A Unified Framework for Fault Detection of Freight Train Images Under Complex Environment

Abstract

Real-time fault detection for freight trains plays a vital role in guaranteeing the security and optimal operation of railway transportation under stringent resource requirements. Despite the promising results for deep learning based approaches, the performance of these fault detectors on freight train images, are far from satisfactory in both accuracy and efficiency. This paper proposes a unified light framework to improve detection accuracy while supporting a real-time operation with a low resource requirement. We firstly design a novel lightweight backbone (RFDNet) to improve the accuracy and reduce computational cost. Then, we propose a multi region proposal network using multi-scale feature maps generated from RFDNet to improve the detection performance. Finally, we present multi level position-sensitive score maps and region of interest pooling to further improve accuracy with few redundant computations. Extensive experimental results on public benchmark datasets suggest that our RFDNet can significantly improve the performance of baseline network with higher accuracy and efficiency. Experiments on six fault datasets show that our method is capable of real-time detection at over 38 frames per second and achieves competitive accuracy and lower computation than the state-ofthe-art detectors.

A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance

“…First, a CNN-based system detects regions of interest, then another CNN extracts bolts edges; lastly, to detect single or multiple bolt loosening, a 3D reconstruction method was used to calculate the distance between the bolt cap and the mounting surface. Results show optimal performances with a relative error smaller than 1.42%, moreover, the processing Faster R-CNN (GoogLeNet+HyperNet) CDR: 99.86% [140] from [152] (as [139]) and [153] Not From [139], [140] As described in [139], [140] OD D6 Brake show key, 9600 images grouped into 2 classes (no-fault, fault) SqueezeNet mCDR: 98.60%…”

“…Differently, in [120], the authors used the ImageNet dataset [93] and VOC2007 [131] to pretrain their architectures, so transferring knowledge from big datasets and then adapting it to their purposes. Reference [111] used the Catenary-5000 [132] to test the proposed [35], [139], [140], [141], [142], [143], [144], [145], [146], [147] [148]…”

“…Reference [139] proposes a defect detection architecture to deal with low image quality and complex background, sliding a set of anchors over multi-level convolutional feature maps.…”

“…Regarding the used datasets, references [139] and [140] leverage those introduced in [152] to train and test their models. In [139], the authors also used the ImageNet dataset [93] to pre-train the model implementing, de facto, a transfer learning approach. Likely, in [142], the authors relied on the BSD500 dataset [154] to pre-train their bolt edge detection model.…”

MPDNet: A 3D Missing Part Detection Network Based on Point Cloud Segmentation

“…This task is usually completed by an intelligent robot or other devices equipped with computer vision models [1,2,3,4], which is much more convenient and economical than manual inspection. There have existed many works [5,6,7,8] that utilize 2D object detection pipelines [9,10,11,12] for missing part detection. However, all existing works only use 2D vision based models that take images or videos as input, which can't handle the situation when occlusion exists.…”