{"id":"W4396662721","doi":"10.1117/1.jrs.18.024504","title":"MDSC-Net: multi-directional spatial connectivity for road extraction in remote sensing images","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Pixel; Pyramid (geometry); Computer vision; Smoothness; Feature extraction; Feature (linguistics); Convolutional neural network; Boundary (topology); Spatial analysis; Remote sensing; Pattern recognition (psychology); Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007123701,0.0002374629,0.0003539323,0.0005077355,0.0001163754,0.000145042,0.00004981266,0.0002126294,0.000004566483],"category_scores_gemma":[0.00007504196,0.0002326269,0.0001760617,0.0002916338,0.00002985778,0.0002934896,0.00001206625,0.0007333818,0.000007117024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004280237,"about_ca_system_score_gemma":0.00006302211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002083772,"about_ca_topic_score_gemma":0.0001072951,"domain_scores_codex":[0.9985772,0.0000316484,0.0005937694,0.0002280677,0.0002613833,0.0003078863],"domain_scores_gemma":[0.9992982,0.0002418601,0.0001772249,0.0001073197,0.0001104348,0.00006502173],"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":[0.00007861276,0.000007161268,4.226449e-7,0.00009022567,0.00005866862,0.00008107784,0.000144504,0.04988088,0.3199548,0.000002618056,0.0001898935,0.6295111],"study_design_scores_gemma":[0.0005957962,0.00002888239,0.0006371418,0.0004751642,0.00006019712,0.001101368,0.000113122,0.9059164,0.08737306,0.0005767862,0.002889558,0.0002325533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1943213,0.0003883499,0.8008104,0.0001062955,0.002947001,0.0001913318,0.000003530261,0.0003101368,0.0009216178],"genre_scores_gemma":[0.8331798,0.00009555926,0.1656881,0.00001666479,0.0009174219,1.907802e-8,0.000003884455,0.00006771446,0.00003082264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8560355,"threshold_uncertainty_score":0.9486249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01316001258199218,"score_gpt":0.2660639671780217,"score_spread":0.2529039545960295,"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."}}