{"id":"W3166943914","doi":"10.1109/vtc2021-spring51267.2021.9448887","title":"UAV-assisted Railway Track Segmentation based on Convolutional Neural Networks","year":2021,"lang":"en","type":"article","venue":"","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Track (disk drive); Convolutional neural network; Segmentation; Intersection (aeronautics); Artificial intelligence; Deep learning; Task (project management); Market segmentation; Encoder; Computer vision; Real-time computing; Engineering; Transport engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003825501,0.0001048991,0.00008685734,0.000031575,0.00005108341,0.00003204866,0.00004059709,0.00005815647,0.0003491638],"category_scores_gemma":[0.000009582246,0.00009805745,0.00005000763,0.0001186415,0.0000119599,0.00007059078,0.000006210222,0.0001367956,0.00001177834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008237279,"about_ca_system_score_gemma":0.00001469628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000026401,"about_ca_topic_score_gemma":0.000007536248,"domain_scores_codex":[0.999423,0.00001515757,0.0001278614,0.0001197936,0.0001195875,0.0001946345],"domain_scores_gemma":[0.9997473,0.00003917893,0.00001262408,0.0001087998,0.00004858129,0.0000434942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009875944,0.000009723443,0.0008460958,0.00001260753,0.00001433258,0.0000203466,0.00002236615,0.9760629,0.007462524,0.0002897784,0.003016312,0.01223313],"study_design_scores_gemma":[0.0004619657,0.00001613324,0.02755558,0.00001695044,0.000008269711,0.000008916448,0.00007429433,0.9555753,0.01517277,0.00002248143,0.000953203,0.0001341578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4021425,0.0002567207,0.5442194,0.0004496222,0.007539369,0.0002926749,0.0000168192,0.001081023,0.04400189],"genre_scores_gemma":[0.9953703,0.000003781491,0.003523558,0.0003436592,0.0003526239,0.00001042894,0.00006963366,0.00001749957,0.000308492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5932279,"threshold_uncertainty_score":0.3998667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008392899637134786,"score_gpt":0.2125919302148336,"score_spread":0.2041990305776988,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}