International Journal of Computer and Information Technology

Open Access Open Access  Restricted Access Subscription Access

A New Computer Vision Based Rail Detection Method Using Entropy and Support Vector Machines


Affiliations
1 Computer Engineering Department, Firat University, Elazig, Turkey
 

Condition monitoring in railways is an important and critical process in terms of travel safety. However, this process is generally done based on observation or with various equipment. Therefore, it is costly and has a high probability of error. In this study, a computer vision-based method for rail detection for condition monitoring in railways is proposed. In addition to the features obtained from the images, a new feature is calculated using entropy. Rail detection is provided by classifying these
features with Support Vector Machine (SVM). It has been seen that the proposed method works successfully and provides improvement in the monitoring process.

Keywords

classification, entropy, support vector machine, image processing, railways
User
Notifications
Font Size


  • A New Computer Vision Based Rail Detection Method Using Entropy and Support Vector Machines

Abstract Views: 213  |  PDF Views: 81

Authors

Kağan Murat
Computer Engineering Department, Firat University, Elazig, Turkey
Mehmet Karaköse
Computer Engineering Department, Firat University, Elazig, Turkey
Erhan Akın
Computer Engineering Department, Firat University, Elazig, Turkey

Abstract


Condition monitoring in railways is an important and critical process in terms of travel safety. However, this process is generally done based on observation or with various equipment. Therefore, it is costly and has a high probability of error. In this study, a computer vision-based method for rail detection for condition monitoring in railways is proposed. In addition to the features obtained from the images, a new feature is calculated using entropy. Rail detection is provided by classifying these
features with Support Vector Machine (SVM). It has been seen that the proposed method works successfully and provides improvement in the monitoring process.

Keywords


classification, entropy, support vector machine, image processing, railways

References