{"id":"W3132587315","doi":"10.1109/igarss39084.2020.9324137","title":"Automated Detection of Manhole Covers in MLS Point Clouds Using a Deep Learning Approach","year":2020,"lang":"en","type":"article","venue":"","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Point cloud; Deep learning; Lidar; Computer science; Road surface; Artificial intelligence; Cover (algebra); Feature (linguistics); Object detection; Computer vision; Point (geometry); Mobile mapping; Feature extraction; Remote sensing; Pattern recognition (psychology); Engineering; Geography; Mathematics; Civil engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00006267861,0.00009344335,0.0001405246,0.00005996538,0.00002174775,0.00001112959,0.00005192561,0.00006241549,0.000009630395],"category_scores_gemma":[0.00002385512,0.0000927878,0.0000326522,0.0002440981,0.00001074743,0.00009619472,0.0000209512,0.0001837778,0.000002703901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008006696,"about_ca_system_score_gemma":0.000005835769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005835545,"about_ca_topic_score_gemma":0.000004733158,"domain_scores_codex":[0.9994528,0.00001395333,0.0001752289,0.0001042429,0.00007898769,0.0001747417],"domain_scores_gemma":[0.9998568,0.000008225499,0.00002586871,0.00005519632,0.00001744079,0.00003646212],"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":[0.000008222983,0.000002112683,0.0007660895,0.00005737598,0.000009798715,0.000002349762,0.000772362,0.7380058,0.2587455,0.00002052665,0.000004073563,0.001605798],"study_design_scores_gemma":[0.0002372893,0.00002125647,0.001587676,0.00001739347,0.000005502062,0.000004376977,0.0007976789,0.8931735,0.103975,0.000009535192,0.00007866071,0.00009219874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8308238,0.00003297739,0.1654385,0.000004204447,0.0001462999,0.0000794423,3.043311e-7,0.0004953654,0.002979143],"genre_scores_gemma":[0.9942679,0.000004925802,0.00561245,0.00001571187,0.00006928803,0.000002629874,0.000001472972,0.00002100324,0.000004645865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1634441,"threshold_uncertainty_score":0.3783776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009213663470463075,"score_gpt":0.2057735336182487,"score_spread":0.1965598701477856,"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."}}