{"id":"W4389396005","doi":"10.5194/isprs-annals-x-1-w1-2023-763-2023","title":"PERFORMANCE ASSESSMENT OF OBJECT DETECTION FROM MULTI SATELLITES AND AERIAL IMAGES","year":2023,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Infrared Target Detection Methodologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Artificial intelligence; Remote sensing; Overfitting; Satellite; Aerial image; Object detection; Computer vision; Panchromatic film; Satellite imagery; Aerial survey; Deep learning; Set (abstract data type); Image resolution; Pattern recognition (psychology); Image (mathematics); Geography; Artificial neural network","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":[0.001075002,0.0001125089,0.000191659,0.0002747396,0.0002019796,0.00009098742,0.0001039573,0.00006533283,0.000001907491],"category_scores_gemma":[0.0003685793,0.00008382407,0.00005078022,0.0006403187,0.0002893415,0.0002984261,0.00006545513,0.0001045112,0.000001144738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007765633,"about_ca_system_score_gemma":0.00001832946,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01512294,"about_ca_topic_score_gemma":0.0005790074,"domain_scores_codex":[0.9990089,0.00008792288,0.0003654636,0.00009678634,0.0002641245,0.0001768093],"domain_scores_gemma":[0.9992924,0.0002478872,0.0001791424,0.000128807,0.0001198605,0.00003185175],"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":[0.00001041786,0.000001273931,0.0004354584,0.00005101645,0.00001391863,4.986967e-8,0.0004618049,0.01591831,0.07337961,2.038184e-7,0.0000161335,0.9097118],"study_design_scores_gemma":[0.00007931796,0.00003907055,0.02141413,0.00002904961,0.000004370522,0.00000181587,0.0002920963,0.5659336,0.4119914,0.00008465671,0.00007472497,0.00005576161],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8200062,0.00004811684,0.1788233,0.00005000879,0.0006088437,0.0001271838,0.00001913001,0.0000966018,0.0002206369],"genre_scores_gemma":[0.9789586,0.0005730519,0.02039412,0.00003243925,0.00002961893,2.275048e-7,0.000003044923,0.00000469697,0.000004214031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.909656,"threshold_uncertainty_score":0.9914355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06811156004728303,"score_gpt":0.325786888866771,"score_spread":0.257675328819488,"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."}}