Abstract
When a high-speed train is running, it is easy for foreign objects like rail-side plastic bags to enter bottom bogies, cables and equipment gaps, which affects the safety of driving. At present, the detection accuracy of such foreign objects is low. To solve this problem, the present study used the latest deep learning based object detection networks, such as SSD and Faster R-CNN, which combined with different feature extractors to build a detection network. Through data augmentation of a sample, the number of sizes was expanded. By the idea of transfer learning, the COCO dataset was used as the source data to transfer features to the new detection network and then retrained to build a train bottom plastic bag detection network based on deep learning. It was shown that through data augmentation, the precision of each combination significantly improved. Moreover, the results using combination of SSD and MobileNet obtained the fastest detection speed with an average time of 41 ms and a precision rate of 81.3%. The accuracy using combination of SSD + Inception V2 combination reached to 89.7%, with an average time of 53 ms.
Highlights
INTRODUCTIONRailway transport has greatly developed worldwide. In China, the advantages of high-speed, on-time arrival and low-cost fares benefited from the optimization of control [1]–[3] has made the railway transport become the most popular choice for many people
In recent decades, railway transport has greatly developed worldwide
At present, the inspection of foreign matter in the train bottom is mostly completed by artificial classification or conventional target recognition methods
Summary
Railway transport has greatly developed worldwide. In China, the advantages of high-speed, on-time arrival and low-cost fares benefited from the optimization of control [1]–[3] has made the railway transport become the most popular choice for many people. He et al.: Detection of Foreign Matter on High-Speed Train Underbody Based on Deep Learning accuracy, it is still necessary to check the acquired images manually because the target detection algorithm of the TEDS system is based on conventional target recognition algorithms, such as SIFT [4] and HOG [5], which requires careful engineering and extensive expertise to design features artificially and identify the targets through these features and combine the corresponding strategies to locate the targets. The positive performance of the latest deep learning-based target detection and recognition models SSD [14] (single shot multibox detector) and Faster R-CNN [15] are created to detect foreign matter.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
