{"id":"W2969510143","doi":"10.1016/j.isprsjprs.2019.08.010","title":"Recovery of urban 3D road boundary via multi-source data","year":2019,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Point cloud; Computer science; Boundary (topology); Global Positioning System; Trajectory; Computer vision; Artificial intelligence; Road surface; Point (geometry); Remote sensing; Geography; Engineering; Mathematics; Geometry","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":[0.0002853993,0.0009132461,0.0005686404,0.003621216,0.0004290164,0.0011242,0.0008753701,0.001270926,0.00232549],"category_scores_gemma":[0.001029696,0.0004696997,0.0009009187,0.00240123,0.0003671707,0.001220701,0.00168393,0.0008359079,0.003056142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002666149,"about_ca_system_score_gemma":0.0007784238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003827057,"about_ca_topic_score_gemma":0.006796395,"domain_scores_codex":[0.9995617,0.00003273461,0.00002037168,0.0001242014,0.0001753392,0.00008563632],"domain_scores_gemma":[0.9996173,0.00005120993,0.00003924384,0.0001374299,0.000135435,0.00001930101],"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":[0.0004092839,0.0004235638,0.01835716,0.0004864299,0.0001790397,0.001233816,0.0004308116,0.1745221,0.1189329,0.004689906,0.01232917,0.6680058],"study_design_scores_gemma":[0.00002861167,0.00005189143,0.02297625,0.00006110888,0.00006747501,0.0003906506,0.0003826735,0.9254425,0.03438501,0.00458593,0.01155791,0.00006996746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3718976,0.0008289775,0.5990768,0.0003702991,0.0001714974,0.0001971836,0.008843037,0.00910924,0.009505293],"genre_scores_gemma":[0.7566568,0.000316882,0.2276123,0.00006123608,0.00004896673,0.0001101737,0.01212104,0.0003677849,0.002704836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003827057,"threshold_uncertainty_score":0.007779598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01338903981515576,"score_gpt":0.2406437063556982,"score_spread":0.2272546665405424,"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."}}