{"id":"W1974154854","doi":"10.1109/lgrs.2012.2193552","title":"Building Detection in Very High Spatial Resolution Multispectral Images Using the Hit-or-Miss Transform","year":2012,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Multispectral image; Dilation (metric space); Image resolution; Computer science; Pixel; Mathematical morphology; Remote sensing; Artificial intelligence; Multispectral pattern recognition; Computer vision; Similarity (geometry); Hyperspectral imaging; Pattern recognition (psychology); Image processing; Geography; Image (mathematics); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003849626,0.0003652423,0.0003900777,0.001144404,0.0002154112,0.000572576,0.0003489559,0.0004235505,0.0008551372],"category_scores_gemma":[0.0007596944,0.0002498857,0.0004538002,0.0007644268,0.0004200151,0.0007029511,0.0004535159,0.0003486478,0.0005104289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001361285,"about_ca_system_score_gemma":0.0001935812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003746597,"about_ca_topic_score_gemma":0.0006864285,"domain_scores_codex":[0.9996893,0.00006229508,0.00001443507,0.00005213415,0.0001522939,0.00002948702],"domain_scores_gemma":[0.9997019,0.00009164056,0.00006092712,0.00004583476,0.0000790064,0.00002072704],"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":[0.0003081505,0.0001134241,0.004235315,0.0002849674,0.0001068476,0.0005231241,0.0001646186,0.02457331,0.4097613,0.004571753,0.001301118,0.554056],"study_design_scores_gemma":[0.00004099013,0.0005434015,0.03205586,0.00004421861,0.0001400783,0.004458869,0.0002443594,0.705458,0.2441728,0.005339921,0.007371708,0.0001298033],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0977218,0.0003546284,0.8996683,0.0001017125,0.0000253081,0.00004178167,0.00007763186,0.0006136266,0.001395232],"genre_scores_gemma":[0.3566901,0.0004054792,0.6410834,0.00003876193,0.00004221954,0.0000430955,0.0001855001,0.00005412464,0.001457275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001144404,"threshold_uncertainty_score":0.002860725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01776498053635428,"score_gpt":0.2404453324716115,"score_spread":0.2226803519352572,"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."}}