{"id":"W2780861787","doi":"10.1109/iccv.2017.372","title":"DeepRoadMapper: Extracting Road Topology from Aerial Images","year":2017,"lang":"en","type":"article","venue":"","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":558,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Focus (optics); Motion planning; Topology (electrical circuits); Aerial image; Artificial intelligence; Shortest path problem; Deep learning; State (computer science); Computer vision; Path (computing); Network topology; Image (mathematics); Algorithm; Engineering; Theoretical computer science; Computer network; Robot","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":[0.00006980266,0.0001173906,0.0001315585,0.00003213012,0.0002903231,0.000161578,0.0002052582,0.00012591,0.0006451318],"category_scores_gemma":[0.00006295827,0.000107682,0.00004353706,0.00001398057,0.00003935643,0.0004068212,0.00003918365,0.0001578387,0.0002191552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002725869,"about_ca_system_score_gemma":0.000006277263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000821855,"about_ca_topic_score_gemma":0.00005746635,"domain_scores_codex":[0.9994079,0.000008905083,0.0001408061,0.0001592781,0.00007138166,0.0002117631],"domain_scores_gemma":[0.9995003,0.00002599405,0.0000521674,0.0003603329,0.0000144133,0.00004681261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002477965,0.00004306222,0.004888237,0.0000214562,0.0001227985,0.00005351445,0.0002057401,0.001971059,0.6231515,0.0004915115,0.0134559,0.3555704],"study_design_scores_gemma":[0.001624563,0.00005807512,0.2937803,0.000076816,0.00008869628,0.00007371926,0.0003896755,0.09275545,0.5544814,0.001954453,0.05359838,0.001118477],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9129413,0.0001501657,0.004878904,0.0002004249,0.002700412,0.00007074758,0.000007427371,0.001073542,0.07797708],"genre_scores_gemma":[0.9954367,0.00004884077,0.003241154,0.0000179365,0.0007303368,0.000006305715,0.000008296518,0.0000241306,0.0004863064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3544519,"threshold_uncertainty_score":0.706374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01295831396303205,"score_gpt":0.256611640676719,"score_spread":0.2436533267136869,"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."}}