{"id":"W2546821789","doi":"10.1109/igarss.2016.7729408","title":"Road network extraction via deep learning and line integral convolution","year":2016,"lang":"en","type":"article","venue":"","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convolution (computer science); Computer science; Convolutional neural network; Artificial intelligence; Pixel; Context (archaeology); Line (geometry); Deep learning; Feature extraction; Pattern recognition (psychology); Artificial neural network; Computer vision; Mathematics; Geography","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":[0.0003464027,0.0009403582,0.0006662555,0.002168954,0.0003802447,0.0008093297,0.0009963927,0.0007475979,0.002070212],"category_scores_gemma":[0.0009140839,0.0005043227,0.0007902785,0.001624361,0.0003715499,0.001874819,0.0008375938,0.0007509699,0.001314575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000629918,"about_ca_system_score_gemma":0.000731266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005572176,"about_ca_topic_score_gemma":0.008403257,"domain_scores_codex":[0.9996276,0.00003665096,0.00001989522,0.0001179571,0.0001359235,0.00006191161],"domain_scores_gemma":[0.9996626,0.00006908589,0.00006260657,0.00008555182,0.000104276,0.00001592539],"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":[0.0001375278,0.0001040014,0.002374024,0.0001857515,0.0001218894,0.0002536372,0.00008917174,0.2344735,0.05667647,0.007621022,0.003548141,0.6944148],"study_design_scores_gemma":[0.000003774048,0.00001947701,0.0009107672,0.000007757628,0.00001859467,0.00008815441,0.00001501565,0.9763168,0.01819567,0.00249717,0.001915325,0.00001150795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01605723,0.0001357648,0.9803048,0.00005020485,0.00001805187,0.00003870521,0.000131167,0.001884159,0.00137992],"genre_scores_gemma":[0.387487,0.0003793264,0.6048521,0.00009128576,0.00004481852,0.00008451785,0.001251171,0.0002706083,0.005539237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005572176,"threshold_uncertainty_score":0.01107949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005274731105027161,"score_gpt":0.2208312837848982,"score_spread":0.2155565526798711,"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."}}