{"id":"W4311163792","doi":"10.18280/ts.390525","title":"Traffic Lights Detection and Recognition with New Benchmark Datasets Using Deep Learning and TensorFlow Object Detection API","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Deep learning; Artificial intelligence; Computer science; Transfer of learning; Object detection; Machine learning; Variable (mathematics); Cognitive neuroscience of visual object recognition; Object (grammar); Computer vision; Pattern recognition (psychology); Geography; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001753299,0.003216781,0.001242232,0.004654796,0.0008050374,0.001419012,0.002610622,0.001447577,0.002688158],"category_scores_gemma":[0.003149403,0.0004352423,0.001481624,0.003019205,0.0005797656,0.00135009,0.001142589,0.001550811,0.001773988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001865208,"about_ca_system_score_gemma":0.001145762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03417759,"about_ca_topic_score_gemma":0.03129029,"domain_scores_codex":[0.9983947,0.0001896207,0.0002219202,0.0004713986,0.0004662731,0.0002559624],"domain_scores_gemma":[0.9984186,0.000206882,0.000167158,0.0003413121,0.0007105554,0.0001555981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004083654,0.005799559,0.05283539,0.002011709,0.001284909,0.001641491,0.0002167584,0.2004766,0.02339146,0.003186865,0.3258123,0.3792594],"study_design_scores_gemma":[0.0004076421,0.001176551,0.07196858,0.0002093889,0.0002572881,0.0007117475,0.0004607459,0.8360782,0.04693141,0.003364882,0.03816987,0.0002636504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7094466,0.002866253,0.0462141,0.001251924,0.002181935,0.001040635,0.186038,0.03637663,0.01458391],"genre_scores_gemma":[0.5104312,0.0007295227,0.05907587,0.0003091777,0.0002509789,0.0006044972,0.4216648,0.0006760891,0.006257749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03417759,"threshold_uncertainty_score":0.06795734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01742262742400995,"score_gpt":0.231398055678907,"score_spread":0.2139754282548971,"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."}}