{"id":"W3203828160","doi":"10.1109/jstars.2021.3116281","title":"Road Extraction Using a Dual Attention Dilated-LinkNet Based on Satellite Images and Floating Vehicle Trajectory Data","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Natural Science Basic Research Program of Shaanxi Province; China Postdoctoral Science Foundation; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Computer science; Artificial intelligence; Feature extraction; Trajectory; Computer vision; Convolutional neural network; Redundancy (engineering); Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003005739,0.00013067,0.0001918174,0.0001838752,0.0001382214,0.00009642166,0.00003635249,0.0001277375,0.000001604311],"category_scores_gemma":[0.0000588014,0.0001337464,0.00002130312,0.0004246338,0.00002203117,0.0002347751,0.00001120451,0.0004570505,2.133634e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005672246,"about_ca_system_score_gemma":0.0000711698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002906301,"about_ca_topic_score_gemma":0.00005808309,"domain_scores_codex":[0.9990086,0.00004575777,0.0004158358,0.0001718008,0.0001946223,0.0001633781],"domain_scores_gemma":[0.9994088,0.00007499564,0.0001526671,0.0001445069,0.0001701528,0.00004883892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001507949,0.00001637149,0.0002429643,0.00005197325,0.00002500412,0.00004171037,0.00006400933,0.07384206,0.7457972,0.000003695746,0.00001226116,0.1798876],"study_design_scores_gemma":[0.0004595498,0.00001857483,0.08496815,0.0002874302,0.00004179991,0.0001713657,0.00007478152,0.8858413,0.0276851,0.00003931653,0.000279063,0.0001335834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9676709,0.000350089,0.03130725,0.00008927203,0.0003466578,0.00007034837,0.000005153187,0.00005136435,0.0001089723],"genre_scores_gemma":[0.9230399,0.0004749658,0.07611682,0.0000341667,0.0002783421,2.0338e-8,0.00002405724,0.0000214081,0.00001029095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8119992,"threshold_uncertainty_score":0.5454019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03640943136859533,"score_gpt":0.2581251990387129,"score_spread":0.2217157676701176,"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."}}