Enhanced rail component detection and consolidation for rail track inspection

Abstract

For safety purposes, railroad tracks need to be inspected on a regular basis for physical defects or design noncompliances. Such track defects and non-compliances, if not detected in a timely manner, may eventually lead to grave consequences such as train derailments.In this paper, we present a real-time automatic visionbased rail inspection system, with main focus on anchorsan important rail component type, and anchor-related rail defects, or exceptions. Our system robustly detects important rail components including ties, tie plates, anchors with high accuracy and efficiency. Detected objects are then consolidated across video frames and across camera views to map to physical rail objects, by combining the video data streams from all camera views with GPS information and speed information from the distance measuring instrument (DMI). After these rail components are detected and consolidated, further data integration and analysis is followed to detect sequence-level track defects, or exceptions. Quantitative analysis performed on a real online field test conducted on different track conditions demonstrates that our system achieves very promising performance in terms of rail component detection, anchor condition assessment, and compliance-level exception detection. We also show that our system outperforms another advanced rail inspection system in anchor detection.

Rail Component Detection, Optimization, and Assessment for Automatic Rail Track Inspection

“…To study the performance, we annotated tie plates on 6000 video frames (including all four camera views). Table III tabulates the performances of three different approaches, where we see that both of our batch and real-time optimization algorithms have outperformed our previous approach, which only relies on visual cues from a single camera view [15]. Moreover, the batch algorithm has achieved the best performance, with 84% precision and 92% recall rates.…”

Block Sparse Low-rank Matrix Decomposition based Visual Defect Inspection of Rail Track Surfaces

“…Generally, global or local spatial patterns of intensity extraction is the key issue in the above mentioned approaches, which will obtain good results for uniform textured rail surface images. However, because different rail track appearances and dynamic backgrounds are caused by heavy random noise and varying camera quality, these methods may fail in complex situations [44]. Moreover, most techniques require case-by-case adjustment of parameters, which is complex and depends heavily on individual experience.…”

Detection of rail faults using morphological feature extraction based image processing

“…L.Chen ve diğerleri [8], ray yüzeyindeki arızaları belirlemek için ray görüntüsüne görüntü iyileştirme, gürültü temizleme, özellik çıkarımı ve adaptive eşikleme gibi görüntü işleme yöntemlerini uygulamıştır. H.Trinh ve diğerleri [9], ray hatalarını ve arızalarını incelemiştir. GPS bilgisi ve uzaklık ölçümünden elde edilen hız bilgisi ile tüm kamera görüntülerinden elde edilen video akışı birleştirilerek ray nesnelerini tespit ettikten sonra ray arızalarının algılanması için ileri veri entegrasyonu ve veri analizi yapmıştır.…”