Detection of Foreign Matter on High-Speed Train Underbody Based on Deep Learning

He, Deqiang; Yao, Zikai; Jiang, Zhou; Chen, Yanjun; Deng, Jianxin; Xiang, Weibin

doi:10.1109/access.2019.2960439

Cited by 20 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed model consumed approximately around 1134 seconds for training the model over 20 epochs. The computational time to MobileNet V2 with LSTM over MobileNet V2 has not drastically reduced [ 92 , 93 ]. Still, MobileNet V2 exhibited a better prediction accuracy in terms of other performance evolution measures like Sensitivity, Specificity, and Accuracy.…”

Section: Resultsmentioning

confidence: 99%

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Srinivasu

SivaSai

Ijaz

et al. 2021

Sensors

449

169

View full text Add to dashboard Cite

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

show abstract

Section: Resultsmentioning

confidence: 99%

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Srinivasu

SivaSai

Ijaz

et al. 2021

Sensors

449

169

View full text Add to dashboard Cite

show abstract

“…For a complex surface with blur defects, image analysis techniques such as image filtering [9], local binary patterns (LBP) [10] and Gabor filtering [11] are overwhelmingly dominant. Especially for metal surfaces, vision-based detection methods have been widely used [12]- [14], such as histogram of oriented gradient (HoG) [15], scale-invariant feature transformation (SIFT) [16], spatial pyramids and support vector machine classifier (SVM) [17].…”

Section: A Traditional Methods For the Defect Detection Taskmentioning

confidence: 99%

“…The defect detection algorithm for EMU can be regarded as two types. The traditional image processing method based on the hand-crafted feature is widely used for decades [2]- [4]. However, performance highly depends on manual features designed by experts.…”

Section: Introductionmentioning

confidence: 99%

Defect Detection Method for Electric Multiple Units Key Components Based on Deep Learning

Zhao

Dai

et al. 2020

IEEE Access

View full text Add to dashboard Cite

It is inevitable that defects happen to key components of the long-running high-speed trains. Thus as an effective inspection approach for defects, image detection becomes significantly important for operation and maintenance in the railway industry. However, a massive number of images collected by inspection devices challenge traditional methods based on manual effort. To address this issue, this paper proposed an automatic detection method, termed as multi-stage pipeline for defect detection (MPDD). MPDD includes two stages, component detection stage improves RPN anchor mechanism and way of feature fusion to promote detection performance, defect classification stage combines super-resolution strategy with CNN to improve defect classification performance. Experiments on high-speed train defect dataset shown that MPDD can reach the highest mAP of 0.792. The mAP on NEU surface defect database reached to 0.765 at the speed of 203ms per image.

show abstract

“…Wei et al [23] applied a Faster-RCNN [24] to detect railway track fasteners. He et al [25] combined SSD [26] and Faster-RCNN to detect foreign matter in a high-speed train base. We [27] have also proposed an improved Faster-RCNN, which can accurately locate and identify the dropper of the OCS and has achieved great performance.…”

Section: A the Ocs Analysis And Fault Detectionmentioning

confidence: 99%

A Nested Residual Encoder-Decoder Network for Overhead Contact System Fastener Anomaly Detection

et al. 2021

View full text Add to dashboard Cite

An overhead contact system (OCS) is key to providing power to high-speed railways. OCS detection is an important measure to ensure the safe operation of a high-speed railway. At present, OCS anomaly detection mainly relies on the manual analysis of the images regularly collected by the 4C system, which is very inefficient and can easily miss anomalies. Although some classification and object detection methods based on deep learning can be used for OCS anomaly detection, the effective training of deep networks can be difficult to support due to the small number of anomaly OCS image samples. Considering that most OCS faults are abnormal fasteners, we propose an abnormal detection method based on normal images, called the nested residual encoder-decoder network (NRE-Net). This network consists of two nested encoder-decoder networks, where the encoder is the shared part, and a residual structure is added to the encoding and decoding branches to enhance the feature expression ability. The experimental results show that the method can greatly improve the accuracy of anomaly detection for the CIFAR-10 dataset and OCS fastener dataset.

show abstract

Detection of Foreign Matter on High-Speed Train Underbody Based on Deep Learning

Cited by 20 publications

References 21 publications

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Defect Detection Method for Electric Multiple Units Key Components Based on Deep Learning

A Nested Residual Encoder-Decoder Network for Overhead Contact System Fastener Anomaly Detection

Contact Info

Product

Resources

About