{"id":"W2613985965","doi":"10.1109/jurse.2017.7924619","title":"Road detection using Deep Neural Network in high spatial resolution images","year":2017,"lang":"en","type":"article","venue":"","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Orthophoto; Artificial intelligence; Computer science; Artificial neural network; Data set; Support vector machine; Deep learning; Object detection; Pattern recognition (psychology); Image resolution; Computer vision; Set (abstract data type); Pixel; Precision and recall; Remote sensing; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009424023,0.00008945372,0.00008785613,0.0000538757,0.0002253405,0.00009466141,0.00007805762,0.00009046737,0.00002415884],"category_scores_gemma":[0.00001718471,0.00008872167,0.00002475501,0.00004696691,0.00001631678,0.0003935595,0.00002124506,0.0001410858,0.00001090544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009185265,"about_ca_system_score_gemma":0.000002476457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003018114,"about_ca_topic_score_gemma":0.001429226,"domain_scores_codex":[0.9994696,0.00001416584,0.0001309763,0.0001091065,0.00007206609,0.0002040278],"domain_scores_gemma":[0.9997398,0.000007018079,0.00004353945,0.0001734952,0.00001195339,0.00002423227],"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":[0.00001117608,0.000006360863,0.002155324,0.00001007427,0.000006227876,0.000007065273,0.00001292749,0.8361536,0.042406,0.00001309832,0.0000464626,0.1191718],"study_design_scores_gemma":[0.0001472641,0.0000082617,0.2329047,0.00001279992,0.000005387952,0.000008175928,0.000004100494,0.7602969,0.006416014,0.00006443718,0.00004475036,0.00008719913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.909121,0.00006039188,0.08803473,0.00002013289,0.00137048,0.00006853555,4.509857e-7,0.0003759458,0.0009483606],"genre_scores_gemma":[0.9976799,0.00001328974,0.001779101,0.000004935934,0.0004768216,0.000003100155,0.000002316244,0.00001772354,0.00002282578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2307493,"threshold_uncertainty_score":0.4562506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01199136707895763,"score_gpt":0.2368460443729388,"score_spread":0.2248546772939812,"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."}}