{"id":"W2947146195","doi":"10.5194/isprs-annals-iv-2-w5-247-2019","title":"MODELLING UNCERTAINTY OF SINGLE IMAGE INDOOR LOCALISATION USING A 3D MODEL AND DEEP LEARNING","year":2019,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eidgenössische Technische Hochschule Zürich; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Computer vision; Convolutional neural network; Sampling (signal processing); Image (mathematics); Deep learning; Bayesian probability; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.001068958,0.0008249222,0.0008270442,0.0007952164,0.0002976961,0.001036544,0.001236887,0.001193138,0.001059823],"category_scores_gemma":[0.003959723,0.0007852643,0.0008331251,0.0007382312,0.001421447,0.001366485,0.001694765,0.001325001,0.0002843213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001289021,"about_ca_system_score_gemma":0.0008007422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01332163,"about_ca_topic_score_gemma":0.01124732,"domain_scores_codex":[0.9994832,0.000146569,0.00002244298,0.0001375629,0.0001446415,0.00006556221],"domain_scores_gemma":[0.9985121,0.0008476814,0.0002059517,0.000162072,0.000212883,0.00005934923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004525476,0.000009006299,0.0004285524,0.00002131475,0.00001283055,0.00003232433,0.00002715109,0.9843237,0.001167246,0.001441337,0.0001458055,0.01234549],"study_design_scores_gemma":[0.000001342538,0.000005614437,0.0001213948,0.00000287576,0.000001667667,0.000008255333,0.000002848763,0.9983971,0.0003438474,0.001044218,0.00006713539,0.00000376369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05080946,0.0002088425,0.9471405,0.0001837545,0.00003140757,0.00001473487,0.0001107319,0.0004677517,0.001032853],"genre_scores_gemma":[0.9440923,0.000177472,0.05423899,0.00007615365,0.00002595276,0.0000301137,0.0002224631,0.0000737877,0.001062644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01332163,"threshold_uncertainty_score":0.02648818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04060100659916301,"score_gpt":0.2584121282140779,"score_spread":0.2178111216149149,"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."}}