{"id":"W2617647211","doi":"10.1016/j.landurbplan.2017.05.010","title":"Green streets − Quantifying and mapping urban trees with street-level imagery and computer vision","year":2017,"lang":"en","type":"article","venue":"Landscape and Urban Planning","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":316,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Metric (unit); Computer science; Lidar; Tree (set theory); Field (mathematics); Urban planning; Cover (algebra); Remote sensing; Representation (politics); Feature (linguistics); Geography; Land cover; Cartography; Computer vision; Land use; Mathematics; Ecology","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":[0.0001548543,0.0001833358,0.0002229624,0.00003990716,0.0006875693,0.0003605245,0.0001393922,0.00006430838,0.00003110823],"category_scores_gemma":[0.000002856087,0.0001256646,0.00001588419,0.00003316571,0.00005019934,0.000619182,0.0002880997,0.00009659477,0.000006298098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000618323,"about_ca_system_score_gemma":0.000003000125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004022301,"about_ca_topic_score_gemma":0.0009315435,"domain_scores_codex":[0.999038,0.00002037578,0.0001472676,0.0003804862,0.0001497996,0.0002640701],"domain_scores_gemma":[0.9994456,0.00005202031,0.0001302164,0.0002337161,0.000004782872,0.0001336466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003074864,0.000009772672,0.9946437,0.00005633777,0.00002029718,0.00006315589,0.0009619219,0.00001903164,0.0001512166,0.000006598136,0.0009961863,0.003041066],"study_design_scores_gemma":[0.0006683737,0.0001256797,0.9787109,0.0003017578,0.00002224316,0.00003977791,0.0003065779,0.01809942,0.00002983456,0.00001424656,0.001450091,0.0002310669],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975581,0.0006421792,0.0001352174,0.0001092824,0.00004645198,0.00009297801,0.00001354214,0.00003131138,0.001370983],"genre_scores_gemma":[0.9989335,0.00005516695,0.0006854612,0.00008341392,0.000131799,0.00000297006,0.0000132653,0.00001382933,0.00008060887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01808039,"threshold_uncertainty_score":0.5288297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02996876402580172,"score_gpt":0.2428211193567201,"score_spread":0.2128523553309184,"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."}}