{"id":"W2319416747","doi":"10.1080/07038992.2016.1160770","title":"Optimization of Multiresolution Segmentation for Object-Oriented Road Detection from High-Resolution Images","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Image segmentation; Computer vision; Segmentation; Computer science; Pattern recognition (psychology); Geography; Pixel; Object (grammar); Set (abstract data type); Support vector machine; Scale (ratio); Image (mathematics); Fuzzy logic; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001643277,0.0001032038,0.0001521311,0.0003251469,0.0001015705,0.00001971914,0.00003800213,0.0001064284,0.000007451563],"category_scores_gemma":[0.0001328359,0.00009012213,0.00007031321,0.0001458831,0.00002937968,0.0003422011,0.000001951713,0.00007643694,0.000001166965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004710679,"about_ca_system_score_gemma":0.00008835414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005704673,"about_ca_topic_score_gemma":0.003419628,"domain_scores_codex":[0.999229,0.00003271259,0.00035868,0.00008928401,0.0001106528,0.0001796686],"domain_scores_gemma":[0.9992341,0.00004899745,0.0002461422,0.00007846617,0.0002689895,0.0001233055],"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":[0.00002482364,0.000001394849,0.000008649516,0.00001220058,0.00003290592,0.000003353522,0.0000903759,0.1081304,0.3609996,0.000001281015,0.00009045053,0.5306045],"study_design_scores_gemma":[0.0008025969,0.00006840469,0.001558289,0.0003187087,0.00006308924,0.00004009996,0.00009186156,0.6746314,0.3218608,0.00007511498,0.0003704554,0.0001191218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3073363,0.0001290236,0.6913726,0.00004466148,0.0009626921,0.00008639073,0.00001959908,0.00003230027,0.00001641693],"genre_scores_gemma":[0.8154597,0.00004147874,0.1842474,0.000004565959,0.0002034356,5.355461e-8,0.00001320129,0.00002152293,0.00000860245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.566501,"threshold_uncertainty_score":0.8623797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007513855376367338,"score_gpt":0.2068584463369883,"score_spread":0.1993445909606209,"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."}}