{"id":"W4393631426","doi":"10.1109/tetci.2024.3378651","title":"A Small Object Real-Time Detection Method for Power Line Inspection in Low-Illuminance Environments","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Illuminance; Line (geometry); Computer science; Power (physics); Computer vision; Object (grammar); Artificial intelligence; Optics; Mathematics; Physics","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":[0.0004214902,0.0001886504,0.000193066,0.0005811494,0.00009328192,0.00005110632,0.00008336951,0.0001697425,0.00003306395],"category_scores_gemma":[0.00001139235,0.0002139453,0.0001098258,0.0006458585,0.00002178508,0.00015315,0.000001284949,0.0003794897,0.00004973553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004557296,"about_ca_system_score_gemma":0.00002702794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001426393,"about_ca_topic_score_gemma":0.0001907459,"domain_scores_codex":[0.998664,0.00006427157,0.0005156894,0.0003494493,0.0001862343,0.0002203338],"domain_scores_gemma":[0.9994474,0.0003270903,0.00003420717,0.000124968,0.00002899755,0.0000373045],"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":[0.0000335623,0.00004264041,0.000001529646,0.00005515826,0.00001757135,0.000005151777,0.000348973,0.8750612,0.00274484,0.0001014042,0.000006826539,0.1215812],"study_design_scores_gemma":[0.0001476628,0.0001500832,0.0000738205,0.0002650089,0.000008151702,0.0000110284,0.00007254004,0.9497086,0.04745687,0.001302608,0.0006068422,0.00019681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04301987,0.00006104091,0.9534926,0.00004175901,0.00249519,0.0004203779,0.0000164588,0.0002612608,0.0001914829],"genre_scores_gemma":[0.9888545,0.00008617901,0.01047426,0.00001317339,0.0001394005,0.0001595839,0.000004430441,0.00003775071,0.0002306855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9458346,"threshold_uncertainty_score":0.8724436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03049701573601609,"score_gpt":0.2980562263637444,"score_spread":0.2675592106277283,"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."}}