, respectively, and their elongation and tensile strength were compared with products made with a traditional method.

show abstract

“…For collecting track conditions, the railway industry has employed various dedicated devices, such as track inspection vehicles [31] and visual inspection systems [32]. Although these devices perform well in detecting track conditions, the expensive cost and the interference for regular operation limit their usage in urban rail transit systems.…”

Section: Introductionmentioning

confidence: 99%

Using Vehicle Interior Noise Classification for Monitoring Urban Rail Transit Infrastructure

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

This study developed a multi-classification model for vehicle interior noise from the subway system, collected on smartphones. The proposed model has the potential to be used to analyze the causes of abnormal noise using statistical methods and evaluate the effect of rail maintenance work. To this end, first, we developed a multi-source data (audio, acceleration, and angle rate) collection framework via smartphone built-in sensors. Then, considering the Shannon entropy, a 1-second window was selected to segment the time-series signals. This study extracted 45 features from the time- and frequency-domains to establish the classifier. Next, we investigated the effects of balancing the training dataset with the Synthetic Minority Oversampling Technique (SMOTE). By comparing and analyzing the classification results of importance-based and mutual information-based feature selection methods, the study employed a feature set consisting of the top 10 features by importance score. Comparisons with other classifiers indicated that the proposed XGBoost-based classifier runs fast while maintaining good accuracy. Finally, case studies were provided to extend the applications of this classifier to the analysis of abnormal vehicle interior noise events and evaluate the effects of rail grinding.

show abstract

An Implementation of Environment Recognition for Enhancement of Advanced Video Based Railway Inspection Car Detection Modules

Cited by 4 publications

References 0 publications

Implementation of Image Processing in Studying Contact Conditions of Overhead Contact Line-Pantograph at 400 km/h

Implementation of Image Processing in Studying Contact Conditions of Overhead Contact Line-Pantograph at 400 km/h

An improvement of manufacturing process using 3D printing technology for overhead line components on railway electrification

Using Vehicle Interior Noise Classification for Monitoring Urban Rail Transit Infrastructure

Contact Info

Product

Resources

About