{"id":"W4301480362","doi":"10.1080/07038992.2022.2103397","title":"A Method for Fully Automatic Building Footprint Extraction From Remote Sensing Images","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote Sensing and Land Use","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Footprint; Orientation (vector space); Computer science; Artificial intelligence; Deep learning; Computer vision; Ecological footprint; Segmentation; Geography; Sustainable development","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":[0.0003950094,0.001144487,0.0008927746,0.002011208,0.0004595045,0.000836637,0.001171041,0.00102276,0.003011801],"category_scores_gemma":[0.0007724811,0.0007189791,0.001374801,0.001412417,0.0004779928,0.00110327,0.001037155,0.001155708,0.003070091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003259534,"about_ca_system_score_gemma":0.0009677183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004227186,"about_ca_topic_score_gemma":0.008378104,"domain_scores_codex":[0.9994521,0.00003506359,0.00003120376,0.0001609994,0.0002586163,0.00006200827],"domain_scores_gemma":[0.9997154,0.00004988877,0.0000311506,0.00006363576,0.0001187036,0.00002131667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009505048,0.00006155648,0.0008720098,0.0002035461,0.00009168977,0.0001915508,0.00007243318,0.01798248,0.06422845,0.002938953,0.01162052,0.9016417],"study_design_scores_gemma":[0.00003593673,0.00009598275,0.004419409,0.00005722561,0.00008506009,0.001239022,0.00007548458,0.8871268,0.06534331,0.007201622,0.0342172,0.0001029209],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004278347,0.0002736187,0.9908227,0.00007991789,0.00009332679,0.000068643,0.000279088,0.003140874,0.0009635085],"genre_scores_gemma":[0.05342697,0.0004789811,0.938229,0.0001324552,0.0001175693,0.0001484372,0.001476567,0.0004346739,0.005555396],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004227186,"threshold_uncertainty_score":0.01007545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02081294965232295,"score_gpt":0.2590915747179829,"score_spread":0.2382786250656599,"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."}}