{"id":"W3174913242","doi":"10.1080/07038992.2021.1937087","title":"Combined Improved Dirichlet Models and Deep Learning Models for Road Extraction from Remote Sensing Images","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Deep learning; Computation; Convolutional neural network; Pixel; Segmentation; Pattern recognition (psychology); Filter (signal processing); Representation (politics); Dirichlet distribution; Image (mathematics); Computer vision; Mathematics; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.001384684,0.001486385,0.001518214,0.002130244,0.0005268651,0.001333865,0.002325852,0.001568532,0.001983008],"category_scores_gemma":[0.003029681,0.001104144,0.002450786,0.001916969,0.0007043204,0.002706189,0.001594891,0.002715137,0.001263271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001534833,"about_ca_system_score_gemma":0.001235754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01198341,"about_ca_topic_score_gemma":0.01885401,"domain_scores_codex":[0.9991149,0.0002453724,0.00005267415,0.0003033537,0.0001635456,0.0001201356],"domain_scores_gemma":[0.999168,0.0004045302,0.00008044956,0.000147695,0.000153562,0.00004580334],"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":[0.0002132153,0.0001649211,0.00189327,0.0001848687,0.0001859923,0.0001139135,0.0001303793,0.6116496,0.007185155,0.01553543,0.005217391,0.3575259],"study_design_scores_gemma":[0.000003049021,0.000005256749,0.00009804182,0.000004728307,0.000007332171,0.00001397838,0.000005806024,0.9940814,0.001104113,0.004202627,0.0004660516,0.000007634103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00755064,0.0004745862,0.9896016,0.0002087414,0.00005095387,0.0000337321,0.0001637399,0.001035599,0.0008803867],"genre_scores_gemma":[0.4061722,0.001279868,0.5802639,0.0006497788,0.0002720735,0.0002395392,0.002054453,0.0004849679,0.008583253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01198341,"threshold_uncertainty_score":0.02382731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01589753233081077,"score_gpt":0.2235822556029456,"score_spread":0.2076847232721348,"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."}}