{"id":"W73112891","doi":"10.1007/978-3-642-15567-3_16","title":"Learning to Detect Roads in High-Resolution Aerial Images","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":624,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Initialization; Artificial intelligence; Context (archaeology); Task (project management); Feature engineering; Artificial neural network; Feature (linguistics); Deep learning; Object detection; Machine learning; Computer vision; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003266565,0.0008769922,0.0005824394,0.0006477407,0.0001940321,0.0005769858,0.001096178,0.0009717071,0.002817764],"category_scores_gemma":[0.0009665521,0.000422027,0.0008086578,0.0007491094,0.0003405999,0.001004823,0.0006213082,0.0008589133,0.001936452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002746439,"about_ca_system_score_gemma":0.0003927748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002939788,"about_ca_topic_score_gemma":0.006639276,"domain_scores_codex":[0.9998203,0.00001647297,0.00001078988,0.00007976364,0.0000448863,0.00002773735],"domain_scores_gemma":[0.9995604,0.0001995944,0.00004655134,0.00007173696,0.0001024147,0.00001924884],"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":[0.00006444812,0.0001507261,0.002805942,0.0001630692,0.00008645654,0.00007632258,0.00005329476,0.06550387,0.02587972,0.001057873,0.004770793,0.8993875],"study_design_scores_gemma":[0.00001911728,0.0001718991,0.004105415,0.00002648957,0.00007431678,0.0001920524,0.00008363697,0.9649997,0.0211896,0.006238913,0.002883807,0.00001508247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1112955,0.0008866823,0.8784538,0.0003555748,0.00008581844,0.0001163618,0.0007011337,0.003130098,0.004975115],"genre_scores_gemma":[0.5547719,0.00122041,0.4275517,0.0003020173,0.0001637051,0.000162608,0.003765642,0.0001622462,0.01189976],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002939788,"threshold_uncertainty_score":0.009426296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006167981939215608,"score_gpt":0.2146971444104521,"score_spread":0.2085291624712365,"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."}}