Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378805000> ?p ?o ?g. }
- W4378805000 endingPage "15018" @default.
- W4378805000 startingPage "15010" @default.
- W4378805000 abstract "Rail surface defect (RSD) is an important railroad track quality indicator and impacts the overall track safety and ride quality. Railroads need to inspect and evaluate RSD conditions regularly to make proper maintenance plan for both freight and passenger services. Unfortunately, current field practices for RSD defection have not been fully automated yet and significant amount of manual inspections are still involved, which could be labor-intensive but low-efficient. Earlier efforts have proposed multiple automatic RSD detection systems, but the accuracy and equipment cost issues have limited their applications in the field. To address the needs in track inspections, this study proposes an improved Deeplabv3-plus model using a lightweight backbone, attention module, and the Lovász-Softmax loss to automatically detect RSD. The improved model not only improves the detection performance but also keeps the computational cost manageable. The ResNet-18 backbone is adopted for the encoder design to reduce the computational cost and maximize the inference speed. The convolutional block attention module (CBAM) attention module is unified with the decoder structure for critical features’ representation. The optimum crop size is determined in the training process. The Lovász-Softmax loss is implemented to address the severe class-imbalance issue. The improved DeepLabv3-plus model is compared with five other models to validate the performance. Experimental results on both original data and noisy data confirm the proposed model achieves the best performance on evaluation metrics and visualization. This work provides a feasible solution for the future implementation of automatic railroad track inspection." @default.
- W4378805000 created "2023-06-01" @default.
- W4378805000 creator A5026282390 @default.
- W4378805000 creator A5036076192 @default.
- W4378805000 creator A5049860836 @default.
- W4378805000 date "2023-07-01" @default.
- W4378805000 modified "2023-10-11" @default.
- W4378805000 title "Automatic Rail Surface Defect Inspection Using the Pixelwise Semantic Segmentation Model" @default.
- W4378805000 cites W1903029394 @default.
- W4378805000 cites W2029440482 @default.
- W4378805000 cites W2049384457 @default.
- W4378805000 cites W2069747077 @default.
- W4378805000 cites W2102219944 @default.
- W4378805000 cites W2194775991 @default.
- W4378805000 cites W2331159061 @default.
- W4378805000 cites W2462812143 @default.
- W4378805000 cites W2555875178 @default.
- W4378805000 cites W2560023338 @default.
- W4378805000 cites W2606490591 @default.
- W4378805000 cites W2748643398 @default.
- W4378805000 cites W2761216034 @default.
- W4378805000 cites W2783496566 @default.
- W4378805000 cites W2793513544 @default.
- W4378805000 cites W2794841368 @default.
- W4378805000 cites W2795587607 @default.
- W4378805000 cites W2800919934 @default.
- W4378805000 cites W2803930526 @default.
- W4378805000 cites W2889460162 @default.
- W4378805000 cites W2890733150 @default.
- W4378805000 cites W2893813411 @default.
- W4378805000 cites W2901014246 @default.
- W4378805000 cites W2905127877 @default.
- W4378805000 cites W2913074553 @default.
- W4378805000 cites W2956776634 @default.
- W4378805000 cites W2963037989 @default.
- W4378805000 cites W2982220924 @default.
- W4378805000 cites W3004377299 @default.
- W4378805000 cites W3041526222 @default.
- W4378805000 cites W3088602441 @default.
- W4378805000 cites W3090474196 @default.
- W4378805000 cites W3092600573 @default.
- W4378805000 cites W3109298970 @default.
- W4378805000 cites W3113270537 @default.
- W4378805000 cites W3119622082 @default.
- W4378805000 cites W3129040539 @default.
- W4378805000 cites W3161489491 @default.
- W4378805000 cites W3181721058 @default.
- W4378805000 cites W4292161270 @default.
- W4378805000 doi "https://doi.org/10.1109/jsen.2023.3280117" @default.
- W4378805000 hasPublicationYear "2023" @default.
- W4378805000 type Work @default.
- W4378805000 citedByCount "1" @default.
- W4378805000 crossrefType "journal-article" @default.
- W4378805000 hasAuthorship W4378805000A5026282390 @default.
- W4378805000 hasAuthorship W4378805000A5036076192 @default.
- W4378805000 hasAuthorship W4378805000A5049860836 @default.
- W4378805000 hasConcept C111919701 @default.
- W4378805000 hasConcept C118505674 @default.
- W4378805000 hasConcept C127413603 @default.
- W4378805000 hasConcept C13280743 @default.
- W4378805000 hasConcept C154945302 @default.
- W4378805000 hasConcept C185798385 @default.
- W4378805000 hasConcept C188441871 @default.
- W4378805000 hasConcept C200601418 @default.
- W4378805000 hasConcept C205649164 @default.
- W4378805000 hasConcept C41008148 @default.
- W4378805000 hasConcept C79403827 @default.
- W4378805000 hasConcept C81363708 @default.
- W4378805000 hasConcept C89992363 @default.
- W4378805000 hasConceptScore W4378805000C111919701 @default.
- W4378805000 hasConceptScore W4378805000C118505674 @default.
- W4378805000 hasConceptScore W4378805000C127413603 @default.
- W4378805000 hasConceptScore W4378805000C13280743 @default.
- W4378805000 hasConceptScore W4378805000C154945302 @default.
- W4378805000 hasConceptScore W4378805000C185798385 @default.
- W4378805000 hasConceptScore W4378805000C188441871 @default.
- W4378805000 hasConceptScore W4378805000C200601418 @default.
- W4378805000 hasConceptScore W4378805000C205649164 @default.
- W4378805000 hasConceptScore W4378805000C41008148 @default.
- W4378805000 hasConceptScore W4378805000C79403827 @default.
- W4378805000 hasConceptScore W4378805000C81363708 @default.
- W4378805000 hasConceptScore W4378805000C89992363 @default.
- W4378805000 hasFunder F4320332391 @default.
- W4378805000 hasIssue "13" @default.
- W4378805000 hasLocation W43788050001 @default.
- W4378805000 hasOpenAccess W4378805000 @default.
- W4378805000 hasPrimaryLocation W43788050001 @default.
- W4378805000 hasRelatedWork W1895390915 @default.
- W4378805000 hasRelatedWork W2596556980 @default.
- W4378805000 hasRelatedWork W2758063741 @default.
- W4378805000 hasRelatedWork W2883041339 @default.
- W4378805000 hasRelatedWork W2949389737 @default.
- W4378805000 hasRelatedWork W2963556241 @default.
- W4378805000 hasRelatedWork W2977314777 @default.
- W4378805000 hasRelatedWork W3000978536 @default.
- W4378805000 hasRelatedWork W3018421652 @default.
- W4378805000 hasRelatedWork W3171731982 @default.
- W4378805000 hasVolume "23" @default.