Railway equipment detection using exact height function shape descriptor based on fast adaptive Markov random field

Sun, Guodong; Zhang, Yang; Tang, Hanbing; Zhang, Huiming; Liu, Moyun; Zhao, Debin

doi:10.1117/1.oe.57.5.053114

Cited by 14 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental environment is as follows: Windows 10 (×64) operating system, CPU Intel Core I7-6700 v4 @2.60GHz and 16GB RAM, all experiments are implemented by Matlab and Tensorflow. Furthermore, in order to effectively verify the performance of the algorithm, four evaluation indicators are established [29]: correct detection rate (CDR), missing detection rate (MDR), false detection rate (FDR), and detection speed. For example, suppose the number of all fault images in the test set is n, the number of detected fault images is a, the number of undetected fault images is b, and the number of incorrect image detection results is c. So, the above indexes can be defined as: CDR = a/n, MDR = b/n, FDR = c/n.…”

Section: Resultsmentioning

confidence: 99%

A Fast Fabric Defect Detection Framework for Multi-Layer Convolutional Neural Network Based on Histogram Back-Projection

Sun

Zhou

Gao

et al. 2019

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

In this paper we design a fast fabric defect detection framework (Fast-DDF) based on gray histogram back-projection, which adopts end to end multi-convoluted network model to realize defect classification. First, the back-projection image is established through the gray histogram on fabric image, and the closing operation and adaptive threshold segmentation method are performed to screen the impurity information and extract the defect regions. Then, the defect images segmented by the Fast-DDF are marked and normalized into the multi-layer convolutional neural network for training. Finally, in order to solve the problem of difficult adjustment of network model parameters and long training time, some strategies such as batch normalization of samples and network fine tuning are proposed. The experimental results on the TILDA database show that our method can deal with various defect types of textile fabrics. The average detection accuracy with a higher rate of 96.12% in the database of five different defects, and the single image detection speed only needs 0.72s. key words: back-projection, gray histogram, fabric detection, multi-layer convolutional neural network Guodong Sun is a professor in the School of Mechanical Engineering at the Hubei University of Technology. He received his BS degree in energy and power engineering and his PhD degree in mechanical and electronic engineering from Huazhong University of Science and Technology in 2002 and 2008, respectively. His current research interests include machine vision and imaging processing. Zhen Zhoureceived the B.S. degree from in 2017. He is currently pursuing the M.S. degree with the School of Mechanical Engineering, Hubei University of Technology, Wuhan, China. His current research interests are machine learning and imaging processing.

show abstract

Section: Resultsmentioning

confidence: 99%

A Fast Fabric Defect Detection Framework for Multi-Layer Convolutional Neural Network Based on Histogram Back-Projection

Sun

Zhou

Gao

et al. 2019

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…To illustrate the superiority of our method, we compare our framework called as Light-weight Real-time FTI-FDet (LR FTI-FDet) with traditional detectors (Cascade detector with local binary pattern (LBP) [15], FAMRF + EHF [15], histogram of oriented gradient (HOG) + Adaboost + SVM [35]), one-stage detectors (YOLOv3 [19], SSD [20], RefineDet [22], RON [21], DSOD), two-stage detectors (Faster R-CNN [5], MLKP [24], R-FCN [6], Cascade R-CNN [25], FTI-FDet [7], Light FTI-FDet [4]), and light-weight detectors (MobileNetV2-SSD [11], MobileNetV2-SSDLite [11], ShuffleNetV2-SSD [26], Tiny-DSOD [28], Pelee [29]). In addition, we compare RFDNet-SSD with all above methods to discuss the performance of RFDNet and depthwise separable Conv.-based networks (e.g.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…However, these methods only detect one type of faults, which greatly influence their effectiveness. In addition, Sun et al [15] proposed a fast adaptive Markov random field (FAMRF) for image segmentation and an exact height function (EHF) for shape matching of fault region. This method solves the problem of multi-fault detection, but it is too complex to achieve enough accuracy and fast speed.…”

Section: Related Workmentioning

confidence: 99%

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

Yang

Linb

Zhan

et al. 2018

2018 25th IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…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%…”

Section: A Bogie and Framementioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

Within Artificial Intelligence, Deep Learning (DL) represents a paradigm that has been showing unprecedented performance in image and audio processing by supporting or even replacing humans in defect and anomaly detection. The Railway sector is expected to benefit from DL applications, especially in predictive maintenance applications, where smart audio and video sensors can be leveraged yet kept distinct from safety-critical functions. Such separation is crucial, as it allows for improving system dependability with no impact on its safety certification. This is further supported by the development of DL in other transportation domains, such as automotive and avionics, opening for knowledge transfer opportunities and highlighting the potential of such a paradigm in railways. In order to summarize the recent state-of-the-art while inquiring about future opportunities, this paper reviews DL approaches for the analysis of data generated by acoustic and visual sensors in railway maintenance applications that have been published until August 31st, 2021. In this paper, the current state of the research is investigated and evaluated using a structured and systematic method, in order to highlight promising approaches and successful applications, as well as to identify available datasets, current limitations, open issues, challenges, and recommendations about future research directions.

show abstract

Railway equipment detection using exact height function shape descriptor based on fast adaptive Markov random field

Cited by 14 publications

References 34 publications

A Fast Fabric Defect Detection Framework for Multi-Layer Convolutional Neural Network Based on Histogram Back-Projection

A Fast Fabric Defect Detection Framework for Multi-Layer Convolutional Neural Network Based on Histogram Back-Projection

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

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

Contact Info

Product

Resources

About