{"id":"W4319878658","doi":"10.1016/j.engstruct.2023.115676","title":"Vision-based real-time structural vibration measurement through deep-learning-based detection and tracking methods","year":2023,"lang":"en","type":"article","venue":"Engineering Structures","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":190,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Tracking (education); Computer science; Computer vision; Feature (linguistics); Noise (video); Parametric statistics; Deep learning; Bounding overwatch; Key (lock); Earthquake shaking table; Structural health monitoring; Object detection; Vibration; Engineering; Pattern recognition (psychology); Image (mathematics); Acoustics; Mathematics; Structural 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004509462,0.0004103674,0.0003303451,0.0003392805,0.0002288261,0.0001254138,0.0001671439,0.0002365129,0.00002544306],"category_scores_gemma":[0.0002646773,0.0004093712,0.00008133362,0.0005844039,0.00003480325,0.0002594745,0.00002957118,0.0004753061,0.000004789079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003220072,"about_ca_system_score_gemma":0.00002301457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006202961,"about_ca_topic_score_gemma":0.000003462315,"domain_scores_codex":[0.9981406,0.00009994562,0.0003987394,0.000378131,0.0004579396,0.0005246326],"domain_scores_gemma":[0.999158,0.0002598853,0.00007129861,0.0002879703,0.0001003049,0.0001225209],"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":[0.00001354969,8.306427e-7,0.0000502205,0.0002862876,0.00002384606,0.000003873212,0.0001799612,0.8110308,0.1315638,0.00005551641,0.00002621286,0.05676503],"study_design_scores_gemma":[0.0002370599,0.0000774374,0.103308,0.00007675125,0.00001942548,0.000005635141,0.00001282866,0.7309742,0.1641416,0.0005048679,0.000299731,0.0003424119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6546396,0.0003718649,0.3342035,0.00005946913,0.001552011,0.0005067203,0.000006061825,0.008621631,0.00003913989],"genre_scores_gemma":[0.8755117,0.00002926788,0.1239956,0.00001490589,0.0002594187,0.00005084714,0.00001943459,0.0001160781,0.000002763934],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2208721,"threshold_uncertainty_score":0.9998358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01978547674158573,"score_gpt":0.3144961184014202,"score_spread":0.2947106416598345,"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."}}