{"id":"W3047485635","doi":"10.5194/isprs-annals-v-2-2020-617-2020","title":"BOUNDARY REGULARIZED BUILDING FOOTPRINT EXTRACTION FROM SATELLITE IMAGES USING DEEP NEURAL NETWORKS","year":2020,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Computer vision; Deep learning; Satellite imagery; Boundary (topology); Artificial neural network; Satellite; Feature extraction; Pattern recognition (psychology); Remote sensing; Geography; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003851402,0.0001719438,0.000214183,0.0001241785,0.0003970175,0.0003785789,0.0001609193,0.0001032825,0.000003092194],"category_scores_gemma":[0.0001284691,0.000134861,0.0001057955,0.0005577675,0.0002048373,0.0004688357,0.00006425751,0.0002339319,7.192754e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001704018,"about_ca_system_score_gemma":0.0000154005,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02518116,"about_ca_topic_score_gemma":0.0003707956,"domain_scores_codex":[0.9987364,0.00005987731,0.0004577498,0.0001533405,0.0003284111,0.000264152],"domain_scores_gemma":[0.9993163,0.00008125013,0.0002682198,0.0001379446,0.0001015836,0.00009464716],"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":[0.00001823629,0.000001889153,0.00004554901,0.00001978174,0.00001702551,3.958106e-7,0.000298163,0.1634715,0.04316111,8.182766e-7,0.00001561993,0.7929499],"study_design_scores_gemma":[0.0001177572,0.0000291775,0.001725909,0.00005954174,0.00001865246,0.00001361053,0.0002195985,0.9267107,0.07005864,0.00016745,0.0007297837,0.0001492395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3367045,0.0002707422,0.6617268,0.0004104692,0.0005319187,0.000111728,0.000004076126,0.0001335199,0.0001062039],"genre_scores_gemma":[0.9911546,0.0002048942,0.008202438,0.0002895617,0.0001321738,7.580445e-8,0.000005392451,0.00001011686,8.001595e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7928006,"threshold_uncertainty_score":0.9813102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03840098730008425,"score_gpt":0.2861596139254887,"score_spread":0.2477586266254044,"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."}}