{"id":"W3149333486","doi":"10.18280/ts.380120","title":"An Efficient Multi-stage Object-Based Classification to Extract Urban Building Footprints from HR Satellite Images","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Remote sensing; Satellite; Computer science; Digital elevation model; Thresholding; Artificial intelligence; Digital surface; Terrain; Computer vision; Normalized Difference Vegetation Index; Pixel; Segmentation; Geography; Lidar; Image (mathematics); Geology; Cartography; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005933888,0.0007088718,0.0007541006,0.002586488,0.0004264218,0.0006784213,0.0009037904,0.000627647,0.00141155],"category_scores_gemma":[0.0004786149,0.000352408,0.0009429744,0.001616068,0.0002299334,0.000812545,0.0005350811,0.0003914407,0.0010549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003038551,"about_ca_system_score_gemma":0.0006603858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004985958,"about_ca_topic_score_gemma":0.008442449,"domain_scores_codex":[0.9995562,0.00004758845,0.00002925418,0.0001174346,0.0001899505,0.00005949895],"domain_scores_gemma":[0.9996922,0.00005058545,0.00003259877,0.00006070694,0.0001459139,0.00001801553],"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":[0.0001212777,0.0002329905,0.00593885,0.0001768122,0.0001265683,0.00009680742,0.0001116657,0.01377838,0.09261844,0.0008425418,0.002531273,0.8834245],"study_design_scores_gemma":[0.00004174665,0.0003439668,0.03845387,0.00003633504,0.000157766,0.0005524827,0.0001513836,0.8779394,0.07365521,0.001173523,0.00740963,0.00008476492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05171788,0.0003208211,0.943624,0.00006349217,0.00004587825,0.0002035172,0.000330936,0.002411841,0.00128169],"genre_scores_gemma":[0.2108227,0.0002535489,0.7838176,0.00006249364,0.00003071312,0.0002311358,0.001329775,0.00009102019,0.003360884],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004985958,"threshold_uncertainty_score":0.009913862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03617525662098911,"score_gpt":0.2907999540648225,"score_spread":0.2546246974438334,"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."}}