Matches in SemOpenAlex for { <https://semopenalex.org/work/W4291201881> ?p ?o ?g. }
- W4291201881 abstract "Abstract Train rolling stock examination (TRSE) is a physical procedure for inspecting the bogie parts during transit at a little over 30 kmph. Currently, this process is manually performed across many railway networks across the world. This work proposes to automate the process of TRSE using artificial intelligence techniques. The previous works have proposed active contour-based models for the segmentation of bogie parts. Though accurate, the models require manual intervention and are found to be iterative making them unsuitable for real-time operations. In this work, we propose a segmentation model followed by a deep learning classifier that can accurately increase the deployability of such systems in real time. We apply the UNet model for the segmentation of bogie parts which are further classified using an attention-based convolutional neural network (CNN) classifier. In this work, we propose a shape deformable attention model to identify shape variations occurring in the video sequence due to viewpoint changes during the train movement. The TRSNet is trained and tested on the high-speed train bogie videos captured across four different trains. The results of the experimentation have been shown to improve the recognition accuracy of the proposed system by 6% over the state-of-the-art classifiers previously developed for TRSE." @default.
- W4291201881 created "2022-08-13" @default.
- W4291201881 creator A5000603832 @default.
- W4291201881 creator A5021694052 @default.
- W4291201881 creator A5040608966 @default.
- W4291201881 date "2022-08-13" @default.
- W4291201881 modified "2023-09-26" @default.
- W4291201881 title "Train rolling stock video segmentation and classification for bogie part inspection automation: a deep learning approach" @default.
- W4291201881 cites W1671049577 @default.
- W4291201881 cites W1987028625 @default.
- W4291201881 cites W2035232228 @default.
- W4291201881 cites W2049324726 @default.
- W4291201881 cites W2064163566 @default.
- W4291201881 cites W2099807160 @default.
- W4291201881 cites W2111417878 @default.
- W4291201881 cites W2115664739 @default.
- W4291201881 cites W2116040950 @default.
- W4291201881 cites W2154964969 @default.
- W4291201881 cites W2188747816 @default.
- W4291201881 cites W2271132848 @default.
- W4291201881 cites W2563266287 @default.
- W4291201881 cites W2565813159 @default.
- W4291201881 cites W2734556049 @default.
- W4291201881 cites W2752200756 @default.
- W4291201881 cites W2792220137 @default.
- W4291201881 cites W2794026873 @default.
- W4291201881 cites W2806565734 @default.
- W4291201881 cites W2898199467 @default.
- W4291201881 cites W2901169858 @default.
- W4291201881 cites W2909494862 @default.
- W4291201881 cites W2945653427 @default.
- W4291201881 cites W2955271382 @default.
- W4291201881 cites W2963881378 @default.
- W4291201881 cites W2963936229 @default.
- W4291201881 cites W2964227007 @default.
- W4291201881 cites W2998526951 @default.
- W4291201881 cites W3005184133 @default.
- W4291201881 cites W3036018707 @default.
- W4291201881 cites W3040250913 @default.
- W4291201881 cites W3087353686 @default.
- W4291201881 cites W3088134661 @default.
- W4291201881 cites W3094412822 @default.
- W4291201881 cites W3202664683 @default.
- W4291201881 cites W4200525103 @default.
- W4291201881 cites W4210919941 @default.
- W4291201881 cites W4226095742 @default.
- W4291201881 doi "https://doi.org/10.1186/s44147-022-00128-x" @default.
- W4291201881 hasPublicationYear "2022" @default.
- W4291201881 type Work @default.
- W4291201881 citedByCount "0" @default.
- W4291201881 crossrefType "journal-article" @default.
- W4291201881 hasAuthorship W4291201881A5000603832 @default.
- W4291201881 hasAuthorship W4291201881A5021694052 @default.
- W4291201881 hasAuthorship W4291201881A5040608966 @default.
- W4291201881 hasBestOaLocation W42912018811 @default.
- W4291201881 hasConcept C108583219 @default.
- W4291201881 hasConcept C111919701 @default.
- W4291201881 hasConcept C115901376 @default.
- W4291201881 hasConcept C119857082 @default.
- W4291201881 hasConcept C123045823 @default.
- W4291201881 hasConcept C127413603 @default.
- W4291201881 hasConcept C153180895 @default.
- W4291201881 hasConcept C154945302 @default.
- W4291201881 hasConcept C190839683 @default.
- W4291201881 hasConcept C205649164 @default.
- W4291201881 hasConcept C31972630 @default.
- W4291201881 hasConcept C41008148 @default.
- W4291201881 hasConcept C50644808 @default.
- W4291201881 hasConcept C58640448 @default.
- W4291201881 hasConcept C78519656 @default.
- W4291201881 hasConcept C81363708 @default.
- W4291201881 hasConcept C89600930 @default.
- W4291201881 hasConcept C95623464 @default.
- W4291201881 hasConcept C98045186 @default.
- W4291201881 hasConceptScore W4291201881C108583219 @default.
- W4291201881 hasConceptScore W4291201881C111919701 @default.
- W4291201881 hasConceptScore W4291201881C115901376 @default.
- W4291201881 hasConceptScore W4291201881C119857082 @default.
- W4291201881 hasConceptScore W4291201881C123045823 @default.
- W4291201881 hasConceptScore W4291201881C127413603 @default.
- W4291201881 hasConceptScore W4291201881C153180895 @default.
- W4291201881 hasConceptScore W4291201881C154945302 @default.
- W4291201881 hasConceptScore W4291201881C190839683 @default.
- W4291201881 hasConceptScore W4291201881C205649164 @default.
- W4291201881 hasConceptScore W4291201881C31972630 @default.
- W4291201881 hasConceptScore W4291201881C41008148 @default.
- W4291201881 hasConceptScore W4291201881C50644808 @default.
- W4291201881 hasConceptScore W4291201881C58640448 @default.
- W4291201881 hasConceptScore W4291201881C78519656 @default.
- W4291201881 hasConceptScore W4291201881C81363708 @default.
- W4291201881 hasConceptScore W4291201881C89600930 @default.
- W4291201881 hasConceptScore W4291201881C95623464 @default.
- W4291201881 hasConceptScore W4291201881C98045186 @default.
- W4291201881 hasIssue "1" @default.
- W4291201881 hasLocation W42912018811 @default.
- W4291201881 hasOpenAccess W4291201881 @default.
- W4291201881 hasPrimaryLocation W42912018811 @default.
- W4291201881 hasRelatedWork W2005437358 @default.
- W4291201881 hasRelatedWork W2517104666 @default.
- W4291201881 hasRelatedWork W2731899572 @default.