Application of computer vision algorithms in the problem of coupling of the locomotive with railcars

Gavrilova, N. M.; Dailid, I. A.; Molodyakov, Sergey A.; Korolev, I. N.; Попов, П. А.

doi:10.1109/isce.2018.8408904

Cited by 6 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of the application, the considered distances are short-range. Evaluation results showed that, on a straight section of railway track at distances up to 50 m, an absolute error of measuring the distance to a locomotive or wagon did not exceed 1.2 m. The problem of calculating the distance between a shunting locomotive and a wagon using video from a camera mounted on the locomotive is also considered in [ 45 ]. Here, in a two-stage method, first, the rail tracks were detected using traditional CV methods, Canny edge detection and Hough line transform; then, detection of Haar features and a Neural Networks-based search for wagons in the detected rail track region was performed.…”

Section: Vision-based On-board Obstacle Detection In Railwaysmentioning

confidence: 99%

A Review of Vision-Based On-Board Obstacle Detection and Distance Estimation in Railways

Ristić-Durrant

Franke

Michels

2021

Sensors

View full text Add to dashboard Cite

This paper provides a review of the literature on vision-based on-board obstacle detection and distance estimation in railways. Environment perception is crucial for autonomous detection of obstacles in a vehicle’s surroundings. The use of on-board sensors for road vehicles for this purpose is well established, and advances in Artificial Intelligence and sensing technologies have motivated significant research and development in obstacle detection in the automotive field. However, research and development on obstacle detection in railways has been less extensive. To the best of our knowledge, this is the first comprehensive review of on-board obstacle detection methods for railway applications. This paper reviews currently used sensors, with particular focus on vision sensors due to their dominant use in the field. It then discusses and categorizes the methods based on vision sensors into methods based on traditional Computer Vision and methods based on Artificial Intelligence.

show abstract

Section: Vision-based On-board Obstacle Detection In Railwaysmentioning

confidence: 99%