{"id":"W4388597122","doi":"10.1007/s11042-023-17363-w","title":"Building height estimation from street-view imagery using deep learning, image processing and automated geospatial analysis","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Geospatial analysis; Computer science; Footprint; Field (mathematics); Scalability; Deep learning; Data set; Data science; Image processing; Set (abstract data type); Artificial intelligence; Machine learning; Data mining; Image (mathematics); Remote sensing; Database","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004185317,0.0001537431,0.0002589205,0.0002073762,0.0004545145,0.0005320787,0.0002038464,0.00006638613,0.000005379354],"category_scores_gemma":[0.0001109519,0.0001484228,0.00005196168,0.001471872,0.00007114938,0.0006547002,0.0001592146,0.0001362977,0.00001025068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001833967,"about_ca_system_score_gemma":0.00002949762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001920709,"about_ca_topic_score_gemma":0.0000435149,"domain_scores_codex":[0.9987133,0.00009945408,0.0002756894,0.0004992206,0.0001731821,0.0002392064],"domain_scores_gemma":[0.9989728,0.0004076137,0.0001635758,0.0002686383,0.00008683125,0.0001005932],"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":[0.000001067768,0.00001871897,0.01019915,0.00003003084,0.00006406596,0.000003516573,0.0003503292,0.006139585,0.004608708,0.0001319536,0.000008409639,0.9784445],"study_design_scores_gemma":[0.000146461,0.000005228934,0.1154116,0.00002048461,0.00008444863,0.000001329302,0.00002652642,0.8827788,0.0004530438,0.0006462355,0.0002707388,0.0001551108],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1235507,0.0004478318,0.8748808,0.000113256,0.00002489174,0.0002083356,0.00001898476,0.0007364307,0.00001873113],"genre_scores_gemma":[0.4197446,0.0001142417,0.5798553,0.00002182609,0.00006447845,0.00007800765,0.0001060608,0.0000105792,0.000004854122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9782894,"threshold_uncertainty_score":0.6052505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02874933826506523,"score_gpt":0.3312389039748356,"score_spread":0.3024895657097704,"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."}}