Rail defect detection with real time image processing technique

Taştimur, Canan; Karaköse, Mehmet; Akın, Erhan; Aydın, İlhan

doi:10.1109/indin.2016.7819194

Cited by 37 publications

(31 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditional image processing techniques extract hand-crafted features to describe and detect defects, which can be mainly divided into four categories: structural-based, threshold-based, spectral-based, and model-based methods [7]. In detail, the commonly used structuralbased methods include skeleton-based [8], template match [9], edge-based [10], and morphological operations [11]. The threshold-based methods mainly contain the iterative optimal threshold [12], the Otsu method [13], contrast adjustment threshold method [14], and the Kittler method [15].…”

Section: Traditional Methodsmentioning

confidence: 99%

Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network

Duan

Jiajia

et al. 2020

Sensors

174

View full text Add to dashboard Cite

Metallic surface defect detection is an essential and necessary process to control the qualities of industrial products. However, due to the limited data scale and defect categories, existing defect datasets are generally unavailable for the deployment of the detection model. To address this problem, we contribute a new dataset called GC10-DET for large-scale metallic surface defect detection. The GC10-DET dataset has great challenges on defect categories, image number, and data scale. Besides, traditional detection approaches are poor in both efficiency and accuracy for the complex real-world environment. Thus, we also propose a novel end-to-end defect detection network (EDDN) based on the Single Shot MultiBox Detector. The EDDN model can deal with defects with different scales. Furthermore, a hard negative mining method is designed to alleviate the problem of data imbalance, while some data augmentation methods are adopted to enrich the training data for the expensive data collection problem. Finally, the extensive experiments on two datasets demonstrate that the proposed method is robust and can meet accuracy requirements for metallic defect detection.

show abstract

Section: Traditional Methodsmentioning

confidence: 99%

Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network

Duan

Jiajia

et al. 2020

Sensors

174

View full text Add to dashboard Cite

show abstract

“…Şekil 1. Ray yüzeyi kusur türleri [4] Bu çalışmada, önce ray-temas bölgeleri doğru şekilde tespit edilmiş ve bu bölgeler üzerinde bütün kusur tiplerini tespit edebilen sütun ortalama algoritma, eşik yöntemi kullanılmıştır. Eşik değeri ray-temas bölgesinin sütunlarından elde edilmiş olduğundan doğru şekilde bölgesel, çatlak ve noktasal kusur tespitlerinin yapıldığı görülmüştür.…”

Section: Ray Kullanımında Oluşan Kusurlarunclassified

Two New Methods Developed to Detect Railway Rail and Defects

Çelik

2020

Demiryolu Mühendisliği

View full text Add to dashboard Cite

Öz: Raylı sistem araçları günümüzde çok yaygın kullanılmaktadır. Bu yaygın kullanımın nedeni, en güvenli yolcu ve yük taşıma aracı olmasından kaynaklanmaktadır. Bu güvenilirliğin devam etmesi için demiryolu raylarının sık sık kontrol edilmesi gerekmektedir. Bu kontroller yardımıyla demiryolu ray kusurları bulunarak, istenmeyen kazaların önüne geçilebilmektedir. Günümüzde demiryolu raylarında yapılan kontroller yıl içinde birkaç kez belirli dönemlerde yapılmaktadır. Bu demiryolu ray kontrol işlemi çoğunlukla çalışan personel tarafından gözlem yapılarak gerçekleşmektedir. Bu yöntem güvenilir değildir ayrıca uzun zaman alabilmektedir. Demiryolları devamlı kullanıldığından kontrollerin kısa sürede tamamlanması gerekmektedir. Bu kontroller yapılırken ray yapısında, tahribat yapılmaması gerekmektedir. Bu yüzden tahribatsız yöntemler tercih edilmektedir. Bilgisayar destekli görsel muayene yöntemi tahribatsız muayene yöntemlerinden biridir. Bu çalışmada, bir kamera yardımıyla elde ray görüntüleri üzerinde, bilgisayar destekli görüntü işleme algoritmaları kullanılarak, ray temas bölgesi tespit edilmiştir. Ray görüntüleri üzerinde, özgün olarak geliştirilen Yatay-Dikey ve Yatay-Yatay görüntü işleme algoritmaları uygulanmıştır. Elde edilen sonuçlara göre Yatay-Dikey algoritmasının ray-temas bölgelerini doğru şekilde tespit ettiği görülmüştür. En son aşamada işaretlenen ray-temas bölgeleri üzerinde, kusur tespiti yapmak için sütun ortalaması, eşikleme yöntemi önerilmiştir.

show abstract

“…The traditional image processing method uses the primitive attributes reflected by local anomalies to detect and segment defects, which can be further divided into the structural method, threshold method, spectral method, and model-based method [11]. The structural method includes edge [12], skeleton [13], template match [14], and morphological operations [15]. The threshold methods include the iterative optimal threshold [16], Otsu method [17], contrast adjustment threshold method [18], Kittler method [19], and watershed method [20], etc.…”

Section: Introductionmentioning

confidence: 99%

Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks

et al. 2018

View full text Add to dashboard Cite

Automatic metallic surface defect inspection has received increased attention in relation to the quality control of industrial products. Metallic defect detection is usually performed against complex industrial scenarios, presenting an interesting but challenging problem. Traditional methods are based on image processing or shallow machine learning techniques, but these can only detect defects under specific detection conditions, such as obvious defect contours with strong contrast and low noise, at certain scales, or under specific illumination conditions. This paper discusses the automatic detection of metallic defects with a twofold procedure that accurately localizes and classifies defects appearing in input images captured from real industrial environments. A novel cascaded autoencoder (CASAE) architecture is designed for segmenting and localizing defects. The cascading network transforms the input defect image into a pixel-wise prediction mask based on semantic segmentation. The defect regions of segmented results are classified into their specific classes via a compact convolutional neural network (CNN). Metallic defects under various conditions can be successfully detected using an industrial dataset. The experimental results demonstrate that this method meets the robustness and accuracy requirements for metallic defect detection. Meanwhile, it can also be extended to other detection applications.

show abstract

Rail defect detection with real time image processing technique

Cited by 37 publications

References 18 publications

Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network

Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network

Two New Methods Developed to Detect Railway Rail and Defects

Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks

Contact Info

Product

Resources

About